%0 Journal Article %@ 1438-8871 %I JMIR Publications %V 27 %N %P e65547 %T Large Language Models in Summarizing Radiology Report Impressions for Lung Cancer in Chinese: Evaluation Study %A Hu,Danqing %A Zhang,Shanyuan %A Liu,Qing %A Zhu,Xiaofeng %A Liu,Bing %+ Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education), Department of Thoracic Surgery II, Peking University Cancer Hospital and Institute, 52 Fucheng Road, Haidian District, Beijing, 100142, China, 86 15201469501, liubing983811735@126.com %K large language model %K impression summarization %K radiology report %K radiology %K evaluation study %K ChatGPT %K natural language processing %K ultrasound %K radiologist %K thoracic surgeons %D 2025 %7 3.4.2025 %9 Original Paper %J J Med Internet Res %G English %X Background: Large language models (LLMs), such as ChatGPT, have demonstrated impressive capabilities in various natural language processing tasks, particularly in text generation. However, their effectiveness in summarizing radiology report impressions remains uncertain. Objective: This study aims to evaluate the capability of nine LLMs, that is, Tongyi Qianwen, ERNIE Bot, ChatGPT, Bard, Claude, Baichuan, ChatGLM, HuatuoGPT, and ChatGLM-Med, in summarizing Chinese radiology report impressions for lung cancer. Methods: We collected 100 Chinese computed tomography (CT), positron emission tomography (PET)–CT, and ultrasound (US) reports each from Peking University Cancer Hospital and Institute. All these reports were from patients with suspected or confirmed lung cancer. Using these reports, we created zero-shot, one-shot, and three-shot prompts with or without complete example reports as inputs to generate impressions. We used both automatic quantitative evaluation metrics and five human evaluation metrics (completeness, correctness, conciseness, verisimilitude, and replaceability) to assess the generated impressions. Two thoracic surgeons (SZ and BL) and one radiologist (QL) compared the generated impressions with reference impressions, scoring them according to the five human evaluation metrics. Results: In the automatic quantitative evaluation, ERNIE Bot, Tongyi Qianwen, and Claude demonstrated the best overall performance in generating impressions for CT, PET-CT, and US reports, respectively. In the human semantic evaluation, ERNIE Bot outperformed the other LLMs in terms of conciseness, verisimilitude, and replaceability on CT impression generation, while its completeness and correctness scores were comparable to those of other LLMs. Tongyi Qianwen excelled in PET-CT impression generation, with the highest scores for correctness, conciseness, verisimilitude, and replaceability. Claude achieved the best conciseness, verisimilitude, and replaceability scores on US impression generation, and its completeness and correctness scores are close to the best results obtained by other LLMs. The generated impressions were generally complete and correct but lacked conciseness and verisimilitude. Although one-shot and few-shot prompts improved conciseness and verisimilitude, clinicians noted a significant gap between the generated impressions and those written by radiologists. Conclusions: Current LLMs can produce radiology impressions with high completeness and correctness but fall short in conciseness and verisimilitude, indicating they cannot yet fully replace impressions written by radiologists. %M 40179389 %R 10.2196/65547 %U https://www.jmir.org/2025/1/e65547 %U https://doi.org/10.2196/65547 %U http://www.ncbi.nlm.nih.gov/pubmed/40179389 %0 Journal Article %@ 1929-0748 %I JMIR Publications %V 14 %N %P e58529 %T Lung Cancer Screening in Family Members and Peers of Patients With Lung Cancer: Protocol for a Prospective Cohort Study %A Pitrou,Isabelle %A Petrangelo,Adriano %A Besson,Charlotte %A Pepe,Carmela %A Waschke,Annika Helen %A Agulnik,Jason %A Gonzalez,Anne V %A Ezer,Nicole %+ Centre for Outcomes Research and Evaluation (CORE), Research Institute McGill University Health Centre, 5252 De Maisonneuve, Montréal, QC, H4A 3S9, Canada, 1 5149341934 ext 76192, nicole.ezer@mcgill.ca %K lung cancer %K low-dose CT %K chest tomography %K lung cancer screening %K patient advocacy %K early detection of cancer %K referral and consultation %K cohort study %K patient empowerment %K patient experience %D 2025 %7 28.3.2025 %9 Protocol %J JMIR Res Protoc %G English %X 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 %R 10.2196/58529 %U https://www.researchprotocols.org/2025/1/e58529 %U https://doi.org/10.2196/58529 %0 Journal Article %@ 2369-1999 %I JMIR Publications %V 11 %N %P e53328 %T Assessing Public Interest in Mammography, Computed Tomography Lung Cancer Screening, and Computed Tomography Colonography Screening Examinations Using Internet Search Data: Cross-Sectional Study %A Zippi,Zachary D %A Cortopassi,Isabel O %A Grage,Rolf A %A Johnson,Elizabeth M %A McCann,Matthew R %A Mergo,Patricia J %A Sonavane,Sushil K %A Stowell,Justin T %A Little,Brent P %K lung cancer %K lung cancer screening %K breast cancer %K mammography %K colon cancer %K CT colonography %K Google search %K internet %K Google Trends %K imaging-based %K cancer screening %K search data %K noninvasive %K cancer %K CT %K online %K public awareness %K big data %K analytics %K patient education %K screening uptake %D 2025 %7 11.3.2025 %9 %J JMIR Cancer %G English %X Background: The noninvasive imaging examinations of mammography (MG), low-dose computed tomography (CT) for lung cancer screening (LCS), and CT colonography (CTC) play important roles in screening for the most common cancer types. Internet search data can be used to gauge public interest in screening techniques, assess common screening-related questions and concerns, and formulate public awareness strategies. Objective: This study aims to compare historical Google search volumes for MG, LCS, and CTC and to determine the most common search topics. Methods: Google Trends data were used to quantify relative Google search frequencies for these imaging screening modalities over the last 2 decades. A commercial search engine tracking product (keywordtool.io) was used to assess the content of related Google queries over the year from May 1, 2022, to April 30, 2023, and 2 authors used an iterative process to agree upon a list of thematic categories for these queries. Queries with at least 10 monthly instances were independently assigned to the most appropriate category by the 2 authors, with disagreements resolved by consensus. Results: The mean 20-year relative search volume for MG was approximately 10-fold higher than for LCS and 25-fold higher than for CTC. Search volumes for LCS have trended upward since 2011. The most common topics of MG-related searches included nearby screening locations (60,850/253,810, 24%) and inquiries about procedural discomfort (28,970/253,810, 11%). Most common LCS-related searches included CT-specific inquiries (5380/11,150, 48%) or general inquiries (1790/11,150, 16%), use of artificial intelligence or deep learning (1210/11,150, 11%), and eligibility criteria (1020/11,150, 9%). For CTC, the most common searches were CT-specific inquiries (1800/5590, 32%) or procedural details (1380/5590, 25%). Conclusions: Over the past 2 decades, Google search volumes have been significantly higher for MG than for either LCS or CTC, although search volumes for LCS have trended upward since 2011. Knowledge of public interest and queries related to imaging-based screening techniques may help guide public awareness efforts. %R 10.2196/53328 %U https://cancer.jmir.org/2025/1/e53328 %U https://doi.org/10.2196/53328 %0 Journal Article %@ 2369-1999 %I JMIR Publications %V 11 %N %P e65118 %T Treatment Outcomes From Erlotinib and Gefitinib in Advanced Epidermal Growth Factor Receptor–Mutated Nonsquamous Non–Small Cell Lung Cancer in Aotearoa New Zealand From 2010 to 2020: Nationwide Whole-of-Patient-Population Retrospective Cohort Study %A Aye,Phyu Sin %A Barnes,Joanne %A Laking,George %A Cameron,Laird %A Anderson,Malcolm %A Luey,Brendan %A Delany,Stephen %A Harris,Dean %A McLaren,Blair %A Brenman,Elliott %A Wong,Jayden %A Lawrenson,Ross %A Arendse,Michael %A Tin Tin,Sandar %A Elwood,Mark %A Hope,Philip %A McKeage,Mark James %K non–small cell lung cancer %K mutations %K epidemiology %K target therapy %K retrospective cohort study %D 2025 %7 3.3.2025 %9 %J JMIR Cancer %G English %X Background: Health care system–wide outcomes from routine treatment with erlotinib and gefitinib are incompletely understood. Objective: The aim of the study is to describe the effectiveness of erlotinib and gefitinib during the first decade of their routine use for treating advanced epidermal growth factor receptor (EGFR) mutation-positive nonsquamous non–small cell lung cancer in the entire cohort of patients treated in Aotearoa New Zealand. Methods: Patients were identified, and data collated from national pharmaceutical dispensing, cancer registration, and mortality registration electronic databases by deterministic data linkage using National Health Index numbers. Time-to-treatment discontinuation and overall survival were measured from the date of first dispensing of erlotinib or gefitinib and analyzed by Kaplan-Meier curves. Associations of treatment outcomes with baseline factors were evaluated using univariable and multivariable Cox regressions. Results: Overall, 752 patients were included who started treatment with erlotinib (n=418) or gefitinib (n=334) before October 2020. Median time-to-treatment discontinuation was 11.6 (95% CI 10.8‐12.4) months, and median overall survival was 20.1 (95% CI 18.1‐21.6) months. Shorter time-to-treatment discontinuation was independently associated with high socioeconomic deprivation (hazard ratio [HR] 1.3, 95% CI 1.1‐1.5 compared to the New Zealand Index of Deprivation 1‐4 group), EGFR L858R mutations (HR 1.3, 95% CI 1.1‐1.6 compared to exon 19 deletion), and distant disease at cancer diagnosis (HR 1.4, 95% CI 1.2‐1.7 compared to localized or regional disease). The same factors were independently associated with shorter overall survival. Outcome estimates and predictors remained unchanged in sensitivity analyses. Conclusions: Outcomes from routine treatment with erlotinib and gefitinib in New Zealand patients with advanced EGFR-mutant nonsquamous non–small cell lung cancer are comparable with those reported in randomized trials and other health care system–wide retrospective cohort studies. Socioeconomic status, EGFR mutation subtype, and disease extent at cancer diagnosis were independent predictors of treatment outcomes in that setting. Trial Registration: Australia New Zealand Clinical Trials Registry ACTRN12615000998549; https://www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=368928&isReview=true International Registered Report Identifier (IRRID): RR2-10.2196/51381 %R 10.2196/65118 %U https://cancer.jmir.org/2025/1/e65118 %U https://doi.org/10.2196/65118 %0 Journal Article %@ 2291-5222 %I JMIR Publications %V 13 %N %P e60115 %T Digital Therapeutics–Based Cardio-Oncology Rehabilitation for Lung Cancer Survivors: Randomized Controlled Trial %A Li,Guangqi %A Zhou,Xueyan %A Deng,Junyue %A Wang,Jiao %A Ai,Ping %A Zeng,Jingyuan %A Ma,Xuelei %A Liao,Hu %+ Department of Thoracic Surgery, West China Hospital, Sichuan University, No. 37 GuoXue Alley, Chengdu, 610041, China, 86 18980605130, drliaohu@scu.edu.cn %K cardio-oncology rehabilitation %K digital therapeutics %K telerehabilitation %K non-small cell lung cancer %K exercise prescription %K cardiology %K oncology %K rehabilitation %K cardiorespiratory fitness %K cardiopulmonary %K cancer %K physical activity %K digital health %K digital technology %K randomized controlled trial %K wearable %K app %K quality of life %K survivor %D 2025 %7 25.2.2025 %9 Original Paper %J JMIR Mhealth Uhealth %G English %X Background: Lung cancer ranks as the leading cause of cancer-related deaths. For lung cancer survivors, cardiopulmonary fitness is a strong independent predictor of survival, while surgical interventions impact both cardiovascular and pulmonary function. Home-based cardiac telerehabilitation through wearable devices and mobile apps is a substitution for traditional, center-based rehabilitation with equal efficacy and a higher completion rate. However, it has not been widely used in clinical practice. Objective: The objective of this study was to broaden the use of digital health care in the cardiopulmonary rehabilitation of lung cancer survivors and to assess its impact on cardiopulmonary fitness and quality of life (QOL). Methods: Early-stage nonsmall cell lung cancer survivors aged 18-70 years were included. All the participants received surgery 1-2 months before enrollment and did not require further antitumor therapy. Participants were randomly assigned to receive cardiac telerehabilitation or usual care for 5 months. Artificial intelligence–driven exercise prescription with a video guide and real-time heart rate (HR) monitoring was generated based on cardiopulmonary exercise testing. Aerobic exercise combining elastic band–based resistance exercises were recommended with a frequency of 3-5 d/wk and a duration of 90-150 min/wk. The effective exercise duration was recorded when patients’ HR reached the target zone (HRresting + [HRmax – HRresting] × [≈40%-60%]), representing the duration under the target intensity. The prescription used a gradual progression in duration and action intensity based on the exercise data and feedback. Outcome measurements included cardiopulmonary fitness; lung function; cardiac function; tumor marker; safety; compliance; and scales assessing symptoms, psychology, sleep, fatigue, and QOL. Results: A total of 40 (85%) out of 47 patients finished the trial. The average prescription compliance rate of patients in the telerehabilitation group reached 101.2%, with an average exercise duration of 151.4 min/wk and an average effective exercise duration of 92.3 min/wk. The cardiac telerehabilitation was associated with higher improvement of maximal oxygen uptake peak (3.66, SD 3.23 mL/Kg/min vs 1.09, SD 3.23 mL/Kg/min; P=.02) and global health status or QOL (16.25, SD 23.02 vs 1.04, SD 13.90; P=.03) compared with usual care. Better alleviation of affective interference (–0.88, SD 1.50 vs 0.21, SD 1.22; P=.048), fatigue (–8.89, SD 15.96 vs 1.39, SD 12.09; P=.02), anxiety (–0.31, SD 0.44 vs –0.05, SD 0.29; P=.048), and daytime dysfunction (–0.55, SD 0.69 vs 0.00, SD 0.52; P=.02) was also observed in the telerehabilitation group. No exercise-related adverse events were identified during the intervention period. Conclusions: The 5-month, digital therapeutics–based telerehabilitation improved cardiorespiratory fitness in lung cancer survivors with good compliance and safety. Patients receiving telerehabilitation also reported improved QOL with reduced levels of fatigue, anxiety, and daytime dysfunction. Trial Registration: Chinese Clinical Trial Registry ChiCTR2200064000; https://www.chictr.org.cn/showproj.html?proj=180594 %M 39999435 %R 10.2196/60115 %U https://mhealth.jmir.org/2025/1/e60115 %U https://doi.org/10.2196/60115 %U http://www.ncbi.nlm.nih.gov/pubmed/39999435 %0 Journal Article %@ 2817-1705 %I JMIR Publications %V 4 %N %P e60847 %T Advancing Privacy-Preserving Health Care Analytics and Implementation of the Personal Health Train: Federated Deep