TY - JOUR AU - Huang, Xiayuan AU - Ren, Shushun AU - Mao, Xinyue AU - Chen, Sirui AU - Chen, Elle AU - He, Yuqi AU - Jiang, Yun PY - 2025/5/2 TI - Association Between Risk Factors and Major Cancers: Explainable Machine Learning Approach JO - JMIR Cancer SP - e62833 VL - 11 KW - electronic health record KW - EHR KW - cancer risk modeling KW - risk factor analysis KW - explainable machine learning KW - machine learning KW - ML KW - risk factor KW - major cancers KW - monitoring KW - cancer risk KW - breast cancer KW - colorectal cancer KW - lung cancer KW - prostate cancer KW - cancer patients KW - clinical decision-making N2 - Background: Cancer is a life-threatening disease and a leading cause of death worldwide, with an estimated 611,000 deaths and over 2 million new cases in the United States in 2024. The rising incidence of major cancers, including among younger individuals, highlights the need for early screening and monitoring of risk factors to manage and decrease cancer risk. Objective: This study aimed to leverage explainable machine learning models to identify and analyze the key risk factors associated with breast, colorectal, lung, and prostate cancers. By uncovering significant associations between risk factors and these major cancer types, we sought to enhance the understanding of cancer diagnosis risk profiles. Our goal was to facilitate more precise screening, early detection, and personalized prevention strategies, ultimately contributing to better patient outcomes and promoting health equity. Methods: Deidentified electronic health record data from Medical Information Mart for Intensive Care (MIMIC)?III was used to identify patients with 4 types of cancer who had longitudinal hospital visits prior to their diagnosis presence. Their records were matched and combined with those of patients without cancer diagnoses using propensity scores based on demographic factors. Three advanced models, penalized logistic regression, random forest, and multilayer perceptron (MLP), were conducted to identify the rank of risk factors for each cancer type, with feature importance analysis for random forest and MLP models. The rank biased overlap was adopted to compare the similarity of ranked risk factors across cancer types. Results: Our framework evaluated the prediction performance of explainable machine learning models, with the MLP model demonstrating the best performance. It achieved an area under the receiver operating characteristic curve of 0.78 for breast cancer (n=58), 0.76 for colorectal cancer (n=140), 0.84 for lung cancer (n=398), and 0.78 for prostate cancer (n=104), outperforming other baseline models (P<.001). In addition to demographic risk factors, the most prominent nontraditional risk factors overlapped across models and cancer types, including hyperlipidemia (odds ratio [OR] 1.14, 95% CI 1.11?1.17; P<.01), diabetes (OR 1.34, 95% CI 1.29?1.39; P<.01), depressive disorders (OR 1.11, 95% CI 1.06?1.16; P<.01), heart diseases (OR 1.42, 95% CI 1.32?1.52; P<.01), and anemia (OR 1.22, 95% CI 1.14?1.30; P<.01). The similarity analysis indicated the unique risk factor pattern for lung cancer from other cancer types. Conclusions: The study?s findings demonstrated the effectiveness of explainable ML models in assessing nontraditional risk factors for major cancers and highlighted the importance of considering unique risk profiles for different cancer types. Moreover, this research served as a hypothesis-generating foundation, providing preliminary results for future investigation into cancer diagnosis risk analysis and management. Furthermore, expanding collaboration with clinical experts for external validation would be essential to refine model outputs, integrate findings into practice, and enhance their impact on patient care and cancer prevention efforts. UR - https://cancer.jmir.org/2025/1/e62833 UR - http://dx.doi.org/10.2196/62833 ID - info:doi/10.2196/62833 ER - TY - JOUR AU - Li, Huanhuan AU - Zhao, Yanjie AU - Li, Wei AU - Wang, Wenxia AU - Zhi, Shengze AU - Wu, Yifan AU - Zhong, Qiqing AU - Wang, Rui AU - Sun, Jiao PY - 2025/4/21 TI - A WeChat-Based Decision Aid Intervention to Promote Informed Decision-Making for Family Members Regarding the Genetic Testing of Patients With Colorectal Cancer: Randomized Controlled Trial JO - J Med Internet Res SP - e60681 VL - 27 KW - decision aid KW - genetic testing KW - hereditary colorectal cancer KW - informed decision-making KW - RCT KW - WeChat based N2 - Background: Identifying patients with inherited colorectal cancer (CRC) syndromes offers many potential benefits. However, individuals often experience decisional conflict regarding genetic testing for CRC, and the uptake rate remains low. Given the growing popularity of genetic testing and the increasing demands on genetic service providers, strategies are needed to promote informed decision-making, increase genetic testing uptake among at-risk individuals, and ensure the rational use of genetic service resources. Objective: This study aims to determine whether a decision aid (DA) tool could promote informed decision-making among family members regarding the genetic testing of a patient with CRC. Methods: A single-center, parallel-group, randomized controlled trial was conducted. We randomized 82 family members of patients with CRC, who were involved in major medical decision-making for the patient, to either a DA intervention or usual care. The primary outcome was informed decision-making, assessed through measures of knowledge, decisional conflict, decision self-efficacy, and preparation for decision-making. Secondary outcomes included patients? uptake of genetic counseling and testing, participants? CRC screening behavior, healthy lifestyle scores, anxiety and depression levels, quality of life, and satisfaction with the intervention. Data were collected at baseline (T0), after the intervention (T1), and 3 months after the baseline survey (T2). The DA intervention and outcome assessments at T1 and T2 were delivered via WeChat. The effects of the intervention were analyzed using generalized estimating equation models. Results: Statistically significant improvements were observed in knowledge (T1: ?=2.049, P<.001; T2: ?=3.317, P<.001), decisional conflict (T1: ?=?11.660, P<.001; T2: ?=?17.587, P<.001), and decision self-efficacy (T1: ?=15.353, P<.001; T2: ?=22.337, P<.001) in the DA group compared with the usual care group at both T1 and T2. Additionally, the DA group showed significantly greater improvement in processed and red meat intake (?=?1.494, P<.001) at T1 and in healthy lifestyle scores (?=1.073, P=.03) at T2. No differences were found between the groups for other outcomes. Conclusions: A DA tool may be a safe, effective, and resource-efficient approach to facilitate informed decision-making about genetic testing. However, the current DA tool requires optimization and further evaluation?for example, by leveraging more advanced technology than WeChat to develop a simpler and more intelligent DA system. Trial Registration: Chinese Clinical Trial Registry ChiCTR2100048051; https://www.chictr.org.cn/showproj.html?proj=129054 UR - https://www.jmir.org/2025/1/e60681 UR - http://dx.doi.org/10.2196/60681 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/60681 ER - TY - JOUR AU - Wang, Longyun AU - Wang, Zeyu AU - Zhao, Bowei AU - Wang, Kai AU - Zheng, Jingying AU - Zhao, Lijing PY - 2025/4/18 TI - Diagnosis Test Accuracy of Artificial Intelligence for Endometrial Cancer: Systematic Review and Meta-Analysis JO - J Med Internet Res SP - e66530 VL - 27 KW - artificial intelligence KW - endometrial cancer KW - diagnostic test accuracy KW - systematic review KW - meta-analysis KW - machine learning KW - deep learning N2 - Background: Endometrial cancer is one of the most common gynecological tumors, and early screening and diagnosis are crucial for its treatment. Research on the application of artificial intelligence (AI) in the diagnosis of endometrial cancer is increasing, but there is currently no comprehensive meta-analysis to evaluate the diagnostic accuracy of AI in screening for endometrial cancer. Objective: This paper presents a systematic review of AI-based endometrial cancer screening, which is needed to clarify its diagnostic accuracy and provide evidence for the application of AI technology in screening for endometrial cancer. Methods: A search was conducted across PubMed, Embase, Cochrane Library, Web of Science, and Scopus databases to include studies published in English, which evaluated the performance of AI in endometrial cancer screening. A total of 2 independent reviewers screened the titles and abstracts, and the quality of the selected studies was assessed using the Quality Assessment of Diagnostic Accuracy Studies?2 (QUADAS-2) tool. The certainty of the diagnostic test evidence was evaluated using the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) system. Results: A total of 13 studies were included, and the hierarchical summary receiver operating characteristic model used for the meta-analysis showed that the overall sensitivity of AI-based endometrial cancer screening was 86% (95% CI 79%-90%) and specificity was 92% (95% CI 87%-95%). Subgroup analysis revealed similar results across AI type, study region, publication year, and study type, but the overall quality of evidence was low. Conclusions: AI-based endometrial cancer screening can effectively detect patients with endometrial cancer, but large-scale population studies are needed in the future to further clarify the diagnostic accuracy of AI in screening for endometrial cancer. Trial Registration: PROSPERO CRD42024519835; https://www.crd.york.ac.uk/PROSPERO/view/CRD42024519835 UR - https://www.jmir.org/2025/1/e66530 UR - http://dx.doi.org/10.2196/66530 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/66530 ER - TY - JOUR AU - Bak, Marieke AU - Hartman, Laura AU - Graafland, Charlotte AU - Korfage, J. Ida AU - Buyx, Alena AU - Schermer, Maartje AU - PY - 2025/4/10 TI - Ethical Design of Data-Driven Decision Support Tools for Improving Cancer Care: Embedded Ethics Review of the 4D PICTURE Project JO - JMIR Cancer SP - e65566 VL - 11 KW - shared decision-making KW - oncology KW - IT KW - ethics KW - decision support tools KW - big data KW - medical decision-making KW - artificial intelligence UR - https://cancer.jmir.org/2025/1/e65566 UR - http://dx.doi.org/10.2196/65566 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/65566 ER - TY - JOUR AU - Xu, He-Li AU - Gong, Ting-Ting AU - Song, Xin-Jian AU - Chen, Qian AU - Bao, Qi AU - Yao, Wei AU - Xie, Meng-Meng AU - Li, Chen AU - Grzegorzek, Marcin AU - Shi, Yu AU - Sun, Hong-Zan AU - Li, Xiao-Han AU - Zhao, Yu-Hong AU - Gao, Song AU - Wu, Qi-Jun PY - 2025/4/1 TI - Artificial Intelligence Performance in Image-Based Cancer Identification: Umbrella Review of Systematic Reviews JO - J Med Internet Res SP - e53567 VL - 27 KW - artificial intelligence KW - biomedical imaging KW - cancer diagnosis KW - meta-analysis KW - systematic review KW - umbrella review N2 - Background: Artificial intelligence (AI) has the potential to transform cancer diagnosis, ultimately leading to better patient outcomes. Objective: We performed an umbrella review to summarize and critically evaluate the evidence for the AI-based imaging diagnosis of cancers. Methods: PubMed, Embase, Web of Science, Cochrane, and IEEE databases were searched for relevant systematic reviews from inception to June 19, 2024. Two independent investigators abstracted data and assessed the quality of evidence, using the Joanna Briggs Institute (JBI) Critical Appraisal Checklist for Systematic Reviews and Research Syntheses. We further assessed the quality of evidence in each meta-analysis by applying the Grading of Recommendations, Assessment, Development, and Evaluation (GRADE) criteria. Diagnostic performance data were synthesized narratively. Results: In a comprehensive analysis of 158 included studies evaluating the performance of AI algorithms in noninvasive imaging diagnosis across 8 major human system cancers, the accuracy of the classifiers for central nervous system cancers varied widely (ranging from 48% to 100%). Similarities were observed in the diagnostic performance for cancers of the head and neck, respiratory system, digestive system, urinary system, female-related systems, skin, and other sites. Most meta-analyses demonstrated positive summary performance. For instance, 9 reviews meta-analyzed sensitivity and specificity for esophageal cancer, showing ranges of 90%-95% and 80%-93.8%, respectively. In the case of breast cancer detection, 8 reviews calculated the pooled sensitivity and specificity within the ranges of 75.4%-92% and 83%-90.6%, respectively. Four meta-analyses reported the ranges of sensitivity and specificity in ovarian cancer, and both were 75%-94%. Notably, in lung cancer, the pooled specificity was relatively low, primarily distributed between 65% and 80%. Furthermore, 80.4% (127/158) of the included studies were of high quality according to the JBI Critical Appraisal Checklist, with the remaining studies classified as medium quality. The GRADE assessment indicated that the overall quality of the evidence was moderate to low. Conclusions: Although AI shows great potential for achieving accelerated, accurate, and more objective diagnoses of multiple cancers, there are still hurdles to overcome before its implementation in clinical settings. The present findings highlight that a concerted effort from the research community, clinicians, and policymakers is required to overcome existing hurdles and translate this potential into improved patient outcomes and health care delivery. Trial Registration: PROSPERO CRD42022364278; https://www.crd.york.ac.uk/PROSPERO/view/CRD42022364278 UR - https://www.jmir.org/2025/1/e53567 UR - http://dx.doi.org/10.2196/53567 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/53567 ER - TY - JOUR AU - Pitrou, Isabelle AU - Petrangelo, Adriano AU - Besson, Charlotte AU - Pepe, Carmela AU - Waschke, Helen Annika AU - Agulnik, Jason AU - Gonzalez, V. Anne AU - Ezer, Nicole PY - 2025/3/28 TI - Lung Cancer Screening in Family Members and Peers of Patients With Lung Cancer: Protocol for a Prospective Cohort Study JO - JMIR Res Protoc SP - e58529 VL - 14 KW - lung cancer KW - low-dose CT KW - chest tomography KW - lung cancer screening KW - patient advocacy KW - early detection of cancer KW - referral and consultation KW - cohort study KW - patient empowerment KW - patient experience N2 - Background: Low-dose computed tomography (LDCT) screening is promising for the early detection of lung cancer (LC) and the reduction of LC-related mortality. Despite the implementation of LC screening programs worldwide, recruitment is challenging. While recruitment for LC screening is based on physician referrals and mass advertising, novel recruitment strategies are needed to improve the enrollment of high-risk individuals into LC screening. Objective: We aim to identify whether patients with LC can act as advocates to enroll their family members and close contacts into LC screening and whether this strategy increases screening uptake at the population level. Methods: We designed a prospective cohort study comprising 2 cohorts constituted between June 2023 and January 2024 with a prospective follow-up of 18 months. Patients with LC (cohort 1) are approached at clinics of the McGill University Health Centre, educated on tools for communicating with family members and close contacts about the benefits of LC screening, and invited to refer their close ones. Referred individuals (cohort 2) are directed to this study?s web-based questionnaire to assess their LC risk score with the PLCOm2012 (Prostate, Lung, Colorectal and Ovarian Cancer Screening Trial) prediction model. Individuals meeting the eligibility criteria for LC screening (PLCOm2012 score ?2% and aged 55-74 years) are directed toward the Quebec LC screening program. Data collected include sociodemographic characteristics, health literacy and smoking status (all participants), patient activation (cohort 1), perceived risk of LC, and generalized anxiety at baseline and at 28 days (cohort 2). LDCT completion within 18 months from referral is assessed from health records. Focus groups will identify the barriers and facilitators in the uptake of LC screening and preventative behaviors based on perceived genetic and clinical LC risks. The primary outcomes are the number of referred participants per survivor of LC and the mean risk of LC of the referred population based on PLCOm2012 scores. The secondary outcomes are the proportion of (1) participants eligible for LC screening; (2) participants eligible for screening who complete LDCT screening within 18 months of referral from a survivor of LC; (3) participants showing interest in genetic testing to inform LC risk; and (4) participants showing interest in a smoking cessation program. Multivariable logistic regression will identify the predictive factors of being referred for LC screening. PLCOm2012 scores will be compared for referred participants and controls from the provincial LC screening program. Results: Overall, 25 survivors of LC and 84 close contacts were enrolled from June 2023 to January 2024, with followed up through July 2025. The results are expected by the end of 2025. Conclusions: We describe an approach to LC screening referral, leveraging patients with LC as advocates to increase screening awareness and uptake among their family and peers. Trial Registration: ClinicalTrials.gov NCT05645731; https://clinicaltrials.gov/ct2/show/NCT05645731 International Registered Report Identifier (IRRID): DERR1-10.2196/58529 UR - https://www.researchprotocols.org/2025/1/e58529 UR - http://dx.doi.org/10.2196/58529 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/58529 ER - TY - JOUR AU - Johnson, Rose Anna AU - Longfellow, Anne Grace AU - Lee, N. Clara AU - Ormseth, Benjamin AU - Skolnick, B. Gary AU - Politi, C. Mary AU - Rivera, M. Yonaira AU - Myckatyn, Terence PY - 2025/3/5 TI - Social Media as a Platform for Cancer Care Decision-Making Among Women: Internet Survey-Based Study on Trust, Engagement, and Preferences JO - JMIR Cancer SP - e64724 VL - 11 KW - shared decision-making KW - SDM KW - decision aids KW - cancer treatment KW - breast cancer KW - digital health KW - social media KW - health communication KW - online decision aids KW - health information-seeking behavior KW - trust in health information KW - healthcare accessibility KW - mhealth N2 - Background: Decision aids improve patient and clinician decision-making but are underused and often restricted to clinical settings. Objective: Given limited studies analyzing the feasibility of disseminating decision aids through social media, this study aimed to evaluate the acceptability, trust, and engagement of women with social media as a tool to deliver online decision aids for cancer treatment. Methods: To prepare for potential dissemination of a breast cancer decision aid via social media, a cross-sectional survey in February 2023 was conducted via Prime Panels, an online market research platform, of women aged 35-75 years in the United States. Demographics, health, cancer information-seeking behaviors, social media use, trust in social media for health information, as well as the likelihood of viewing cancer-related health information and clicking on decision aids through social media, were assessed. Statistical analyses included descriptive statistics, correlations, and multivariable ordinal regression. Results: Of 607 respondents, 397 (65.4%) had searched for cancer information, with 185 (46.6%) using the internet as their primary source. Facebook (Meta) was the most popular platform (511/607, 84.2%). Trust in social media for health information was higher among Black (14/72, 19.4%) and Asian respondents (7/27, 25.9%) than among White respondents (49/480, 10.2%; P=.003). Younger respondents aged 35-39 years (17/82, 20.7%) showed higher trust than those aged 70-79 years (12/70, 17.1%; P<.001). Trust in social media for health information was linked to a higher likelihood of viewing cancer information and accessing a decision aid online (P<.001). Participants who rated social media as ?Trustworthy? (n=73) were more likely to view cancer information (61/73, 83.6%) and click on decision aids (61/73, 83.6%) than those who found it ?Untrustworthy? (n=277; view: 133/277, 48.0%; click: 125/277, 45.1%). Engagement with social media positively correlated with viewing online cancer information (Spearman ?=0.20, P<.001) and willingness to use decision aids (?=0.21, P<.001). Multivariable ordinal regression analyses confirmed that perception of social media?s trustworthiness is a significant predictor of engagement with decision aids (untrustworthy vs trustworthy ?=?1.826, P<.001; neutral vs trustworthy ?=?0.926, P=.007) and of viewing cancer information (untrustworthy vs trustworthy ?=?1.680, P<.001, neutral vs trustworthy ?=?0.581, P=.098), while age and employment status were not significant predictors. Conclusions: This exploratory study suggests that social media platforms may increase access to health information and decision aids. No significant differences were observed between demographic variables and the use or trust in social media for health information. However, trust in social media emerged as a mediating factor between demographics and engagement with cancer information online. Before disseminating decision aids on social media, groups should identify existing trust and engagement patterns with different platforms within their target demographic. UR - https://cancer.jmir.org/2025/1/e64724 UR - http://dx.doi.org/10.2196/64724 UR - http://www.ncbi.nlm.nih.gov/pubmed/40053770 ID - info:doi/10.2196/64724 ER - TY - JOUR AU - Berman, Eliza AU - Sundberg Malek, Holly AU - Bitzer, Michael AU - Malek, Nisar AU - Eickhoff, Carsten PY - 2025/3/5 TI - Retrieval Augmented Therapy Suggestion for Molecular Tumor Boards: Algorithmic Development and Validation Study JO - J Med Internet Res SP - e64364 VL - 27 KW - large language models KW - retrieval augmented generation KW - LLaMA KW - precision oncology KW - molecular tumor board KW - molecular tumor KW - LLMs KW - augmented therapy KW - MTB KW - oncology KW - tumor KW - clinical trials KW - patient care KW - treatment KW - evidence-based KW - accessibility to care N2 - Background: Molecular tumor boards (MTBs) require intensive manual investigation to generate optimal treatment recommendations for patients. Large language models (LLMs) can catalyze MTB recommendations, decrease human error, improve accessibility to care, and enhance the efficiency of precision oncology. Objective: In this study, we aimed to investigate the efficacy of LLM-generated treatments for MTB patients. We specifically investigate the LLMs? ability to generate evidence-based treatment recommendations using PubMed references. Methods: We built a retrieval augmented generation pipeline using PubMed data. We prompted the resulting LLM to generate treatment recommendations with PubMed references using a test set of patients from an MTB conference at a large comprehensive cancer center at a tertiary care institution. Members of the MTB manually assessed the relevancy and correctness of the generated responses. Results: A total of 75% of the referenced articles were properly cited from PubMed, while 17% of the referenced articles were hallucinations, and the remaining were not properly cited from PubMed. Clinician-generated LLM queries achieved higher accuracy through clinician evaluation than automated queries, with clinicians labeling 25% of LLM responses as equal to their recommendations and 37.5% as alternative plausible treatments. Conclusions: This study demonstrates how retrieval augmented generation?enhanced LLMs can be a powerful tool in accelerating MTB conferences, as LLMs are sometimes capable of achieving clinician-equal treatment recommendations. However, further investigation is required to achieve stable results with zero hallucinations. LLMs signify a scalable solution to the time-intensive process of MTB investigations. However, LLM performance demonstrates that they must be used with heavy clinician supervision, and cannot yet fully automate the MTB pipeline. UR - https://www.jmir.org/2025/1/e64364 UR - http://dx.doi.org/10.2196/64364 UR - http://www.ncbi.nlm.nih.gov/pubmed/40053768 ID - info:doi/10.2196/64364 ER - TY - JOUR AU - Tang, Wen-Zhen AU - Mo, Shu-Tian AU - Xie, Yuan-Xi AU - Wei, Tian-Fu AU - Chen, Guo-Lian AU - Teng, Yan-Juan AU - Jia, Kui PY - 2025/3/4 TI - Predicting Overall Survival in Patients with Male Breast Cancer: Nomogram Development and External Validation Study JO - JMIR Cancer SP - e54625 VL - 11 KW - male breast cancer KW - specific survival KW - prediction model KW - nomogram KW - Surveillance, Epidemiology, and End Results database KW - SEER database N2 - Background: Male breast cancer (MBC) is an uncommon disease. Few studies have discussed the prognosis of MBC due to its rarity. Objective: This study aimed to develop a nomogram to predict the overall survival of patients with MBC and externally validate it using cases from China. Methods: Based on the Surveillance, Epidemiology, and End Results (SEER) database, male patients who were diagnosed with breast cancer between January 2010, and December 2015, were enrolled. These patients were randomly assigned to either a training set (n=1610) or a validation set (n=713) in a 7:3 ratio. Additionally, 22 MBC cases diagnosed at the First Affiliated Hospital of Guangxi Medical University between January 2013 and June 2021 were used for external validation, with the follow-up endpoint being June 10, 2023. Cox regression analysis was performed to identify significant risk variables and construct a nomogram to predict the overall survival of patients with MBC. Information collected from the test set was applied to validate the model. The concordance index (C-index), receiver operating characteristic (ROC) curve, decision curve analysis (DCA), and a Kaplan-Meier survival curve were used to evaluate the accuracy and reliability of the model. Results: A total of 2301 patients with MBC in the SEER database and 22 patients with MBC from the study hospital were included. The predictive model included 7 variables: age (hazard ratio [HR] 1.89, 95% CI 1.50?2.38), surgery (HR 0.38, 95% CI 0.29?0.51), marital status (HR 0.75, 95% CI 0.63?0.89), tumor stage (HR 1.17, 95% CI 1.05?1.29), clinical stage (HR 1.41, 95% CI 1.15?1.74), chemotherapy (HR 0.62, 95% CI 0.50?0.75), and HER2 status (HR 2.68, 95% CI 1.20?5.98). The C-index was 0.72, 0.747, and 0.981 in the training set, internal validation set, and external validation set, respectively. The nomogram showed accurate calibration, and the ROC curve confirmed the advantage of the model in clinical validity. The DCA analysis indicated that the model had good clinical applicability. Furthermore, the nomogram classification allowed for more accurate differentiation of risk subgroups, and patients with low-risk MBC demonstrated substantially improved survival outcomes compared with medium- and high-risk patients (P<.001). Conclusions: A survival prognosis prediction nomogram with 7 variables for patients with MBC was constructed in this study. The model can predict the survival outcome of these patients and provide a scientific basis for clinical diagnosis and treatment. UR - https://cancer.jmir.org/2025/1/e54625 UR - http://dx.doi.org/10.2196/54625 ID - info:doi/10.2196/54625 ER - TY - JOUR AU - Kuerbanjiang, Warisijiang AU - Peng, Shengzhe AU - Jiamaliding, Yiershatijiang AU - Yi, Yuexiong PY - 2025/2/5 TI - Performance Evaluation of Large Language Models in Cervical Cancer Management Based on a Standardized Questionnaire: Comparative Study JO - J Med Internet Res SP - e63626 VL - 27 KW - large language model KW - cervical cancer KW - screening KW - artificial intelligence KW - model interpretability N2 - Background: Cervical cancer remains the fourth leading cause of death among women globally, with a particularly severe burden in low-resource settings. A comprehensive approach?from screening to diagnosis and treatment?is essential for effective prevention and management. Large language models (LLMs) have emerged as potential tools to support health care, though their specific role in cervical cancer management remains underexplored. Objective: This study aims to systematically evaluate the performance and interpretability of LLMs in cervical cancer management. Methods: Models were selected from the AlpacaEval leaderboard version 2.0 and based on the capabilities of our computer. The questions inputted into the models cover aspects of general knowledge, screening, diagnosis, and treatment, according to guidelines. The prompt was developed using the Context, Objective, Style, Tone, Audience, and Response (CO-STAR) framework. Responses were evaluated for accuracy, guideline compliance, clarity, and practicality, graded as A, B, C, and D with corresponding scores of 3, 2, 1, and 0. The effective rate was calculated as the ratio of A and B responses to the total number of designed questions. Local Interpretable Model-Agnostic Explanations (LIME) was used to explain and enhance physicians? trust in model outputs within the medical context. Results: Nine models were included in this study, and a set of 100 standardized questions covering general information, screening, diagnosis, and treatment was designed based on international and national guidelines. Seven models (ChatGPT-4.0 Turbo, Claude 2, Gemini Pro, Mistral-7B-v0.2, Starling-LM-7B alpha, HuatuoGPT, and BioMedLM 2.7B) provided stable responses. Among all the models included, ChatGPT-4.0 Turbo ranked first with a mean score of 2.67 (95% CI 2.54-2.80; effective rate 94.00%) with a prompt and 2.52 (95% CI 2.37-2.67; effective rate 87.00%) without a prompt, outperforming the other 8 models (P<.001). Regardless of prompts, QiZhenGPT consistently ranked among the lowest-performing models, with P<.01 in comparisons against all models except BioMedLM. Interpretability analysis showed that prompts improved alignment with human annotations for proprietary models (median intersection over union 0.43), while medical-specialized models exhibited limited improvement. Conclusions: Proprietary LLMs, particularly ChatGPT-4.0 Turbo and Claude 2, show promise in clinical decision-making involving logical analysis. The use of prompts can enhance the accuracy of some models in cervical cancer management to varying degrees. Medical-specialized models, such as HuatuoGPT and BioMedLM, did not perform as well as expected in this study. By contrast, proprietary models, particularly those augmented with prompts, demonstrated notable accuracy and interpretability in medical tasks, such as cervical cancer management. However, this study underscores the need for further research to explore the practical application of LLMs in medical practice. UR - https://www.jmir.org/2025/1/e63626 UR - http://dx.doi.org/10.2196/63626 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/63626 ER - TY - JOUR AU - Jonnalagedda-Cattin, Magali AU - Moukam Datchoua, Manoëla Alida AU - Yakam, Flore Virginie AU - Kenfack, Bruno AU - Petignat, Patrick AU - Thiran, Jean-Philippe AU - Schönenberger, Klaus AU - Schmidt, C. Nicole PY - 2025/2/5 TI - Barriers and Facilitators to the Preadoption of a Computer-Aided Diagnosis Tool for Cervical Cancer: Qualitative Study on Health Care Providers? Perspectives in Western Cameroon JO - JMIR Cancer SP - e50124 VL - 11 KW - qualitative research KW - technology acceptance KW - cervical cancer KW - diagnosis KW - computer-assisted KW - decision support systems KW - artificial intelligence KW - health personnel attitudes KW - Cameroon KW - mobile phone N2 - Background: Computer-aided detection and diagnosis (CAD) systems can enhance the objectivity of visual inspection with acetic acid (VIA), which is widely used in low- and middle-income countries (LMICs) for cervical cancer detection. VIA?s reliance on subjective health care provider (HCP) interpretation introduces variability in diagnostic accuracy. CAD tools can address some limitations; nonetheless, understanding the contextual factors affecting CAD integration is essential for effective adoption and sustained use, particularly in resource-constrained settings. Objective: This study investigated the barriers and facilitators perceived by HCPs in Western Cameroon regarding sustained CAD tool use for cervical cancer detection using VIA. The aim was to guide smooth technology adoption in similar settings by identifying specific barriers and facilitators and optimizing CAD?s potential benefits while minimizing obstacles. Methods: The perspectives of HCPs on adopting CAD for VIA were explored using a qualitative methodology. The study participants included 8 HCPs (6 midwives and 2 gynecologists) working in the Dschang district, Cameroon. Focus group discussions were conducted with midwives, while individual interviews were conducted with gynecologists to comprehend unique perspectives. Each interview was audio-recorded, transcribed, and independently coded by 2 researchers using the ATLAS.ti (Lumivero, LLC) software. The technology acceptance lifecycle framework guided the content analysis, focusing on the preadoption phases to examine the perceived acceptability and initial acceptance of the CAD tool in clinical workflows. The study findings were reported adhering to the COREQ (Consolidated Criteria for Reporting Qualitative Research) and SRQR (Standards for Reporting Qualitative Research) checklists. Results: Key elements influencing the sustained use of CAD tools for VIA by HCPs were identified, primarily within the technology acceptance lifecycle?s preadoption framework. Barriers included the system?s ease of use, particularly challenges associated with image acquisition, concerns over confidentiality and data security, limited infrastructure and resources such as the internet and device quality, and potential workflow changes. Facilitators encompassed the perceived improved patient care, the potential for enhanced diagnostic accuracy, and the integration of CAD tools into routine clinical practices, provided that infrastructure and training were adequate. The HCPs emphasized the importance of clinical validation, usability testing, and iterative feedback mechanisms to build trust in the CAD tool?s accuracy and utility. Conclusions: This study provides practical insights from HCPs in Western Cameroon regarding the adoption of CAD tools for VIA in clinical settings. CAD technology can aid diagnostic objectivity; however, data management, workflow adaptation, and infrastructure limitations must be addressed to avoid ?pilotitis??the failure of digital health tools to progress beyond the pilot phase. Effective implementation requires comprehensive technology management, including regulatory compliance, infrastructure support, and user-focused training. Involving end users can ensure that CAD tools are fully integrated and embraced in LMICs to aid cervical cancer screening. UR - https://cancer.jmir.org/2025/1/e50124 UR - http://dx.doi.org/10.2196/50124 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/50124 ER - TY - JOUR AU - Mourato, Beatriz Maria AU - Pratas, Nuno AU - Branco Pereira, Andreia AU - Taré, Filipa AU - Chança, Raphael AU - Fronteira, Inês AU - Dinis, Rui AU - Areia, Miguel PY - 2025/2/3 TI - Effectiveness of Gastric Cancer Endoscopic Screening in Intermediate-Risk Countries: Protocol for a Systematic Review and Meta-Analysis JO - JMIR Res Protoc SP - e56791 VL - 14 KW - gastric cancers KW - endoscopic screening KW - intermediate-risk countries KW - neoplasia KW - early detection KW - diagnosis KW - cancer screening KW - survival KW - meta-analysis KW - gastrointestinal cancers N2 - Background: Gastric cancer (GC) is the fifth most prevalent neoplasm worldwide and the fourth with the highest mortality, and its geographical distribution is not homogeneous with high-risk, intermediate-risk (IR), and low-risk areas. Advanced stages at diagnosis are related to high mortality, but early detection greatly increases the chances of survival. Upper endoscopy with biopsy is the gold standard for GC diagnosis. Several studies have investigated the relevance of endoscopic screening and how to implemente it in IR countries. However, most Western societies recommend screening only in selected populations with high-risk factors for GC. No systematic reviews on GC endoscopic screening in IR countries exist. Objective: We aimed to determine the effectiveness of endoscopic GC screening in IR countries. Methods: We will include randomized and nonrandomized controlled trials, cohort studies, case-control studies, cross-sectional studies, and economic studies focusing on endoscopic screening of GC in the asymptomatic population of IR countries. The search will be conducted in MEDLINE, SCOPUS, Embase, and Web of Science. Other gray literature sources will be additionally searched. Studies published in English, Portuguese, or Spanish until September 2024 will be included. Two independent reviewers will screen the titles and abstracts of all search results. The selected studies will then be fully analyzed, and the data will be collected and coded in a database. To minimize the risk of bias, the included studies will undergo a quality analysis according to Cochrane risk of bias tools, RoB 2 of randomized trials and ROBINS-I for nonrandomized trials; Newcastle-Ottawa Quality Assessment Scale for case-control and cohort studies; and National Heart, Lung and Blood Institute study quality assessment tools for cross-sectional studies. The data collected will be cataloged in 2 categories: efficacy or effectiveness data and economic data, and separate meta-analyses will be performed for each category if appropriate. Results: This study is expected to provide results on the efficacy, effectiveness, and cost-effectiveness of endoscopic screening in an IR population. To date, 969 studies were screened for title and abstract, 75 were selected for full-text screening, and 44 were retained for data analysis. Additionally, 2 studies were selected from our manual search. Currently, the study is in the early stages of data extraction and risk of bias assessment and is expected to be published in the first quarter of 2025. Conclusions: To our knowledge, this review will be the first to provide evidence on the effectiveness of endoscopic GC screening in IR countries. In doing so, we believe we will help guide future research, inform health care decisions and assist policy makers in this area, and support future decisions to implement GC screening programs in this type of population. Trial Registration: PROSPERO CRD42024502174; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=502174 International Registered Report Identifier (IRRID): DERR1-10.2196/56791 UR - https://www.researchprotocols.org/2025/1/e56791 UR - http://dx.doi.org/10.2196/56791 UR - http://www.ncbi.nlm.nih.gov/pubmed/39545590 ID - info:doi/10.2196/56791 ER - TY - JOUR AU - Li, Yanong AU - He, Yixuan AU - Liu, Yawei AU - Wang, Bingchen AU - Li, Bo AU - Qiu, Xiaoguang PY - 2025/1/30 TI - Identification of Intracranial Germ Cell Tumors Based on Facial Photos: Exploratory Study on the Use of Deep Learning for Software Development JO - J Med Internet Res SP - e58760 VL - 27 KW - deep learning KW - facial recognition KW - intracranial germ cell tumors KW - endocrine indicators KW - software development KW - artificial intelligence KW - machine learning models KW - software engineering KW - neural networks KW - algorithms KW - cohort studies N2 - Background: Primary intracranial germ cell tumors (iGCTs) are highly malignant brain tumors that predominantly occur in children and adolescents, with an incidence rate ranking third among primary brain tumors in East Asia (8%-15%). Due to their insidious onset and impact on critical functional areas of the brain, these tumors often result in irreversible abnormalities in growth and development, as well as cognitive and motor impairments in affected children. Therefore, early diagnosis through advanced screening techniques is vital for improving patient outcomes and quality of life. Objective: This study aimed to investigate the application of facial recognition technology in the early detection of iGCTs in children and adolescents. Early diagnosis through advanced screening techniques is vital for improving patient outcomes and quality of life. Methods: A multicenter, phased approach was adopted for the development and validation of a deep learning model, GVisageNet, dedicated to the screening of midline brain tumors from normal controls (NCs) and iGCTs from other midline brain tumors. The study comprised the collection and division of datasets into training (n=847, iGCTs=358, NCs=300, other midline brain tumors=189) and testing (n=212, iGCTs=79, NCs=70, other midline brain tumors=63), with an additional independent validation dataset (n=336, iGCTs=130, NCs=100, other midline brain tumors=106) sourced from 4 medical institutions. A regression model using clinically relevant, statistically significant data was developed and combined with GVisageNet outputs to create a hybrid model. This integration sought to assess the incremental value of clinical data. The model?s predictive mechanisms were explored through correlation analyses with endocrine indicators and stratified evaluations based on the degree of hypothalamic-pituitary-target axis damage. Performance metrics included area under the curve (AUC), accuracy, sensitivity, and specificity. Results: On the independent validation dataset, GVisageNet achieved an AUC of 0.938 (P<.01) in distinguishing midline brain tumors from NCs. Further, GVisageNet demonstrated significant diagnostic capability in distinguishing iGCTs from the other midline brain tumors, achieving an AUC of 0.739, which is superior to the regression model alone (AUC=0.632, P<.001) but less than the hybrid model (AUC=0.789, P=.04). Significant correlations were found between the GVisageNet?s outputs and 7 endocrine indicators. Performance varied with hypothalamic-pituitary-target axis damage, indicating a further understanding of the working mechanism of GVisageNet. Conclusions: GVisageNet, capable of high accuracy both independently and with clinical data, shows substantial potential for early iGCTs detection, highlighting the importance of combining deep learning with clinical insights for personalized health care. UR - https://www.jmir.org/2025/1/e58760 UR - http://dx.doi.org/10.2196/58760 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/58760 ER - TY - JOUR AU - Jones, Tudor Owain AU - Calanzani, Natalia AU - Scott, E. Suzanne AU - Matin, N. Rubeta AU - Emery, Jon AU - Walter, M. Fiona PY - 2025/1/28 TI - User and Developer Views on Using AI Technologies to Facilitate the Early Detection of Skin Cancers in Primary Care Settings: Qualitative Semistructured Interview Study JO - JMIR Cancer SP - e60653 VL - 11 KW - artificial intelligence KW - AI KW - machine learning KW - ML KW - primary care KW - skin cancer KW - melanoma KW - qualitative research KW - mobile phone N2 - Background: Skin cancers, including melanoma and keratinocyte cancers, are among the most common cancers worldwide, and their incidence is rising in most populations. Earlier detection of skin cancer leads to better outcomes for patients. Artificial intelligence (AI) technologies have been applied to skin cancer diagnosis, but many technologies lack clinical evidence and/or the appropriate regulatory approvals. There are few qualitative studies examining the views of relevant stakeholders or evidence about the implementation and positioning of AI technologies in the skin cancer diagnostic pathway. Objective: This study aimed to understand the views of several stakeholder groups on the use of AI technologies to facilitate the early diagnosis of skin cancer, including patients, members of the public, general practitioners, primary care nurse practitioners, dermatologists, and AI researchers. Methods: This was a qualitative, semistructured interview study with 29 stakeholders. Participants were purposively sampled based on age, sex, and geographical location. We conducted the interviews via Zoom between September 2022 and May 2023. Transcribed recordings were analyzed using thematic framework analysis. The framework for the Nonadoption, Abandonment, and Challenges to Scale-Up, Spread, and Sustainability was used to guide the analysis to help understand the complexity of implementing diagnostic technologies in clinical settings. Results: Major themes were ?the position of AI in the skin cancer diagnostic pathway? and ?the aim of the AI technology?; cross-cutting themes included trust, usability and acceptability, generalizability, evaluation and regulation, implementation, and long-term use. There was no clear consensus on where AI should be placed along the skin cancer diagnostic pathway, but most participants saw the technology in the hands of either patients or primary care practitioners. Participants were concerned about the quality of the data used to develop and test AI technologies and the impact this could have on their accuracy in clinical use with patients from a range of demographics and the risk of missing skin cancers. Ease of use and not increasing the workload of already strained health care services were important considerations for participants. Health care professionals and AI researchers reported a lack of established methods of evaluating and regulating AI technologies. Conclusions: This study is one of the first to examine the views of a wide range of stakeholders on the use of AI technologies to facilitate early diagnosis of skin cancer. The optimal approach and position in the diagnostic pathway for these technologies have not yet been determined. AI technologies need to be developed and implemented carefully and thoughtfully, with attention paid to the quality and representativeness of the data used for development, to achieve their potential. UR - https://cancer.jmir.org/2025/1/e60653 UR - http://dx.doi.org/10.2196/60653 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/60653 ER - TY - JOUR AU - Almashmoum, Maryam AU - Cunningham, James AU - Ainsworth, John PY - 2024/11/13 TI - Evaluating Factors Affecting Knowledge Sharing Among Health Care Professionals in the Medical Imaging Departments of 2 Cancer Centers: Concurrent Mixed Methods Study JO - JMIR Hum Factors SP - e53780 VL - 11 KW - knowledge management KW - knowledge sharing KW - medical imaging departments KW - cancer centers KW - The Christie KW - Kuwait Cancer Control Center KW - concurrent mixed methods KW - factors KW - challenges KW - definition KW - mechanisms KW - practices N2 - Background: Knowledge sharing is a crucial part of any knowledge management implementation. It refers to sharing skills and experience among team members in an organization. In a health care setting, sharing knowledge, whether tacit or explicit, is important and can lead to better health care services. In medical imaging departments, knowledge sharing can be of particular importance. There are several factors that affect knowledge-sharing practices in medical imaging departments: individual, departmental, and technological. Evaluating the importance of these factors and understanding their use can help with improving knowledge-sharing practices in medical imaging departments. Objective: We aimed to assess the level of motivation, identify current knowledge-sharing tools, and evaluate factors affecting knowledge sharing in the medical imaging departments of 2 cancer centers, The Christie, United Kingdom, and the Kuwait Cancer Control Center (KCCC). Methods: A concurrent mixed methods study was conducted through nonprobability sampling techniques between February 1, 2023, and July 30, 2023. Semistructured interviews were used to validate the results of the quantitative analysis. Data were collected using an electronic questionnaire that was distributed among health care professionals in both cancer centers using Qualtrics. Semistructured interviews were conducted online using Microsoft Teams. The quantitative data were analyzed using the Qualtrics MX software to report the results for each question, whereas the qualitative data were analyzed using a thematic approach with codes classified through NVivo. Results: In total, 56 respondents from the KCCC and 29 from The Christie participated, with a 100% response rate (56/56, 100% and 29/29, 100%, respectively) based on the Qualtrics survey tool. A total of 59% (17/29) of health care professionals from The Christie shared their knowledge using emails and face-to-face communication as their main tools on a daily basis, and 57% (32/56) of health care professionals from the KCCC used face-to-face communication for knowledge sharing. The mean Likert-scale score of all the components that assessed the factors that affected knowledge-sharing behaviors fell between ?somewhat agree? and ?strongly agree? in both centers, excepting extrinsic motivation, which was rated as ?neither agree nor disagree.? This was similar to the results related to incentives. It was shown that 52% (15/29) of health care professionals at The Christie had no incentives to encourage knowledge-sharing practices. Therefore, establishing clear policies to manage incentives is important to increase knowledge-sharing practices. Conclusions: This study offered an evaluation of factors that affect knowledge sharing in 2 cancer centers. Most health care professionals were aware of the importance of knowledge-sharing practices in enhancing health care services. Several challenges were identified, such as time constraints, a lack of staff, and the language barrier, which limit knowledge-sharing practices. Therefore, establishing a clear policy for knowledge sharing is vital to practicing knowledge-sharing behaviors and facing any challenges that limit this practice. UR - https://humanfactors.jmir.org/2024/1/e53780 UR - http://dx.doi.org/10.2196/53780 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/53780 ER - TY - JOUR AU - Renne, Lorenzo Salvatore AU - Cammelli, Manuela AU - Santori, Ilaria AU - Tassan-Mangina, Marta AU - Samà, Laura AU - Ruspi, Laura AU - Sicoli, Federico AU - Colombo, Piergiuseppe AU - Terracciano, Maria Luigi AU - Quagliuolo, Vittorio AU - Cananzi, Maria Ferdinando Carlo PY - 2024/10/22 TI - True Mitotic Count Prediction in Gastrointestinal Stromal Tumors: Bayesian Network Model and PROMETheus (Preoperative Mitosis Estimator Tool) Application Development JO - J Med Internet Res SP - e50023 VL - 26 KW - GIST mitosis KW - risk classification KW - mHealth KW - mobile health KW - neoadjuvant therapy KW - patient stratification KW - Gastrointestinal Stroma KW - preoperative risk N2 - Background: Gastrointestinal stromal tumors (GISTs) present a complex clinical landscape, where precise preoperative risk assessment plays a pivotal role in guiding therapeutic decisions. Conventional methods for evaluating mitotic count, such as biopsy-based assessments, encounter challenges stemming from tumor heterogeneity and sampling biases, thereby underscoring the urgent need for innovative approaches to enhance prognostic accuracy. Objective: The primary objective of this study was to develop a robust and reliable computational tool, PROMETheus (Preoperative Mitosis Estimator Tool), aimed at refining patient stratification through the precise estimation of mitotic count in GISTs. Methods: Using advanced Bayesian network methodologies, we constructed a directed acyclic graph (DAG) integrating pertinent clinicopathological variables essential for accurate mitotic count prediction on the surgical specimen. Key parameters identified and incorporated into the model encompassed tumor size, location, mitotic count from biopsy specimens, surface area evaluated during biopsy, and tumor response to therapy, when applicable. Rigorous testing procedures, including prior predictive simulations, validation utilizing synthetic data sets were employed. Finally, the model was trained on a comprehensive cohort of real-world GIST cases (n=80), drawn from the repository of the Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS) Humanitas Research Hospital, with a total of 160 cases analyzed. Results: Our computational model exhibited excellent diagnostic performance on synthetic data. Different model architecture were selected based on lower deviance and robust out-of-sample predictive capabilities. Posterior predictive checks (retrodiction) further corroborated the model?s accuracy. Subsequently, PROMETheus was developed. This is an intuitive tool that dynamically computes predicted mitotic count and risk assessment on surgical specimens based on tumor-specific attributes, including size, location, surface area, and biopsy-derived mitotic count, using posterior probabilities derived from the model. Conclusions: The deployment of PROMETheus represents a potential advancement in preoperative risk stratification for GISTs, offering clinicians a precise and reliable means to anticipate mitotic counts on surgical specimens and a solid base to stratify patients for clinical studies. By facilitating tailored therapeutic strategies, this innovative tool is poised to revolutionize clinical decision-making paradigms, ultimately translating into improved patient outcomes and enhanced prognostic precision in the management of GISTs. UR - https://www.jmir.org/2024/1/e50023 UR - http://dx.doi.org/10.2196/50023 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/50023 ER - TY - JOUR AU - Hesso, Iman AU - Zacharias, Lithin AU - Kayyali, Reem AU - Charalambous, Andreas AU - Lavdaniti, Maria AU - Stalika, Evangelia AU - Ajami, Tarek AU - Acampa, Wanda AU - Boban, Jasmina AU - Nabhani-Gebara, Shereen PY - 2024/10/10 TI - Artificial Intelligence for Optimizing Cancer Imaging: User Experience Study JO - JMIR Cancer SP - e52639 VL - 10 KW - artificial intelligence KW - cancer KW - cancer imaging KW - UX design workshops KW - Delphi method KW - INCISIVE AI toolbox KW - user experience N2 - Background: The need for increased clinical efficacy and efficiency has been the main force in developing artificial intelligence (AI) tools in medical imaging. The INCISIVE project is a European Union?funded initiative aiming to revolutionize cancer imaging methods using AI technology. It seeks to address limitations in imaging techniques by developing an AI-based toolbox that improves accuracy, specificity, sensitivity, interpretability, and cost-effectiveness. Objective: To ensure the successful implementation of the INCISIVE AI service, a study was conducted to understand the needs, challenges, and expectations of health care professionals (HCPs) regarding the proposed toolbox and any potential implementation barriers. Methods: A mixed methods study consisting of 2 phases was conducted. Phase 1 involved user experience (UX) design workshops with users of the INCISIVE AI toolbox. Phase 2 involved a Delphi study conducted through a series of sequential questionnaires. To recruit, a purposive sampling strategy based on the project?s consortium network was used. In total, 16 HCPs from Serbia, Italy, Greece, Cyprus, Spain, and the United Kingdom participated in the UX design workshops and 12 completed the Delphi study. Descriptive statistics were performed using SPSS (IBM Corp), enabling the calculation of mean rank scores of the Delphi study?s lists. The qualitative data collected via the UX design workshops was analyzed using NVivo (version 12; Lumivero) software. Results: The workshops facilitated brainstorming and identification of the INCISIVE AI toolbox?s desired features and implementation barriers. Subsequently, the Delphi study was instrumental