Learning Study %A Choudhury,Ananya %A Volmer,Leroy %A Martin,Frank %A Fijten,Rianne %A Wee,Leonard %A Dekker,Andre %A Soest,Johan van %+ , GROW Research Institute for Oncology and Reproduction, Maastricht University Medical Center+, Paul Henri Spakalaan 1, Maastricht, 6229EN, Netherlands, 31 0686008485, ananya.aus@gmail.com %K gross tumor volume segmentation %K federated learning infrastructure %K privacy-preserving technology %K cancer %K deep learning %K artificial intelligence %K lung cancer %K oncology %K radiotherapy %K imaging %K data protection %K data privacy %D 2025 %7 6.2.2025 %9 Original Paper %J JMIR AI %G English %X Background: The rapid advancement of deep learning in health care presents significant opportunities for automating complex medical tasks and improving clinical workflows. However, widespread adoption is impeded by data privacy concerns and the necessity for large, diverse datasets across multiple institutions. Federated learning (FL) has emerged as a viable solution, enabling collaborative artificial intelligence model development without sharing individual patient data. To effectively implement FL in health care, robust and secure infrastructures are essential. Developing such federated deep learning frameworks is crucial to harnessing the full potential of artificial intelligence while ensuring patient data privacy and regulatory compliance. Objective: The objective is to introduce an innovative FL infrastructure called the Personal Health Train (PHT) that includes the procedural, technical, and governance components needed to implement FL on real-world health care data, including training deep learning neural networks. The study aims to apply this federated deep learning infrastructure to the use case of gross tumor volume segmentation on chest computed tomography images of patients with lung cancer and present the results from a proof-of-concept experiment. Methods: The PHT framework addresses the challenges of data privacy when sharing data, by keeping data close to the source and instead bringing the analysis to the data. Technologically, PHT requires 3 interdependent components: “tracks” (protected communication channels), “trains” (containerized software apps), and “stations” (institutional data repositories), which are supported by the open source “Vantage6” software. The study applies this federated deep learning infrastructure to the use case of gross tumor volume segmentation on chest computed tomography images of patients with lung cancer, with the introduction of an additional component called the secure aggregation server, where the model averaging is done in a trusted and inaccessible environment. Results: We demonstrated the feasibility of executing deep learning algorithms in a federated manner using PHT and presented the results from a proof-of-concept study. The infrastructure linked 12 hospitals across 8 nations, covering 4 continents, demonstrating the scalability and global reach of the proposed approach. During the execution and training of the deep learning algorithm, no data were shared outside the hospital. Conclusions: The findings of the proof-of-concept study, as well as the implications and limitations of the infrastructure and the results, are discussed. The application of federated deep learning to unstructured medical imaging data, facilitated by the PHT framework and Vantage6 platform, represents a significant advancement in the field. The proposed infrastructure addresses the challenges of data privacy and enables collaborative model development, paving the way for the widespread adoption of deep learning–based tools in the medical domain and beyond. The introduction of the secure aggregation server implied that data leakage problems in FL can be prevented by careful design decisions of the infrastructure. Trial Registration: ClinicalTrials.gov NCT05775068; https://clinicaltrials.gov/study/NCT05775068 %M 39912580 %R 10.2196/60847 %U https://ai.jmir.org/2025/1/e60847 %U https://doi.org/10.2196/60847 %U http://www.ncbi.nlm.nih.gov/pubmed/39912580 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 27 %N %P e64649 %T Enhancing Diagnostic Accuracy of Lung Nodules in Chest Computed Tomography Using Artificial Intelligence: Retrospective Analysis %A Liu,Weiqi %A Wu,You %A Zheng,Zhuozhao %A Bittle,Mark %A Yu,Wei %A Kharrazi,Hadi %+ Department of Radiology, Beijing Anzhen Hospital, Capital Medical University, 2 Anzhen Road, Chaoyang District, Beijing, 100029, China, 86 10 84005287, nxyw1969@163.com %K artificial intelligence %K diagnostic accuracy %K lung nodule %K radiology %K AI system %D 2025 %7 27.1.2025 %9 Original Paper %J J Med Internet Res %G English %X Background: Uncertainty in the diagnosis of lung nodules is a challenge for both patients and physicians. Artificial intelligence (AI) systems are increasingly being integrated into medical imaging to assist diagnostic procedures. However, the accuracy of AI systems in identifying and measuring lung nodules on chest computed tomography (CT) scans remains unclear, which requires further evaluation. Objective: This study aimed to evaluate the impact of an AI-assisted diagnostic system on the diagnostic efficiency of radiologists. It specifically examined the report modification rates and missed and misdiagnosed rates of junior radiologists with and without AI assistance. Methods: We obtained effective data from 12,889 patients in 2 tertiary hospitals in Beijing before and after the implementation of the AI system, covering the period from April 2018 to March 2022. Diagnostic reports written by both junior and senior radiologists were included in each case. Using reports by senior radiologists as a reference, we compared the modification rates of reports written by junior radiologists with and without AI assistance. We further evaluated alterations in lung nodule detection capability over 3 years after the integration of the AI system. Evaluation metrics of this study include lung nodule detection rate, accuracy, false negative rate, false positive rate, and positive predictive value. The statistical analyses included descriptive statistics and chi-square, Cochran-Armitage, and Mann-Kendall tests. Results: The AI system was implemented in Beijing Anzhen Hospital (Hospital A) in January 2019 and Tsinghua Changgung Hospital (Hospital C) in June 2021. The modification rate of diagnostic reports in the detection of lung nodules increased from 4.73% to 7.23% (χ21=12.15; P<.001) at Hospital A. In terms of lung nodule detection rates postimplementation, Hospital C increased from 46.19% to 53.45% (χ21=25.48; P<.001) and Hospital A increased from 39.29% to 55.22% (χ21=122.55; P<.001). At Hospital A, the false negative rate decreased from 8.4% to 5.16% (χ21=9.85; P=.002), while the false positive rate increased from 2.36% to 9.77% (χ21=53.48; P<.001). The detection accuracy demonstrated a decrease from 93.33% to 92.23% for Hospital A and from 95.27% to 92.77% for Hospital C. Regarding the changes in lung nodule detection capability over a 3-year period following the integration of the AI system, the detection rates for lung nodules exhibited a modest increase from 54.6% to 55.84%, while the overall accuracy demonstrated a slight improvement from 92.79% to 93.92%. Conclusions: The AI system enhanced lung nodule detection, offering the possibility of earlier disease identification and timely intervention. Nevertheless, the initial reduction in accuracy underscores the need for standardized diagnostic criteria and comprehensive training for radiologists to maximize the effectiveness of AI-enabled diagnostic systems. %M 39869890 %R 10.2196/64649 %U https://www.jmir.org/2025/1/e64649 %U https://doi.org/10.2196/64649 %U http://www.ncbi.nlm.nih.gov/pubmed/39869890 %0 Journal Article %@ 2369-1999 %I JMIR Publications %V 11 %N %P e57275 %T Large Language Model Approach for Zero-Shot Information Extraction and Clustering of Japanese Radiology Reports: Algorithm Development and Validation %A Yamagishi,Yosuke %A Nakamura,Yuta %A Hanaoka,Shouhei %A Abe,Osamu %K radiology reports %K clustering %K large language model %K natural language processing %K information extraction %K lung cancer %K machine learning %D 2025 %7 23.1.2025 %9 %J JMIR Cancer %G English %X Background: The application of natural language processing in medicine has increased significantly, including tasks such as information extraction and classification. Natural language processing plays a crucial role in structuring free-form radiology reports, facilitating the interpretation of textual content, and enhancing data utility through clustering techniques. Clustering allows for the identification of similar lesions and disease patterns across a broad dataset, making it useful for aggregating information and discovering new insights in medical imaging. However, most publicly available medical datasets are in English, with limited resources in other languages. This scarcity poses a challenge for development of models geared toward non-English downstream tasks. Objective: This study aimed to develop and evaluate an algorithm that uses large language models (LLMs) to extract information from Japanese lung cancer radiology reports and perform clustering analysis. The effectiveness of this approach was assessed and compared with previous supervised methods. Methods: This study employed the MedTxt-RR dataset, comprising 135 Japanese radiology reports from 9 radiologists who interpreted the computed tomography images of 15 lung cancer patients obtained from Radiopaedia. Previously used in the NTCIR-16 (NII Testbeds and Community for Information Access Research) shared task for clustering performance competition, this dataset was ideal for comparing the clustering ability of our algorithm with those of previous methods. The dataset was split into 8 cases for development and 7 for testing, respectively. The study’s approach involved using the LLM to extract information pertinent to lung cancer findings and transforming it into numeric features for clustering, using the K-means method. Performance was evaluated using 135 reports for information extraction accuracy and 63 test reports for clustering performance. This study focused on the accuracy of automated systems for extracting tumor size, location, and laterality from clinical reports. The clustering performance was evaluated using normalized mutual information, adjusted mutual information , and the Fowlkes-Mallows index for both the development and test data. Results: The tumor size was accurately identified in 99 out of 135 reports (73.3%), with errors in 36 reports (26.7%), primarily due to missing or incorrect size information. Tumor location and laterality were identified with greater accuracy in 112 out of 135 reports (83%); however, 23 reports (17%) contained errors mainly due to empty values or incorrect data. Clustering performance of the test data yielded an normalized mutual information of 0.6414, adjusted mutual information of 0.5598, and Fowlkes-Mallows index of 0.5354. The proposed method demonstrated superior performance across all evaluation metrics compared to previous methods. Conclusions: The unsupervised LLM approach surpassed the existing supervised methods in clustering Japanese radiology reports. These findings suggest that LLMs hold promise for extracting information from radiology reports and integrating it into disease-specific knowledge structures. %R 10.2196/57275 %U https://cancer.jmir.org/2025/1/e57275 %U https://doi.org/10.2196/57275 %0 Journal Article %@ 1929-0748 %I JMIR Publications %V 14 %N %P e60420 %T Impact of Remote Symptom Management on Exercise Adherence After Video-Assisted Thoracic Surgery for Lung Cancer in a Tertiary Hospital in China: Protocol for a Prospective Randomized Controlled Trial %A Su,Jianwei %A Ye,Cuiling %A Zhang,Qian %A Liang,Yi %A Wu,Jianwei %A Liang,Guixi %A Cheng,Yalan %A Yang,Xiaojuan %+ Department of cardiothoracic Surgery, Zhongshan City People’s Hospital, No.2 Sunwen East Rd., Zhongshan, 528403, China, 86 0760 88823566, ZPH_XJYang@163.com %K thoracic surgery %K rehabilitation medicine %K patient-reported outcome measures %K patient participation %K telemedicine %K eHealth %K mobile phone %D 2025 %7 1.1.2025 %9 Protocol %J JMIR Res Protoc %G English %X Background: Regular pulmonary rehabilitation exercises are crucial for patients with lung cancer after surgery. However, poor adherence to outpatient exercises is difficult to address due to inadequate supervision. The integration of remote symptom management through electronic patient-reported outcomes (ePROs) offers a potential solution to improve adherence by enabling more effective monitoring and intervention. Objective: This study aims to evaluate the impact of ePRO-based remote symptom management on enhancing adherence to outpatient pulmonary rehabilitation exercises following video-assisted thoracic surgery for lung cancer. Methods: In this single-center, prospective, randomized controlled trial, 736 patients undergoing minimally invasive lung resection will be recruited. All patients will use a smartphone app for perioperative management, allowing periodic PRO measurement and recording of exercise participation. Upon discharge, patients will be randomly assigned 1:1 into either an intervention or control group. The intervention group will complete the Perioperative Symptom Assessment for Patients Undergoing Lung Surgery (PSA-Lung) scale on the day of discharge and postdischarge days 3, 7, 14, 21, and 28. Alerts will be triggered at the provider side if any of the 5 core symptoms (pain, cough, shortness of breath, sleep disturbance, and fatigue) scored ≥4, prompting remote symptom management. The control group will complete the PRO measures without triggering alerts. The primary outcome is the rehabilitation exercise adherence rate. Secondary outcomes include postdischarge pulmonary complication rate, 30-day readmission rate, trajectory of symptom severity changes, exercise participation rate, and patient satisfaction. Results: The enrollment of study participants started in December 2023 and is expected to end in March 2025. The final comprehensive analysis of the results is planned for May 2025, after all data have been collected and thoroughly reviewed. Conclusions: This study is among the first to investigate the feasibility and effectiveness of ePRO-based remote symptom management in enhancing rehabilitation adherence after video-assisted thoracic surgery for lung cancer. If successful, this approach could significantly influence postoperative care practices and potentially be adopted in similar settings. Trial Registration: ClinicalTrials.gov NCT05990946; https://clinicaltrials.gov/study/NCT05990946 International Registered Report Identifier (IRRID): DERR1-10.2196/60420 %M 39610048 %R 10.2196/60420 %U https://www.researchprotocols.org/2025/1/e60420 %U https://doi.org/10.2196/60420 %U http://www.ncbi.nlm.nih.gov/pubmed/39610048 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 12 %N %P e67056 %T Automated Pathologic TN Classification Prediction and Rationale Generation From Lung Cancer Surgical Pathology Reports Using a Large Language Model Fine-Tuned With Chain-of-Thought: Algorithm Development and Validation Study %A Kim,Sanghwan %A Jang,Sowon %A Kim,Borham %A Sunwoo,Leonard %A Kim,Seok %A Chung,Jin-Haeng %A Nam,Sejin %A Cho,Hyeongmin %A Lee,Donghyoung %A Lee,Keehyuck %A Yoo,Sooyoung %+ Office of eHealth Research and Business, Seoul National University Bundang Hospital, Healthcare Innovation Park, Seongnam, 13605, Republic of Korea, 82 317878980, yoosoo0@snubh.org %K AJCC Cancer Staging Manual 8th edition %K American Joint Committee on Cancer %K large language model %K chain-of-thought %K rationale %K lung cancer %K report analysis %K AI %K surgery %K pathology reports %K tertiary hospital %K generative language models %K efficiency %K accuracy %K automated %D 2024 %7 20.12.2024 %9 Original Paper %J JMIR Med Inform %G English %X Background: Traditional rule-based natural language processing approaches in electronic health record systems are effective but are often time-consuming and prone to errors when handling unstructured data. This is primarily due to the substantial manual effort required to parse and extract information from diverse types of documentation. Recent advancements in large language model (LLM) technology have made it possible to automatically interpret medical context and support pathologic staging. However, existing LLMs encounter challenges in rapidly adapting to specialized guideline updates. In this study, we fine-tuned an LLM specifically for lung cancer pathologic staging, enabling it to incorporate the latest guidelines for pathologic TN classification. Objective: This study aims to evaluate the performance of fine-tuned generative language models in automatically inferring pathologic TN classifications and extracting their rationale from lung cancer surgical pathology reports. By addressing the inefficiencies and extensive parsing efforts associated with rule-based methods, this approach seeks to enable rapid and accurate reclassification aligned with the latest cancer staging guidelines. Methods: We conducted a comparative performance evaluation of 6 open-source LLMs for automated TN classification and rationale generation, using 3216 deidentified lung cancer surgical pathology reports based on the American Joint Committee on Cancer (AJCC) Cancer Staging Manual8th edition, collected from a tertiary hospital. The dataset was preprocessed by segmenting each report according to lesion location and morphological diagnosis. Performance was assessed using exact match ratio (EMR) and semantic match ratio (SMR) as evaluation metrics, which measure classification accuracy and the contextual alignment of the generated rationales, respectively. Results: Among the 6 models, the Orca2_13b model achieved the highest performance with an EMR of 0.934 and an SMR of 0.864. The Orca2_7b model also demonstrated strong performance, recording an EMR of 0.914 and an SMR of 0.854. In contrast, the Llama2_7b model achieved an EMR of 0.864 and an SMR of 0.771, while the Llama2_13b model showed an EMR of 0.762 and an SMR of 0.690. The Mistral_7b and Llama3_8b models, on the other hand, showed lower performance, with EMRs of 0.572 and 0.489, and SMRs of 0.377 and 0.456, respectively. Overall, the Orca2 models consistently outperformed the others in both TN stage classification and rationale generation. Conclusions: The generative language model approach presented in this study has the potential to enhance and automate TN classification in complex cancer staging, supporting both clinical practice and oncology data curation. With additional fine-tuning based on cancer-specific guidelines, this approach can be effectively adapted to other cancer types. %M 39705675 %R 10.2196/67056 %U https://medinform.jmir.org/2024/1/e67056 %U https://doi.org/10.2196/67056 %U http://www.ncbi.nlm.nih.gov/pubmed/39705675 %0 Journal Article %@ 1929-0748 %I JMIR Publications %V 13 %N %P e59152 %T Ultrasound-Guided High-Intensity Focused Ultrasound Combined With PD-1 Blockade in Patients With Liver Metastases From Lung Cancer: Protocol for a Single-Arm Phase 2 Trial %A Hu,Chao %A Fu,Qiang %A Gao,Fei Fei %A Zeng,Jian %A Xiao,Wei %A Li,Hui %A Peng,Li %A Huang,Xi %A Yang,Li %A Chen,Wen Zhi %A Jiang,Ming Yan %+ Respiratory Department, Xiangtan Central Hospital, 120 Heping Road, Xiangtan, 411100, China, 86 073158286315, jiangmingyan1979@163.com %K high-intensity focused ultrasound %K programmed cell death protein %K PD-1 blockade %K liver metastases %K lung cancer %K immunotherapy %K treatment efficacy %K quality of life %K HILL study %D 2024 %7 29.11.2024 %9 Protocol %J JMIR Res Protoc %G English %X Background: While immunotherapy has revolutionized oncological management, its efficacy in lung cancer patients with liver metastases remains limited, potentially due to the unique immunosuppressive microenvironment of the liver. Local liver treatment has been shown to enhance the immunotherapy response, and high-intensity focused ultrasound (HIFU), a minimally invasive local treatment, has demonstrated promising results in combination with immunotherapy. However, clinical data regarding HIFU in lung cancer with liver metastases are limited. Objective: We designed the HILL (Ultrasound-Guided High-Intensity Focused Ultrasound Combined With PD-1 Blockade in Patients With Liver Metastases From Lung Cancer) study to investigate the effectiveness and safety of HIFU in combination with immunotherapy for lung cancer with liver metastases. Methods: The HILL study is a single-armed, single-center, phase 2 clinical trial that will enroll 30 patients with lung cancer and liver metastases. The treatment regimen involves administering HIFU to liver metastases 1 week before the first dose of a programmed cell death protein (PD)–1 blockade, which is then administered every 3 weeks. The primary aim is to determine the overall response rate based on immune-related response criteria. Secondary aims include safety, progression-free survival, overall response, overall survival, and quality of life. Exploratory studies will also be conducted using whole blood, plasma, archival cancer tissue, and tumor biopsies during progression or relapse to identify potential biomarkers. Results: The study was funded on March 14, 2022, and received ethical approval on April 27, 2022. Clinical trial registration was completed by June 10, 2022, with participant recruitment beginning on July 10, 2022. Data collection commenced on July 14, 2022, with the enrollment of the first patient. By April 2024, 6 participants had been recruited. The results are expected to be published in December 2026. Conclusions: This study seeks to improve treatment outcomes for lung cancer patients with liver metastases by combining HIFU and PD-1 inhibition. The study also aims to identify potential biomarkers through exploratory research that can aid in selecting patients for optimized outcomes in the future. Trial Registration: Chinese Clinical Trial Registry ChiCTR2200061076; https://www.chictr.org.cn/showproj.html?proj=170967 International Registered Report Identifier (IRRID): DERR1-10.2196/59152 %M 39612480 %R 10.2196/59152 %U https://www.researchprotocols.org/2024/1/e59152 %U https://doi.org/10.2196/59152 %U http://www.ncbi.nlm.nih.gov/pubmed/39612480 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 26 %N %P e56795 %T Effectiveness and Feasibility of Digital Pulmonary Rehabilitation in Patients Undergoing Lung Cancer Surgery: Systematic Review and Meta-Analysis %A Lu,Taiping %A Deng,Ting %A Long,Yangyang %A Li,Jin %A Hu,Anmei %A Hu,Yufan %A Ouyang,Li %A Wang,Huiping %A Ma,Junliang %A Chen,Shaolin %A Hu,Jiale %+ Nursing Department, Affiliated Hospital of Zunyi Medical University, Number 149, Dalian Road, Huichuan District, Zunyi, 563000, China, 86 13762910513, 30363284@qq.com %K app-based %K digital rehabilitation %K internet-based intervention %K lung cancer %K perioperative pulmonary rehabilitation %K systematic review %K telerehabilitation %D 2024 %7 11.11.2024 %9 Review %J J Med Internet Res %G English %X Background: Pulmonary rehabilitation (PR) has been shown to effectively support postsurgical recovery in patients with lung cancer (LC) at various stages. While digital PR programs offer a potential solution to traditional challenges, such as time and space constraints, their efficacy and feasibility for patients undergoing LC surgery remain unclear. Objective: This systematic review aims to assess the feasibility and effectiveness of digital PR programs for individuals undergoing LC surgery. Methods: A systematic review was conducted, retrieving data from 6 English and 4 Chinese databases from their inception to January 1, 2024. References in related studies were also manually reviewed. The primary outcomes assessed were physical capacity, lung function, and the incidence of postoperative pulmonary complications (PPCs). The secondary outcomes were compliance, hospital stay, chest tube duration, anxiety, depression, and quality of life. Where applicable, recruitment and withdrawal rates were also evaluated. Meta-analysis and descriptive analysis were used to assess the outcomes. Results: A total of 5 randomized controlled trials and 6 quasi-experimental studies (n=1063) were included, with 4 studies being included in the meta-analyses. Our meta-analyses revealed that digital PR reduced the decline in 6-minute walk distance (6-MWD) by an average of 15 m compared with routine PR programs from admission to discharge, demonstrating a clinically significant improvement in physical capacity (mean difference –15.00, 95% CI –25.65 to –4.34, P=.006). Additionally, digital PR was associated with a reduction (26/58, 45%) in the likelihood of PPCs (risk ratio 0.45, 95% CI 0.30-0.66, P<.001) and a reduction of 1.53 days in chest tube duration (mean difference –1.53, 95% CI –2.95 to –0.12, P=.03), without a statistically significant effect on postoperative hospital stay (mean difference –1.42, 95% CI –3.45 to 0.62, P=.17). Descriptive analyses suggested that digital PR has the potential to improve knowledge, lung function, quality of life, and self-efficacy, while reducing depression and anxiety. Notably, digital PR was found to be a safe, feasible, and acceptable supplementary intervention. Despite challenges with low recruitment, digital PR enhanced exercise compliance, increased patient satisfaction, and lowered dropout rates. Conclusions: This systematic review is the first comprehensive analysis to suggest that digital PR is a safe, feasible, acceptable, and effective intervention for promoting recovery in patients with LC after surgery. Digital PR has the potential to be a valuable supplement, expanding access to traditional PR programs. Future research should prioritize the development of interactive and inclusive digital solutions tailored to diverse age groups and educational backgrounds. Rigorous studies, including large-scale, high-quality randomized controlled trials with detailed protocols and robust methodologies, are needed to assess the short-, medium-, and long-term efficacy of digital PR, ensuring reproducibility in future research. Trial Registration: PROSPERO CRD42023430271; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=430271 %M 39527799 %R 10.2196/56795 %U https://www.jmir.org/2024/1/e56795 %U https://doi.org/10.2196/56795 %U http://www.ncbi.nlm.nih.gov/pubmed/39527799 %0 Journal Article %@ 1929-0748 %I JMIR Publications %V 13 %N %P e64950 %T Efficacy and Safety of a Therapy Combining Sintilimab and Chemotherapy With Cryoablation in the First-Line Treatment of Advanced Nonsquamous Non–Small Cell Lung Cancer: Protocol for a Phase II, Pilot, Single-Arm, Single-Center Study %A Gao,Zhiqiang %A Teng,Jiajun %A Qiao,Rong %A Qian,Jialin %A Pan,Feng %A Ma,Meili %A Lu,Jun %A Zhang,Bo %A Chu,Tianqing %A Zhong,Hua %+ Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, 241 Huaihai West Road, Xuhui District, Shanghai, China, 86 02122200000, zhonghua_gcp@163.com %K cryoablation %K immunotherapy %K nonsquamous non–small cell lung cancer %D 2024 %7 8.11.2024 %9 Protocol %J JMIR Res Protoc %G English %X Background: Immunotherapy has significantly advanced lung cancer treatment, particularly in nonsquamous non–small cell lung cancer (NSCLC), with overall response rates between 50% and 60%. However, about 30% of patients only achieve a stable disease state. Cryoablation has shown potential to enhance immunotherapy by modifying the tumor’s immune microenvironment through the release of antigens and immune factors. Addressing how to boost the immune response in these patients is critical. Objective: This study aims to investigate the efficacy and safety of immunochemotherapy in combination with cryoablation as a first-line treatment for advanced NSCLC. Methods: This is a phase II, pilot, open-label, single arm, single center, interventional study. Patients with stage IIIB to IIIC or IV NSCLC with T staging ranging from T1 to T2b will receive sintilimab (200 mg/m2 every 3 weeks) and chemotherapy. After 2 cycles, the feasibility of cryoablation will be considered for those with stable disease by a multidisciplinary team. Cryoablation with 3 freeze-thaw cycles will be performed for the main lesion. The third cycle of systemic therapy will begin 7 (SD 3) days after cryoablation. A total of 20 patients will be enrolled. Treatment will continue until the disease progresses, there is unacceptable toxicity, a participant withdraws consent, other discontinuation criteria are met, or the study reaches completion. The primary objective is to assess progression-free survival (PFS). The secondary objective is to assess efficacy through duration of response, disease control rate, overall survival (OS), and the safety profile. The exploratory objective is to investigate and compare immune factor changes after 2 cycles of immunochemotherapy and at 1, 3, and 7 days after cryoablation. Survival time will be estimated using the Kaplan-Meier method to calculate median PFS and OS. Any adverse events that occur during the trial will be promptly recorded. Results: The project was funded in 2024, and enrollment will be completed in 2025. The first results are expected to be submitted for publication in 2027. Conclusions: This study will provide evidence for the efficacy and safety of the combination of immunochemotherapy and cryoablation as a first-line treatment for advanced NSCLC. Although it has a limited sample size, the findings of this study will be used in the future to inform the design of a fully powered, 2-arm, larger-scale study. Trial Registration: ClinicalTrials.gov NCT06483009; https://clinicaltrials.gov/study/NCT06483009 International Registered Report Identifier (IRRID): PRR1-10.2196/64950 %M 39514267 %R 10.2196/64950 %U https://www.researchprotocols.org/2024/1/e64950 %U https://doi.org/10.2196/64950 %U http://www.ncbi.nlm.nih.gov/pubmed/39514267 %0 Journal Article %@ 1929-0748 %I JMIR Publications %V 13 %N %P e57183 %T Outcomes of Patients With Early and Locally Advanced Lung Cancer: Protocol for the Italian Lung Cancer Observational Study (LUCENT) %A Bertolaccini,Luca %A Ciani,Oriana %A Lucchi,Marco %A Zaraca,Francesco %A Bertani,Alessandro %A Crisci,Roberto %A Spaggiari,Lorenzo %A , %+ Department of Thoracic Surgery, IEO, European Institute of Oncology IRCCS, Via Ripamonti 435, Milan, 20141, Italy, 39 0257489665, luca.bertolaccini@gmail.com %K lung cancer %K quality of life %K observational study %K economic aspects %K multicenter study %D 2024 %7 8.10.2024 %9 Protocol %J JMIR Res Protoc %G English %X Background: Lung cancer, predominantly