in ranking these features, showing a strong consensus among HCPs (W=0.741, P<.001). Additionally, this study also identified implementation barriers, revealing a strong consensus among HCPs (W=0.705, P<.001). Key findings indicated that the INCISIVE AI toolbox could assist in areas such as misdiagnosis, overdiagnosis, delays in diagnosis, detection of minor lesions, decision-making in disagreement, treatment allocation, disease prognosis, prediction, treatment response prediction, and care integration throughout the patient journey. Limited resources, lack of organizational and managerial support, and data entry variability were some of the identified barriers. HCPs also had an explicit interest in AI explainability, desiring feature relevance explanations or a combination of feature relevance and visual explanations within the toolbox. Conclusions: The results provide a thorough examination of the INCISIVE AI toolbox?s design elements as required by the end users and potential barriers to its implementation, thus guiding the design and implementation of the INCISIVE technology. The outcome offers information about the degree of AI explainability required of the INCISIVE AI toolbox across the three services: (1) initial diagnosis; (2) disease staging, differentiation, and characterization; and (3) treatment and follow-up indicated for the toolbox. By considering the perspective of end users, INCISIVE aims to develop a solution that effectively meets their needs and drives adoption. UR - https://cancer.jmir.org/2024/1/e52639 UR - http://dx.doi.org/10.2196/52639 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/52639 ER - TY - JOUR AU - Tao, Jin AU - Liu, Dan AU - Hu, Fu-Bi AU - Zhang, Xiao AU - Yin, Hongkun AU - Zhang, Huiling AU - Zhang, Kai AU - Huang, Zixing AU - Yang, Kun PY - 2024/10/9 TI - Development and Validation of a Computed Tomography?Based Model for Noninvasive Prediction of the T Stage in Gastric Cancer: Multicenter Retrospective Study JO - J Med Internet Res SP - e56851 VL - 26 KW - gastric cancer KW - computed tomography KW - radiomics KW - T stage KW - deep learning KW - cancer KW - multicenter study KW - accuracy KW - binary classification KW - tumor KW - hybrid model KW - performance KW - pathological stage N2 - Background: As part of the TNM (tumor-node-metastasis) staging system, T staging based on tumor depth is crucial for developing treatment plans. Previous studies have constructed a deep learning model based on computed tomographic (CT) radiomic signatures to predict the number of lymph node metastases and survival in patients with resected gastric cancer (GC). However, few studies have reported the combination of deep learning and radiomics in predicting T staging in GC. Objective: This study aimed to develop a CT-based model for automatic prediction of the T stage of GC via radiomics and deep learning. Methods: A total of 771 GC patients from 3 centers were retrospectively enrolled and divided into training, validation, and testing cohorts. Patients with GC were classified into mild (stage T1 and T2), moderate (stage T3), and severe (stage T4) groups. Three predictive models based on the labeled CT images were constructed using the radiomics features (radiomics model), deep features (deep learning model), and a combination of both (hybrid model). Results: The overall classification accuracy of the radiomics model was 64.3% in the internal testing data set. The deep learning model and hybrid model showed better performance than the radiomics model, with overall classification accuracies of 75.7% (P=.04) and 81.4% (P=.001), respectively. On the subtasks of binary classification of tumor severity, the areas under the curve of the radiomics, deep learning, and hybrid models were 0.875, 0.866, and 0.886 in the internal testing data set and 0.820, 0.818, and 0.972 in the external testing data set, respectively, for differentiating mild (stage T1~T2) from nonmild (stage T3~T4) patients, and were 0.815, 0.892, and 0.894 in the internal testing data set and 0.685, 0.808, and 0.897 in the external testing data set, respectively, for differentiating nonsevere (stage T1~T3) from severe (stage T4) patients. Conclusions: The hybrid model integrating radiomics features and deep features showed favorable performance in diagnosing the pathological stage of GC. UR - https://www.jmir.org/2024/1/e56851 UR - http://dx.doi.org/10.2196/56851 UR - http://www.ncbi.nlm.nih.gov/pubmed/39382960 ID - info:doi/10.2196/56851 ER - TY - JOUR AU - McLoughlin, E. Daniel AU - Moreno Echevarria, M. Fabiola AU - Badawy, M. Sherif PY - 2024/9/11 TI - Lessons Learned From Shared Decision-Making With Oral Anticoagulants: Viewpoint on Suggestions for the Development of Oral Chemotherapy Decision Aids JO - JMIR Cancer SP - e56935 VL - 10 KW - shared decision-making KW - SDM KW - decision aids KW - decision aids design KW - oral chemotherapy KW - oral anticoagulants KW - drug delivery KW - chemotherapy KW - chemo KW - anticoagulants KW - drug deliveries KW - cancer KW - oncology KW - oncologist KW - metastases KW - literature review KW - literature reviews UR - https://cancer.jmir.org/2024/1/e56935 UR - http://dx.doi.org/10.2196/56935 UR - http://www.ncbi.nlm.nih.gov/pubmed/39187430 ID - info:doi/10.2196/56935 ER - TY - JOUR AU - Garcia-Saiso, Sebastian AU - Marti, Myrna AU - Pesce, Karina AU - Luciani, Silvana AU - Mujica, Oscar AU - Hennis, Anselm AU - D'Agostino, Marcelo PY - 2024/8/12 TI - Artificial Intelligence as a Potential Catalyst to a More Equitable Cancer Care JO - JMIR Cancer SP - e57276 VL - 10 KW - digital health KW - public health KW - cancer KW - artificial intelligence KW - AI KW - catalyst KW - cancer care KW - cost KW - costs KW - demographic KW - epidemiological KW - change KW - changes KW - healthcare KW - equality KW - health system KW - mHealth KW - mobile health UR - https://cancer.jmir.org/2024/1/e57276 UR - http://dx.doi.org/10.2196/57276 UR - http://www.ncbi.nlm.nih.gov/pubmed/39133537 ID - info:doi/10.2196/57276 ER - TY - JOUR AU - Weile, Synne Kathrine AU - Mathiasen, René AU - Winther, Falck Jeanette AU - Hasle, Henrik AU - Henriksen, Tram Louise PY - 2024/7/25 TI - Hjernetegn.dk?The Danish Central Nervous System Tumor Awareness Initiative Digital Decision Support Tool: Design and Implementation Report JO - JMIR Med Inform SP - e58886 VL - 12 KW - digital health initiative KW - digital health initiatives KW - clinical decision support KW - decision support KW - decision support system KW - decision support systems KW - decision support tool KW - decision support tools KW - diagnostic delay KW - awareness initiative KW - pediatric neurology KW - pediatric CNS tumors KW - CNS tumor KW - CNS tumour KW - CNS tumours KW - co-creation KW - health systems and services KW - communication KW - central nervous system N2 - Background: Childhood tumors in the central nervous system (CNS) have longer diagnostic delays than other pediatric tumors. Vague presenting symptoms pose a challenge in the diagnostic process; it has been indicated that patients and parents may be hesitant to seek help, and health care professionals (HCPs) may lack awareness and knowledge about clinical presentation. To raise awareness among HCPs, the Danish CNS tumor awareness initiative hjernetegn.dk was launched. Objective: This study aims to present the learnings from designing and implementing a decision support tool for HCPs to reduce diagnostic delay in childhood CNS tumors. The aims also include decisions regarding strategies for dissemination and use of social media, and an evaluation of the digital impact 6 months after launch. Methods: The phases of developing and implementing the tool include participatory co-creation workshops, designing the website and digital platforms, and implementing a press and media strategy. The digital impact of hjernetegn.dk was evaluated through website analytics and social media engagement. Implementation (Results): hjernetegn.dk was launched in August 2023. The results after 6 months exceeded key performance indicators. The analysis showed a high number of website visitors and engagement, with a plateau reached 3 months after the initial launch. The LinkedIn campaign and Google Search strategy also generated a high number of impressions and clicks. Conclusions: The findings suggest that the initiative has been successfully integrated, raising awareness and providing a valuable tool for HCPs in diagnosing childhood CNS tumors. The study highlights the importance of interdisciplinary collaboration, co-creation, and ongoing community management, as well as broad dissemination strategies when introducing a digital support tool. UR - https://medinform.jmir.org/2024/1/e58886 UR - http://dx.doi.org/10.2196/58886 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/58886 ER - TY - JOUR AU - Raghu, Ananya AU - Raghu, Anisha AU - Wise, F. Jillian PY - 2024/7/24 TI - Deep Learning?Based Identification of Tissue of Origin for Carcinomas of Unknown Primary Using MicroRNA Expression: Algorithm Development and Validation JO - JMIR Bioinform Biotech SP - e56538 VL - 5 KW - cancer genomics KW - machine learning algorithms KW - deep learning KW - gene expression KW - RNA KW - RNAs KW - cancer KW - oncology KW - tumor KW - tumors KW - tissue KW - tissues KW - metastatic KW - microRNA KW - microRNAs KW - gene KW - genes KW - genomic KW - genomics KW - machine learning KW - algorithm KW - algorithms KW - carcinoma KW - genetics KW - genome KW - detection KW - bioinformatics N2 - Background: Carcinoma of unknown primary (CUP) is a subset of metastatic cancers in which the primary tissue source of the cancer cells remains unidentified. CUP is the eighth most common malignancy worldwide, accounting for up to 5% of all malignancies. Representing an exceptionally aggressive metastatic cancer, the median survival is approximately 3 to 6 months. The tissue in which cancer arises plays a key role in our understanding of sensitivities to various forms of cell death. Thus, the lack of knowledge on the tissue of origin (TOO) makes it difficult to devise tailored and effective treatments for patients with CUP. Developing quick and clinically implementable methods to identify the TOO of the primary site is crucial in treating patients with CUP. Noncoding RNAs may hold potential for origin identification and provide a robust route to clinical implementation due to their resistance against chemical degradation. Objective: This study aims to investigate the potential of microRNAs, a subset of noncoding RNAs, as highly accurate biomarkers for detecting the TOO through data-driven, machine learning approaches for metastatic cancers. Methods: We used microRNA expression data from The Cancer Genome Atlas data set and assessed various machine learning approaches, from simple classifiers to deep learning approaches. As a test of our classifiers, we evaluated the accuracy on a separate set of 194 primary tumor samples from the Sequence Read Archive. We used permutation feature importance to determine the potential microRNA biomarkers and assessed them with principal component analysis and t-distributed stochastic neighbor embedding visualizations. Results: Our results show that it is possible to design robust classifiers to detect the TOO for metastatic samples on The Cancer Genome Atlas data set, with an accuracy of up to 97% (351/362), which may be used in situations of CUP. Our findings show that deep learning techniques enhance prediction accuracy. We progressed from an initial accuracy prediction of 62.5% (226/362) with decision trees to 93.2% (337/362) with logistic regression, finally achieving 97% (351/362) accuracy using deep learning on metastatic samples. On the Sequence Read Archive validation set, a lower accuracy of 41.2% (77/188) was achieved by the decision tree, while deep learning achieved a higher accuracy of 80.4% (151/188). Notably, our feature importance analysis showed the top 3 most important features for predicting TOO to be microRNA-10b, microRNA-205, and microRNA-196b, which aligns with previous work. Conclusions: Our findings highlight the potential of using machine learning techniques to devise accurate tests for detecting TOO for CUP. Since microRNAs are carried throughout the body via extracellular vesicles secreted from cells, they may serve as key biomarkers for liquid biopsy due to their presence in blood plasma. Our work serves as a foundation toward developing blood-based cancer detection tests based on the presence of microRNA. UR - https://bioinform.jmir.org/2024/1/e56538 UR - http://dx.doi.org/10.2196/56538 UR - http://www.ncbi.nlm.nih.gov/pubmed/39046787 ID - info:doi/10.2196/56538 ER - TY - JOUR AU - Yeung, Y. Nelson C. AU - Lau, Y. Stephanie T. AU - Mak, S. Winnie W. AU - Cheng, Cecilia AU - Chan, Y. Emily Y. AU - Siu, M. Judy Y. AU - Cheung, Y. Polly S. PY - 2024/6/27 TI - Applying the Unified Theory of Acceptance and Use of Technology to Identify Factors Associated With Intention to Use Teledelivered Supportive Care Among Recently Diagnosed Breast Cancer Survivors During COVID-19 in Hong Kong: Cross-Sectional Survey JO - JMIR Cancer SP - e51072 VL - 10 KW - telehealth KW - tele-delivered supportive cancer care KW - breast cancer KW - COVID-19 KW - technology acceptance KW - UTAUT N2 - Background: Many supportive cancer care (SCC) services were teledelivered during COVID-19, but what facilitates patients? intentions to use teledelivered SCC is unknown. Objective: The study aimed to use the unified theory of acceptance and use of technology to investigate the factors associated with the intentions of breast cancer survivors (BCS) in Hong Kong to use various types of teledelivered SCC (including psychosocial care, medical consultation, complementary care, peer support groups). Favorable telehealth-related perceptions (higher performance expectancy, lower effort expectancy, more facilitating conditions, positive social influences), less technological anxiety, and greater fear of COVID-19 were hypothesized to be associated with higher intentions to use teledelivered SCC. Moreover, the associations between telehealth-related perceptions and intentions to use teledelivered SCC were hypothesized to be moderated by education level, such that associations between telehealth-related perceptions and intentions to use teledelivered SCC would be stronger among those with a higher education level. Methods: A sample of 209 (209/287, 72.8% completion rate) women diagnosed with breast cancer since the start of the COVID-19 outbreak in Hong Kong (ie, January 2020) were recruited from the Hong Kong Breast Cancer Registry to complete a cross-sectional survey between June 2022 and December 2022. Participants? intentions to use various types of teledelivered SCC (dependent variables), telehealth-related perceptions (independent variables), and sociodemographic variables (eg, education, as a moderator variable) were measured using self-reported, validated measures. Results: Hierarchical regression analysis results showed that greater confidence using telehealth, performance expectancy (believing telehealth helps with daily tasks), social influence (important others encouraging telehealth use), and facilitating conditions (having resources for telehealth use) were associated with higher intentions to use teledelivered SCC (range: ?=0.16, P=.03 to ?=0.34, P<.001). Moreover, 2-way interactions emerged between education level and 2 of the telehealth perception variables. Education level moderated the associations between (1) performance expectancy and intention to use teledelivered complementary care (?=0.34, P=.04) and (2) facilitating conditions and intention to use teledelivered peer support groups (?=0.36, P=.03). The positive associations between those telehealth perceptions and intentions were only significant among those with a higher education level. Conclusions: The findings of this study implied that enhancing BCS? skills at using telehealth, BCS? and their important others? perceived benefits of telehealth, and providing assistance for telehealth use could increase BCS? intentions to use teledelivered SCC. For intentions to use specific types of SCC, addressing relevant factors (performance expectancy, facilitating conditions) might be particularly beneficial for those with a higher education level. UR - https://cancer.jmir.org/2024/1/e51072 UR - http://dx.doi.org/10.2196/51072 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/51072 ER - TY - JOUR AU - Meng, Fan-Tsui AU - Jhuang, Jing-Rong AU - Peng, Yan-Teng AU - Chiang, Chun-Ju AU - Yang, Ya-Wen AU - Huang, Chi-Yen AU - Huang, Kuo-Ping AU - Lee, Wen-Chung PY - 2024/5/31 TI - Predicting Lung Cancer Survival to the Future: Population-Based Cancer Survival Modeling Study JO - JMIR Public Health Surveill SP - e46737 VL - 10 KW - lung cancer KW - survival KW - survivorship-period-cohort model KW - prediction KW - prognosis KW - early diagnosis KW - lung cancer screening KW - survival trend KW - population-based KW - population health KW - public health KW - surveillance KW - low-dose computed tomography N2 - Background: Lung cancer remains the leading cause of cancer-related mortality globally, with late diagnoses often resulting in poor prognosis. In response, the Lung Ambition Alliance aims to double the 5-year survival rate by 2025. Objective: Using the Taiwan Cancer Registry, this study uses the survivorship-period-cohort model to assess the feasibility of achieving this goal by predicting future survival rates of patients with lung cancer in Taiwan. Methods: This retrospective study analyzed data from 205,104 patients with lung cancer registered between 1997 and 2018. Survival rates were calculated using the survivorship-period-cohort model, focusing on 1-year interval survival rates and extrapolating to predict 5-year outcomes for diagnoses up to 2020, as viewed from 2025. Model validation involved comparing predicted rates with actual data using symmetric mean absolute percentage error. Results: The study identified notable improvements in survival rates beginning in 2004, with the predicted 5-year survival rate for 2020 reaching 38.7%, marking a considerable increase from the most recent available data of 23.8% for patients diagnosed in 2013. Subgroup analysis revealed varied survival improvements across different demographics and histological types. Predictions based on current trends indicate that achieving the Lung Ambition Alliance?s goal could be within reach. Conclusions: The analysis demonstrates notable improvements in lung cancer survival rates in Taiwan, driven by the adoption of low-dose computed tomography screening, alongside advances in diagnostic technologies and treatment strategies. While the ambitious target set by the Lung Ambition Alliance appears achievable, ongoing advancements in medical technology and health policies will be crucial. The study underscores the potential impact of continued enhancements in lung cancer management and the importance of strategic health interventions to further improve survival outcomes. UR - https://publichealth.jmir.org/2024/1/e46737 UR - http://dx.doi.org/10.2196/46737 UR - http://www.ncbi.nlm.nih.gov/pubmed/38819904 ID - info:doi/10.2196/46737 ER - TY - JOUR AU - Dong, Pei AU - Mao, Ayan AU - Qiu, Wuqi AU - Li, Guanglin PY - 2024/2/27 TI - Improvement of Cancer Prevention and Control: Reflection on the Role of Emerging Information Technologies JO - J Med Internet Res SP - e50000 VL - 26 KW - emerging information technologies KW - cancer KW - prevention and control UR - https://www.jmir.org/2024/1/e50000 UR - http://dx.doi.org/10.2196/50000 UR - http://www.ncbi.nlm.nih.gov/pubmed/38412009 ID - info:doi/10.2196/50000 ER - TY - JOUR AU - Ruan, Xiaohao AU - Zhang, Ning AU - Wang, Dawei AU - Huang, Jingyi AU - Huang, Jinlun AU - Huang, Da AU - Chun, Stacia Tsun Tsun AU - Ho, Ho Brian Sze AU - Ng, Tsui-Lin Ada AU - Tsu, Hok-Leung James AU - Zhan, Yongle AU - Na, Rong PY - 2024/1/18 TI - The Impact of Prostate-Specific Antigen Screening on Prostate Cancer Incidence and Mortality in China: 13-Year Prospective Population-Based Cohort Study JO - JMIR Public Health Surveill SP - e47161 VL - 10 KW - prostate-specific antigen KW - PSA KW - prostate cancer KW - prostate screening KW - screening interval KW - incidence KW - mortality KW - cohort study KW - electronic health record KW - China N2 - Background: The status of prostate-specific antigen (PSA) screening is unclear in China. Evidence regarding the optimal frequency and interval of serial screening for prostate cancer (PCa) is disputable. Objective: This study aimed to depict the status of PSA screening and to explore the optimal screening frequency for PCa in China. Methods: A 13-year prospective cohort study was conducted using the Chinese Electronic Health Records Research in Yinzhou study?s data set. A total of 420,941 male participants aged ?45 years were included between January 2009 and June 2022. Diagnosis of PCa, cancer-specific death, and all-cause death were obtained from the electronic health records and vital statistic system. Hazard ratios (HRs) with 95% CIs were estimated using Cox regression analysis. Results: The cumulative rate of ever PSA testing was 17.9% with an average annual percent change (AAPC) of 8.7% (95% CI 3.6%-14.0%) in the past decade in China. People with an older age, a higher BMI, higher waist circumference, tobacco smoking and alcohol drinking behaviors, higher level of physical activity, medication use, and comorbidities were more likely to receive PSA screening, whereas those with a lower education level and a widowed status were less likely to receive the test. People receiving serial screening ?3 times were at a 67% higher risk of PCa detection (HR 1.67; 95% CI 1.48-1.88) but a 64% lower risk of PCa-specific mortality (HR 0.36; 95% CI 0.18-0.70) and a 28% lower risk of overall mortality (HR 0.72; 95% CI 0.67-0.77). People following a serial screening strategy at least once every 4 years were at a 25% higher risk of PCa detection (HR 1.25; 95% CI 1.13-1.36) but 70% (HR 0.30; 95% CI 0.16-0.57) and 23% (HR 0.77; 95% CI 0.73-0.82) lower risks of PCa-specific and all-cause mortality, respectively. Conclusions: This study reveals a low coverage of PSA screening in China and provides the first evidence of its benefits in the general Chinese population. The findings of this study indicate that receiving serial screening at least once every 4 years is beneficial for overall and PCa-specific survival. Further studies based on a nationwide population and with long-term follow-up are warranted to identify the optimal screening interval in China. UR - https://publichealth.jmir.org/2024/1/e47161 UR - http://dx.doi.org/10.2196/47161 UR - http://www.ncbi.nlm.nih.gov/pubmed/38236627 ID - info:doi/10.2196/47161 ER - TY - JOUR AU - Kim, Sunghak AU - Jung, Timothy AU - Sohn, Kyung Dae AU - Chae, Yoon AU - Kim, Ae Young AU - Kang, Hyun Seung AU - Park, Yujin AU - Chang, Jung Yoon PY - 2023/11/30 TI - The Multidomain Metaverse Cancer Care Digital Platform: Development and Usability Study JO - JMIR Serious Games SP - e46242 VL - 11 KW - metaverse KW - virtual reality KW - cancer education KW - cancer care KW - digital health KW - cancer treatment KW - patient care KW - cross-sectional survey KW - digital health intervention N2 - Background: As cancer treatment methods have diversified and the importance of self-management, which lowers the dependence rate on direct hospital visits, has increased, effective cancer care education and management for health professionals and patients have become necessary. The metaverse is in the spotlight as a means of digital health that allows users to engage in cancer care education and management beyond physical constraints. However, it is difficult to find a multipurpose medical metaverse that can not only be used in the field but also complements current cancer care. Objective: This study aimed to develop an integrated metaverse cancer care platform, Dr. Meta, and examine its usability. Methods: We conducted a multicenter, cross-sectional survey between November and December 2021. A descriptive analysis was performed to examine users? experiences with Dr. Meta. In addition, a supplementary open-ended question was used to ask users for their suggestions and improvements regarding the platform. Results: Responses from 70 Korean participants (male: n=19, 27% and female: n=51, 73%) were analyzed. More than half (n=37, 54%) of the participants were satisfied with Dr. Meta; they responded that it was an interesting and immersive platform (n=50, 72%). Less than half perceived no discomfort when using Dr. Meta (n=34, 49%) and no difficulty in wearing and operating the device (n=30, 43%). Furthermore, more than half (n=50, 72%) of the participants reported that Dr. Meta would help provide non?face-to-face and noncontact services. More than half also wanted to continue using this platform in the future (n=41, 59%) and recommended it to others (n=42, 60%). Conclusions: We developed a multidomain metaverse cancer care platform that can support both health professionals and patients in non?face-to-face cancer care. The platform was uniquely disseminated and implemented in multiple regional hospitals and showed the potential to perform successful cancer care. UR - https://games.jmir.org/2023/1/e46242 UR - http://dx.doi.org/10.2196/46242 UR - http://www.ncbi.nlm.nih.gov/pubmed/38032697 ID - info:doi/10.2196/46242 ER - TY - JOUR AU - Oakley-Girvan, Ingrid AU - Yunis, Reem AU - Fonda, J. Stephanie AU - Longmire, Michelle AU - Veuthey, L. Tess AU - Shieh, Jennifer AU - Aghaee, Sara AU - Kubo, Ai AU - Davis, W. Sharon AU - Liu, Raymond AU - Neeman, Elad PY - 2023/11/21 TI - Correlation Between Remote Symptom Reporting by Caregivers and Adverse Clinical Outcomes: Mixed Methods Study JO - J Med Internet Res SP - e49100 VL - 25 KW - adverse events KW - cancer KW - decentralized clinical trials KW - electronic patient-reported outcomes KW - ePROs KW - mobile health app KW - observer-reported outcomes KW - Patient-Reported Outcomes Measurement Information System Patient-Reported Outcome Common Terminology Criteria for Adverse Events KW - patient-reported outcomes KW - PRO-CTCAE KW - PROMIS KW - remote clinical trials KW - remote monitoring KW - smartphone N2 - Background: Timely collection of patient-reported outcomes (PROs) decreases emergency department visits and hospitalizations and increases survival. However, little is known about the outcome predictivity of unpaid informal caregivers? reporting using similar clinical outcome assessments. Objective: The aim of this study is to assess whether caregivers and adults with cancer adhered to a planned schedule for electronically collecting patient-reported outcomes (PROs) and if PROs were associated with future clinical events. Methods: We developed 2 iPhone apps to collect PROs, one for patients with cancer and another for caregivers. We enrolled 52 patient-caregiver dyads from Kaiser Permanente Northern California in a nonrandomized study. Participants used the apps independently for 4 weeks. Specific clinical events were obtained from the patients? electronic health records up to 6 months following the study. We used logistic and quasi-Poisson regression analyses to test associations between PROs and clinical events. Results: Participants completed 97% (251/260) of the planned Patient-Reported Outcomes Common Terminology Criteria for Adverse Events (PRO-CTCAE) surveys and 98% (254/260) of the Patient-Reported Outcomes Measurement Information System (PROMIS) surveys. PRO-CTCAE surveys completed by caregivers were associated with patients? hospitalizations or emergency department visits, grade 3-4 treatment-related adverse events, dose reductions (P<.05), and hospice referrals (P=.03). PROMIS surveys completed by caregivers were associated with hospice referrals (P=.02). PRO-CTCAE surveys completed by patients were not associated with any