non-small cell lung cancer (NSCLC), remains a formidable challenge, necessitating an in-depth understanding of evolving treatment paradigms. The Italian Lung Cancer Observational Study (LUCENT) addresses this need by investigating the outcomes of patients with early and locally advanced lung cancer in Italy. Objective: With a focus on real-world data and patient registries, this study aims to provide comprehensive insights into clinical, psychosocial, and economic impacts, contributing to informed decision-making in health care. Methods: LUCENT is a prospective observational multicenter cohort study enrolling patients eligible for minimally invasive manual, robot-assisted, or traditional open surgery. The study will develop a web-based registry to collect longitudinal surgical, oncological, and socioeconomic outcome data. The primary objectives include performance assessment through the establishment of national benchmarks based on risk-adjusted outcomes and processes of care indicators. The secondary objectives encompass economic and psychosocial impact assessments of innovative technologies and treatment pathways. The multicenter design ensures a diverse and representative study population. Results: The evolving landscape of NSCLC treatment necessitates a nuanced approach with consideration of the dynamic shifts in therapeutic strategies. LUCENT strives to fill existing knowledge gaps by providing a platform for collecting and analyzing real-world data, emphasizing the importance of patient-reported outcomes in enhancing the understanding of the disease. By developing a web-based registry, the study not only facilitates efficient data collection but also addresses the limitations of traditional methods, such as suboptimal response rates and costs associated with paper-and-pencil questionnaires. Recruitment will be conducted from January 01, 2024, to December 31, 2026. Follow-up will be performed for a minimum of 2 years. The study will be completed in the year 2028. Conclusions: LUCENT’s potential implications are substantial. Establishing national benchmarks will enable a thorough evaluation of outcomes and care processes, guiding clinicians and policymakers in optimizing patient management. Furthermore, the study’s secondary objectives, focusing on economic and psychosocial impacts, align with the contemporary emphasis on holistic cancer care. Insights gained from this study may influence treatment strategies, resource utilization, and patient well-being, thereby contributing to the ongoing refinement of lung cancer management. Trial Registration: ClinicalTrials.gov NCT05851755; https://clinicaltrials.gov/study/NCT05851755. ISRCTN 67197140; https://www.isrctn.com/ISRCTN67197140 International Registered Report Identifier (IRRID): PRR1-10.2196/57183 %R 10.2196/57183 %U https://www.researchprotocols.org/2024/1/e57183 %U https://doi.org/10.2196/57183 %0 Journal Article %@ 2561-326X %I JMIR Publications %V 8 %N %P e48284 %T Effects of Intervention Timing on Health-Related Fake News: Simulation Study %A Gwon,Nahyun %A Jeong,Wonjeong %A Kim,Jee Hyun %A Oh,Kyoung Hee %A Jun,Jae Kwan %+ Cancer Knowledge and Information Center, National Cancer Control Institute, National Cancer Center, 323 Ilsan-ro, Ilsandong-gu, Goyang, 10408, Republic of Korea, 82 31 920 2184, jkjun@ncc.re.kr %K disinformation %K fenbendazole %K cancer information %K simulation %K fake news %K online social networking %K misinformation %K lung cancer %D 2024 %7 7.8.2024 %9 Original Paper %J JMIR Form Res %G English %X Background: Fake health-related news has spread rapidly through the internet, causing harm to individuals and society. Despite interventions, a fenbendazole scandal recently spread among patients with lung cancer in South Korea. It is crucial to intervene appropriately to prevent the spread of fake news. Objective: This study investigated the appropriate timing of interventions to minimize the side effects of fake news. Methods: A simulation was conducted using the susceptible-infected-recovered (SIR) model, which is a representative model of the virus spread mechanism. We applied this model to the fake news spread mechanism. The parameters were set similarly to those in the digital environment, where the fenbendazole scandal occurred. NetLogo, an agent-based model, was used as the analytical tool. Results: Fake news lasted 278 days in the absence of interventions. As a result of adjusting and analyzing the timing of the intervention in response to the fenbendazole scandal, we found that faster intervention leads to a shorter duration of fake news (intervention at 54 days = fake news that lasted for 210 days; intervention at 16 days = fake news that lasted for 187 days; and intervention at 10 days = fake news that lasted for 157 days). However, no significant differences were observed when the intervention was performed within 10 days. Conclusions: Interventions implemented within 10 days were effective in reducing the duration of the spread of fake news. Our findings suggest that timely intervention is critical for preventing the spread of fake news in the digital environment. Additionally, a monitoring system that can detect fake news should be developed for a rapid response %M 39109788 %R 10.2196/48284 %U https://formative.jmir.org/2024/1/e48284 %U https://doi.org/10.2196/48284 %U http://www.ncbi.nlm.nih.gov/pubmed/39109788 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 26 %N %P e53015 %T Supportive eHealth Technologies and Their Effects on Physical Functioning and Quality of Life for People With Lung Cancer: Systematic Review %A Kirkpatrick,Suriya %A Davey,Zoe %A Wright,Peter Richard %A Henshall,Catherine %+ School of Nursing, Faculty of Health and Life Sciences, Oxford Brookes University, Headington Rd, Headington, Oxford, OX3 0BP, United Kingdom, 44 07909921833, 19228607@brookes.ac.uk %K lung cancer %K physical activity %K exercise %K physical functioning %K mobile technology %K smartphone apps %K digital health %K mobile phone %D 2024 %7 26.7.2024 %9 Review %J J Med Internet Res %G English %X Background: Despite advancements in treatment and early diagnosis, people with lung cancer are not living as long as those with other cancers. The more common symptoms of lung cancer, such as breathlessness, fatigue, and depression, can be alleviated by improving patients’ physical functioning. Therefore, good symptom management and improved health-related quality of life (HRQoL) are priorities in this patient group. However, current health care services have limited capacity to provide this support. One way to address this issue of health care resources is to empower patients to self-manage their condition using eHealth technologies. Objective: The purpose of this review was to identify and assess available research on technologies that support persons with lung cancer to improve or maintain their physical functioning, HRQoL, or both. Methods: Six databases—PubMed, Web of Science, CINAHL, MEDLINE, SPORTDiscus, and PsycINFO—were searched from January 1, 1990, to April 30, 2023. Studies were suitable for inclusion if the participants included people with lung cancer aged >18 years who had been exposed to a physical activity, exercise, or training intervention that was delivered via an electronic or web-based application with or without a comparator. Furthermore, the study had to report on the impact of the intervention on physical functioning and HRQoL. Studies that focused on telemedicine without a digital intervention were excluded. The Grading of Recommendations Assessment, Development, and Evaluation system was used to assess the quality of the included papers. Due to the heterogeneity of the studies, a narrative synthesis was undertaken. Results: This review is reported in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. A total of 794 papers were initially identified through our search, of which, after screening, 8 (1%) were confirmed suitable for inclusion in the review. As 2 (25%) of the 8 papers reported on different stages of the same study, we included only 7 studies in our analysis. The studies were undertaken between 2010 and 2018 across multiple countries and aimed to develop a technology and test its feasibility or acceptance. The 7 technologies identified included web-based applications, mobile apps, and gaming consoles. The studies demonstrated impact on walking distance, muscle strength, balance, dyspnea symptoms, and cancer-related fatigue. HRQoL scores also showed improvement. Conclusions: The findings indicate that eHealth technologies can positively impact physical functioning and well-being for people with lung cancer, but there are limited studies that demonstrate the impact of these digital interventions over longer periods. None of the studies reported on the implementation or adoption of a mobile health or eHealth intervention in routine clinical practice, highlighting the need for further research in this area. Trial Registration: PROSPERO CRD42023414094; https://tinyurl.com/39hhbwyx %M 39059003 %R 10.2196/53015 %U https://www.jmir.org/2024/1/e53015 %U https://doi.org/10.2196/53015 %U http://www.ncbi.nlm.nih.gov/pubmed/39059003 %0 Journal Article %@ 1929-0748 %I JMIR Publications %V 13 %N %P e51381 %T Erlotinib or Gefitinib for Treating Advanced Epidermal Growth Factor Receptor Mutation–Positive Lung Cancer in Aotearoa New Zealand: Protocol for a National Whole-of-Patient-Population Retrospective Cohort Study and Results of a Validation Substudy %A Aye,Phyu Sin %A Barnes,Joanne %A Laking,George %A Cameron,Laird %A Anderson,Malcolm %A Luey,Brendan %A Delany,Stephen %A Harris,Dean %A McLaren,Blair %A Brenman,Elliott %A Wong,Jayden %A Lawrenson,Ross %A Arendse,Michael %A Tin Tin,Sandar %A Elwood,Mark %A Hope,Philip %A McKeage,Mark James %+ Department of Pharmacology and Clinical Pharmacology, University of Auckland, 85 Park Road, Auckland, 1025, New Zealand, 64 21 859 588, m.mckeage@auckland.ac.nz %K epidermal growth factor receptor %K erlotinib %K gefitinib %K lung cancer %K retrospective cohort %K study protocol %K validation %D 2024 %7 2.7.2024 %9 Protocol %J JMIR Res Protoc %G English %X Background: Starting in 2010, the epidermal growth factor receptor (EGFR) kinase inhibitors erlotinib and gefitinib were introduced into routine use in Aotearoa New Zealand (NZ) for treating advanced lung cancer, but their impact in this setting is unknown. Objective: The study described in this protocol aims to understand the effectiveness and safety of these new personalized lung cancer treatments and the contributions made by concomitant medicines and other factors to adverse outcomes in the general NZ patient population. A substudy aimed to validate national electronic health databases as the data source and the methods for determining patient eligibility and identifying outcomes and variables. Methods: This study will include all NZ patients with advanced EGFR mutation–positive lung cancer who were first dispensed erlotinib or gefitinib before October 1, 2020, and followed until death or for at least 1 year. Routinely collected health administrative and clinical data will be collated from national electronic cancer registration, hospital discharge, mortality registration, and pharmaceutical dispensing databases by deterministic data linkage using National Health Index numbers. The primary effectiveness and safety outcomes will be time to treatment discontinuation and serious adverse events, respectively. The primary variable will be high-risk concomitant medicines use with erlotinib or gefitinib. For the validation substudy (n=100), data from clinical records were compared to those from national electronic health databases and analyzed by agreement analysis for categorical data and by paired 2-tailed t tests for numerical data. Results: In the validation substudy, national electronic health databases and clinical records agreed in determining patient eligibility and for identifying serious adverse events, high-risk concomitant medicines use, and other categorical data with overall agreement and κ statistic of >90% and >0.8000, respectively; for example, for the determination of patient eligibility, the comparison of proxy and standard eligibility criteria applied to national electronic health databases and clinical records, respectively, showed overall agreement and κ statistic of 96% and 0.8936, respectively. Dates for estimating time to treatment discontinuation and other numerical variables and outcomes showed small differences, mostly with nonsignificant P values and 95% CIs overlapping with zero difference; for example, for the dates of the first dispensing of erlotinib or gefitinib, national electronic health databases and clinical records differed on average by approximately 4 days with a nonsignificant P value of .33 and 95% CIs overlapping with zero difference. As of May 2024, the main study is ongoing. Conclusions: A protocol is presented for a national whole-of-patient-population retrospective cohort study designed to describe the safety and effectiveness of erlotinib and gefitinib during their first decade of routine use in NZ for treating EGFR mutation–positive lung cancer. The validation substudy demonstrated the feasibility and validity of using national electronic health databases and the methods for determining patient eligibility and identifying the study outcomes and variables proposed in the study protocol. Trial Registration: Australian New Zealand Clinical Trials Registry ACTRN12615000998549; https://www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=368928 International Registered Report Identifier (IRRID): DERR1-10.2196/51381 %M 38954434 %R 10.2196/51381 %U https://www.researchprotocols.org/2024/1/e51381 %U https://doi.org/10.2196/51381 %U http://www.ncbi.nlm.nih.gov/pubmed/38954434 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 26 %N %P e50224 %T Intensive Longitudinal Methods Among Adults With Breast or Lung Cancer: Scoping Review %A Geeraerts,Joran %A de Nooijer,Kim %A Pivodic,Lara %A De Ridder,Mark %A Van den Block,Lieve %+ End-of-Life Care Research Group, Vrije Universiteit Brussel, Laarbeeklaan 103, Brussels, 1090, Belgium, 32 2 477 47 56, joran.geeraerts@vub.be %K diary %K ecological momentary assessment %K neoplasms %K quality of life %K self-report %K telemedicine %K scoping review %K longitudinal methods %K breast cancer %K lung cancer %K patients with cancer %K cancer %K intensive monitoring %K advanced disease stages %K mobile phone %D 2024 %7 12.6.2024 %9 Review %J J Med Internet Res %G English %X Background: Intensive longitudinal methods offer a powerful tool for capturing daily experiences of individuals. However, its feasibility, effectiveness, and optimal methodological approaches for studying or monitoring experiences of oncology patients remain uncertain. Objective: This scoping review aims to describe to what extent intensive longitudinal methods with daily electronic assessments have been used among patients with breast or lung cancer and with which methodologies, associated outcomes, and influencing factors. Methods: We searched the electronic databases (PubMed, Embase, and PsycINFO) up to January 2024 and included studies reporting on the use of these methods among adults with breast or lung cancer. Data were extracted on population characteristics, intensive