clinical events, but their baseline PROMIS surveys were associated with mortality (P=.03), while their antecedent or final PROMIS surveys were associated with all clinical events examined except for total days of treatment breaks. Conclusions: In this study, caregivers and patients completed PROs using smartphone apps as requested. The association of caregiver PRO-CTCAE surveys with patient clinical events suggests that this is a feasible approach to reducing patient burden in clinical trial data collection and may help provide early information about increasing symptom severity. UR - https://www.jmir.org/2023/1/e49100 UR - http://dx.doi.org/10.2196/49100 UR - http://www.ncbi.nlm.nih.gov/pubmed/37988151 ID - info:doi/10.2196/49100 ER - TY - JOUR AU - Gong, Jeong Eun AU - Bang, Seok Chang AU - Lee, Jun Jae AU - Jeong, Min Hae AU - Baik, Ho Gwang AU - Jeong, Hoon Jae AU - Dick, Sigmund AU - Lee, Hun Gi PY - 2023/10/30 TI - Clinical Decision Support System for All Stages of Gastric Carcinogenesis in Real-Time Endoscopy: Model Establishment and Validation Study JO - J Med Internet Res SP - e50448 VL - 25 KW - atrophy KW - intestinal metaplasia KW - metaplasia KW - deep learning KW - endoscopy KW - gastric neoplasms KW - neoplasm KW - neoplasms KW - internal medicine KW - cancer KW - oncology KW - decision support KW - real time KW - gastrointestinal KW - gastric KW - intestinal KW - machine learning KW - clinical decision support system KW - CDSS KW - computer aided KW - diagnosis KW - diagnostic KW - carcinogenesis N2 - Background: Our research group previously established a deep-learning?based clinical decision support system (CDSS) for real-time endoscopy-based detection and classification of gastric neoplasms. However, preneoplastic conditions, such as atrophy and intestinal metaplasia (IM) were not taken into account, and there is no established model that classifies all stages of gastric carcinogenesis. Objective: This study aims to build and validate a CDSS for real-time endoscopy for all stages of gastric carcinogenesis, including atrophy and IM. Methods: A total of 11,868 endoscopic images were used for training and internal testing. The primary outcomes were lesion classification accuracy (6 classes: advanced gastric cancer, early gastric cancer, dysplasia, atrophy, IM, and normal) and atrophy and IM lesion segmentation rates for the segmentation model. The following tests were carried out to validate the performance of lesion classification accuracy: (1) external testing using 1282 images from another institution and (2) evaluation of the classification accuracy of atrophy and IM in real-world procedures in a prospective manner. To estimate the clinical utility, 2 experienced endoscopists were invited to perform a blind test with the same data set. A CDSS was constructed by combining the established 6-class lesion classification model and the preneoplastic lesion segmentation model with the previously established lesion detection model. Results: The overall lesion classification accuracy (95% CI) was 90.3% (89%-91.6%) in the internal test. For the performance validation, the CDSS achieved 85.3% (83.4%-97.2%) overall accuracy. The per-class external test accuracies for atrophy and IM were 95.3% (92.6%-98%) and 89.3% (85.4%-93.2%), respectively. CDSS-assisted endoscopy showed an accuracy of 92.1% (88.8%-95.4%) for atrophy and 95.5% (92%-99%) for IM in the real-world application of 522 consecutive screening endoscopies. There was no significant difference in the overall accuracy between the invited endoscopists and established CDSS in the prospective real-clinic evaluation (P=.23). The CDSS demonstrated a segmentation rate of 93.4% (95% CI 92.4%-94.4%) for atrophy or IM lesion segmentation in the internal testing. Conclusions: The CDSS achieved high performance in terms of computer-aided diagnosis of all stages of gastric carcinogenesis and demonstrated real-world application potential. UR - https://www.jmir.org/2023/1/e50448 UR - http://dx.doi.org/10.2196/50448 UR - http://www.ncbi.nlm.nih.gov/pubmed/37902818 ID - info:doi/10.2196/50448 ER - TY - JOUR AU - Diefenbach, A. Michael AU - Marziliano, Allison AU - Tagai, K. Erin AU - Pfister, Halie AU - Lapitan, Emmanuel AU - Hall, J. Simon AU - Vira, Manish AU - Ibrahim, Said AU - Aibel, Kelli AU - Kutikov, Alexander AU - Horwitz, M. Eric AU - Miyamoto, Curtis AU - Reese, C. Adam AU - Miller, M. Suzanne PY - 2023/10/20 TI - Preference Elicitation and Treatment Decision-Making Among Men Diagnosed With Prostate Cancer: Randomized Controlled Trial Results of Healium JO - J Med Internet Res SP - e46552 VL - 25 KW - prostate cancer KW - decision-making KW - decision support KW - decision tool KW - web-based intervention KW - patient preferences KW - preference elicitation software KW - preference KW - RCT KW - randomized controlled trial KW - oncology KW - prostate KW - men?s health KW - emotional N2 - Background: Elicitation of patients? preferences is an integral part of shared decision-making, the recommended approach for prostate cancer decision-making. Existing decision aids for this population often do not specifically focus on patients? preferences. Healium is a brief interactive web-based decision aid that aims to elicit patients? treatment preferences and is designed for a low health literate population. Objective: This study used a randomized controlled trial to evaluate whether Healium, designed to target preference elicitation, is as efficacious as Healing Choices, a comprehensive education and decision tool, in improving outcomes for decision-making and emotional quality of life. Methods: Patients diagnosed with localized prostate cancer who had not yet made a treatment decision were randomly assigned to the brief Healium intervention or Healing Choices, a decision aid previously developed by our group that serves as a virtual information center on prostate cancer diagnosis and treatment. Assessments were completed at baseline, 6 weeks, and 3 months post baseline, and included decisional outcomes (decisional conflict, satisfaction with decision, and preparation for decision-making), and emotional quality of life (anxiety/tension and depression), along with demographics, comorbidities, and health literacy. Results: A total of 327 individuals consented to participate in the study (171 were randomized to the Healium intervention arm and 156 were randomized to Healing Choices). The majority of the sample was non-Hispanic (272/282, 96%), White (239/314, 76%), married (251/320, 78.4%), and was on average 62.4 (SD 6.9) years old. Within both arms, there was a significant decrease in decisional conflict from baseline to 6 weeks postbaseline (Healium, P?.001; Healing Choices, P?.001), and a significant increase in satisfaction with one?s decision from 6 weeks to 3 months (Healium, P=.04; Healing Choices, P=.01). Within both arms, anxiety/tension (Healium, P=.23; Healing Choices, P=.27) and depression (Healium, P=.001; Healing Choices, P?.001) decreased from baseline to 6 weeks, but only in the case of depression was the decrease statistically significant. Conclusions: Healium, our brief decision aid focusing on treatment preference elicitation, is as successful in reducing decisional conflict as our previously tested comprehensive decision aid, Healing Choices, and has the added benefit of brevity, making it the ideal tool for integration into the physician consultation and electronic medical record. Trial Registration: ClinicalTrials.gov NCT05800483; https://clinicaltrials.gov/study/NCT05800483 UR - https://www.jmir.org/2023/1/e46552 UR - http://dx.doi.org/10.2196/46552 UR - http://www.ncbi.nlm.nih.gov/pubmed/37862103 ID - info:doi/10.2196/46552 ER - TY - JOUR AU - Liu, Jen-Hsuan AU - Shih, Chih-Yuan AU - Huang, Hsien-Liang AU - Peng, Jen-Kuei AU - Cheng, Shao-Yi AU - Tsai, Jaw-Shiun AU - Lai, Feipei PY - 2023/8/18 TI - Evaluating the Potential of Machine Learning and Wearable Devices in End-of-Life Care in Predicting 7-Day Death Events Among Patients With Terminal Cancer: Cohort Study JO - J Med Internet Res SP - e47366 VL - 25 KW - artificial intelligence KW - end-of-life care KW - machine learning KW - palliative care KW - survival prediction KW - terminal cancer KW - wearable device N2 - Background: An accurate prediction of mortality in end-of-life care is crucial but presents challenges. Existing prognostic tools demonstrate moderate performance in predicting survival across various time frames, primarily in in-hospital settings and single-time evaluations. However, these tools may fail to capture the individualized and diverse trajectories of patients. Limited evidence exists regarding the use of artificial intelligence (AI) and wearable devices, specifically among patients with cancer at the end of life. Objective: This study aimed to investigate the potential of using wearable devices and AI to predict death events among patients with cancer at the end of life. Our hypothesis was that continuous monitoring through smartwatches can offer valuable insights into the progression of patients at the end of life and enable the prediction of changes in their condition, which could ultimately enhance personalized care, particularly in outpatient or home care settings. Methods: This prospective study was conducted at the National Taiwan University Hospital. Patients diagnosed with cancer and receiving end-of-life care were invited to enroll in wards, outpatient clinics, and home-based care settings. Each participant was given a smartwatch to collect physiological data, including steps taken, heart rate, sleep time, and blood oxygen saturation. Clinical assessments were conducted weekly. The participants were followed until the end of life or up to 52 weeks. With these input features, we evaluated the prediction performance of several machine learning?based classifiers and a deep neural network in 7-day death events. We used area under the receiver operating characteristic curve (AUROC), F1-score, accuracy, and specificity as evaluation metrics. A Shapley additive explanations value analysis was performed to further explore the models with good performance. Results: From September 2021 to August 2022, overall, 1657 data points were collected from 40 patients with a median survival time of 34 days, with the detection of 28 death events. Among the proposed models, extreme gradient boost (XGBoost) yielded the best result, with an AUROC of 96%, F1-score of 78.5%, accuracy of 93%, and specificity of 97% on the testing set. The Shapley additive explanations value analysis identified the average heart rate as the most important feature. Other important features included steps taken, appetite, urination status, and clinical care phase. Conclusions: We demonstrated the successful prediction of patient deaths within the next 7 days using a combination of wearable devices and AI. Our findings highlight the potential of integrating AI and wearable technology into clinical end-of-life care, offering valuable insights and supporting clinical decision-making for personalized patient care. It is important to acknowledge that our study was conducted in a relatively small cohort; thus, further research is needed to validate our approach and assess its impact on clinical care. Trial Registration: ClinicalTrials.gov NCT05054907; https://classic.clinicaltrials.gov/ct2/show/NCT05054907 UR - https://www.jmir.org/2023/1/e47366 UR - http://dx.doi.org/10.2196/47366 UR - http://www.ncbi.nlm.nih.gov/pubmed/37594793 ID - info:doi/10.2196/47366 ER - TY - JOUR AU - Stringer, Eleah AU - Lum, J. Julian AU - Livergant, Jonathan AU - Kushniruk, W. Andre PY - 2023/6/5 TI - Decision Aids for Patients With Head and Neck Cancer: Qualitative Elicitation of Design Recommendations From Patient End Users JO - JMIR Hum Factors SP - e43551 VL - 10 KW - decision support KW - decision aid KW - app design KW - oncology KW - head and neck cancer KW - patient information needs KW - qualitative N2 - Background: Patients with head and neck cancer (HNC) carry a clinically significant symptom burden, have alterations in function (eg, impaired ability to chew, swallow, and talk), and decrease in quality of life. Furthermore, treatment impacts social activities and interactions as patients report reduced sexuality and shoulder the highest rates of depression across cancer types. Patients suffer undue anxiety because they find the treatment incomprehensible, which is partially a function of limited, understandable information. Patients? perceptions of having obtained adequate information prior to and during treatment are predictive of positive outcomes. Providing patient-centered decision support and utilizing visual images may increase understanding of treatment options and associated risks to improve satisfaction with their decision and consultation, while reducing decisional conflict. Objective: This study aims to gather requirements from survivors of HNC on the utility of key visual components to be used in the design of an electronic decision aid (eDA) to assist with decision-making on treatment options. Methods: Informed by a scoping review on eDAs for patients with HNC, screens and visualizations for an eDA were created and then presented to 12 survivors of HNC for feedback on their utility, features, and further requirements. The semistructured interviews were video-recorded and thematically analyzed to inform co-design recommendations. Results: A total of 9 themes were organized into 2 categories. The first category, eDAs and decision support, included 3 themes: familiarity with DAs, support of concept, and versatility of the prototype. The second category, evaluation of mock-up, contained 6 themes: reaction to the screens and visualizations, favorite features, complexity, preference for customizability, presentation device, and suggestions for improvement. Conclusions: All participants felt an eDA, used in the presence of their oncologist, would support a more thorough and transparent explanation of treatment or augment the quality of education received. Participants liked the simple design of the mock-ups they were shown but, ultimately, desired customizability to adapt the eDA to their individual information needs. This research highlights the value of user-centered design, rooted in acceptability and utility, in medical health informatics, recognizing cancer survivors as the ultimate knowledge holders. This research highlights the value of incorporating visuals into technology-based innovations to engage all patients in treatment decisions. UR - https://humanfactors.jmir.org/2023/1/e43551 UR - http://dx.doi.org/10.2196/43551 UR - http://www.ncbi.nlm.nih.gov/pubmed/37276012 ID - info:doi/10.2196/43551 ER - TY - JOUR AU - Hodroj, Khalil AU - Pellegrin, David AU - Menard, Cindy AU - Bachelot, Thomas AU - Durand, Thierry AU - Toussaint, Philippe AU - Dufresne, Armelle AU - Mery, Benoite AU - Tredan, Olivier AU - Goulvent, Thibaut AU - Heudel, Pierre PY - 2023/5/18 TI - A Digital Solution for an Advanced Breast Tumor Board: Pilot Application Cocreation and Implementation Study JO - JMIR Cancer SP - e39072 VL - 9 KW - digital health KW - multidisciplinary meeting KW - advanced breast cancer KW - cancer KW - breast cancer KW - tumor KW - clinician KW - confidence KW - treatment KW - pathology KW - genomic KW - care KW - patient KW - software KW - data KW - neoplastic KW - pain KW - follow-up KW - electronic medical records KW - records N2 - Background: Cancer treatment is constantly evolving toward a more personalized approach based on clinical features, imaging, and genomic pathology information. To ensure the best care for patients, multidisciplinary teams (MDTs) meet regularly to review cases. Notwithstanding, the conduction of MDT meetings is challenged by medical time restrictions, the unavailability of critical MDT members, and the additional administrative work required. These issues may result in members missing information during MDT meetings and postponed treatment. To explore and facilitate improved approaches for MDT meetings in France, using advanced breast cancers (ABCs) as a model, Centre Léon Bérard (CLB) and ROCHE Diagnostics cocreated an MDT application prototype based on structured data. Objective: In this paper, we want to describe how an application prototype was implemented for ABC MDT meetings at CLB to support clinical decisions. Methods: Prior to the initiation of cocreation activities, an organizational audit of ABC MDT meetings identified the following four key phases for the MDT: the instigation, preparation, execution, and follow-up phases. For each phase, challenges and opportunities were identified that informed the new cocreation activities. The MDT application prototype became software that integrated structured data from medical files for the visualization of the neoplastic history of a patient. The digital solution was assessed via a before-and-after audit and a survey questionnaire that was administered to health care professionals involved in the MDT. Results: The ABC MDT meeting audit was carried out during 3 MDT meetings, including 70 discussions of clinical cases before and 58 such discussions after the implementation of the MDT application prototype. We identified 33 pain points related to the preparation, execution, and follow-up phases. No issues were identified related to the instigation phase. Difficulties were grouped as follows: process challenges (n=18), technological limitations (n=9), and the lack of available resources (n=6). The preparation of MDT meetings was the phase in which the most issues (n=16) were seen. A repeat audit, which was undertaken after the implementation of the MDT application, demonstrated that (1) the discussion times per case remained comparable (2 min and 22 s vs 2 min and 14 s), (2) the capture of MDT decisions improved (all cases included a therapeutic proposal), (3) there was no postponement of treatment decisions, and (4) the mean confidence of medical oncologists in decision-making increased. Conclusions: The introduction of the MDT application prototype at CLB to support the ABC MDT seemed to improve the quality of and confidence in clinical decisions. The integration of an MDT application with the local electronic medical record and the utilization of structured data conforming to international terminologies could enable a national network of MDTs to support sustained improvements to patient care. UR - https://cancer.jmir.org/2023/1/e39072 UR - http://dx.doi.org/10.2196/39072 UR - http://www.ncbi.nlm.nih.gov/pubmed/37200077 ID - info:doi/10.2196/39072 ER - TY - JOUR AU - Han, Yuting AU - Zhu, Xia AU - Hu, Yizhen AU - Yu, Canqing AU - Guo, Yu AU - Hang, Dong AU - Pang, Yuanjie AU - Pei, Pei AU - Ma, Hongxia AU - Sun, Dianjianyi AU - Yang, Ling AU - Chen, Yiping AU - Du, Huaidong AU - Yu, Min AU - Chen, Junshi AU - Chen, Zhengming AU - Huo, Dezheng AU - Jin, Guangfu AU - Lv, Jun AU - Hu, Zhibin AU - Shen, Hongbing AU - Li, Liming PY - 2023/3/15 TI - Electronic Health Record?Based Absolute Risk Prediction Model for Esophageal Cancer in the Chinese Population: Model Development and External Validation JO - JMIR Public Health Surveill SP - e43725 VL - 9 KW - esophageal cancer KW - prediction model KW - absolute risk KW - China KW - prospective cohort KW - screening KW - primary prevention KW - development KW - external validation KW - electronic health record N2 - Background: China has the largest burden of esophageal cancer (EC). Prediction models can be used to identify high-risk individuals for intensive lifestyle interventions and endoscopy screening. However, the current prediction models are limited by small sample size and a lack of external validation, and none of them can be embedded into the booming electronic health records (EHRs) in China. Objective: This study aims to develop and validate absolute risk prediction models for EC in the Chinese population. In particular, we assessed whether models that contain only EHR-available predictors performed well. Methods: A prospective cohort recruiting 510,145 participants free of cancer from both high EC-risk and low EC-risk areas in China was used to develop EC models. Another prospective cohort of 18,441 participants was used for validation. A flexible parametric model was used to develop a 10-year absolute risk model by considering the competing risks (full model). The full model was then abbreviated by keeping only EHR-available predictors. We internally and externally validated the models by using the area under the receiver operating characteristic curve (AUC) and calibration plots and compared them based on classification measures. Results: During a median of 11.1 years of follow-up, we observed 2550 EC incident cases. The models consisted of age, sex, regional EC-risk level (high-risk areas: 2 study regions; low-risk areas: 8 regions), education, family history of cancer (simple model), smoking, alcohol use, BMI (intermediate model), physical activity, hot tea consumption, and fresh fruit consumption (full model). The performance was only slightly compromised after the abbreviation. The simple and intermediate models showed good calibration and excellent discriminating ability with AUCs (95% CIs) of 0.822 (0.783-0.861) and 0.830 (0.792-0.867) in the external validation and 0.871 (0.858-0.884) and 0.879 (0.867-0.892) in the internal validation, respectively. Conclusions: Three nested 10-year EC absolute risk prediction models for Chinese adults aged 30-79 years were developed and validated, which may be particularly useful for populations in low EC-risk areas. Even the simple model with only 5 predictors available from EHRs had excellent discrimination and good calibration, indicating its potential for broader use in tailored EC prevention. The simple and intermediate models have the potential to be widely used for both primary and secondary prevention of EC. UR - https://publichealth.jmir.org/2023/1/e43725 UR - http://dx.doi.org/10.2196/43725 UR - http://www.ncbi.nlm.nih.gov/pubmed/36781293 ID - info:doi/10.2196/43725 ER - TY - JOUR AU - Xue, Peng AU - Si, Mingyu AU - Qin, Dongxu AU - Wei, Bingrui AU - Seery, Samuel AU - Ye, Zichen AU - Chen, Mingyang AU - Wang, Sumeng AU - Song, Cheng AU - Zhang, Bo AU - Ding, Ming AU - Zhang, Wenling AU - Bai, Anying AU - Yan, Huijiao AU - Dang, Le AU - Zhao, Yuqian AU - Rezhake, Remila AU - Zhang, Shaokai AU - Qiao, Youlin AU - Qu, Yimin AU - Jiang, Yu PY - 2023/3/2 TI - Unassisted Clinicians Versus Deep Learning?Assisted Clinicians in Image-Based Cancer Diagnostics: Systematic Review With Meta-analysis JO - J Med Internet Res SP - e43832 VL - 25 KW - deep learning KW - cancer diagnosis KW - systematic review KW - meta-analysis N2 - Background: A number of publications have demonstrated that deep learning (DL) algorithms matched or outperformed clinicians in image-based cancer diagnostics, but these algorithms are frequently considered as opponents rather than partners. Despite the clinicians-in-the-loop DL approach having great potential, no study has systematically quantified the diagnostic accuracy of clinicians with and without the assistance of DL in image-based cancer identification. Objective: We systematically quantified the diagnostic accuracy of clinicians with and without the assistance of DL in image-based cancer identification. Methods: PubMed, Embase, IEEEXplore, and the Cochrane Library were searched for studies published between January 1, 2012, and December 7, 2021. Any type of study design was permitted that focused on comparing unassisted clinicians and DL-assisted clinicians in cancer identification using medical imaging. Studies using medical waveform-data graphics material and those investigating image segmentation rather than classification were excluded. Studies providing binary diagnostic accuracy data and contingency tables were included for further meta-analysis. Two subgroups were defined and analyzed, including cancer type and imaging modality. Results: In total, 9796 studies were identified, of which 48 were deemed eligible for systematic review. Twenty-five of these studies made comparisons between unassisted clinicians and DL-assisted clinicians and provided sufficient data for statistical synthesis. We found a pooled sensitivity of 83% (95% CI 80%-86%) for unassisted clinicians and 88% (95% CI 86%-90%) for DL-assisted clinicians. Pooled specificity was 86% (95% CI 83%-88%) for unassisted clinicians and 88% (95% CI 85%-90%) for DL-assisted clinicians. The pooled sensitivity and specificity values for DL-assisted clinicians were higher than for unassisted clinicians, at ratios of 1.07 (95% CI 1.05-1.09) and 1.03 (95% CI 1.02-1.05), respectively. Similar diagnostic performance by DL-assisted clinicians was also observed across the predefined subgroups. Conclusions: The diagnostic performance of DL-assisted clinicians appears better than unassisted clinicians in image-based cancer identification. However, caution should be exercised, because the evidence provided in the reviewed studies does not cover all the minutiae involved in real-world clinical practice. Combining qualitative insights from clinical practice with data-science approaches may improve DL-assisted practice, although further research is required. Trial Registration: PROSPERO CRD42021281372; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=281372 UR - https://www.jmir.org/2023/1/e43832 UR - http://dx.doi.org/10.2196/43832 UR - http://www.ncbi.nlm.nih.gov/pubmed/36862499 ID - info:doi/10.2196/43832 ER - TY - JOUR AU - Raj, Minakshi AU - Ryan, Kerry AU - Amara, Sahr Philip AU - Nong, Paige AU - Calhoun, Karen AU - Trinidad, Grace M. AU - Thiel, Daniel AU - Spector-Bagdady, Kayte AU - De Vries, Raymond AU - Kardia, Sharon AU - Platt, Jodyn PY - 2023/1/31 TI - Policy Preferences Regarding Health Data Sharing Among Patients With Cancer: Public Deliberations JO - JMIR Cancer SP - e39631 VL - 9 KW - public deliberation KW - data sharing KW - precision health KW - health information exchange N2 - Background: Precision health offers the promise of advancing clinical care in data-driven, evidence-based, and personalized ways. However, complex data sharing infrastructures, for-profit (commercial) and nonprofit partnerships, and systems for data governance have been created with little attention to the values, expectations, and preferences of patients about how they want to be engaged in the sharing and use of their health information. We solicited patient opinions about institutional policy options using public deliberation methods to address this gap. Objective: We aimed to understand the policy preferences of current and former patients with cancer regarding the sharing of health information collected in the contexts of health information exchange and commercial partnerships and to identify the values invoked and perceived risks and benefits of health data sharing considered by the participants when formulating their policy preferences. Methods: We conducted 2 public deliberations, including predeliberation and postdeliberation surveys, with patients who had a current or former cancer diagnosis (n=61). Following informational presentations, the participants engaged in facilitated small-group deliberations to discuss and rank policy preferences related to health information sharing, such as the use of a patient portal, email or SMS text messaging, signage in health care settings, opting out of commercial data sharing, payment, and preservation of the status quo. The participants ranked their policy preferences individually, as small groups by mutual agreement, and then again individually in the postdeliberation survey. Results: After deliberation, the patient portal was ranked as the most preferred policy choice. The participants ranked no change in status quo as the least preferred policy option by a wide margin. Throughout the study, the participants expressed concerns about transparency and awareness, convenience, and