monitoring methodologies used, study findings, and factors influencing the implementation of these methods in research and clinical practice. Results: We identified 1311 articles and included 52 articles reporting on 41 studies. Study aims and intensive monitoring methodologies varied widely, but most studies focused on measuring physical and psychological symptom constructs, such as pain, anxiety, or depression. Compliance and attrition rates seemed acceptable for most studies, although complete methodological reporting was often lacking. Few studies specifically examined these methods among patients with advanced cancer. Factors influencing implementation were linked to both patient (eg, confidence with intensive monitoring system) and methodology (eg, option to use personal devices). Conclusions: Intensive longitudinal methods with daily electronic assessments hold promise to provide unique insights into the daily lives of patients with cancer. Intensive longitudinal methods may be feasible among people with breast or lung cancer. Our findings encourage further research to determine optimal conditions for intensive monitoring, specifically in more advanced disease stages. %M 38865186 %R 10.2196/50224 %U https://www.jmir.org/2024/1/e50224 %U https://doi.org/10.2196/50224 %U http://www.ncbi.nlm.nih.gov/pubmed/38865186 %0 Journal Article %@ 2369-1999 %I JMIR Publications %V 10 %N %P e53354 %T Real-World Survival Comparisons Between Radiotherapy and Surgery for Metachronous Second Primary Lung Cancer and Predictions of Lung Cancer–Specific Outcomes Using Machine Learning: Population-Based Study %A Zheng,Yue %A Zhao,Ailin %A Yang,Yuqi %A Wang,Laduona %A Hu,Yifei %A Luo,Ren %A Wu,Yijun %+ Division of Thoracic Tumor Multimodality Treatment, Cancer Center, West China Hospital, Sichuan University, Guoxue Lane 37, Chengdu, 610041, China, 86 17888841669, wuyj01029@wchscu.cn %K metachronous second primary lung cancer %K radiotherapy %K surgical resection %K propensity score matching analysis %K machine learning %D 2024 %7 12.6.2024 %9 Original Paper %J JMIR Cancer %G English %X Background: Metachronous second primary lung cancer (MSPLC) is not that rare but is seldom studied. Objective: We aim to compare real-world survival outcomes between different surgery strategies and radiotherapy for MSPLC. Methods: This retrospective study analyzed data collected from patients with MSPLC between 1988 and 2012 in the Surveillance, Epidemiology, and End Results (SEER) database. Propensity score matching (PSM) analyses and machine learning were performed to compare variables between patients with MSPLC. Survival curves were plotted using the Kaplan-Meier method and were compared using log-rank tests. Results: A total of 2451 MSPLC patients were categorized into the following treatment groups: 864 (35.3%) received radiotherapy, 759 (31%) underwent surgery, 89 (3.6%) had surgery plus radiotherapy, and 739 (30.2%) had neither treatment. After PSM, 470 pairs each for radiotherapy and surgery were generated. The surgery group had significantly better survival than the radiotherapy group (P<.001) and the untreated group (563 pairs; P<.001). Further analysis revealed that both wedge resection (85 pairs; P=.004) and lobectomy (71 pairs; P=.002) outperformed radiotherapy in overall survival for MSPLC patients. Machine learning models (extreme gradient boosting, random forest classifier, adaptive boosting) demonstrated high predictive performance based on area under the curve (AUC) values. Least absolute shrinkage and selection operator (LASSO) regression analysis identified 9 significant variables impacting cancer-specific survival, emphasizing surgery’s consistent influence across 1 year to 10 years. These variables encompassed age at diagnosis, sex, year of diagnosis, radiotherapy of initial primary lung cancer (IPLC), primary site, histology, surgery, chemotherapy, and radiotherapy of MPSLC. Competing risk analysis highlighted lower mortality for female MPSLC patients (hazard ratio [HR]=0.79, 95% CI 0.71-0.87) and recent IPLC diagnoses (HR=0.79, 95% CI 0.73-0.85), while radiotherapy for IPLC increased mortality (HR=1.31, 95% CI 1.16-1.50). Surgery alone had the lowest cancer-specific mortality (HR=0.83, 95% CI 0.81-0.85), with sublevel resection having the lowest mortality rate among the surgical approaches (HR=0.26, 95% CI 0.21-0.31). The findings provide valuable insights into the factors that influence cumulative cancer-specific mortality. Conclusions: Surgical resections such as wedge resection and lobectomy confer better survival than radiation therapy for MSPLC, but radiation can be a valid alternative for the treatment of MSPLC. %M 38865182 %R 10.2196/53354 %U https://cancer.jmir.org/2024/1/e53354 %U https://doi.org/10.2196/53354 %U http://www.ncbi.nlm.nih.gov/pubmed/38865182 %0 Journal Article %@ 2369-2960 %I JMIR Publications %V 10 %N %P e46737 %T Predicting Lung Cancer Survival to the Future: Population-Based Cancer Survival Modeling Study %A Meng,Fan-Tsui %A Jhuang,Jing-Rong %A Peng,Yan-Teng %A Chiang,Chun-Ju %A Yang,Ya-Wen %A Huang,Chi-Yen %A Huang,Kuo-Ping %A Lee,Wen-Chung %+ Institute of Health Data Analytics and Statistics, College of Public Health, National Taiwan University, Room 536, No 17, Xuzhou Road, Taipei, 100, Taiwan, 886 233668036, wenchung@ntu.edu.tw %K lung cancer %K survival %K survivorship-period-cohort model %K prediction %K prognosis %K early diagnosis %K lung cancer screening %K survival trend %K population-based %K population health %K public health %K surveillance %K low-dose computed tomography %D 2024 %7 31.5.2024 %9 Original Paper %J JMIR Public Health Surveill %G English %X 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. %M 38819904 %R 10.2196/46737 %U https://publichealth.jmir.org/2024/1/e46737 %U https://doi.org/10.2196/46737 %U http://www.ncbi.nlm.nih.gov/pubmed/38819904 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 26 %N %P e51059 %T Association of Remote Patient-Reported Outcomes and Step Counts With Hospitalization or Death Among Patients With Advanced Cancer Undergoing Chemotherapy: Secondary Analysis of the PROStep Randomized Trial %A Manz,Christopher R %A Schriver,Emily %A Ferrell,William J %A Williamson,Joelle %A Wakim,Jonathan %A Khan,Neda %A Kopinsky,Michael %A Balachandran,Mohan %A Chen,Jinbo %A Patel,Mitesh S %A Takvorian,Samuel U %A Shulman,Lawrence N %A Bekelman,Justin E %A Barnett,Ian J %A Parikh,Ravi B %+ Division of Health Policy, Perelman School of Medicine, University of Pennsylvania, 423 Guardian Drive, Room 1102, Philadelphia, PA, 19104, United States, 1 3524224285, Ravi.Parikh@pennmedicine.upenn.edu %K wearables %K accelerometers %K patient-reported outcomes %K step counts %K oncology %K accelerometer %K patient-generated health data %K cancer %K death %K chemotherapy %K symptoms %K gastrointestinal cancer %K lung cancer %K monitoring %K symptom burden %K risk %K hospitalization %K mobile phone %D 2024 %7 17.5.2024 %9 Original Paper %J J Med Internet Res %G English %X Background: Patients with advanced cancer undergoing chemotherapy experience significant symptoms and declines in functional status, which are associated with poor outcomes. Remote monitoring of patient-reported outcomes (PROs; symptoms) and step counts (functional status) may proactively identify patients at risk of hospitalization or death. Objective: The aim of this study is to evaluate the association of (1) longitudinal PROs with step counts and (2) PROs and step counts with hospitalization or death. Methods: The PROStep randomized trial enrolled 108 patients with advanced gastrointestinal or lung cancers undergoing cytotoxic chemotherapy at a large academic cancer center. Patients were randomized to weekly text-based monitoring of 8 PROs plus continuous step count monitoring via Fitbit (Google) versus usual care. This preplanned secondary analysis included 57 of 75 patients randomized to the intervention who had PRO and step count data. We analyzed the associations between PROs and mean daily step counts and the associations of PROs and step counts with the composite outcome of hospitalization or death using bootstrapped generalized linear models to account for longitudinal data. Results: Among 57 patients, the mean age was 57 (SD 10.9) years, 24 (42%) were female, 43 (75%) had advanced gastrointestinal cancer, 14 (25%) had advanced lung cancer, and 25 (44%) were hospitalized or died during follow-up. A 1-point weekly increase (on a 32-point scale) in aggregate PRO score was associated with 247 fewer mean daily steps (95% CI –277 to –213; P<.001). PROs most strongly associated with step count decline were patient-reported activity (daily step change –892), nausea score (–677), and constipation score (524). A 1-point weekly increase in aggregate PRO score was associated with 20% greater odds of hospitalization or death (adjusted odds ratio [aOR] 1.2, 95% CI 1.1-1.4; P=.01). PROs most strongly associated with hospitalization or death were pain (aOR 3.2, 95% CI 1.6-6.5; P<.001), decreased activity (aOR 3.2, 95% CI 1.4-7.1; P=.01), dyspnea (aOR 2.6, 95% CI 1.2-5.5; P=.02), and sadness (aOR 2.1, 95% CI 1.1-4.3; P=.03). A decrease in 1000 steps was associated with 16% greater odds of hospitalization or death (aOR 1.2, 95% CI 1.0-1.3; P=.03). Compared with baseline, mean daily step count decreased 7% (n=274 steps), 9% (n=351 steps), and 16% (n=667 steps) in the 3, 2, and 1 weeks before hospitalization or death, respectively. Conclusions: In this secondary analysis of a randomized trial among patients with advanced cancer, higher symptom burden and decreased step count were independently associated with and predictably worsened close to hospitalization or death. Future interventions should leverage longitudinal PRO and step count data to target interventions toward patients at risk for poor outcomes. Trial Registration: ClinicalTrials.gov NCT04616768; https://clinicaltrials.gov/study/NCT04616768 International Registered Report Identifier (IRRID): RR2-10.1136/bmjopen-2021-054675 %M 38758583 %R 10.2196/51059 %U https://www.jmir.org/2024/1/e51059 %U https://doi.org/10.2196/51059 %U http://www.ncbi.nlm.nih.gov/pubmed/38758583 %0 Journal Article %@ 2369-1999 %I JMIR Publications %V 9 %N %P e44612 %T Advanced Messaging Intervention for Medication Adherence and Clinical Outcomes Among Patients With Cancer: Randomized Controlled Trial %A Ni,Chen-Xu %A Lu,Wen-Jie %A Ni,Min %A Huang,Fang %A Li,Dong-Jie %A Shen,Fu-Ming %+ Department of Pharmacy, Shanghai Tenth People’s Hospital, Tongji University School of Medicine, 301 Middle Yanchang Road, Shanghai, 200072, China, 86 66302570, fumingshen@tongji.edu.cn %K 5G messaging %K fifth-generation %K medication adherence %K patients with cancer %K clinical pharmacists %K randomized controlled trial %D 2023 %7 31.8.2023 %9 Original Paper %J JMIR Cancer %G English %X Background: Medication adherence is crucial for improving clinical outcomes in the treatment of patients with cancer. The lack of adherence and adverse drug reactions can reduce the effectiveness of cancer therapy including the quality of life. The commonly used intervention methods for medication adherence continue to evolve, and the age of fifth-generation (5G) messaging has arrived. Objective: In this study, we conducted a prospective, pilot randomized controlled trial to evaluate the effect of 5G messaging on medication adherence and clinical outcomes among patients with cancer in China. Methods: The research population was patients with nonsmall cell lung cancer undergoing pemetrexed chemotherapy who require regular folic acid (FA) and vitamin B12 supplements. The intervention and control groups were assigned to 5G messaging and second-generation (2G) messaging, respectively. The patients’ medication adherence and quality of life were assessed at baseline and 1-month and 3-month time points. Moreover, the chemotherapy-related hematologic or nonhematologic toxicities, as well as the serum levels of FA and vitamin B12, were measured. Results: Of the 567 patients assessed for eligibility between January and May 2021, a total of 154 (27.2%) patients were included. Overall, 80 were randomized to the control group and 74 to the intervention group. The odds of adherence in the 5G messaging intervention group were significantly higher than the control group at the 1-month (62/69, 90% vs 56/74, 76%; adjusted odds ratio 2.67, 95% CI 1.02-7.71) and 3-month (50/60, 83% vs 48/64, 75%; adjusted odds ratio 2.36, 95% CI 1.00-5.23) time points. Correspondingly, the FA and vitamin B12 serum levels of patients in the 5G messaging group were higher than those of the control group. Regarding hematologic toxicities, only the incidence of leukopenia in the intervention group was lower than that in the control group (25/80, 31% in the control group vs 12/74, 16% in the intervention group; P=.04). There were no differences in nonhematologic toxicities and quality of life between the 2 groups. Conclusions: In summary, we conclude that compared with conventional 2G text-based messaging, a 5G messaging intervention can better improve medication adherence and clinical outcome among patients with cancer. Trial Registration: Chinese Clinical Trial Registry ChiCTR2200058188; https://www.chictr.org.cn/showproj.html?proj=164489 %M 37651170 %R 10.2196/44612 %U https://cancer.jmir.org/2023/1/e44612 %U https://doi.org/10.2196/44612 %U http://www.ncbi.nlm.nih.gov/pubmed/37651170 %0 Journal Article %@ 2369-1999 %I JMIR Publications %V 9 %N %P e45707 %T Using Health-Related Social Media to Understand the Experiences of Adults With Lung Cancer in the Era of Immuno-Oncology and Targeted Therapies: Observational Study %A Booth,Alison %A Manson,Stephanie %A Halhol,Sonia %A Merinopoulou,Evie %A Raluy-Callado,Mireia %A Hareendran,Asha %A Knoll,Stefanie %+ Data Analytics, Evidera, The Ark, 201 Talgarth Rd, London, W6 8BJ,, United Kingdom, 44 208 576 5064, sonia.halhol@evidera.com %K non-small cell lung cancer %K data science %K machine learning %K natural language processing %K social media data %K patient experience %K patient preference %K immunotherapy %K targeted therapies %K lung cancer %K social media %D 2023 %7 12.7.2023 %9 Original Paper %J JMIR Cancer %G English %X Background: The treatment of non–small cell lung cancer (NSCLC) has evolved dramatically with the approval of immuno-oncology (IO) and targeted therapies (TTs). Insights on the patient experience with these therapies and their impacts are lacking. Health-related social media has been increasingly used by patients to share their disease and treatment experiences, thus representing a valuable source of real-world data to understand the patient’s voice and uncover potential unmet needs. Objective: This study aimed to describe the experiences of patients with NSCLC as reported in discussions posted on lung cancer–specific social media with respect to their disease symptoms and associated impacts. Methods: Publicly available posts (2010-2019) were extracted from selected lung cancer– or NSCLC-specific websites. Social media users (patients and caregivers posting on these websites) were stratified by metastatic- and adjuvant-eligible subgroups and treatment received using natural language processing (NLP) and machine learning methods. Automated identification of symptoms was conducted using NLP. Qualitative data