accessibility of information about health data sharing. Concerns about the status quo centered around a lack of transparency, awareness, and control. Specifically, the patients were not aware of how, when, or why their data were being used and wanted more transparency in these regards as well as greater control and autonomy around the use of their health data. The deliberations suggested that patient portals would be a good place to provide additional information about data sharing practices but that over time, notifications should be tailored to patient preferences. Conclusions: Our study suggests the need for increased disclosure of health information sharing practices. Describing health data sharing practices through patient portals or other mechanisms personalized to patient preferences would minimize the concerns expressed by patients about the extent of data sharing that occurs without their knowledge. Future research and policies should identify ways to increase patient control over health data sharing without reducing the societal benefits of data sharing. UR - https://cancer.jmir.org/2023/1/e39631 UR - http://dx.doi.org/10.2196/39631 UR - http://www.ncbi.nlm.nih.gov/pubmed/36719719 ID - info:doi/10.2196/39631 ER - TY - JOUR AU - Guo, Lanwei AU - Meng, Qingcheng AU - Zheng, Liyang AU - Chen, Qiong AU - Liu, Yin AU - Xu, Huifang AU - Kang, Ruihua AU - Zhang, Luyao AU - Liu, Shuzheng AU - Sun, Xibin AU - Zhang, Shaokai PY - 2023/1/6 TI - Lung Cancer Risk Prediction Nomogram in Nonsmoking Chinese Women: Retrospective Cross-sectional Cohort Study JO - JMIR Public Health Surveill SP - e41640 VL - 9 KW - lung cancer KW - risk model KW - forecasting KW - validation KW - female KW - nonsmokers N2 - Background: It is believed that smoking is not the cause of approximately 53% of lung cancers diagnosed in women globally. Objective: The study aimed to develop and validate a simple and noninvasive model that could assess and stratify lung cancer risk in nonsmoking Chinese women. Methods: Based on the population-based Cancer Screening Program in Urban China, this retrospective, cross-sectional cohort study was carried out with a vast population base and an immense number of participants. The training set and the validation set were both constructed using a random distribution of the data. Following the identification of associated risk factors by multivariable Cox regression analysis, a predictive nomogram was developed. Discrimination (area under the curve) and calibration were further performed to assess the validation of risk prediction nomogram in the training set, which was then validated in the validation set. Results: In sum, 151,834 individuals signed up to take part in the survey. Both the training set (n=75,917) and the validation set (n=75,917) were comprised of randomly selected participants. Potential predictors for lung cancer included age, history of chronic respiratory disease, first-degree family history of lung cancer, menopause, and history of benign breast disease. We displayed 1-year, 3-year, and 5-year lung cancer risk?predicting nomograms using these 5 factors. In the training set, the 1-year, 3-year, and 5-year lung cancer risk areas under the curve were 0.762, 0.718, and 0.703, respectively. In the validation set, the model showed a moderate predictive discrimination. Conclusions: We designed and validated a simple and noninvasive lung cancer risk model for nonsmoking women. This model can be applied to identify and triage people at high risk for developing lung cancers among nonsmoking women. UR - https://publichealth.jmir.org/2023/1/e41640 UR - http://dx.doi.org/10.2196/41640 UR - http://www.ncbi.nlm.nih.gov/pubmed/36607729 ID - info:doi/10.2196/41640 ER - TY - JOUR AU - Maksimenko, Jelena AU - Rodrigues, Pereira Pedro AU - Nakazawa-Mikla?evi?a, Miki AU - Pinto, David AU - Mikla?evi?s, Edvins AU - Trofimovi?s, Genadijs AU - Gardovskis, J?nis AU - Cardoso, Fatima AU - Cardoso, João Maria PY - 2022/12/29 TI - Effectiveness of Secondary Risk?Reducing Strategies in Patients With Unilateral Breast Cancer With Pathogenic Variants of BRCA1 and BRCA2 Subjected to Breast-Conserving Surgery: Evidence-Based Simulation Study JO - JMIR Form Res SP - e37144 VL - 6 IS - 12 KW - BRCA1 and BRCA2 KW - secondary prophylactic strategies KW - breast-conserving therapy KW - breast cancer N2 - Background: Approximately 62% of patients with breast cancer with a pathogenic variant (BRCA1 or BRCA2) undergo primary breast-conserving therapy. Objective: The study aims to develop a personalized risk management decision support tool for carriers of a pathogenic variant (BRCA1 or BRCA2) who underwent breast-conserving therapy for unilateral early-stage breast cancer. Methods: We developed a Bayesian network model of a hypothetical cohort of carriers of BRCA1 or BRCA2 diagnosed with stage I/II unilateral breast cancer and treated with breast-conserving treatment who underwent subsequent second primary cancer risk?reducing strategies. Using event dependencies structured according to expert knowledge and conditional probabilities obtained from published evidence, we predicted the 40-year overall survival rate of different risk-reducing strategies for 144 cohorts of women defined by the type of pathogenic variants (BRCA1 or BRCA2), age at primary breast cancer diagnosis, breast cancer subtype, stage of primary breast cancer, and presence or absence of adjuvant chemotherapy. Results: Absence of adjuvant chemotherapy was the most powerful factor that was linked to a dramatic decline in survival. There was a negligible decline in the mortality in patients with triple-negative breast cancer, who received no chemotherapy and underwent any secondary risk?reducing strategy, compared with surveillance. The potential survival benefit from any risk-reducing strategy was more modest in patients with triple-negative breast cancer who received chemotherapy compared with patients with luminal breast cancer. However, most patients with triple-negative breast cancer in stage I benefited from bilateral risk-reducing mastectomy and risk-reducing salpingo-oophorectomy or just risk-reducing salpingo-oophorectomy. Most patients with luminal stage I/II unilateral breast cancer benefited from bilateral risk-reducing mastectomy and risk-reducing salpingo-oophorectomy. The impact of risk-reducing salpingo-oophorectomy in patients with luminal breast cancer in stage I/II increased with age. Most older patients with the BRCA1 and BRCA2 pathogenic variants in exons 12-24/25 with luminal breast cancer may gain a similar survival benefit from other risk-reducing strategies or surveillance. Conclusions: Our study showed that it is mandatory to consider the complex interplay between the types of BRCA1 and BRCA2 pathogenic variants, age at primary breast cancer diagnosis, breast cancer subtype and stage, and received systemic treatment. As no prospective study results are available at the moment, our simulation model, which will integrate a decision support system in the near future, could facilitate the conversation between the health care provider and patient and help to weigh all the options for risk-reducing strategies leading to a more balanced decision. UR - https://formative.jmir.org/2022/12/e37144 UR - http://dx.doi.org/10.2196/37144 UR - http://www.ncbi.nlm.nih.gov/pubmed/36580360 ID - info:doi/10.2196/37144 ER - TY - JOUR AU - Dodd, H. Rachael AU - Zhang, Chenyue AU - Sharman, R. Ashleigh AU - Carlton, Julie AU - Tang, Ruijin AU - Rankin, M. Nicole PY - 2022/8/30 TI - Assessing Information Available for Health Professionals and Potential Participants on Lung Cancer Screening Program Websites: Cross-sectional Study JO - JMIR Cancer SP - e34264 VL - 8 IS - 3 KW - lung cancer screening KW - communication KW - recommendation KW - lung cancer KW - cancer KW - cross-sectional study KW - cancer screening KW - screening program KW - screening N2 - Background: Lung cancer is the leading cause of cancer death worldwide. The US Preventive Services Task Force (USPSTF) updated recommendations for lung cancer screening in 2021, adjusting the age of screening to 50 years (from 55 years) and reducing the number of pack-years used to estimate total firsthand cigarette smoke exposure to 20 (from 30). With many individuals using the internet to find health care information, it is important to understand what information is available for individuals contemplating lung cancer screening. Objective: This study aimed to assess the eligibility criteria and information available on lung cancer screening program websites for both health professionals and potential screening participants. Methods: A descriptive cross-sectional analysis of 151 lung cancer screening program websites of academic (n=76) and community medical centers (n=75) in the United States with information for health professionals and potential screening participants was conducted in March 2021. Presentation of eligibility criteria for potential screening participants and presence of information available specific to health professionals about lung cancer screening were the primary outcomes. Secondary outcomes included presentation of information about cost and smoking cessation, inclusion of an online risk assessment tool, mention of any clinical guidelines, and use of multimedia to present information. Results: Eligibility criteria for lung cancer screening was included in nearly all 151 websites (n=142, 94%), as well as age range (n=139, 92.1%) and smoking history (n=141, 93.4%). Age was only consistent with the latest recommendations in 14.5% (n=22) of websites, and no websites had updated smoking history. Half the websites (n=76, 50.3%) mentioned screening costs as related to the type of insurance held. A total of 23 (15.2%) websites featured an online assessment tool to determine eligibility. The same proportion (n=23, 15.2%) hosted information specifically for health professionals. In total, 44 (29.1%) websites referred to smoking cessation, and 46 (30.5%) websites used multimedia to present information, such as short videos or podcasts. Conclusions: Most websites of US lung cancer screening programs provide information about eligibility criteria, but this is not consistent and has not been updated across all websites following the latest USPSTF recommendations. Online resources require updating to present standardized information that is accessible for all. UR - https://cancer.jmir.org/2022/3/e34264 UR - http://dx.doi.org/10.2196/34264 UR - http://www.ncbi.nlm.nih.gov/pubmed/36040773 ID - info:doi/10.2196/34264 ER - TY - JOUR AU - Mangsbacka, Maria AU - Gustavell, Tina PY - 2022/5/16 TI - Nurses? Experiences Using an Interactive System to Assess and Manage Treatment-Related Symptoms of Patients With Pancreatic Cancer: Interview Study JO - JMIR Nursing SP - e36654 VL - 5 IS - 1 KW - app KW - health care professionals KW - mobile health KW - mHealth KW - nurses KW - pancreatic cancer KW - person-centered care KW - symptom-management KW - qualitative interview KW - nursing KW - interview N2 - Background: Treatment for pancreatic cancer entails symptom distress and a high burden of self-care. Patient-reported outcomes, collected with the support of mobile health (mHealth), have shown positive effects on symptom management, patient satisfaction, and quality of life for patients with cancer. For mHealth tools to become an integral part of clinical routine, experiences from health care professionals are needed. Objective: The aim of this paper is to describe nurses? experiences of integrating an interactive system (Interaktor) for symptom assessment and management into daily practice, when caring for patients following pancreaticoduodenectomy and during chemotherapy treatment due to pancreatic cancer. Methods: Patients reported symptoms via the Interaktor app daily for 6 months. In the event of alarming symptoms, an alert was triggered to the patient?s nurse who then called the patient to offer advice and support. All nurses (n=8) who assessed patients were interviewed either individually or in a group. Transcribed interviews were analyzed using qualitative thematic analysis. Results: mHealth can facilitate person-centered care by offering nurses a way to gain knowledge about patients and to build relationships. Further, obstacles to implementation could be seen due to a lack of structural prerequisites and uncertainty about multiple ways to interact with patients. Conclusions: The Interaktor system can provide person-centered care. However, to implement mHealth tools as a clinical routine, focus needs to be placed on creating the necessary organizational conditions. UR - https://nursing.jmir.org/2022/1/e36654 UR - http://dx.doi.org/10.2196/36654 UR - http://www.ncbi.nlm.nih.gov/pubmed/35576577 ID - info:doi/10.2196/36654 ER - TY - JOUR AU - Lowery, Julie AU - Fagerlin, Angela AU - Larkin, R. Angela AU - Wiener, S. Renda AU - Skurla, E. Sarah AU - Caverly, J. Tanner PY - 2022/4/1 TI - Implementation of a Web-Based Tool for Shared Decision-making in Lung Cancer Screening: Mixed Methods Quality Improvement Evaluation JO - JMIR Hum Factors SP - e32399 VL - 9 IS - 2 KW - shared decision-making KW - lung cancer KW - screening KW - clinical decision support KW - academic detailing KW - quality improvement KW - implementation N2 - Background: Lung cancer risk and life expectancy vary substantially across patients eligible for low-dose computed tomography lung cancer screening (LCS), which has important consequences for optimizing LCS decisions for different patients. To account for this heterogeneity during decision-making, web-based decision support tools are needed to enable quick calculations and streamline the process of obtaining individualized information that more accurately informs patient-clinician LCS discussions. We created DecisionPrecision, a clinician-facing web-based decision support tool, to help tailor the LCS discussion to a patient?s individualized lung cancer risk and estimated net benefit. Objective: The objective of our study is to test two strategies for implementing DecisionPrecision in primary care at eight Veterans Affairs medical centers: a quality improvement (QI) training approach and academic detailing (AD). Methods: Phase 1 comprised a multisite, cluster randomized trial comparing the effectiveness of standard implementation (adding a link to DecisionPrecision in the electronic health record vs standard implementation plus the Learn, Engage, Act, and Process [LEAP] QI training program). The primary outcome measure was the use of DecisionPrecision at each site before versus after LEAP QI training. The second phase of the study examined the potential effectiveness of AD as an implementation strategy for DecisionPrecision at all 8 medical centers. Outcomes were assessed by comparing absolute tool use before and after AD visits and conducting semistructured interviews with a subset of primary care physicians (PCPs) following the AD visits. Results: Phase 1 findings showed that sites that participated in the LEAP QI training program used DecisionPrecision significantly more often than the standard implementation sites (tool used 190.3, SD 174.8 times on average over 6 months at LEAP sites vs 3.5 SD 3.7 at standard sites; P<.001). However, this finding was confounded by the lack of screening coordinators at standard implementation sites. In phase 2, there was no difference in the 6-month tool use between before and after AD (95% CI ?5.06 to 6.40; P=.82). Follow-up interviews with PCPs indicated that the AD strategy increased provider awareness and appreciation for the benefits of the tool. However, other priorities and limited time prevented PCPs from using them during routine clinical visits. Conclusions: The phase 1 findings did not provide conclusive evidence of the benefit of a QI training approach for implementing a decision support tool for LCS among PCPs. In addition, phase 2 findings showed that our light-touch, single-visit AD strategy did not increase tool use. To enable tool use by PCPs, prediction-based tools must be fully automated and integrated into electronic health records, thereby helping providers personalize LCS discussions among their many competing demands. PCPs also need more time to engage in shared decision-making discussions with their patients. Trial Registration: ClinicalTrials.gov NCT02765412; https://clinicaltrials.gov/ct2/show/NCT02765412 UR - https://humanfactors.jmir.org/2022/2/e32399 UR - http://dx.doi.org/10.2196/32399 UR - http://www.ncbi.nlm.nih.gov/pubmed/35363144 ID - info:doi/10.2196/32399 ER - TY - JOUR AU - Mitchell, Ross Joseph AU - Szepietowski, Phillip AU - Howard, Rachel AU - Reisman, Phillip AU - Jones, D. Jennie AU - Lewis, Patricia AU - Fridley, L. Brooke AU - Rollison, E. Dana PY - 2022/3/23 TI - A Question-and-Answer System to Extract Data From Free-Text Oncological Pathology Reports (CancerBERT Network): Development Study JO - J Med Internet Res SP - e27210 VL - 24 IS - 3 KW - natural language processing KW - NLP KW - BERT KW - transformer KW - pathology KW - ICD-O-3 KW - deep learning KW - cancer N2 - Background: Information in pathology reports is critical for cancer care. Natural language processing (NLP) systems used to extract information from pathology reports are often narrow in scope or require extensive tuning. Consequently, there is growing interest in automated deep learning approaches. A powerful new NLP algorithm, bidirectional encoder representations from transformers (BERT), was published in late 2018. BERT set new performance standards on tasks as diverse as question answering, named entity recognition, speech recognition, and more. Objective: The aim of this study is to develop a BERT-based system to automatically extract detailed tumor site and histology information from free-text oncological pathology reports. Methods: We pursued three specific aims: extract accurate tumor site and histology descriptions from free-text pathology reports, accommodate the diverse terminology used to indicate the same pathology, and provide accurate standardized tumor site and histology codes for use by downstream applications. We first trained a base language model to comprehend the technical language in pathology reports. This involved unsupervised learning on a training corpus of 275,605 electronic pathology reports from 164,531 unique patients that included 121 million words. Next, we trained a question-and-answer (Q&A) model that connects a Q&A layer to the base pathology language model to answer pathology questions. Our Q&A system was designed to search for the answers to two predefined questions in each pathology report: What organ contains the tumor? and What is the kind of tumor or carcinoma? This involved supervised training on 8197 pathology reports, each with ground truth answers to these 2 questions determined by certified tumor registrars. The data set included 214 tumor sites and 193 histologies. The tumor site and histology phrases extracted by the Q&A model were used to predict International Classification of Diseases for Oncology, Third Edition (ICD-O-3), site and histology codes. This involved fine-tuning two additional BERT models: one to predict site codes and another to predict histology codes. Our final system includes a network of 3 BERT-based models. We call this CancerBERT network (caBERTnet). We evaluated caBERTnet using a sequestered test data set of 2050 pathology reports with ground truth answers determined by certified tumor registrars. Results: caBERTnet?s accuracies for predicting group-level site and histology codes were 93.53% (1895/2026) and 97.6% (1993/2042), respectively. The top 5 accuracies for predicting fine-grained ICD-O-3 site and histology codes with 5 or more samples each in the training data set were 92.95% (1794/1930) and 96.01% (1853/1930), respectively. Conclusions: We have developed an NLP system that outperforms existing algorithms at predicting ICD-O-3 codes across an extensive range of tumor sites and histologies. Our new system could help reduce treatment delays, increase enrollment in clinical trials of new therapies, and improve patient outcomes. UR - https://www.jmir.org/2022/3/e27210 UR - http://dx.doi.org/10.2196/27210 UR - http://www.ncbi.nlm.nih.gov/pubmed/35319481 ID - info:doi/10.2196/27210 ER - TY - JOUR AU - Hibler, A. Elizabeth AU - Fought, J. Angela AU - Kershaw, N. Kiarri AU - Molsberry, Rebecca AU - Nowakowski, Virginia AU - Lindner, Deborah PY - 2022/2/24 TI - Novel Interactive Tool for Breast and Ovarian Cancer Risk Assessment (Bright Pink Assess Your Risk): Development and Usability Study JO - J Med Internet Res SP - e29124 VL - 24 IS - 2 KW - breast cancer KW - ovarian cancer KW - risk assessment KW - genetic testing N2 - Background: The lifetime risk of breast and ovarian cancer is significantly higher among women with genetic susceptibility or a strong family history. However, current risk assessment tools and clinical practices may identify only 10% of asymptomatic carriers of susceptibility genes. Bright Pink developed the Assess Your Risk (AYR) tool to estimate breast and ovarian cancer risk through a user-friendly, informative web-based quiz for risk assessment at the population level. Objective: This study aims to present the AYR tool, describe AYR users, and present evidence that AYR works as expected by comparing classification using the AYR tool with gold standard genetic testing guidelines. Methods: The AYR is a recently developed population-level risk assessment tool that includes 26 questions based on the National Comprehensive Cancer Network (NCCN) guidelines and factors from other commonly used risk assessment tools. We included all women who completed the AYR between November 2018 and January 2019, with the exception of self-reported cancer or no knowledge of family history. We compared AYR classifications with those that were independently created using NCCN criteria using measures of validity and the McNemar test. Results: There were 143,657 AYR completions, and most participants were either at increased or average risk for breast cancer or ovarian cancer (137,315/143,657, 95.59%). Using our estimates of increased and average risk as the gold standard, based on the NCCN guidelines, we estimated the sensitivity and specificity for the AYR algorithm?generated risk categories as 100% and 89.9%, respectively (P<.001). The specificity improved when we considered the additional questions asked by the AYR to define increased risk, which were not examined by the NCCN criteria. By race, ethnicity, and age group; we found that the lowest observed specificity was for the Asian race (85.9%) and the 30 to 39 years age group (87.6%) for the AYR-generated categories compared with the NCCN criteria. Conclusions: These results demonstrate that Bright Pink?s AYR is an accurate tool for use by the general population to identify women at increased risk of breast and ovarian cancer. We plan to validate the tool longitudinally in future studies, including the impact of race, ethnicity, and age on breast and ovarian cancer risk assessment. UR - https://www.jmir.org/2022/2/e29124 UR - http://dx.doi.org/10.2196/29124 UR - http://www.ncbi.nlm.nih.gov/pubmed/35200148 ID - info:doi/10.2196/29124 ER - TY - JOUR AU - Shah, K. Sumit AU - McElfish, A. Pearl PY - 2022/2/24 TI - Cancer Screening Recommendations During the COVID-19 Pandemic: Scoping Review JO - JMIR Cancer SP - e34392 VL - 8 IS - 1 KW - COVID-19 KW - cancer prevention and early detection KW - cancer screenings KW - breast cancer screening KW - cervical cancer screening KW - colorectal cancer screening N2 - Background: Cancer screening tests are recommended to prevent cancer-associated mortality by detecting precancerous and cancerous lesions in early stages. The COVID-19 pandemic disrupted the use of preventive health care services. Although there was an increase in the number of cancer screening tests beginning in late 2020, screenings remained 29% to 36% lower than in the prepandemic era. Objective: The aim of this review is to assist health care providers in identifying approaches for prioritizing patients and increasing breast, cervical, and colorectal cancer screening during the uncertainty of the COVID-19 pandemic. Methods: We used the scoping review framework to identify articles on PubMed and EBSCO databases. A total of 403 articles were identified, and 23 articles were selected for this review. The literature review ranged from January 1, 2020, to September 30, 2021. Results: The articles included two primary categories of recommendations: (1) risk stratification and triage to prioritize screenings and (2) alternative methods to conduct cancer screenings. Risk stratification and triage recommendations focused on prioritizing high-risk patients with an abnormal or suspicious result on the previous screening test, patients in certain age groups and sex, patients with a personal medical or family cancer history, patients that are currently symptomatic, and patients that are predisposed to hereditary cancers and cancer-causing mutations. Other recommended strategies included identifying areas facing the most disparities, creating algorithms and using artificial intelligence to create cancer risk scores, leveraging in-person visits to assess cancer risk, and providing the option of open access screenings where patients can schedule screenings and can be assigned a priority category by health care staff. Some recommended using telemedicine to categorize patients and determine screening eligibility for patients with new complaints. Several articles noted the importance of implementing preventive measures such as COVID-19 screening prior to the procedures, maintaining hygiene measures, and social distancing in waiting rooms. Alternative screening methods that do not require an in-person clinic visit and can effectively screen patients for cancers included mailing self-collection sampling kits for cervical and colorectal cancers, and implementing or expanding mobile screening units. Conclusions: Although the COVID-19 pandemic had devastating effects on population health globally, it could be an opportunity to adapt and evolve cancer screening methods. Disruption often creates innovation, and focus on alternative methods for cancer screenings may help reach rural and underresourced areas after the pandemic has ended. UR - https://cancer.jmir.org/2022/1/e34392 UR - http://dx.doi.org/10.2196/34392 UR - http://www.ncbi.nlm.nih.gov/pubmed/35142621 ID - info:doi/10.2196/34392 ER - TY - JOUR AU - Mosa, Mohammad Abu Saleh AU - Rana, Zaman Md Kamruz AU - Islam, Humayera AU - Hossain, Mosharraf A. K. M. AU - Yoo, Illhoi PY - 2021/12/2 TI - A Smartphone-Based Decision Support Tool for Predicting Patients at Risk of Chemotherapy-Induced Nausea and Vomiting: Retrospective Study on App Development Using Decision Tree Induction JO - JMIR Mhealth Uhealth SP - e27024 VL - 9 IS - 12 KW - chemotherapy KW - CINV risk factors KW - data mining KW - prediction KW - decision trees KW - clinical decision support KW - smartphone app N2 - Background: Chemotherapy-induced nausea and vomiting (CINV) are the two most frightful and unpleasant side effects of chemotherapy. CINV is accountable for poor treatment outcomes, treatment failure, or even death. It can affect patients' overall quality of life, leading to many social, economic, and clinical consequences. Objective: This study compared the performances of different data mining models for predicting the risk of CINV among the patients and developed a smartphone app for clinical decision support to recommend the risk of CINV at the point of care. Methods: Data were collected by retrospective record review from the electronic medical records used at the University of Missouri Ellis Fischel Cancer Center. Patients who received chemotherapy and standard antiemetics at the oncology outpatient service from June 1, 2010, to July 31, 2012, were included in the study. There were six independent data sets of patients based on emetogenicity (low, moderate, and high) and two phases of CINV (acute and delayed). A total of 14 risk factors of CINV were chosen for data mining. For our study, we used five popular data mining algorithms: (1) naive Bayes algorithm, (2) logistic regression classifier, (3) neural network, (4) support vector machine (using sequential minimal optimization), and (5) decision tree. Performance measures, such as accuracy, sensitivity, and specificity with 10-fold cross-validation, were used for model comparisons. A smartphone app called CINV Risk Prediction Application was developed using the ResearchKit in iOS utilizing the decision tree algorithm, which conforms to the criteria of explainable, usable, and actionable artificial intelligence. The app was created using both the bulk questionnaire approach and the adaptive approach. Results: The decision tree performed well in both phases of high emetogenic chemotherapies, with a significant margin compared to the other algorithms. The accuracy measure for the six patient groups ranged from 79.3% to 94.8%. The app was developed using the results from the decision tree because of its consistent performance and simple, explainable nature. The bulk questionnaire approach asks 14 questions in the smartphone app, while the adaptive approach can determine questions based on the previous questions' answers. The adaptive approach saves time and can be beneficial when used at the point of care. Conclusions: This study solved a real clinical problem, and the solution can be used for personalized and precise evidence-based CINV management, leading to a better life quality for patients and reduced health care costs. UR - https://mhealth.jmir.org/2021/12/e27024 UR - http://dx.doi.org/10.2196/27024 UR - http://www.ncbi.nlm.nih.gov/pubmed/34860677 ID - info:doi/10.2196/27024 ER - TY - JOUR AU - Chavez-Yenter, Daniel AU - Kimball, E. Kadyn AU - Kohlmann, Wendy AU - Lorenz Chambers, Rachelle AU - Bradshaw, L. Richard AU - Espinel, F. Whitney AU - Flynn, Michael AU - Gammon, Amanda AU - Goldberg, Eric AU - Hagerty, J. Kelsi AU - Hess, Rachel AU - Kessler, Cecilia AU - Monahan, Rachel AU - Temares, Danielle AU - Tobik, Katie AU - Mann, M. Devin AU - Kawamoto, Kensaku AU - Del Fiol, Guilherme AU - Buys, S. Saundra AU - Ginsburg, Ophira AU - Kaphingst, A. Kimberly PY - 2021/11/18 TI - Patient Interactions With an Automated Conversational Agent Delivering Pretest Genetics Education: Descriptive Study JO - J Med Internet Res SP - e29447 VL - 23 IS - 11 KW - cancer KW - genetic testing KW - virtual conversational agent KW - user interaction KW - smartphone KW - mobile phone N2 - Background: Cancer genetic testing to assess an individual?s cancer risk and to enable genomics-informed cancer treatment has grown exponentially in the past decade. Because of this continued growth and a shortage of health care workers, there is a need for automated strategies that provide high-quality genetics services to patients to reduce the clinical demand for genetics providers. Conversational agents have shown promise in managing mental health, pain, and other chronic conditions and are increasingly being used in cancer genetic services. However, research on how patients interact with these agents to satisfy their information needs is limited. Objective: Our primary aim is to assess user interactions with a conversational agent for pretest genetics education. Methods: We conducted a feasibility study of user interactions with a conversational agent who delivers pretest genetics education to primary care patients without cancer who are eligible for cancer genetic evaluation. The conversational agent provided scripted content similar to that delivered in a pretest genetic counseling visit for cancer genetic testing. Outside of a core set of information delivered to all patients, users were able to navigate within the chat to request additional content in their areas of interest. An artificial intelligence?based preprogrammed library was also established to allow users to ask open-ended questions to the conversational agent. Transcripts of the interactions were recorded. Here, we describe the information selected, time spent to complete the chat, and use of the open-ended question feature. Descriptive statistics were used for quantitative measures, and thematic analyses were used for qualitative responses. Results: We invited 103 patients to participate, of which 88.3% (91/103) were offered access to the conversational agent, 39% (36/91) started the chat, and 32% (30/91) completed the chat. Most users who completed the chat indicated that they wanted to continue with genetic testing (21/30, 70%), few were unsure (9/30, 30%), and no patient declined to move forward with testing. Those who decided to test spent an average of 10 (SD 2.57) minutes on the chat, selected an average of 1.87 (SD 1.2) additional pieces of information, and generally did not ask open-ended questions. Those who were unsure spent 4 more minutes on average (mean 14.1, SD 7.41; P=.03) on the chat, selected an average of 3.67 (SD 2.9) additional pieces of information, and asked at least one open-ended question. Conclusions: The pretest chat provided enough information for most patients to decide on cancer genetic testing, as indicated by the small number of open-ended questions. A subset of participants were still unsure about receiving genetic testing and may require additional education or interpersonal support before making a testing decision. Conversational agents have the potential to become a scalable alternative for pretest genetics education, reducing the clinical demand on genetics providers. UR - https://www.jmir.org/2021/11/e29447 UR - http://dx.doi.org/10.2196/29447 UR - http://www.ncbi.nlm.nih.gov/pubmed/34792472 ID - info:doi/10.2196/29447 ER - TY - JOUR AU - Marron, Manuela AU - Brackmann, Kim Lara AU - Schwarz, Heike AU - Hummel-Bartenschlager, Willempje AU - Zahnreich, Sebastian AU - Galetzka, Danuta AU - Schmitt, Iris AU - Grad, Christian AU - Drees, Philipp AU - Hopf, Johannes AU - Mirsch, Johanna AU - Scholz-Kreisel, Peter AU - Kaatsch, Peter AU - Poplawski, Alicia AU - Hess, Moritz AU - Binder, Harald AU - Hankeln, Thomas AU - Blettner, Maria AU - Schmidberger, Heinz PY - 2021/11/11 TI - Identification of Genetic Predispositions Related to Ionizing Radiation in Primary Human Skin Fibroblasts From Survivors of Childhood and Second Primary Cancer as Well as Cancer-Free Controls: Protocol for the Nested Case-Control Study KiKme JO - JMIR Res Protoc SP - e32395 VL - 10 IS - 11 KW - fibroblast KW - irradiation KW - childhood cancer KW - neoplasm KW - second primary neoplasm KW - second cancer KW - study design KW - participation KW - feasibility KW - cell line N2 - Background: Therapy for a first primary neoplasm (FPN) in childhood with high doses of ionizing radiation is an established risk factor for second primary neoplasms (SPN). An association between exposure to low doses and childhood cancer is also suggested; however, results are inconsistent. As only subgroups of children with FPNs develop SPNs, an interaction between radiation, genetic, and other risk factors is presumed to influence cancer development. Objective: Therefore, the population-based, nested case-control study KiKme aims to identify differences in genetic predisposition and radiation response between childhood cancer survivors with and without SPNs as well as cancer-free controls. Methods: We conducted a population-based, nested case-control study KiKme. Besides questionnaire information, skin biopsies and saliva samples are available. By measuring individual reactions to different exposures to radiation (eg, 0.05 and 2 Gray) in normal somatic cells of the same person, our design enables us to create several exposure scenarios for the same person simultaneously and measure several different molecular markers (eg, DNA, messenger RNA, long noncoding RNA, copy number variation). Results: Since 2013, 101 of 247 invited SPN patients, 340 of 1729 invited FPN patients, and 150 of 246 invited cancer-free controls were recruited and matched by age and sex. Childhood cancer patients were additionally matched by tumor morphology, year of diagnosis, and age at diagnosis. Participants reported on lifestyle, socioeconomical, and anthropometric factors, as well as on medical radiation history, health, and family history of diseases (n=556). Primary human fibroblasts from skin biopsies of the participants were cultivated (n=499) and cryopreserved (n=3886). DNA was extracted from fibroblasts (n=488) and saliva (n=510). Conclusions: This molecular-epidemiological study is the first to combine observational epidemiological research with standardized experimental components in primary human skin fibroblasts to identify genetic predispositions related to ionizing radiation in childhood and SPNs. In the future, fibroblasts of the participants will be used for standardized irradiation experiments, which will inform analysis of the case-control study and vice versa. Differences between participants will be identified using several molecular markers. With its innovative combination of experimental and observational components, this new study will provide valuable data to forward research on radiation-related risk factors in childhood cancer and SPNs. International Registered Report Identifier (IRRID): DERR1-10.2196/32395 UR - https://www.researchprotocols.org/2021/11/e32395 UR - http://dx.doi.org/10.2196/32395 UR - http://www.ncbi.nlm.nih.gov/pubmed/34762066 ID - info:doi/10.2196/32395 ER - TY - JOUR AU - Yung, Alan AU - Kay, Judy AU - Beale, Philip AU - Gibson, A. Kathryn AU - Shaw, Tim PY - 2021/10/26 TI - Computer-Based Decision Tools for Shared Therapeutic Decision-making in Oncology: Systematic Review JO - JMIR Cancer SP - e31616 VL - 7 IS - 4 KW - oncology KW - cancer KW - computer-based KW - decision support KW - decision-making KW - system KW - tool KW - machine learning KW - artificial intelligence KW - uncertainty KW - shared decision-making N2 - Background: Therapeutic decision-making in oncology is a complex process because physicians must consider many forms of medical data and protocols. Another challenge for physicians is to clearly communicate their decision-making process to patients to ensure informed consent. Computer-based decision tools have the potential to play a valuable role in supporting this process. Objective: This systematic review aims to investigate the extent to which computer-based decision tools have been successfully adopted in oncology consultations to improve patient-physician joint therapeutic decision-making. Methods: This review was conducted in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 checklist and guidelines. A literature search was conducted on February 4, 2021, across the Cochrane Database of Systematic Reviews (from 2005 to January 28, 2021), the Cochrane Central Register of Controlled Trials (December 2020), MEDLINE (from 1946 to February 4, 2021), Embase (from 1947 to February 4, 2021), Web of Science (from 1900 to 2021), Scopus (from 1969 to 2021), and PubMed (from 1991 to 2021). We used a snowball approach to identify additional studies by searching the reference lists of the studies included for full-text review. Additional supplementary searches of relevant journals and gray literature websites were conducted. The reviewers screened the articles eligible for review for quality and inclusion before data extraction. Results: There are relatively few studies looking at the use of computer-based decision tools in oncology consultations. Of the 4431 unique articles obtained from the searches, only 10 (0.22%) satisfied the selection criteria. From the 10 selected studies, 8 computer-based decision tools were identified. Of the 10 studies, 6 (60%) were conducted in the United States. Communication and information-sharing were improved between physicians and patients. However, physicians did not change their habits to take advantage of computer-assisted decision-making tools or the information they provide. On average, the use of these computer-based decision tools added approximately 5 minutes to the total length of consultations. In addition, some physicians felt that the technology increased patients? anxiety. Conclusions: Of the 10 selected studies, 6 (60%) demonstrated positive outcomes, 1 (10%) showed negative results, and 3 (30%) were neutral. Adoption of computer-based decision tools during oncology consultations continues to be low. This review shows that information-sharing and communication between physicians and patients can be improved with the assistance of technology. However, the lack of integration with electronic health records is a barrier. This review provides key requirements for enhancing the chance of success of future computer-based decision tools. However, it does not show the effects of health care policies, regulations, or business administration on physicians? propensity to adopt the technology. Nevertheless, it is important that future research address the influence of these higher-level factors as well. Trial Registration: PROSPERO International Prospective Register of Systematic Reviews CRD42021226087; https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42021226087 UR - https://cancer.jmir.org/2021/4/e31616 UR - http://dx.doi.org/10.2196/31616 UR - http://www.ncbi.nlm.nih.gov/pubmed/34544680 ID - info:doi/10.2196/31616 ER - TY - JOUR AU - Yamada, Reiko AU - Isaji, Shuji AU - Fujii, Takehiro AU - Mizuno, Shugo AU - Kishiwada, Masashi AU - Murata, Yasuhiro AU - Hayasaki, Aoi AU - Inoue, Hiroyuki AU - Umeda, Yuhei AU - Tanaka, Kyosuke AU - Hamada, Yasuhiko AU - Tsuboi, Junya AU - Kato, Toshio AU - Kondo, Yoshihiro AU - Matsuda, Shinsuke AU - Watanabe, Noriko AU - Ogura, Toru AU - Tamaru, Satoshi PY - 2021/10/22 TI - Improving the Prognosis of Pancreatic Cancer Through Early Detection: Protocol for a Prospective Observational Study JO - JMIR Res Protoc SP - e26898 VL - 10 IS - 10 KW - pancreatic cancer KW - prognosis KW - early diagnosis KW - risk factors KW - scoring system KW - referral N2 - Background: Pancreatic cancer is associated with high mortality and its rates of detection are very low; as such, the disease is typically diagnosed at an advanced stage. A number of risk factors for pancreatic cancer have been reported and may be used to identify individuals at high risk for the development of this disease. Objective: The aim of this prospective, observational trial is to evaluate a scoring metric for systematic early detection of pancreatic cancer in Mie Prefecture, Japan. Methods: Eligible patients aged 20 years and older will be referred from participating clinics in the Tsu City area to the Faculty of Medicine, Gastroenterology, and Hepatology at Mie University Graduate School, until September 30, 2022. Participants will undergo a detailed examination for pancreatic cancer. Data collection will include diagnostic and follow-up imaging data and disease staging information. Results: The study was initiated in September 2020 and aims to recruit at least 150 patients in a 2-year period. Recruitment of patients is currently still underway. Final data analysis is expected to be complete by March 2025. Conclusions: This study will provide insights into the feasibility of using a scoring system for the early detection of pancreatic cancer, thus potentially improving the survival outcomes of diagnosed patients. Trial Registration: UMIN-CTR Clinical Trials Registry UMIN000041624; https://tinyurl.com/94tbbn3s International Registered Report Identifier (IRRID): DERR1-10.2196/26898 UR - https://www.researchprotocols.org/2021/10/e26898 UR - http://dx.doi.org/10.2196/26898 UR - http://www.ncbi.nlm.nih.gov/pubmed/34677132 ID - info:doi/10.2196/26898 ER - TY - JOUR AU - Meng, Weilin AU - Mosesso, M. Kelly AU - Lane, A. Kathleen AU - Roberts, R. Anna AU - Griffith, Ashley AU - Ou, Wanmei AU - Dexter, R. Paul PY - 2021/10/12 TI - An Automated Line-of-Therapy Algorithm for Adults With Metastatic Non?Small Cell Lung Cancer: Validation Study Using Blinded Manual Chart Review JO - JMIR Med Inform SP - e29017 VL - 9 IS - 10 KW - automated algorithm KW - line of therapy KW - longitudinal changes KW - manual chart review KW - non?small cell lung cancer KW - systemic anticancer therapy N2 - Background: Extraction of line-of-therapy (LOT) information from electronic health record and claims data is essential for determining longitudinal changes in systemic anticancer therapy in real-world clinical settings. Objective: The aim of this retrospective cohort analysis is to validate and refine our previously described open-source LOT algorithm by comparing the output of the algorithm with results obtained through blinded manual chart review. Methods: We used structured electronic health record data and clinical documents to identify 500 adult patients treated for metastatic non?small cell lung cancer with systemic anticancer therapy from 2011 to mid-2018; we assigned patients to training (n=350) and test (n=150) cohorts, randomly divided proportional to the overall ratio of simple:complex cases (n=254:246). Simple cases were patients who received one LOT and no maintenance therapy; complex cases were patients who received more than one LOT and/or maintenance therapy. Algorithmic changes were performed using the training cohort data, after which the refined algorithm was evaluated against the test cohort. Results: For simple cases, 16 instances of discordance between the LOT algorithm and chart review prerefinement were reduced to 8 instances postrefinement; in the test cohort, there was no discordance between algorithm and chart review. For complex cases, algorithm refinement reduced the discordance from 68 to 62 instances, with 37 instances in the test cohort. The percentage agreement between LOT algorithm output and chart review for patients who received one LOT was 89% prerefinement, 93% postrefinement, and 93% for the test cohort, whereas the likelihood of precise matching between algorithm output and chart review decreased with an increasing number of unique regimens. Several areas of discordance that arose from differing definitions of LOTs and maintenance therapy could not be objectively resolved because of a lack of precise definitions in the medical literature. Conclusions: Our findings identify common sources of discordance between the LOT algorithm and clinician documentation, providing the possibility of targeted algorithm refinement. UR - https://medinform.jmir.org/2021/10/e29017 UR - http://dx.doi.org/10.2196/29017 UR - http://www.ncbi.nlm.nih.gov/pubmed/34636730 ID - info:doi/10.2196/29017 ER - TY - JOUR AU - Laryionava, Katsiaryna AU - Schildmann, Jan AU - Wensing, Michael AU - Wedding, Ullrich AU - Surmann, Bastian AU - Woydack, Lena AU - Krug, Katja AU - Winkler, Eva PY - 2021/9/17 TI - Development and Evaluation of a Decision Aid to Support Patients? Participatory Decision-Making for Tumor-Specific and Palliative Therapy for Advanced Cancer: Protocol for a Pre-Post Study JO - JMIR Res Protoc SP - e24954 VL - 10 IS - 9 KW - decision aid KW - neoplasms KW - palliative care KW - clinical trials KW - longitudinal study N2 - Background: To support advanced cancer patients and their oncologists in therapeutic decisions, we aim to develop a decision aid (DA) in a multiphased, bicentric study. The DA aims to help patients to better understand risks and benefits of the available treatment options including the options of standard palliative care or cancer-specific treatment (ie, off-label drug use within an individual treatment plan). Objective: This study protocol outlines the development and testing of the DA in a pre-post study targeting a heterogeneous population of advanced cancer patients. Methods: In the first step, we will assess patients? information and decisional needs as well as the views of the health care providers regarding the content and implementation of the DA. Through a scoping review, we aim to analyze specific characteristics of the decision-making process and to specify the treatment options, outcomes, and probabilities. An interdisciplinary research group of experts will develop and review the DA. In the second step, testing of the DA (design and field testing) with patients and oncologists will be conducted. As a last step, we will run a pre-post design study with 70 doctor-patient encounters to assess improvements on the primary study outcome: patients? level of decisional conflict. In addition, the user acceptance of all involved parties will be tested. Results: Interviews with cancer patients, oncologists, and health care providers (ie, nurses, nutritionists) as well as a literature review from phase I have been completed. The field testing is scheduled for April 2021 to August 2021, with the final revision scheduled for September 2021. The pre-post study of the DA and acceptance testing are scheduled to start in October 2021 and shall be finished in September 2022. Conclusions: A unique feature of this study is the development of a DA for patients with different types of advanced cancer, which covers a wide range of topics relevant for patients near the end of life such as forgoing cancer-specific therapy and switching to best supportive care. Trial Registration: ClinicalTrials.gov NCT04606238; https://clinicaltrials.gov/ct2/show/NCT04606238. International Registered Report Identifier (IRRID): DERR1-10.2196/24954 UR - https://www.researchprotocols.org/2021/9/e24954 UR - http://dx.doi.org/10.2196/24954 UR - http://www.ncbi.nlm.nih.gov/pubmed/34533464 ID - info:doi/10.2196/24954 ER - TY - JOUR AU - Ainiwaer, Abidan AU - Zhang, Shuai AU - Ainiwaer, Xiayiabasi AU - Ma, Feicheng PY - 2021/9/16 TI - Effects of Message Framing on Cancer Prevention and Detection Behaviors, Intentions, and Attitudes: Systematic Review and Meta-analysis JO - J Med Internet Res SP - e27634 VL - 23 IS - 9 KW - gain framing KW - loss framing KW - attitude KW - intention KW - behaviors KW - cancer prevention KW - cancer detection N2 - Background: With the increasing health care burden of cancer, public health organizations are increasingly emphasizing the importance of calling people to engage in long-term prevention and periodical detection. How to best deliver behavioral recommendations and health outcomes in messaging is an important issue. Objective: This study aims to disaggregate the effects of gain-framed and loss-framed messages on cancer prevention and detection behaviors and intentions and attitudes, which has the potential to inform cancer control programs. Methods: A search of three electronic databases (Web of Science, Scopus, and PubMed) was conducted for studies published between January 2000 and December 2020. After a good agreement achieved on a sample by two authors, the article selection (?=0.8356), quality assessment (?=0.8137), and data extraction (?=0.9804) were mainly performed by one author. The standardized mean difference (attitude and intention) and the odds ratio (behaviors) were calculated to evaluate the effectiveness of message framing (gain-framed message and loss-framed message). Calculations were conducted, and figures were produced by Review Manager 5.3. Results: The title and abstract of 168 unique citations were scanned, of which 53 were included for a full-text review. A total of 24 randomized controlled trials were included, predominantly examining message framing on cancer prevention and detection behavior change interventions. There were 9 studies that used attitude to predict message framing effect and 16 studies that used intention, whereas 6 studies used behavior to examine the message framing effect directly. The use of loss-framed messages improved cancer detection behavior (OR 0.76, 95% CI 0.64-0.90; P=.001), and the results from subgroup analysis indicated that the effect would be weak with time. No effect of framing was found when effectiveness was assessed by attitudes (prevention: SMD=0.02, 95% CI ?0.13 to 0.17; P=.79; detection: SMD=?0.05, 95% CI ?0.15 to 0.05; P=.32) or intentions (prevention: SMD=?0.05, 95% CI ?0.19 to 0.09; P=.48; detection: SMD=0.02, 95% CI ?0.26 to 0.29; P=.92) among studies encouraging cancer prevention and cancer detection. Conclusions: Research has shown that it is almost impossible to change people's attitudes or intentions about cancer prevention and detection with a gain-framed or loss-framed message. However, loss-framed messages have achieved preliminary success in persuading people to adopt cancer detection behaviors. Future studies could improve the intervention design to achieve better intervention effectiveness. UR - https://www.jmir.org/2021/9/e27634 UR - http://dx.doi.org/10.2196/27634 UR - http://www.ncbi.nlm.nih.gov/pubmed/34528887 ID - info:doi/10.2196/27634 ER - TY - JOUR AU - Blasi, Livio AU - Bordonaro, Roberto AU - Serretta, Vincenzo AU - Piazza, Dario AU - Firenze, Alberto AU - Gebbia, Vittorio PY - 2021/9/10 TI - Virtual Clinical and Precision Medicine Tumor Boards?Cloud-Based Platform?Mediated Implementation of Multidisciplinary Reviews Among Oncology Centers in the COVID-19 Era: Protocol for an Observational Study JO - JMIR Res Protoc SP - e26220 VL - 10 IS - 9 KW - virtual tumor board KW - multidisciplinary collaboration KW - oncology KW - multidisciplinary communication KW - health services KW - multidisciplinary oncology consultations KW - virtual health KW - digital health KW - precision medicine KW - tumor KW - cancer KW - cloud-based KW - platform KW - implementation KW - COVID-19 N2 - Background: Multidisciplinary tumor boards play a pivotal role in the patient-centered clinical management and in the decision-making process to provide best evidence-based, diagnostic, and therapeutic care to patients with cancer. Among the barriers to achieve an efficient multidisciplinary tumor board, lack of time and geographical distance play a major role. Therefore, the elaboration of an efficient virtual multidisciplinary tumor board (VMTB) is a key point to successfully obtain an oncology team and implement a network among health professionals and institutions. This need is stronger than ever during the COVID-19 pandemic. Objective: This paper presents a research protocol for an observational study focused on exploring the structuring process and the implementation of a multi-institutional VMTB in Sicily, Italy. Other endpoints include analysis of cooperation between participants, adherence to guidelines, patients? outcomes, and patient satisfaction. Methods: This protocol encompasses a pragmatic, observational, multicenter, noninterventional, prospective trial. The study?s programmed duration is 5 years, with a half-yearly analysis of the primary and secondary objectives? measurements. Oncology care health professionals from various oncology subspecialties at oncology departments in multiple hospitals (academic and general hospitals as well as tertiary centers and community hospitals) are involved in a nonhierarchic manner. VMTB employs an innovative, virtual, cloud-based platform to share anonymized medical data that are discussed via a videoconferencing system both satisfying security criteria and compliance with the Health Insurance Portability and Accountability Act. Results: The protocol is part of a larger research project on communication and multidisciplinary collaboration in oncology units and departments spread in the Sicily region. The results of this study will particularly focus on the organization of VMTBs, involving oncology units present in different hospitals spread in the area, and creating a network to allow best patient care pathways and a hub-and-spoke relationship. The present results will also include data concerning organization skills and pitfalls, barriers, efficiency, number, and types with respect to clinical cases and customer satisfaction. Conclusions: VMTB represents a unique opportunity to optimize