analysis (QDA) was conducted on random samples of posts mentioning pain-related, fatigue-related, respiratory-related, or infection-related symptoms to capture the patient experience with these and associated impacts. Results: Overall, 1724 users (50,390 posts) and 574 users (4531 posts) were included in the metastatic group and adjuvant group, respectively. Among users in the metastatic group, pain, discomfort, and fatigue were the most commonly mentioned symptoms (49.7% and 39.6%, respectively), and in the QDA (258 posts from 134 users), the most frequent impacts related to physical impairments, sleep, and eating habits. Among users in the adjuvant group, pain, discomfort, and respiratory symptoms were the most commonly mentioned (44.8% and 23.9%, respectively), and impacts identified in the QDA (154 posts from 92 users) were mostly related to physical functioning. Conclusions: Findings from this exploratory observational analysis of social media among patients and caregivers informed the lived experience of NSCLC in the era of novel therapies, shedding light on most reported symptoms and their impacts. These findings can be used to inform future research on NSCLC treatment development and patient management. %M 37436789 %R 10.2196/45707 %U https://cancer.jmir.org/2023/1/e45707 %U https://doi.org/10.2196/45707 %U http://www.ncbi.nlm.nih.gov/pubmed/37436789 %0 Journal Article %@ 1929-0748 %I JMIR Publications %V 12 %N %P e46657 %T Using User-Centered Design to Facilitate Adherence to Annual Lung Cancer Screening: Protocol for a Mixed Methods Study for Intervention Development %A Hirsch,Erin A %A Studts,Jamie L %+ Division of Medical Oncology, University of Colorado School of Medicine, University of Colorado Anschutz Medical Campus, 13001 E. 17th Place, Mail Stop B189, Aurora, CO, 80045, United States, 1 303 724 1658, Erin.Hirsch@cuanschutz.edu %K health information processing %K intervention design %K lung cancer %K lung cancer screening %K LCS %K mixed methods %K photovoice %K user-centered design %D 2023 %7 14.4.2023 %9 Protocol %J JMIR Res Protoc %G English %X Background: Lung cancer is the leading cause of cancer-related death in the United States, with the majority of lung cancer occurrence diagnosed after the disease has already metastasized. Lung cancer screening (LCS) with low-dose computed tomography can diagnose early-stage disease, especially when eligible individuals participate in screening on a yearly basis. Unfortunately, annual adherence has emerged as a challenge for academic and community screening programs, endangering the individual and population health benefits of LCS. Reminder messages have effectively increased adherence rates in breast, colorectal, and cervical cancer screenings but have not been tested with LCS participants who experience unique barriers to screening associated with the stigma of smoking and social determinants of health. Objective: This research aims to use a theory-informed, multiphase, and mixed methods approach with LCS experts and participants to develop a set of clear and engaging reminder messages to support LCS annual adherence. Methods: In aim 1, survey data informed by the Cognitive-Social Health Information Processing model will be collected to assess how LCS participants process health information aimed at health protective behavior to develop content for reminder messages and pinpoint options for message targeting and tailoring. Aim 2 focuses on identifying themes for message imagery through a modified photovoice activity that asks participants to identify 3 images that represent LCS and then participate in an interview about the selection, likes, and dislikes of each photo. A pool of candidate messages for multiple delivery platforms will be developed in aim 3, using results from aim 1 for message content and aim 2 for imagery selection. The refinement of message content and imagery combinations will be completed through iterative feedback from LCS experts and participants. Results: Data collection began in July 2022 and will be completed by May 2023. The final reminder message candidates are expected to be completed by June 2023. Conclusions: This project proposes a novel approach to facilitate adherence to annual LCS through the development of reminder messages that embrace content and imagery representative of the target population directly in the design process. Developing effective strategies to increase LCS adherence is instrumental in achieving optimal LCS outcomes at individual and population health levels. International Registered Report Identifier (IRRID): DERR1-10.2196/46657 %M 37058339 %R 10.2196/46657 %U https://www.researchprotocols.org/2023/1/e46657 %U https://doi.org/10.2196/46657 %U http://www.ncbi.nlm.nih.gov/pubmed/37058339 %0 Journal Article %@ 2369-2960 %I JMIR Publications %V 9 %N %P e43651 %T Projections of Lung Cancer Incidence by 2035 in 40 Countries Worldwide: Population-Based Study %A Luo,Ganfeng %A Zhang,Yanting %A Etxeberria,Jaione %A Arnold,Melina %A Cai,Xiuyu %A Hao,Yuantao %A Zou,Huachun %+ School of Public Health (Shenzhen), Sun Yat-sen University, No. 66, Gongchang Road, Guangming District, Shenzhen, 518107, China, 86 20 87335651, zouhuachun@mail.sysu.edu.cn %K lung cancer %K incidence %K projections %K temporal trends %K worldwide %D 2023 %7 17.2.2023 %9 Original Paper %J JMIR Public Health Surveill %G English %X Background: The global burden of lung cancer (LC) is increasing. Quantitative projections of the future LC burden in different world regions could help optimize the allocation of resources and provide a benchmark for evaluating LC prevention and control interventions. Objective: We aimed to predict the future incidence of LC in 40 countries by 2035, with an emphasis on country- and sex-specific disparities. Methods: Data on LC incidence from 1978 to 2012 were extracted from 126 cancer registries of 40 countries in Cancer Incidence in Five Continents Volumes V-XI and used for the projection. Age-standardized incidence rates (ASRs) per 100,000 person-years and the number of incident cases were predicted through 2035, using the NORDPRED age-period-cohort model. Results: Global ASRs of the 40 studied countries were predicted to decrease by 23% (8.2/35.8) among males, from 35.8 per 100,000 person-years in 2010 to 27.6 in 2035, and increase by 2% (0.3/16.8) among females, from 16.8 in 2010 to 17.1 in 2035. The ASRs of LC among females are projected to continue increasing dramatically in most countries by 2035, with peaks after the 2020s in most European, Eastern Asian, and Oceanian countries, whereas the ASRs among males will continue to decline in almost all countries. The ASRs among females are predicted to almost reach those among males in Ireland, Norway, the United Kingdom, the Netherlands, Canada, the United States, and New Zealand in 2025 and in Slovenia in 2035 and even surpass those among males in Denmark in 2020 and in Brazil and Colombia in 2025. In 2035, the highest ASRs are projected to occur among males in Belarus (49.3) and among females in Denmark (36.8). The number of new cases in 40 countries is predicted to increase by 65.32% (858,000/1,314,000), from 1.31 million in 2010 to 2.17 million in 2035. China will have the largest number of new cases. Conclusions: LC incidence is expected to continue to increase through 2035 in most countries, making LC a major public health challenge worldwide. The ongoing transition in the epidemiology of LC highlights the need for resource redistribution and improved LC control measures to reduce future LC burden worldwide. %M 36800235 %R 10.2196/43651 %U https://publichealth.jmir.org/2023/1/e43651 %U https://doi.org/10.2196/43651 %U http://www.ncbi.nlm.nih.gov/pubmed/36800235 %0 Journal Article %@ 2561-326X %I JMIR Publications %V 7 %N %P e37190 %T Patient Perspectives on Value Dimensions of Lung Cancer Care: Cross-sectional Web-Based Survey %A Varriale,Pasquale %A Müller,Borna %A Katz,Grégory %A Dallas,Lorraine %A Aguaron,Alfonso %A Azoulai,Marion %A Girard,Nicolas %+ Global Access, F Hoffmann-La Roche Ltd, Grenzacherstrasse 124, Basel, 4070, Switzerland, 41 79585 2955, borna.mueller@roche.com %K lung %K cancer %K health quality of life %K patient reported outcome %K PROM %K economic burden %K cost %K economic %K burden %K perspective %K survey %K QoL %K quality of life %K questionnaire %K caregiver %K caregiving %K physical well-being %K end of life %K palliative %K physical function %K independence %K distress %D 2023 %7 26.1.2023 %9 Original Paper %J JMIR Form Res %G English %X Background: While the lung cancer (LC) treatment landscape has rapidly evolved in recent years, easing symptom burden and treatment side effects remain central considerations in disease control. Objective: The aim of this study was to assess the relative importance of dimensions of LC care to patients, and to explore the disease burden, including socioeconomic aspects not commonly covered in patient-reported outcomes instruments. Methods: A questionnaire was sent to patients with LC and their caregivers to rate the value of a diverse set of quality of life dimensions in care, to evaluate communication between health care professionals (HCPs) and patients, and to explore the economic impact on respondents. The survey included questions on the dimensions of care covered by patient-reported outcomes instruments for quality-of-life evaluation (Functional Assessment of Cancer Therapy–Lung scale, EQ-5D, the European Organization for Research and Treatment of Cancer’s Core Quality of Life questionnaire, and the European Organization for Research and Treatment of Cancer’s Core Quality of Life in lung cancer 13-item questionnaire), as well as the International Consortium for Health Outcomes Measurement (ICHOM) standard set of patient-centered outcomes for LC. The survey respondents were participants on Carenity’s patient community platform, living either in France, the United Kingdom, Germany, Italy, or Spain. Results: The survey included 150 respondents (115 patients and 35 caregivers). “Physical well-being” and “end-of-life care” (median scores of 9.6, IQR 7.7-10, and 9.7, IQR 8.0-10, on a 10-point scale) were rated highest among the different value dimensions assessed. “Physical well-being and functioning” was the dimension most frequently discussed with health care professionals (82/150, 55%), while only (17/100, 17%) reported discussing “end-of-life care.” After diagnosis, 43% (49/112) of patients younger than 65 years stopped working. Among respondents who indicated their monthly household income before and after diagnosis, 55% (38/69) reported a loss of income. Conclusions: Our results showed the relevance of a broad range of aspects of care for the quality of life of patients with LC. End-of-life care was the dimension of care rated highest by patients with LC, irrespective of stage at diagnosis; however, this aspect is least frequently discussed with HCPs. The results also highlight the considerable socioeconomic impact of the disease, despite insurance coverage of direct costs. %M 36416499 %R 10.2196/37190 %U https://formative.jmir.org/2023/1/e37190 %U https://doi.org/10.2196/37190 %U http://www.ncbi.nlm.nih.gov/pubmed/36416499 %0 Journal Article %@ 2369-2960 %I JMIR Publications %V 9 %N %P e41640 %T Lung Cancer Risk Prediction Nomogram in Nonsmoking Chinese Women: Retrospective Cross-sectional Cohort Study %A Guo,Lanwei %A Meng,Qingcheng %A Zheng,Liyang %A Chen,Qiong %A Liu,Yin %A Xu,Huifang %A Kang,Ruihua %A Zhang,Luyao %A Liu,Shuzheng %A Sun,Xibin %A Zhang,Shaokai %+ Department of Cancer Epidemiology and Prevention, Henan Engineering Research Center of Cancer Prevention and Control, Henan International Joint Laboratory of Cancer Prevention, The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer Hospital, No.127 Dongming Road, Zhengzhou, 450008, China, 86 37165587361, shaokaizhang@126.com %K lung cancer %K risk model %K forecasting %K validation %K female %K nonsmokers %D 2023 %7 6.1.2023 %9 Original Paper %J JMIR Public Health Surveill %G English %X 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. %M 36607729 %R 10.2196/41640 %U https://publichealth.jmir.org/2023/1/e41640 %U https://doi.org/10.2196/41640 %U http://www.ncbi.nlm.nih.gov/pubmed/36607729 %0 Journal Article %@ 2369-2960 %I JMIR Publications %V 8 %N 7 %P e36425 %T Cost-Effectiveness of Lung Cancer Screening Using Low-Dose Computed Tomography Based on Start Age and Interval in China: Modeling Study %A Zhao,Zixuan %A Du,Lingbin %A Li,Yuanyuan %A Wang,Le %A Wang,Youqing %A Yang,Yi %A Dong,Hengjin %+ Department of Science and Education of the Fourth Affiliated Hospital, Center for Health Policy Studies, School of Public Health, Zhejiang University School of Medicine, No. 866 Yuhangtang Road, Xihu District, Hangzhou, 310058, China, 86 13221076129, donghj@zju.edu.cn %K cost-effectiveness analysis %K low-dose computed tomography %K screening %K lung cancer %K China %D 2022 %7 6.7.2022 %9 Original Paper %J JMIR Public Health Surveill %G English %X Background: Lung cancer is the most commonly diagnosed cancer and the leading cause of cancer-related death in China. The effectiveness of screening for lung cancer has been reported to reduce lung cancer–specific and overall mortality, although the cost-effectiveness, optimal start age, and screening interval remain unclear. Objective: This study aimed to assess the cost-effectiveness of lung cancer screening among heavy smokers in China by incorporating start age and screening interval. Methods: A Markov state-transition model was used to assess the cost-effectiveness of a lung cancer screening program in China. The evaluated screening strategies were based on a screening start age of 50-74 years and a screening interval of once or annually. Transition probabilities were obtained from the literature and validated, while cost parameters were derived from databases of local medical insurance bureaus. A societal perspective was adopted. The outputs of the model included costs, quality-adjusted life years (QALYs), and lung cancer–specific mortality, with future costs and outcomes discounted by 5%. A currency exchange rate of 1 CNY=0.1557 USD is applicable. The incremental cost-effectiveness ratio (ICER) was calculated for different screening strategies relative to nonscreening. Results: The proposed model suggested that screening led to a gain of 0.001-0.042 QALYs per person as compared with the findings in the nonscreening cohort. Meanwhile, one-time and annual screenings were associated with reductions in lung cancer–related mortality of 0.004%-1.171% and 6.189%-15.819%, respectively. The ICER ranged from 119,974.08 to 614,167.75 CNY per QALY gained relative to nonscreening. Using the World Health Organization threshold of 212,676 CNY per QALY gained, annual screening from a start age of 55 years and one-time screening from the age of 65 years can be considered as cost-effective in China. Deterministic and probabilistic sensitivity analyses were conducted. Conclusions: This economic evaluation revealed that a population-based lung cancer screening program in China for heavy smokers using low-dose computed tomography was cost-effective for annual screening of smokers aged 55-74 years and one-time screening of those aged 65-74 years. Moreover, annual lung cancer screening should be promoted in China to