patient management through a patient-centered approach. An efficient virtualization and data-banking system is potentially time-saving, a source for outcome data, and a detector of possible holes in the hull of clinical pathways. The observations and results from this VMTB study may hopefully be useful to design nonclinical and organizational interventions that enhance multidisciplinary decision-making in oncology. International Registered Report Identifier (IRRID): DERR1-10.2196/26220 UR - https://www.researchprotocols.org/2021/9/e26220 UR - http://dx.doi.org/10.2196/26220 UR - http://www.ncbi.nlm.nih.gov/pubmed/34387553 ID - info:doi/10.2196/26220 ER - TY - JOUR AU - Lee, Eunsaem AU - Jung, Young Se AU - Hwang, Ju Hyung AU - Jung, Jaewoo PY - 2021/8/30 TI - Patient-Level Cancer Prediction Models From a Nationwide Patient Cohort: Model Development and Validation JO - JMIR Med Inform SP - e29807 VL - 9 IS - 8 KW - prediction KW - model KW - claim data KW - cancer KW - machine learning KW - development KW - cohort KW - validation KW - database KW - algorithm N2 - Background: Nationwide population-based cohorts provide a new opportunity to build automated risk prediction models at the patient level, and claim data are one of the more useful resources to this end. To avoid unnecessary diagnostic intervention after cancer screening tests, patient-level prediction models should be developed. Objective: We aimed to develop cancer prediction models using nationwide claim databases with machine learning algorithms, which are explainable and easily applicable in real-world environments. Methods: As source data, we used the Korean National Insurance System Database. Every Korean in ?40 years old undergoes a national health checkup every 2 years. We gathered all variables from the database including demographic information, basic laboratory values, anthropometric values, and previous medical history. We applied conventional logistic regression methods, light gradient boosting methods, neural networks, survival analysis, and one-class embedding classifier methods to effectively analyze high dimension data based on deep learning?based anomaly detection. Performance was measured with area under the curve and area under precision recall curve. We validated our models externally with a health checkup database from a tertiary hospital. Results: The one-class embedding classifier model received the highest area under the curve scores with values of 0.868, 0.849, 0.798, 0.746, 0.800, 0.749, and 0.790 for liver, lung, colorectal, pancreatic, gastric, breast, and cervical cancers, respectively. For area under precision recall curve, the light gradient boosting models had the highest score with values of 0.383, 0.401, 0.387, 0.300, 0.385, 0.357, and 0.296 for liver, lung, colorectal, pancreatic, gastric, breast, and cervical cancers, respectively. Conclusions: Our results show that it is possible to easily develop applicable cancer prediction models with nationwide claim data using machine learning. The 7 models showed acceptable performances and explainability, and thus can be distributed easily in real-world environments. UR - https://medinform.jmir.org/2021/8/e29807 UR - http://dx.doi.org/10.2196/29807 UR - http://www.ncbi.nlm.nih.gov/pubmed/34459743 ID - info:doi/10.2196/29807 ER - TY - JOUR AU - Shojaie, Danielle AU - Hoffman, S. Aubri AU - Amaku, Ruth AU - Cabanillas, E. Maria AU - Sosa, Ann Julie AU - Waguespack, G. Steven AU - Zafereo, E. Mark AU - Hu, I. Mimi AU - Grubbs, E. Elizabeth PY - 2021/7/16 TI - Decision Making When Cancer Becomes Chronic: Needs Assessment for a Web-Based Medullary Thyroid Carcinoma Patient Decision Aid JO - JMIR Form Res SP - e27484 VL - 5 IS - 7 KW - patient decision aids KW - decision support techniques KW - oncology KW - medullary thyroid cancer KW - targeted therapy KW - clinical trial KW - mobile phone N2 - Background: In cancers with a chronic phase, patients and family caregivers face difficult decisions such as whether to start a novel therapy, whether to enroll in a clinical trial, and when to stop treatment. These decisions are complex, require an understanding of uncertainty, and necessitate the consideration of patients? informed preferences. For some cancers, such as medullary thyroid carcinoma, these decisions may also involve significant out-of-pocket costs and effects on family members. Providers have expressed a need for web-based interventions that can be delivered between consultations to provide education and prepare patients and families to discuss these decisions. To ensure that these tools are effective, usable, and understandable, studies are needed to identify patients?, families?, and providers? decision-making needs and optimal design strategies for a web-based patient decision aid. Objective: Following the international guidelines for the development of a web-based patient decision aid, the objectives of this study are to engage potential users to guide development; review the existing literature and available tools; assess users? decision-making experiences, needs, and design recommendations; and identify shared decision-making approaches to address each need. Methods: This study used the decisional needs assessment approach, which included creating a stakeholder advisory panel, mapping decision pathways, conducting an environmental scan of existing materials, and administering a decisional needs assessment questionnaire. Thematic analyses identified current decision-making pathways, unmet decision-making needs, and decision support strategies for meeting each need. Results: The stakeholders reported wide heterogeneity in decision timing and pathways. Relevant existing materials included 2 systematic reviews, 9 additional papers, and multiple educational websites, but none of these met the criteria for a patient decision aid. Patients and family members (n=54) emphasized the need for plain language (46/54, 85%), shared decision making (45/54, 83%), and help with family discussions (39/54, 72%). Additional needs included information about uncertainty, lived experience, and costs. Providers (n=10) reported needing interventions that address misinformation (9/10, 90%), foster realistic expectations (9/10, 90%), and address mistrust in clinical trials (5/10, 50%). Additional needs included provider tools that support shared decision making. Both groups recommended designing a web-based patient decision aid that can be tailored to (64/64, 100%) and delivered on a hospital website (53/64, 83%), focuses on quality of life (45/64, 70%), and provides step-by-step guidance (43/64, 67%). The study team identified best practices to meet each need, which are presented in the proposed decision support design guide. Conclusions: Patients, families, and providers report multifaceted decision support needs during the chronic phase of cancer. Web-based patient decision aids that provide tailored support over time and explicitly address uncertainty, quality of life, realistic expectations, and effects on families are needed. UR - https://formative.jmir.org/2021/7/e27484 UR - http://dx.doi.org/10.2196/27484 UR - http://www.ncbi.nlm.nih.gov/pubmed/34269691 ID - info:doi/10.2196/27484 ER - TY - JOUR AU - Enriquez, S. José AU - Chu, Yan AU - Pudakalakatti, Shivanand AU - Hsieh, Lin Kang AU - Salmon, Duncan AU - Dutta, Prasanta AU - Millward, Zacharias Niki AU - Lurie, Eugene AU - Millward, Steven AU - McAllister, Florencia AU - Maitra, Anirban AU - Sen, Subrata AU - Killary, Ann AU - Zhang, Jian AU - Jiang, Xiaoqian AU - Bhattacharya, K. Pratip AU - Shams, Shayan PY - 2021/6/17 TI - Hyperpolarized Magnetic Resonance and Artificial Intelligence: Frontiers of Imaging in Pancreatic Cancer JO - JMIR Med Inform SP - e26601 VL - 9 IS - 6 KW - artificial intelligence KW - deep learning KW - hyperpolarization KW - metabolic imaging KW - MRI KW - 13C KW - HP-MR KW - pancreatic ductal adenocarcinoma KW - pancreatic cancer KW - early detection KW - assessment of treatment response KW - probes KW - cancer KW - marker KW - imaging KW - treatment KW - review KW - detection KW - efficacy N2 - Background: There is an unmet need for noninvasive imaging markers that can help identify the aggressive subtype(s) of pancreatic ductal adenocarcinoma (PDAC) at diagnosis and at an earlier time point, and evaluate the efficacy of therapy prior to tumor reduction. In the past few years, there have been two major developments with potential for a significant impact in establishing imaging biomarkers for PDAC and pancreatic cancer premalignancy: (1) hyperpolarized metabolic (HP)-magnetic resonance (MR), which increases the sensitivity of conventional MR by over 10,000-fold, enabling real-time metabolic measurements; and (2) applications of artificial intelligence (AI). Objective: Our objective of this review was to discuss these two exciting but independent developments (HP-MR and AI) in the realm of PDAC imaging and detection from the available literature to date. Methods: A systematic review following the PRISMA extension for Scoping Reviews (PRISMA-ScR) guidelines was performed. Studies addressing the utilization of HP-MR and/or AI for early detection, assessment of aggressiveness, and interrogating the early efficacy of therapy in patients with PDAC cited in recent clinical guidelines were extracted from the PubMed and Google Scholar databases. The studies were reviewed following predefined exclusion and inclusion criteria, and grouped based on the utilization of HP-MR and/or AI in PDAC diagnosis. Results: Part of the goal of this review was to highlight the knowledge gap of early detection in pancreatic cancer by any imaging modality, and to emphasize how AI and HP-MR can address this critical gap. We reviewed every paper published on HP-MR applications in PDAC, including six preclinical studies and one clinical trial. We also reviewed several HP-MR?related articles describing new probes with many functional applications in PDAC. On the AI side, we reviewed all existing papers that met our inclusion criteria on AI applications for evaluating computed tomography (CT) and MR images in PDAC. With the emergence of AI and its unique capability to learn across multimodal data, along with sensitive metabolic imaging using HP-MR, this knowledge gap in PDAC can be adequately addressed. CT is an accessible and widespread imaging modality worldwide as it is affordable; because of this reason alone, most of the data discussed are based on CT imaging datasets. Although there were relatively few MR-related papers included in this review, we believe that with rapid adoption of MR imaging and HP-MR, more clinical data on pancreatic cancer imaging will be available in the near future. Conclusions: Integration of AI, HP-MR, and multimodal imaging information in pancreatic cancer may lead to the development of real-time biomarkers of early detection, assessing aggressiveness, and interrogating early efficacy of therapy in PDAC. UR - https://medinform.jmir.org/2021/6/e26601 UR - http://dx.doi.org/10.2196/26601 UR - http://www.ncbi.nlm.nih.gov/pubmed/34137725 ID - info:doi/10.2196/26601 ER - TY - JOUR AU - Kim, Sue AU - Aceti, Monica AU - Baroutsou, Vasiliki AU - Bürki, Nicole AU - Caiata-Zufferey, Maria AU - Cattaneo, Marco AU - Chappuis, O. Pierre AU - Ciorba, M. Florina AU - Graffeo-Galbiati, Rossella AU - Heinzelmann-Schwarz, Viola AU - Jeong, Joon AU - Jung, M. MiSook AU - Kim, Sung-Won AU - Kim, Jisun AU - Lim, Cheol Myong AU - Ming, Chang AU - Monnerat, Christian AU - Park, Seok Hyung AU - Park, Hyung Sang AU - Pedrazzani, A. Carla AU - Rabaglio, Manuela AU - Ryu, Min Jai AU - Saccilotto, Ramon AU - Wieser, Simon AU - Zürrer-Härdi, Ursina AU - Katapodi, C. Maria PY - 2021/6/11 TI - Using a Tailored Digital Health Intervention for Family Communication and Cascade Genetic Testing in Swiss and Korean Families With Hereditary Breast and Ovarian Cancer: Protocol for the DIALOGUE Study JO - JMIR Res Protoc SP - e26264 VL - 10 IS - 6 KW - HBOC KW - proportion of informed at-risk relatives KW - coping KW - communicating KW - decisional conflict KW - cultural and linguistic adaptation KW - implementation KW - RE-AIM KW - mobile phone N2 - Background: In hereditary breast and ovarian cancer (HBOC), family communication of genetic test results is essential for cascade genetic screening, that is, identifying and testing blood relatives of known mutation carriers to determine whether they also carry the pathogenic variant, and to propose preventive and clinical management options. However, up to 50% of blood relatives are unaware of relevant genetic information, suggesting that potential benefits of genetic testing are not communicated effectively within family networks. Technology can facilitate communication and genetic education within HBOC families. Objective: The aims of this study are to develop the K-CASCADE (Korean?Cancer Predisposition Cascade Genetic Testing) cohort in Korea by expanding an infrastructure developed by the CASCADE (Cancer Predisposition Cascade Genetic Testing) Consortium in Switzerland; develop a digital health intervention to support the communication of cancer predisposition for Swiss and Korean HBOC families, based on linguistic and cultural adaptation of the Family Gene Toolkit; evaluate its efficacy on primary (family communication of genetic results and cascade testing) and secondary (psychological distress, genetic literacy, active coping, and decision making) outcomes; and explore its translatability using the reach, effectiveness, adoption, implementation, and maintenance framework. Methods: The digital health intervention will be available in French, German, Italian, Korean, and English and can be accessed via the web, mobile phone, or tablet (ie, device-agnostic). K-CASCADE cohort of Korean HBOC mutation carriers and relatives will be based on the CASCADE infrastructure. Narrative data collected through individual interviews or mini focus groups from 20 to 24 HBOC family members per linguistic region and 6-10 health care providers involved in genetic services will identify the local cultures and context, and inform the content of the tailored messages. The efficacy of the digital health intervention against a comparison website will be assessed in a randomized trial with 104 HBOC mutation carriers (52 in each study arm). The translatability of the digital health intervention will be assessed using survey data collected from HBOC families and health care providers. Results: Funding was received in October 2019. It is projected that data collection will be completed by January 2023 and results will be published in fall 2023. Conclusions: This study addresses the continuum of translational research, from developing an international research infrastructure and adapting an existing digital health intervention to testing its efficacy in a randomized controlled trial and exploring its translatability using an established framework. Adapting existing interventions, rather than developing new ones, takes advantage of previous valid experiences without duplicating efforts. Culturally sensitive web-based interventions that enhance family communication and understanding of genetic cancer risk are timely. This collaboration creates a research infrastructure between Switzerland and Korea that can be scaled up to cover other hereditary cancer syndromes. Trial Registration: ClinicalTrials.gov NCT04214210; https://clinicaltrials.gov/ct2/show/NCT04214210 and CRiS KCT0005643; https://cris.nih.go.kr/cris/ International Registered Report Identifier (IRRID): PRR1-10.2196/26264 UR - https://www.researchprotocols.org/2021/6/e26264 UR - http://dx.doi.org/10.2196/26264 UR - http://www.ncbi.nlm.nih.gov/pubmed/34114954 ID - info:doi/10.2196/26264 ER - TY - JOUR AU - Donevant, Sara AU - Heiney, P. Sue AU - Wineglass, Cassandra AU - Schooley, Benjamin AU - Singh, Akanksha AU - Sheng, Jingxi PY - 2021/6/11 TI - Perceptions of Endocrine Therapy in African-American Breast Cancer Survivors: Mixed Methods Study JO - JMIR Form Res SP - e23884 VL - 5 IS - 6 KW - mHealth KW - breast cancer survivors KW - medication adherence KW - cultural considerations KW - mobile health applications N2 - Background: Although the incidence of breast cancer is lower in African-American women than in White women, African-American women have a decreased survival rate. The difference in survival rate may stem from poor endocrine therapy adherence, which increases breast cancer recurrence. Therefore, accessible and culturally sensitive interventions to increase endocrine therapy adherence are necessary. Objective: The purpose of this concurrent convergent mixed methods study was to provide further data to guide the development of the proposed culturally sensitive mHealth app, STORY+ for African-American women with breast cancer. Methods: We recruited 20 African-American women diagnosed with estrogen-positive breast cancer and currently prescribed endocrine therapy. We used a concurrent convergent data collection method to (1) assess the use of smartphones and computers related to health care and (2) identify foundational aspects to support endocrine therapy adherence for incorporation in a mobile health app. Results: Overwhelmingly, the participants preferred using smartphones to using computers for health care. Communicating with health care providers and pharmacies was the most frequent health care use of smartphones, followed by exercise tracking, and accessing the patient portal. We identified 4 aspects of adherence to endocrine therapy and smartphone use for incorporation in app development. The factors that emerged from the integrated qualitative and quantitative data were (1) willingness to use, (2) side effects, (3) social connection, and (4) beliefs about endocrine therapy. Conclusions: Further research is needed to develop a culturally sensitive app for African-American women with breast cancer to improve adherence to endocrine therapy. Our work strongly suggests that this population would use the app to connect with other African-American breast cancer survivors and manage endocrine therapy. UR - https://formative.jmir.org/2021/6/e23884 UR - http://dx.doi.org/10.2196/23884 UR - http://www.ncbi.nlm.nih.gov/pubmed/34114955 ID - info:doi/10.2196/23884 ER - TY - JOUR AU - Hoffman, Aubri AU - Crocker, Laura AU - Mathur, Aakrati AU - Holman, Deborah AU - Weston, June AU - Campbell, Sukhkamal AU - Housten, Ashley AU - Bradford, Andrea AU - Agrawala, Shilpi AU - Woodard, L. Terri PY - 2021/6/7 TI - Patients? and Providers? Needs and Preferences When Considering Fertility Preservation Before Cancer Treatment: Decision-Making Needs Assessment JO - JMIR Form Res SP - e25083 VL - 5 IS - 6 KW - cancer KW - decision support techniques KW - fertility preservation KW - oncofertility KW - oncology KW - needs assessment KW - patient decision aids KW - patient needs KW - shared decision making N2 - Background: As cancer treatments continue to improve, it is increasingly important that women of reproductive age have an opportunity to decide whether they want to undergo fertility preservation treatments to try to protect their ability to have a child after cancer. Clinical practice guidelines recommend that providers offer fertility counseling to all young women with cancer; however, as few as 12% of women recall discussing fertility preservation. The long-term goal of this program is to develop an interactive web-based patient decision aid to improve awareness, access, knowledge, and decision making for all young women with cancer. The International Patient Decision Aid Standards collaboration recommends a formal decision-making needs assessment to inform and guide the design of understandable, meaningful, and usable patient decision aid interventions. Objective: This study aims to assess providers? and survivors? fertility preservation decision-making experiences, unmet needs, and initial design preferences to inform the development of a web-based patient decision aid. Methods: Semistructured interviews and an ad hoc focus group assessed current decision-making experiences, unmet needs, and recommendations for a patient decision aid. Two researchers coded and analyzed the transcripts using NVivo (QSR International). A stakeholder advisory panel guided the study and interpretation of results. Results: A total of 51 participants participated in 46 interviews (18 providers and 28 survivors) and 1 ad hoc focus group (7 survivors). The primary themes included the importance of fertility decisions for survivorship, the existence of significant but potentially modifiable barriers to optimal decision making, and a strong support for developing a carefully designed patient decision aid website. Providers reported needing an intervention that could quickly raise awareness and facilitate timely referrals. Survivors reported needing understandable information and help with managing uncertainty, costs, and pressures. Design recommendations included providing tailored information (eg, by age and cancer type), optional interactive features, and multimedia delivery at multiple time points, preferably outside the consultation. Conclusions: Decision making about fertility preservation is an important step in providing high-quality comprehensive cancer care and a priority for many survivors? optimal quality of life. Decision support interventions are needed to address gaps in care and help women quickly navigate toward an informed, values-congruent decision. Survivors and providers support developing a patient decision aid website to make information directly available to women outside of the consultation and to provide self-tailored content according to women?s clinical characteristics and their information-seeking and deliberative styles. UR - https://formative.jmir.org/2021/6/e25083 UR - http://dx.doi.org/10.2196/25083 UR - http://www.ncbi.nlm.nih.gov/pubmed/34096871 ID - info:doi/10.2196/25083 ER - TY - JOUR AU - Rossman, H. Andrea AU - Reid, W. Hadley AU - Pieters, M. Michelle AU - Mizelle, Cecelia AU - von Isenburg, Megan AU - Ramanujam, Nimmi AU - Huchko, J. Megan AU - Vasudevan, Lavanya PY - 2021/5/27 TI - Digital Health Strategies for Cervical Cancer Control in Low- and Middle-Income Countries: Systematic Review of Current Implementations and Gaps in Research JO - J Med Internet Res SP - e23350 VL - 23 IS - 5 KW - cervical cancer KW - digital health KW - mobile phones KW - low- and middle-income countries KW - colposcopy KW - uterine cervical neoplasms KW - telemedicine or mobile apps KW - cell phones KW - developing countries N2 - Background: Nearly 90% of deaths due to cervical cancer occur in low- and middle-income countries (LMICs). In recent years, many digital health strategies have been implemented in LMICs to ameliorate patient-, provider-, and health system?level challenges in cervical cancer control. However, there are limited efforts to systematically review the effectiveness and current landscape of digital health strategies for cervical cancer control in LMICs. Objective: We aim to conduct a systematic review of digital health strategies for cervical cancer control in LMICs to assess their effectiveness, describe the range of strategies used, and summarize challenges in their implementation. Methods: A systematic search was conducted to identify publications describing digital health strategies for cervical cancer control in LMICs from 5 academic databases and Google Scholar. The review excluded digital strategies associated with improving vaccination coverage against human papillomavirus. Titles and abstracts were screened, and full texts were reviewed for eligibility. A structured data extraction template was used to summarize the information from the included studies. The risk of bias and data reporting guidelines for mobile health were assessed for each study. A meta-analysis of effectiveness was planned along with a narrative review of digital health strategies, implementation challenges, and opportunities for future research. Results: In the 27 included studies, interventions for cervical cancer control focused on secondary prevention (ie, screening and treatment of precancerous lesions) and digital health strategies to facilitate patient education, digital cervicography, health worker training, and data quality. Most of the included studies were conducted in sub-Saharan Africa, with fewer studies in other LMIC settings in Asia or South America. A low risk of bias was found in 2 studies, and a moderate risk of bias was found in 4 studies, while the remaining 21 studies had a high risk of bias. A meta-analysis of effectiveness was not conducted because of insufficient studies with robust study designs and matched outcomes or interventions. Conclusions: Current evidence on the effectiveness of digital health strategies for cervical cancer control is limited and, in most cases, is associated with a high risk of bias. Further studies are recommended to expand the investigation of digital health strategies for cervical cancer using robust study designs, explore other LMIC settings with a high burden of cervical cancer (eg, South America), and test a greater diversity of digital strategies. UR - https://www.jmir.org/2021/5/e23350 UR - http://dx.doi.org/10.2196/23350 UR - http://www.ncbi.nlm.nih.gov/pubmed/34042592 ID - info:doi/10.2196/23350 ER - TY - JOUR AU - Petrocchi, Serena AU - Filipponi, Chiara AU - Montagna, Giacomo AU - Bonollo, Marta AU - Pagani, Olivia AU - Meani, Francesco PY - 2021/5/10 TI - A Breast Cancer Smartphone App to Navigate the Breast Cancer Journey: Mixed Methods Study JO - JMIR Form Res SP - e28668 VL - 5 IS - 5 KW - breast cancer KW - decision-making process KW - breast cancer patient KW - smartphone app KW - empowerment KW - breast cancer journey KW - mobile app N2 - Background: Several mobile apps have been designed for patients with a diagnosis of cancer. Unfortunately, despite the promising potential and impressive spread, their effectiveness often remains unclear. Most mobile apps are developed without any medical professional involvement and quality evidence-based assessment. Furthermore, they are often implemented in clinical care before any research is performed to confirm usability, appreciation, and clinical benefits for patients. Objective: We aimed to develop a new smartphone app (Centro di Senologia della Svizzera Italiana [CSSI]) specifically designed by breast care specialists and patients together to help breast cancer patients better understand and organize their journey through the diagnosis and treatment of cancer. We describe the development of the app and present assessments to evaluate its feasibility, usefulness, and capability to improve patient empowerment. Methods: A mixed method study with brief longitudinal quantitative data collection and subsequent qualitative semistructured interviews was designed. Twenty breast cancer patients participated in the study (mean age 51 years, SD 10 years). The usability of the app, the user experience, and empowerment were measured after 1 month. The semistructured interviews measured the utility of the app and the necessary improvements. Results: The app received good responses from the patients in terms of positive perception of the purpose of the app (7/20, 35%), organizing the cure path and being aware of the steps in cancer management (5/20, 25%), facilitating doctor-patient communication (4/20, 20%), and having detailed information about the resources offered by the hospital (2/20, 10%). Correlation and regression analyses showed that user experience increased the level of empowerment of patients (B=0.31, 95% CI 0.22-0.69; P=.009). The interviews suggested the need to constantly keep the app updated and to synchronize it with the hospital?s electronic agenda, and carefully selecting the best time to offer the tool to final users was considered crucial. Conclusions: Despite the very small number of participants in this study, the findings demonstrate