realize the benefits of a guideline-recommended screening program. %M 35793127 %R 10.2196/36425 %U https://publichealth.jmir.org/2022/7/e36425 %U https://doi.org/10.2196/36425 %U http://www.ncbi.nlm.nih.gov/pubmed/35793127 %0 Journal Article %@ 2369-2960 %I JMIR Publications %V 8 %N 4 %P e33633 %T Long-term Changes in the Premature Death Rate in Lung Cancer in a Developed Region of China: Population-based Study %A Ye,Wenjing %A Lu,Weiwei %A Li,Xiaopan %A Chen,Yichen %A Wang,Lin %A Zeng,Guangwang %A Xu,Cheng %A Ji,Chen %A Cai,Yuyang %A Yang,Ling %A Luo,Zheng %+ Shanghai University of Medicine & Health Sciences Affiliated Zhoupu Hospital, Pudong New Area, No.1500 Zhouyuan Rd, Shanghai, 201318, China, 86 18008497518, zhengluo86@foxmail.com %K lung cancer %K mortality %K years of life lost %K trend analysis %K decomposition method %D 2022 %7 20.4.2022 %9 Original Paper %J JMIR Public Health Surveill %G English %X Background: Lung cancer is a leading cause of death worldwide, and its incidence shows an upward trend. A study of the long-term changes in the premature death rate in lung cancer in a developed region of China has great exploratory significance to further clarify the effectiveness of intervention measures. Objective: This study examined long-term changes in premature lung cancer death rates in order to understand the changes in mortality and to design future prevention plans in Pudong New Area (PNA), Shanghai, China. Methods: Cancer death data were collected from the Mortality Registration System of PNA. We analyzed the crude mortality rate (CMR), age-standardized mortality rate by Segi’s world standard population (ASMRW), and years of life lost (YLL) of patients with lung cancer from 1973 to 2019. Temporal trends in the CMR, ASMRW, and YLL rate were calculated by joinpoint regression expressed as an average annual percentage change (AAPC) with the corresponding 95% CI. Results: All registered permanent residents in PNA (80,543,137 person-years) from 1973 to 2019 were enrolled in this study. There were 42,229 deaths from lung cancer. The CMR and ASMRW were 52.43/105 and 27.79/105 person-years, respectively. The YLL due to premature death from lung cancer was 481779.14 years, and the YLL rate was 598.16/105 person-years. The CMR and YLL rate showed significantly increasing trends in men, women, and the total population (P<.001). The CMR of the total population increased by 2.86% (95% CI 2.66-3.07, P<.001) per year during the study period. The YLL rate increased with an AAPC of 2.21% (95% CI 1.92-2.51, P<.001) per year. The contribution rates of increased CMR values caused by demographic factors were more evident than those caused by nondemographic factors. Conclusions: Lung cancer deaths showed an increasing trend in PNA from 1973 to 2019. Demographic factors, such as the aging population, contributed more to an increased CMR. Our research can help us understand the changes in lung cancer mortality and can be used for similar cities in designing future prevention plans. %M 35442209 %R 10.2196/33633 %U https://publichealth.jmir.org/2022/4/e33633 %U https://doi.org/10.2196/33633 %U http://www.ncbi.nlm.nih.gov/pubmed/35442209 %0 Journal Article %@ 2292-9495 %I JMIR Publications %V 9 %N 2 %P e32399 %T Implementation of a Web-Based Tool for Shared Decision-making in Lung Cancer Screening: Mixed Methods Quality Improvement Evaluation %A Lowery,Julie %A Fagerlin,Angela %A Larkin,Angela R %A Wiener,Renda S %A Skurla,Sarah E %A Caverly,Tanner J %+ Center for Clinical Management Research, Ann Arbor VA Healthcare System, 2215 Fuller Road, Ann Arbor, MI, 48105, United States, 1 303 587 1038, tcaverly@med.umich.edu %K shared decision-making %K lung cancer %K screening %K clinical decision support %K academic detailing %K quality improvement %K implementation %D 2022 %7 1.4.2022 %9 Original Paper %J JMIR Hum Factors %G English %X 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 %M 35363144 %R 10.2196/32399 %U https://humanfactors.jmir.org/2022/2/e32399 %U https://doi.org/10.2196/32399 %U http://www.ncbi.nlm.nih.gov/pubmed/35363144 %0 Journal Article %@ 1929-073X %I JMIR Publications %V 11 %N 1 %P e24592 %T Pulmonary Screening Practices of Otolaryngology–Head and Neck Surgeons Across Saudi Arabia in the Posttreatment Surveillance of Squamous Cell Carcinoma: Cross-sectional Survey Study %A Alnefaie,Majed %A Alamri,Abdullah %A Saeedi,Asalh %A Althobaiti,Awwadh %A Alosaimi,Shahad %A Alqurashi,Yousuf %A Marzouki,Hani %A Merdad,Mazin %+ King Fahad Armed Forces Hospital, Medical Services of The Armed Forces, Al Kurnaysh Rd, Al Andalus, Jeddah, 23311, Saudi Arabia, 966 500900450, Majed.n.md@gmail.com %K squamous cell carcinoma of head and neck %K lung neoplasms %K radiography %K otolaryngology %K surgeons %K survey %D 2022 %7 18.3.2022 %9 Original Paper %J Interact J Med Res %G English %X Background: With respect to patients with head and neck squamous cell carcinoma (HNSCC), posttreatment surveillance for distant disease has mostly focused on the lungs, as HNSCC distant metastasis occurs in this organ in 90% of HNSCC cases. Additionally, the incidence rate of primary tumors in the lungs is high due to the field cancerization of the entire upper aerodigestive tract. Objective: Our cross-sectional survey study aims to evaluate the current beliefs and pulmonary screening practices of otolaryngology–head and neck surgeons across Saudi Arabia with respect to the posttreatment surveillance of HNSCC. Methods: This nationwide cross-sectional survey was conducted among head and neck surgeon members of the Saudi Society of Otolaryngology from June 1 to June 30, 2020. A predesigned questionnaire was used for data collection, and a descriptive analysis was carried out. Results: This study included 22 participants and had a 78% (22/28) response rate. This study found that the majority of participants (9/22, 41%) used lung radiography for routine lung screening during posttreatment follow-ups, whereas 32% (7/22) used low-dose computed tomography (CT; 7/22, 32%). With regard to the number of years for which participants perform lung screening during follow-ups, the majority of participants (17/22, 77%) reported 5 years, and only 9% (2/22) have performed lifelong lung screening. With regard to the frequency of lung screening, 77% (17/22) of participants conduct screening annually, 18% (4/22) conduct screening half-yearly, and 5% (1/22) conduct screening biennially. With regard to beliefs about the effectiveness of screening procedures in reducing lung cancer mortality rates during follow-ups, 36% (8/22) of participants believed them to be very effective or somewhat effective, 18% (4/22) did not know, and only 9% (2/22) believed that they were not effective. Conclusions: The participants mainly used lung radiography (9/22, 41%), low-dose CT (7/22, 32%), or positron emission tomography/CT (6/22, 27%) as a routine lung screening method during the posttreatment follow-up of patients with head and neck cancer for 5 years (17/22, 77%) or 10 years (3/22, 14%), and only a small percentage of participants have performed lifelong lung screening (2/22, 9%). Lung screening was mostly conducted annually or half-yearly. Such screening was believed to be very effective or somewhat effective. %M 35302511 %R 10.2196/24592 %U https://www.i-jmr.org/2022/1/e24592 %U https://doi.org/10.2196/24592 %U http://www.ncbi.nlm.nih.gov/pubmed/35302511 %0 Journal Article %@ 1929-0748 %I JMIR Publications %V 11 %N 3 %P e31350 %T Economic Burden of Chronic Obstructive Pulmonary Disease and Lung Cancer Between 2000 and 2015 in Saskatchewan: Study Protocol %A Penz,Erika Dianne %A Fenton,Benjamin John %A Hu,Nianping %A Marciniuk,Darcy %+ Division of Respirology, Critical Care and Sleep Medicine, University of Saskatchewan, Room 537 Ellis Hall, 103 Hospital Drive, Saskatoon, SK, S7N OW8, Canada, 1 306 844 1140, erika.penz@usask.ca %K lung cancer %K COPD %K chronic obstructive pulmonary disease %K productivity loss %K years of life lost %K premature years of life lost %K working years lost %K economic burden of disease %K lung disease %K health economics %K Stats Canada %K epidemiology %K pulmonary disease %K pulmonary health %K disease burden %D 2022 %7 4.3.2022 %9 Protocol %J JMIR Res Protoc %G English %X Background: Chronic obstructive pulmonary disease (COPD) and lung cancer are both detrimental diseases that present great burdens on society. Years of life lost (YLL), premature years of life lost (PYLL), working years lost (WYL), and productivity loss are all effective measures in identifying economic burden of disease. Objective: We propose a population-based study to analyze comprehensive provincial cohorts of Saskatchewan residents with COPD, lung cancer, and combined COPD and lung cancer in order to identify the burden these diseases present. Methods: Saskatchewan residents over the age of 35 years who had COPD, lung cancer, or both, between January 1, 2000, and December 31, 2015, will be identified and used in this study. Data for analysis including age, gender, and date of death, alongside Statistics Canada income estimates, will be used to estimate productivity loss and WYL. Statistics Canada life tables will be used to calculate YLL and PYLL by subtracting the patients’ ages at death by their life expectancies, adjusted using sex and age at death. We will link the Saskatchewan cancer registry with Saskatchewan health administrative databases to create three cohorts: (1) COPD; (2) lung cancer; and (3) COPD and lung cancer. Individuals with lung cancer will be identified using ICDO-T (International Classification of Diseases for Oncology-Topography) codes, and those with COPD will be defined and identified as individuals who had at least 1 visit to a physician with a diagnosis of COPD or 1 hospital separation with a diagnosis of COPD. Those without a valid health care coverage for a consecutive 12 months prior to the first diagnostic code will be excluded from the study. Those with a combined diagnosis of COPD and lung cancer will be identified as individuals who were diagnosed with COPD in the 12 months following their lung cancer diagnosis or anytime preceding their lung cancer diagnosis. Results: As of April 2021, we have had access to all relevant data for this study, have received funding (January 2020), and have begun the preliminary analysis of our data set. Conclusions: It is well documented that COPD and lung cancer are both destructive diseases in terms of YLL, PYLL, WYL, and productivity loss; however, no studies have been conducted to analyze a cohort with combined COPD and lung cancer. Understanding the economic burden associated with each of our 3 cohorts is necessary in understanding and thus reducing the societal impact of COPD and lung cancer. International Registered Report Identifier (IRRID): RR1-10.2196/31350 %M 35254280 %R 10.2196/31350 %U https://www.researchprotocols.org/2022/3/e31350 %U https://doi.org/10.2196/31350 %U http://www.ncbi.nlm.nih.gov/pubmed/35254280 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 23 %N 12 %P e28042 %T Examining Twitter Discourse on Electronic Cigarette and Tobacco Consumption During National Cancer Prevention Month in 2018: Topic Modeling and Geospatial Analysis %A Lu,Jiahui %A Lee,Edmund W J %+ School of New Media and Communication, Tianjin University, No 92 Weijin Road, Tianjin, 300072, China, 86 18222418810, lujiahui@tju.edu.cn %K electronic cigarette %K smoking %K lung cancer %K Twitter %K national cancer prevention month %K policy %K topic modeling %K cessation %K e-cigarette %K cancer %K social media %K eHealth %K cancer prevention %K tweets %K public health %D 2021 %7 29.12.2021 %9 Original Paper %J J Med Internet Res %G English %X Background: Examining public perception of tobacco products is critical for effective tobacco policy making and public education outreach. While the link between traditional tobacco products and lung cancer is well established, it is not known how the public perceives the association between electronic cigarettes (e-cigarettes) and lung cancer. In addition, it is unclear how members of the public interact with official messages during cancer campaigns on tobacco consumption and lung cancer. Objective: In this study, we aimed to analyze e-cigarette and smoking tweets in the context of lung cancer during National Cancer Prevention Month in 2018 and examine how e-cigarette and traditional tobacco product discussions relate to implementation of tobacco control policies across different states in the United States. Methods: We mined tweets that contained the term “lung cancer” on Twitter from February to March 2018. The data set contained 13,946 publicly available tweets that occurred during National Cancer Prevention Month (February 2018), and 10,153 tweets that occurred during March 2018. E-cigarette–related and smoking-related tweets were retrieved, using topic modeling and geospatial analysis. Results: Debates on harmfulness (454/915, 49.7%), personal experiences (316/915, 34.5%), and e-cigarette risks (145/915, 15.8%) were the major themes of e-cigarette tweets related to lung cancer. Policy discussions (2251/3870, 58.1%), smoking risks (843/3870, 21.8%), and personal experiences (776/3870, 20.1%) were the major themes of smoking tweets related to lung cancer. Geospatial analysis showed that discussion on e-cigarette risks was positively correlated with the number of state-level smoke-free policies enacted for e-cigarettes. In particular, the number of indoor and on campus smoke-free policies was related to the number of tweets on e-cigarette risks (smoke-free indoor, r49=0.33, P=.02; smoke-free campus, r49=0.32, P=.02). The total number of e-cigarette policies was also positively related to the number of tweets on e-cigarette risks (r49=0.32, P=.02). In contrast, the number of smoking policies was not significantly associated with any of the smoking themes in the lung cancer discourse (P>.13). Conclusions: Though people recognized the importance of traditional tobacco control policies in reducing lung cancer incidences, their views on e-cigarette risks were divided, and discussions on the importance of e-cigarette policy control were missing from public discourse. Findings suggest the need for health organizations to continuously engage the public in discussions on the potential health risks of e-cigarettes and raise awareness of the insidious lobbying efforts from the tobacco industry. %M 34964716 %R 10.2196/28042 %U https://www.jmir.org/2021/12/e28042 %U https://doi.org/10.2196/28042 %U http://www.ncbi.nlm.nih.gov/pubmed/34964716 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 23 %N 11 %P e28915 %T Data Quality of Longitudinally Collected Patient-Reported Outcomes After Thoracic Surgery: Comparison of Paper- and Web-Based Assessments %A Yu,Hongfan %A Yu,Qingsong %A Nie,Yuxian %A Xu,Wei %A Pu,Yang %A Dai,Wei %A Wei,Xing %A Shi,Qiuling %+ School of Public Health and Management, Chongqing Medical University, No 1, Medical College Road, Yuzhong District, Chonqqing, 400016, China, 86 18290585397, qshi@cqmu.edu.cn %K patient-reported outcome (PRO) %K data quality %K MDASI-LC %K postoperative care %K symptoms %D 2021 %7 9.11.2021 %9 Original Paper %J J Med Internet Res %G English %X Background: High-frequency patient-reported outcome (PRO) assessments are used to measure patients' symptoms after