the potential of the app and support a fully powered trial to evaluate the empowering effect of the mobile health app. More data will be gathered with an improved version of the app in the second phase involving a larger study sample. UR - https://formative.jmir.org/2021/5/e28668 UR - http://dx.doi.org/10.2196/28668 UR - http://www.ncbi.nlm.nih.gov/pubmed/33970120 ID - info:doi/10.2196/28668 ER - TY - JOUR AU - Bang, Seok Chang AU - Ahn, Yong Ji AU - Kim, Jie-Hyun AU - Kim, Young-Il AU - Choi, Ju Il AU - Shin, Geon Woon PY - 2021/4/15 TI - Establishing Machine Learning Models to Predict Curative Resection in Early Gastric Cancer with Undifferentiated Histology: Development and Usability Study JO - J Med Internet Res SP - e25053 VL - 23 IS - 4 KW - early gastric cancer KW - artificial intelligence KW - machine learning KW - endoscopic submucosal dissection KW - undifferentiated KW - gastric cancer KW - endoscopy KW - dissection N2 - Background: Undifferentiated type of early gastric cancer (U-EGC) is included among the expanded indications of endoscopic submucosal dissection (ESD); however, the rate of curative resection remains unsatisfactory. Endoscopists predict the probability of curative resection by considering the size and shape of the lesion and whether ulcers are present or not. The location of the lesion, indicating the likely technical difficulty, is also considered. Objective: The aim of this study was to establish machine learning (ML) models to better predict the possibility of curative resection in U-EGC prior to ESD. Methods: A nationwide cohort of 2703 U-EGCs treated by ESD or surgery were adopted for the training and internal validation cohorts. Separately, an independent data set of the Korean ESD registry (n=275) and an Asan medical center data set (n=127) treated by ESD were chosen for external validation. Eighteen ML classifiers were selected to establish prediction models of curative resection with the following variables: age; sex; location, size, and shape of the lesion; and whether ulcers were present or not. Results: Among the 18 models, the extreme gradient boosting classifier showed the best performance (internal validation accuracy 93.4%, 95% CI 90.4%-96.4%; precision 92.6%, 95% CI 89.5%-95.7%; recall 99.0%, 95% CI 97.8%-99.9%; and F1 score 95.7%, 95% CI 93.3%-98.1%). Attempts at external validation showed substantial accuracy (first external validation 81.5%, 95% CI 76.9%-86.1% and second external validation 89.8%, 95% CI 84.5%-95.1%). Lesion size was the most important feature in each explainable artificial intelligence analysis. Conclusions: We established an ML model capable of accurately predicting the curative resection of U-EGC before ESD by considering the morphological and ecological characteristics of the lesions. UR - https://www.jmir.org/2021/4/e25053 UR - http://dx.doi.org/10.2196/25053 UR - http://www.ncbi.nlm.nih.gov/pubmed/33856358 ID - info:doi/10.2196/25053 ER - TY - JOUR AU - Smit, A. Marloes AU - van Pelt, W. Gabi AU - Dequeker, MC Elisabeth AU - Al Dieri, Raed AU - Tollenaar, AEM Rob AU - van Krieken, JM J. Han AU - Mesker, E. Wilma AU - PY - 2021/3/19 TI - e-Learning for Instruction and to Improve Reproducibility of Scoring Tumor-Stroma Ratio in Colon Carcinoma: Performance and Reproducibility Assessment in the UNITED Study JO - JMIR Form Res SP - e19408 VL - 5 IS - 3 KW - colon cancer KW - tumor-stroma ratio KW - validation KW - e-Learning KW - reproducibility study KW - cancer KW - tumor KW - colon KW - reproducibility KW - carcinoma KW - prognosis KW - diagnostic KW - implementation KW - online learning N2 - Background: The amount of stroma in the primary tumor is an important prognostic parameter. The tumor-stroma ratio (TSR) was previously validated by international research groups as a robust parameter with good interobserver agreement. Objective: The Uniform Noting for International Application of the Tumor-Stroma Ratio as an Easy Diagnostic Tool (UNITED) study was developed to bring the TSR to clinical implementation. As part of the study, an e-Learning module was constructed to confirm the reproducibility of scoring the TSR after proper instruction. Methods: The e-Learning module consists of an autoinstruction for TSR determination (instruction video or written protocol) and three sets of 40 cases (training, test, and repetition sets). Scoring the TSR is performed on hematoxylin and eosin?stained sections and takes only 1-2 minutes. Cases are considered stroma-low if the amount of stroma is ?50%, whereas a stroma-high case is defined as >50% stroma. Inter- and intraobserver agreements were determined based on the Cohen ? score after each set to evaluate the reproducibility. Results: Pathologists and pathology residents (N=63) with special interest in colorectal cancer participated in the e-Learning. Forty-nine participants started the e-Learning and 31 (63%) finished the whole cycle (3 sets). A significant improvement was observed from the training set to the test set; the median ? score improved from 0.72 to 0.77 (P=.002). Conclusions: e-Learning is an effective method to instruct pathologists and pathology residents for scoring the TSR. The reliability of scoring improved from the training to the test set and did not fall back with the repetition set, confirming the reproducibility of the TSR scoring method. Trial Registration: The Netherlands Trial Registry NTR7270; https://www.trialregister.nl/trial/7072 International Registered Report Identifier (IRRID): RR2-10.2196/13464 UR - https://formative.jmir.org/2021/3/e19408 UR - http://dx.doi.org/10.2196/19408 UR - http://www.ncbi.nlm.nih.gov/pubmed/33739293 ID - info:doi/10.2196/19408 ER - TY - JOUR AU - Sato, Ann AU - Haneda, Eri AU - Suganuma, Nobuyasu AU - Narimatsu, Hiroto PY - 2021/2/5 TI - Preliminary Screening for Hereditary Breast and Ovarian Cancer Using a Chatbot Augmented Intelligence Genetic Counselor: Development and Feasibility Study JO - JMIR Form Res SP - e25184 VL - 5 IS - 2 KW - artificial intelligence KW - augmented intelligence KW - hereditary cancer KW - familial cancer KW - IBM Watson KW - preliminary screening KW - cancer KW - genetics KW - chatbot KW - screening KW - feasibility N2 - Background: Breast cancer is the most common form of cancer in Japan; genetic background and hereditary breast and ovarian cancer (HBOC) are implicated. The key to HBOC diagnosis involves screening to identify high-risk individuals. However, genetic medicine is still developing; thus, many patients who may potentially benefit from genetic medicine have not yet been identified. Objective: This study?s objective is to develop a chatbot system that uses augmented intelligence for HBOC screening to determine whether patients meet the National Comprehensive Cancer Network (NCCN) BRCA1/2 testing criteria. Methods: The system was evaluated by a doctor specializing in genetic medicine and certified genetic counselors. We prepared 3 scenarios and created a conversation with the chatbot to reflect each one. Then we evaluated chatbot feasibility, the required time, the medical accuracy of conversations and family history, and the final result. Results: The times required for the conversation were 7 minutes for scenario 1, 15 minutes for scenario 2, and 16 minutes for scenario 3. Scenarios 1 and 2 met the BRCA1/2 testing criteria, but scenario 3 did not, and this result was consistent with the findings of 3 experts who retrospectively reviewed conversations with the chatbot according to the 3 scenarios. A family history comparison ascertained by the chatbot with the actual scenarios revealed that each result was consistent with each scenario. From a genetic medicine perspective, no errors were noted by the 3 experts. Conclusions: This study demonstrated that chatbot systems could be applied to preliminary genetic medicine screening for HBOC. UR - https://formative.jmir.org/2021/2/e25184 UR - http://dx.doi.org/10.2196/25184 UR - http://www.ncbi.nlm.nih.gov/pubmed/33544084 ID - info:doi/10.2196/25184 ER - TY - JOUR AU - Benedict, Catherine AU - Dauber-Decker, L. Katherine AU - King, D'Arcy AU - Hahn, Alexandria AU - Ford, S. Jennifer AU - Diefenbach, Michael PY - 2021/1/22 TI - A Decision Aid Intervention for Family Building After Cancer: Developmental Study on the Initial Steps to Consider When Designing a Web-Based Prototype JO - JMIR Form Res SP - e20841 VL - 5 IS - 1 KW - patient-centered care KW - user-centered design KW - decision support techniques KW - decision aid KW - cancer KW - fertility KW - internet-based intervention KW - web-based intervention KW - mobile phone KW - psychosocial intervention N2 - Background: An important aspect of patient-centered care involves ensuring that patient-directed resources are usable, understandable, and responsive to patients? needs. A user-centered design refers to an empathy-based framework and an iterative design approach for developing a product or solution that is based on an in-depth understanding of users? needs, values, abilities, and limitations. Objective: This study presents the steps taken to develop a prototype for a patient resource for young women who have completed treatment for gonadotoxic cancer to support their decision making about follow-up fertility care and family building. Methods: User-centered design practices were used to develop Roadmap to Parenthood, a decision aid (DA) website for family building after cancer. A multidisciplinary steering group was assembled and input was provided. Guidelines from the International Patient DA Society and the Ottawa Decision Support Framework were used throughout the development process. In addition, guidelines for developing health DAs with respect to patient diversity and health literacy were also followed. Results: The Roadmap to Parenthood DA website prototype was systematically and iteratively developed. An extensive process of designing and developing solutions from the perspective of the end user was followed. The steps taken included formative work to identify user needs; determining goals, format, and delivery; design processes (eg, personas, storyboards, information architecture, user journey mapping, and wireframing); and content development. Additional design considerations addressed the unique needs of this patient population, including the emotional experiences related to this topic and decision-making context wherein decisions could be considered iteratively while involving a multistep process. Conclusions: The design strategies presented in this study describe important steps in the early phases of developing a user-centered resource, which will enhance the starting point for usability testing and further design modifications. Future research will pilot test the DA and a planning tool, and evaluate improvement in the decisional conflict regarding family building after cancer. Consistent with a patient-centered approach to health care, the strategies described here may be generalized and applied to the development of other patient resources and clinical contexts to optimize usability, empathy, and user engagement. UR - http://formative.jmir.org/2021/1/e20841/ UR - http://dx.doi.org/10.2196/20841 UR - http://www.ncbi.nlm.nih.gov/pubmed/33480848 ID - info:doi/10.2196/20841 ER - TY - JOUR AU - Carter-Harris, Lisa AU - Comer, Skipworth Robert AU - Slaven II, E. James AU - Monahan, O. Patrick AU - Vode, Emilee AU - Hanna, H. Nasser AU - Ceppa, Pham DuyKhanh AU - Rawl, M. Susan PY - 2020/11/3 TI - Computer-Tailored Decision Support Tool for Lung Cancer Screening: Community-Based Pilot Randomized Controlled Trial JO - J Med Internet Res SP - e17050 VL - 22 IS - 11 KW - lung cancer screening KW - informed decision-making KW - shared decision-making KW - patient decision aid KW - patient education N2 - Background: Lung cancer screening is a US Preventive Services Task Force Grade B recommendation that has been shown to decrease lung cancer-related mortality by approximately 20%. However, making the decision to screen, or not, for lung cancer is a complex decision because there are potential risks (eg, false positive results, overdiagnosis). Shared decision making was incorporated into the lung cancer screening guideline and, for the first time, is a requirement for reimbursement of a cancer screening test from Medicare. Awareness of lung cancer screening remains low in both the general and screening-eligible populations. When a screening-eligible person visits their clinician never having heard about lung cancer screening, engaging in shared decision making to arrive at an informed decision can be a challenge. Methods to effectively prepare patients for these clinical encounters and support both patients and clinicians to engage in these important discussions are needed. Objective: The aim of the study was to estimate the effects of a computer-tailored decision support tool that meets the certification criteria of the International Patient Decision Aid Standards that will prepare individuals and support shared decision making in lung cancer screening decisions. Methods: A pilot randomized controlled trial with a community-based sample of 60 screening-eligible participants who have never been screened for lung cancer was conducted. Approximately half of the participants (n=31) were randomized to view LungTalk?a web-based tailored computer program?while the other half (n=29) viewed generic information about lung cancer screening from the American Cancer Society. The outcomes that were compared included lung cancer and screening knowledge, lung cancer screening health beliefs (perceived risk, perceived benefits, perceived barriers, and self-efficacy), and perception of being prepared to engage in a discussion about lung cancer screening with their clinician. Results: Knowledge scores increased significantly for both groups with greater improvement noted in the group receiving LungTalk (2.33 vs 1.14 mean change). Perceived self-efficacy and perceived benefits improved in the theoretically expected directions. Conclusions: LungTalk goes beyond other decision tools by addressing lung health broadly, in the context of performing a low-dose computed tomography of the chest that has the potential to uncover other conditions of concern beyond lung cancer, to more comprehensively educate the individual, and extends the work of nontailored decision aids in the field by introducing tailoring algorithms and message framing based upon smoking status in order to determine what components of the intervention drive behavior change when an individual is informed and makes the decision whether to be screened or not to be screened for lung cancer. International Registered Report Identifier (IRRID): RR2-10.2196/resprot.8694 UR - https://www.jmir.org/2020/11/e17050 UR - http://dx.doi.org/10.2196/17050 UR - http://www.ncbi.nlm.nih.gov/pubmed/33141096 ID - info:doi/10.2196/17050 ER - TY - JOUR AU - Yu, Kun-Hsing AU - Lee, Michael Tsung-Lu AU - Yen, Ming-Hsuan AU - Kou, C. S. AU - Rosen, Bruce AU - Chiang, Jung-Hsien AU - Kohane, S. Isaac PY - 2020/8/5 TI - Reproducible Machine Learning Methods for Lung Cancer Detection Using Computed Tomography Images: Algorithm Development and Validation JO - J Med Internet Res SP - e16709 VL - 22 IS - 8 KW - computed tomography, spiral KW - lung cancer KW - machine learning KW - early detection of cancer KW - reproducibility of results N2 - Background: Chest computed tomography (CT) is crucial for the detection of lung cancer, and many automated CT evaluation methods have been proposed. Due to the divergent software dependencies of the reported approaches, the developed methods are rarely compared or reproduced. Objective: The goal of the research was to generate reproducible machine learning modules for lung cancer detection and compare the approaches and performances of the award-winning algorithms developed in the Kaggle Data Science Bowl. Methods: We obtained the source codes of all award-winning solutions of the Kaggle Data Science Bowl Challenge, where participants developed automated CT evaluation methods to detect lung cancer (training set n=1397, public test set n=198, final test set n=506). The performance of the algorithms was evaluated by the log-loss function, and the Spearman correlation coefficient of the performance in the public and final test sets was computed. Results: Most solutions implemented distinct image preprocessing, segmentation, and classification modules. Variants of U-Net, VGGNet, and residual net were commonly used in nodule segmentation, and transfer learning was used in most of the classification algorithms. Substantial performance variations in the public and final test sets were observed (Spearman correlation coefficient = .39 among the top 10 teams). To ensure the reproducibility of results, we generated a Docker container for each of the top solutions. Conclusions: We compared the award-winning algorithms for lung cancer detection and generated reproducible Docker images for the top solutions. Although convolutional neural networks achieved decent accuracy, there is plenty of room for improvement regarding model generalizability. UR - https://www.jmir.org/2020/8/e16709 UR - http://dx.doi.org/10.2196/16709 UR - http://www.ncbi.nlm.nih.gov/pubmed/32755895 ID - info:doi/10.2196/16709 ER - TY - JOUR AU - Liu, Ziqing AU - He, Haiyang AU - Yan, Shixing AU - Wang, Yong AU - Yang, Tao AU - Li, Guo-Zheng PY - 2020/6/16 TI - End-to-End Models to Imitate Traditional Chinese Medicine Syndrome Differentiation in Lung Cancer Diagnosis: Model Development and Validation JO - JMIR Med Inform SP - e17821 VL - 8 IS - 6 KW - traditional Chinese medicine KW - syndrome differentiation KW - lung cancer KW - medical record KW - deep learning KW - model fusion N2 - Background: Traditional Chinese medicine (TCM) has been shown to be an efficient mode to manage advanced lung cancer, and accurate syndrome differentiation is crucial to treatment. Documented evidence of TCM treatment cases and the progress of artificial intelligence technology are enabling the development of intelligent TCM syndrome differentiation models. This is expected to expand the benefits of TCM to lung cancer patients. Objective: The objective of this work was to establish end-to-end TCM diagnostic models to imitate lung cancer syndrome differentiation. The proposed models used unstructured medical records as inputs to capitalize on data collected for practical TCM treatment cases by lung cancer experts. The resulting models were expected to be more efficient than approaches that leverage structured TCM datasets. Methods: We approached lung cancer TCM syndrome differentiation as a multilabel text classification problem. First, entity representation was conducted with Bidirectional Encoder Representations from Transformers and conditional random fields models. Then, five deep learning?based text classification models were applied to the construction of a medical record multilabel classifier, during which two data augmentation strategies were adopted to address overfitting issues. Finally, a fusion model approach was used to elevate the performance of the models. Results: The F1 score of the recurrent convolutional neural network (RCNN) model with augmentation was 0.8650, a 2.41% improvement over the unaugmented model. The Hamming loss for RCNN with augmentation was 0.0987, which is 1.8% lower than that of the same model without augmentation. Among the models, the text-hierarchical attention network (Text-HAN) model achieved the highest F1 scores of 0.8676 and 0.8751. The mean average precision for the word encoding?based RCNN was 10% higher than that of the character encoding?based representation. A fusion model of the text-convolutional neural network, text-recurrent neural network, and Text-HAN models achieved an F1 score of 0.8884, which showed the best performance among the models. Conclusions: Medical records could be used more productively by constructing end-to-end models to facilitate TCM diagnosis. With the aid of entity-level representation, data augmentation, and model fusion, deep learning?based multilabel classification approaches can better imitate TCM syndrome differentiation in complex cases such as advanced lung cancer. UR - https://medinform.jmir.org/2020/6/e17821 UR - http://dx.doi.org/10.2196/17821 UR - http://www.ncbi.nlm.nih.gov/pubmed/32543445 ID - info:doi/10.2196/17821 ER - TY - JOUR AU - Ray, Arnab AU - Gupta, Aman AU - Al, Amutha PY - 2020/5/7 TI - Skin Lesion Classification With Deep Convolutional Neural Network: Process Development and Validation JO - JMIR Dermatol SP - e18438 VL - 3 IS - 1 KW - deep convolutional neural network KW - VGG16, Inceptionv3 KW - Inception ResNet V2 KW - DenseNet KW - skin cancer KW - cancer KW - neural network KW - machine learning KW - melanoma N2 - Background: Skin cancer is the most common cancer and is often ignored by people at an early stage. There are 5.4 million new cases of skin cancer worldwide every year. Deaths due to skin cancer could be prevented by early detection of the mole. Objective: We propose a skin lesion classification system that has the ability to detect such moles at an early stage and is able to easily differentiate between a cancerous and noncancerous mole. Using this system, we would be able to save time and resources for both patients and practitioners. Methods: We created a deep convolutional neural network using an Inceptionv3 and DenseNet-201 pretrained model. Results: We found that using the concepts of fine-tuning and the ensemble learning model yielded superior results. Furthermore, fine-tuning the whole model helped models converge faster compared to fine-tuning only the top layers, giving better accuracy overall. Conclusions: Based on our research, we conclude that deep learning algorithms are highly suitable for classifying skin cancer images. UR - http://derma.jmir.org/2020/1/e18438/ UR - http://dx.doi.org/10.2196/18438 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/18438 ER - TY - JOUR AU - Yongping, Liang AU - Zhou, Ping AU - Juan, Zhang AU - Yongfeng, Zhao AU - Liu, Wengang AU - Shi, Yifan PY - 2020/3/2 TI - Performance of Computer-Aided Diagnosis in Ultrasonography for Detection of Breast Lesions Less and More Than 2 cm: Prospective Comparative Study JO - JMIR Med Inform SP - e16334 VL - 8 IS - 3 KW - ultrasonography KW - breast neoplasm KW - breast imaging reporting and data system (BI-RADS) KW - breast neoplasms diagnosis KW - cancer screening KW - computer diagnostic aid N2 - Background: Computer-aided diagnosis (CAD) is used as an aid tool by radiologists on breast lesion diagnosis in ultrasonography. Previous studies demonstrated that CAD can improve the diagnosis performance of radiologists. However, the optimal use of CAD on breast lesions according to size (below or above 2 cm) has not been assessed. Objective: The aim of this study was to compare the performance of different radiologists using CAD to detect breast tumors less and more than 2 cm in size. Methods: We prospectively enrolled 261 consecutive patients (mean age 43 years; age range 17-70 years), including 398 lesions (148 lesions>2 cm, 79 malignant and 69 benign; 250 lesions?2 cm, 71 malignant and 179 benign) with breast mass as the prominent symptom. One novice radiologist with 1 year of ultrasonography experience and one experienced radiologist with 5 years of ultrasonography experience were each assigned to read the ultrasonography images without CAD, and then again at a second reading while applying the CAD S-Detect. We then compared the diagnostic performance of the readers in the two readings (without and combined with CAD) with breast imaging. The McNemar test for paired data was used for statistical analysis. Results: For the novice reader, the area under the receiver operating characteristic curve (AUC) improved from 0.74 (95% CI 0.67-0.82) from the without-CAD mode to 0.88 (95% CI 0.83-0.93; P<.001) at the combined-CAD mode in lesions?2 cm. For the experienced reader, the AUC improved from 0.84 (95% CI 0.77-0.90) to 0.90 (95% CI 0.86-0.94; P=.002). In lesions>2 cm, the AUC moderately decreased from 0.81 to 0.80 (novice reader) and from 0.90 to 0.82 (experienced reader). The sensitivity of the novice and experienced reader in lesions?2 cm improved from 61.97% and 73.23% at the without-CAD mode to 90.14% and 97.18% (both P<.001) at the combined-CAD mode, respectively. Conclusions: S-Detect is a feasible diagnostic tool that can improve the sensitivity for both novice and experienced readers, while also improving the negative predictive value and AUC for lesions?2 cm, demonstrating important application value in the clinical diagnosis of breast cancer. Trial Registration: Chinese Clinical Trial Registry ChiCTR1800019649; http://www.chictr.org.cn/showprojen.aspx?proj=33094 UR - https://medinform.jmir.org/2020/3/e16334 UR - http://dx.doi.org/10.2196/16334 UR - http://www.ncbi.nlm.nih.gov/pubmed/32130149 ID - info:doi/10.2196/16334 ER - TY - JOUR AU - Wu, Jiangpeng AU - Zan, Xiangyi AU - Gao, Liping AU - Zhao, Jianhong AU - Fan, Jing AU - Shi, Hengxue AU - Wan, Yixin AU - Yu, E. AU - Li, Shuyan AU - Xie, Xiaodong PY - 2019/08/15 TI - A Machine Learning Method for Identifying Lung Cancer Based on Routine Blood Indices: Qualitative Feasibility Study JO - JMIR Med Inform SP - e13476 VL - 7 IS - 3 KW - lung cancer identification KW - routine blood indices KW - Random Forest N2 - Background: Liquid biopsies based on blood samples have been widely accepted as a diagnostic and monitoring tool for cancers, but extremely high sensitivity is frequently needed due to the very low levels of the specially selected DNA, RNA, or protein biomarkers that are released into blood. However, routine blood indices tests are frequently ordered by physicians, as they are easy to perform and are cost effective. In addition, machine learning is broadly accepted for its ability to decipher complicated connections between multiple sets of test data and diseases. Objective: The aim of this study is to discover the potential association between lung cancer and routine blood indices and thereby help clinicians and patients to identify lung cancer based on these routine tests. Methods: The machine learning method known as Random Forest was adopted to build an identification model between routine blood indices and lung cancer that would determine if they were potentially linked. Ten-fold cross-validation and further tests were utilized to evaluate the reliability of the identification model. Results: In total, 277 patients with 49 types of routine blood indices were included in this study, including 183 patients with lung cancer and 94 patients without lung cancer. Throughout the course of the study, there was correlation found between the combination of 19 types of routine blood indices and lung cancer. Lung cancer patients could be identified from other patients, especially those with tuberculosis (which usually has similar clinical symptoms to lung cancer), with a sensitivity, specificity and total accuracy of 96.3%, 94.97% and 95.7% for the cross-validation results, respectively. This identification method is called the routine blood indices model for lung cancer, and it promises to be of help as a tool for both clinicians and patients for the identification of lung cancer based on routine blood indices. Conclusions: Lung cancer can be identified based on the combination of 19 types of routine blood indices, which implies that artificial intelligence can find the connections between a disease and the fundamental indices of blood, which could reduce the necessity of costly, elaborate blood test techniques for this purpose. It may also be possible that the combination of multiple indices obtained from routine blood tests may be connected to other diseases as well. UR - http://medinform.jmir.org/2019/3/e13476/ UR - http://dx.doi.org/10.2196/13476 UR - http://www.ncbi.nlm.nih.gov/pubmed/31418423 ID - info:doi/10.2196/13476 ER -