surgery for surgical research; however, the quality of those longitudinal PRO data has seldom been discussed. Objective: The aim of this study was to determine data quality-influencing factors and to profile error trajectories of data longitudinally collected via paper-and-pencil (P&P) or web-based assessment (electronic PRO [ePRO]) after thoracic surgery. Methods: We extracted longitudinal PRO data with 678 patients scheduled for lung surgery from an observational study (n=512) and a randomized clinical trial (n=166) on the evaluation of different perioperative care strategies. PROs were assessed by the MD Anderson Symptom Inventory Lung Cancer Module and single-item Quality of Life Scale before surgery and then daily after surgery until discharge or up to 14 days of hospitalization. Patient compliance and data error were identified and compared between P&P and ePRO. Generalized estimating equations model and 2-piecewise model were used to describe trajectories of error incidence over time and to identify the risk factors. Results: Among 678 patients, 629 with at least 2 PRO assessments, 440 completed 3347 P&P assessments and 189 completed 1291 ePRO assessments. In total, 49.4% of patients had at least one error, including (1) missing items (64.69%, 1070/1654), (2) modifications without signatures (27.99%, 463/1654), (3) selection of multiple options (3.02%, 50/1654), (4) missing patient signatures (2.54%, 42/1654), (5) missing researcher signatures (1.45%, 24/1654), and (6) missing completion dates (0.30%, 5/1654). Patients who completed ePRO had fewer errors than those who completed P&P assessments (ePRO: 30.2% [57/189] vs. P&P: 57.7% [254/440]; P<.001). Compared with ePRO patients, those using P&P were older, less educated, and sicker. Common risk factors of having errors were a lower education level (P&P: odds ratio [OR] 1.39, 95% CI 1.20-1.62; P<.001; ePRO: OR 1.82, 95% CI 1.22-2.72; P=.003), treated in a provincial hospital (P&P: OR 3.34, 95% CI 2.10-5.33; P<.001; ePRO: OR 4.73, 95% CI 2.18-10.25; P<.001), and with severe disease (P&P: OR 1.63, 95% CI 1.33-1.99; P<.001; ePRO: OR 2.70, 95% CI 1.53-4.75; P<.001). Errors peaked on postoperative day (POD) 1 for P&P, and on POD 2 for ePRO. Conclusions: It is possible to improve data quality of longitudinally collected PRO through ePRO, compared with P&P. However, ePRO-related sampling bias needs to be considered when designing clinical research using longitudinal PROs as major outcomes. %M 34751657 %R 10.2196/28915 %U https://www.jmir.org/2021/11/e28915 %U https://doi.org/10.2196/28915 %U http://www.ncbi.nlm.nih.gov/pubmed/34751657 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 9 %N 10 %P e29017 %T An Automated Line-of-Therapy Algorithm for Adults With Metastatic Non–Small Cell Lung Cancer: Validation Study Using Blinded Manual Chart Review %A Meng,Weilin %A Mosesso,Kelly M %A Lane,Kathleen A %A Roberts,Anna R %A Griffith,Ashley %A Ou,Wanmei %A Dexter,Paul R %+ Regenstrief Institute, Inc, 1101 West 10th Street, Indianapolis, IN, 46202-4800, United States, 1 317 274 9000, prdexter@regenstrief.org %K automated algorithm %K line of therapy %K longitudinal changes %K manual chart review %K non–small cell lung cancer %K systemic anticancer therapy %D 2021 %7 12.10.2021 %9 Original Paper %J JMIR Med Inform %G English %X 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. %M 34636730 %R 10.2196/29017 %U https://medinform.jmir.org/2021/10/e29017 %U https://doi.org/10.2196/29017 %U http://www.ncbi.nlm.nih.gov/pubmed/34636730 %0 Journal Article %@ 2369-1999 %I JMIR Publications %V 7 %N 3 %P e26574 %T Selecting a Subset Based on the Patient-Reported Outcomes Version of the Common Terminology Criteria for Adverse Events for Patient-Reported Symptom Monitoring in Lung Cancer Treatment: Mixed Methods Study %A Veldhuijzen,Evalien %A Walraven,Iris %A Belderbos,José %+ Department of Radiation Oncology, Netherlands Cancer Institute, Plesmanlaan 121, Amsterdam, 1066 CX, Netherlands, 31 020 512 9111, j.belderbos@nki.nl %K PRO-CTCAE %K lung cancer %K side effects %K patient-reported outcomes %K PROM %K symptomatic adverse events %D 2021 %7 14.9.2021 %9 Original Paper %J JMIR Cancer %G English %X Background: The Patient-Reported Outcomes Version of the Common Terminology Criteria for Adverse Events (PRO-CTCAE) item library covers a wide range of symptoms relevant to oncology care. There is a need to select a subset of items relevant to specific patient populations to enable the implementation of PRO-CTCAE–based symptom monitoring in clinical practice. Objective: The aim of this study is to develop a PRO-CTCAE–based subset relevant to patients with lung cancer that can be used for monitoring during multidisciplinary clinical practice. Methods: The PRO-CTCAE–based subset for patients with lung cancer was generated using a mixed methods approach based on the European Organization for Research and Treatment of Cancer guidelines for developing questionnaires, comprising a literature review and semistructured interviews with both patients with lung cancer and health care practitioners (HCPs). Both patients and HCPs were queried on the relevance and impact of all PRO-CTCAE items. The results were summarized, and after a final round of expert review, a selection of clinically relevant items for patients with lung cancer was made. Results: A heterogeneous group of patients with lung cancer (n=25) from different treatment modalities and HCPs (n=22) participated in the study. A final list of eight relevant PRO-CTCAE items was created: decreased appetite, cough, shortness of breath, fatigue, constipation, nausea, sadness, and pain (general). Conclusions: On the basis of the literature and both professional and patient input, a subset of PRO-CTCAE items has been identified for use in patients with lung cancer in clinical practice. Future work is needed to confirm the validity and effectiveness of this PRO-CTCAE–based lung cancer subset internationally and in real-world clinical practice settings. %M 34519658 %R 10.2196/26574 %U https://cancer.jmir.org/2021/3/e26574 %U https://doi.org/10.2196/26574 %U http://www.ncbi.nlm.nih.gov/pubmed/34519658 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 23 %N 8 %P e26256 %T Artificial Intelligence–Based Prediction of Lung Cancer Risk Using Nonimaging Electronic Medical Records: Deep Learning Approach %A Yeh,Marvin Chia-Han %A Wang,Yu-Hsiang %A Yang,Hsuan-Chia %A Bai,Kuan-Jen %A Wang,Hsiao-Han %A Li,Yu-Chuan Jack %+ Department of Dermatology, Wan Fang Hospital, Taipei Medical University, No 111, Section 3, Xinglong Road, Wenshan District, Taipei, 116, Taiwan, 886 29307930 ext 2980, jaak88@gmail.com %K artificial intelligence %K lung cancer screening %K electronic medical record %D 2021 %7 3.8.2021 %9 Original Paper %J J Med Internet Res %G English %X Background: Artificial intelligence approaches can integrate complex features and can be used to predict a patient’s risk of developing lung cancer, thereby decreasing the need for unnecessary and expensive diagnostic interventions. Objective: The aim of this study was to use electronic medical records to prescreen patients who are at risk of developing lung cancer. Methods: We randomly selected 2 million participants from the Taiwan National Health Insurance Research Database who received care between 1999 and 2013. We built a predictive lung cancer screening model with neural networks that were trained and validated using pre-2012 data, and we tested the model prospectively on post-2012 data. An age- and gender-matched subgroup that was 10 times larger than the original lung cancer group was used to assess the predictive power of the electronic medical record. Discrimination (area under the receiver operating characteristic curve [AUC]) and calibration analyses were performed. Results: The analysis included 11,617 patients with lung cancer and 1,423,154 control patients. The model achieved AUCs of 0.90 for the overall population and 0.87 in patients ≥55 years of age. The AUC in the matched subgroup was 0.82. The positive predictive value was highest (14.3%) among people aged ≥55 years with a pre-existing history of lung disease. Conclusions: Our model achieved excellent performance in predicting lung cancer within 1 year and has potential to be deployed for digital patient screening. Convolution neural networks facilitate the effective use of EMRs to identify individuals at high risk for developing lung cancer. %M 34342588 %R 10.2196/26256 %U https://www.jmir.org/2021/8/e26256 %U https://doi.org/10.2196/26256 %U http://www.ncbi.nlm.nih.gov/pubmed/34342588 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 9 %N 7 %P e27955 %T Automatic Extraction of Lung Cancer Staging Information From Computed Tomography Reports: Deep Learning Approach %A Hu,Danqing %A Zhang,Huanyao %A Li,Shaolei %A Wang,Yuhong %A Wu,Nan %A Lu,Xudong %+ College of Biomedical Engineering and Instrumental Science, Zhejiang University, 38 Zheda Road, Hangzhou, 310027, China, 86 13957118891, lvxd@zju.edu.cn %K lung cancer %K clinical staging %K information extraction %K named entity recognition %K relation classification %D 2021 %7 21.7.2021 %9 Original Paper %J JMIR Med Inform %G English %X Background: Lung cancer is the leading cause of cancer deaths worldwide. Clinical staging of lung cancer plays a crucial role in making treatment decisions and evaluating prognosis. However, in clinical practice, approximately one-half of the clinical stages of lung cancer patients are inconsistent with their pathological stages. As one of the most important diagnostic modalities for staging, chest computed tomography (CT) provides a wealth of information about cancer staging, but the free-text nature of the CT reports obstructs their computerization. Objective: We aimed to automatically extract the staging-related information from CT reports to support accurate clinical staging of lung cancer. Methods: In this study, we developed an information extraction (IE) system to extract the staging-related information from CT reports. The system consisted of the following three parts: named entity recognition (NER), relation classification (RC), and postprocessing (PP). We first summarized 22 questions about lung cancer staging based on the TNM staging guideline. Next, three state-of-the-art NER algorithms were implemented to recognize the entities of interest. Next, we designed a novel RC method using the relation sign constraint (RSC) to classify the relations between entities. Finally, a rule-based PP module was established to obtain the formatted answers using the results of NER and RC. Results: We evaluated the developed IE system on a clinical data set containing 392 chest CT reports collected from the Department of Thoracic Surgery II in the Peking University Cancer Hospital. The experimental results showed that the bidirectional encoder representation from transformers (BERT) model outperformed the iterated dilated convolutional neural networks-conditional random field (ID-CNN-CRF) and bidirectional long short-term memory networks-conditional random field (Bi-LSTM-CRF) for NER tasks with macro-F1 scores of 80.97% and 90.06% under the exact and inexact matching schemes, respectively. For the RC task, the proposed RSC showed better performance than the baseline methods. Further, the BERT-RSC model achieved the best performance with a macro-F1 score of 97.13% and a micro-F1 score of 98.37%. Moreover, the rule-based PP module could correctly obtain the formatted results using the extractions of NER and RC, achieving a macro-F1 score of 94.57% and a micro-F1 score of 96.74% for all the 22 questions. Conclusions: We conclude that the developed IE system can effectively and accurately extract information about lung cancer staging from CT reports. Experimental results show that the extracted results have significant potential for further use in stage verification and prediction to facilitate accurate clinical staging. %M 34287213 %R 10.2196/27955 %U https://medinform.jmir.org/2021/7/e27955 %U https://doi.org/10.2196/27955 %U http://www.ncbi.nlm.nih.gov/pubmed/34287213 %0 Journal Article %@ 1929-0748 %I JMIR Publications %V 10 %N 7 %P e23831 %T The VICTORY (Investigation of Inflammacheck to Measure Exhaled Breath Condensate Hydrogen Peroxide in Respiratory Conditions) Study: Protocol for a Cross-sectional Observational Study %A Fox,Lauren %A Gates,Jessica %A De Vos,Ruth %A Wiffen,Laura %A Hicks,Alexander %A Rupani,Hitasha %A Williams,Jane %A Brown,Thomas %A Chauhan,Anoop J %+ Portsmouth Hospitals University NHS Trust, 1st floor Lancaster House, Queen Alexandra Hospital, Southwick Hill Road, Portsmouth, PO6 3LY, United Kingdom, 44 2392286000 ext 3773, lauren.fox@porthosp.nhs.uk %K medical device %K diagnosis %K hydrogen peroxide %K lung diseases %K exhalation %K asthma %K COPD %K bronchiectasis %K interstitial lung disease %K lung cancer %K breathing pattern disorder %K pneumonia %D 2021 %7 9.7.2021 %9 Protocol %J JMIR Res Protoc %G English %X Background: More than 7% of the world’s population is living with a chronic respiratory condition. In the United Kingdom, lung disease affects approximately 1 in 5 people, resulting in over 700,000 hospital admissions each year. People with respiratory conditions have several symptoms and can require multiple health care visits and investigations before a diagnosis is made. The tests available can be difficult to perform, especially if a person is symptomatic, leading to poor quality results. A new, easy-to-perform, point-of-care test that can be performed in any health care setting and that can differentiate between various respiratory conditions would have a significant, beneficial impact on the ability to diagnose respiratory diseases. Objective: The objective of this study is to use a new handheld device (Inflammacheck) in different respiratory conditions to measure the exhaled breath condensate hydrogen peroxide (EBC H2O2) and compare these results with those of healthy controls and with each other. This study also aims to determine whether the device can measure other parameters, including breath humidity, breath temperature, breath flow dynamics, and end tidal carbon dioxide. Methods: We will perform a single-visit, cross-sectional observational study of EBC H2O2 levels, as measured by Inflammacheck, in people with respiratory disease and volunteers with no known lung disease. Participants with a confirmed diagnosis of asthma, chronic obstructive pulmonary disease, lung cancer, bronchiectasis, pneumonia, breathing pattern disorder, and interstitial lung disease as well as volunteers with no history of lung disease will be asked to breathe into the Inflammacheck device to record their breath sample. Results: The results from this study will be available in 2022, in anticipation of COVID-19–related delays. Conclusions: This study will investigate the EBC H2O2, as well as other exhaled breath parameters, for use as a future diagnostic tool. %M 34255725 %R 10.2196/23831 %U https://www.researchprotocols.org/2021/7/e23831 %U https://doi.org/10.2196/23831 %U http://www.ncbi.nlm.nih.gov/pubmed/34255725 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 23 %N 7 %P e25791 %T Measurement of Cancer-Related Fatigue Based on Heart Rate Variability: Observational Study %A Shih,Chi-Huang %A Chou,Pai-Chien %A Chou,Ting-Ling %A Huang,Tsai-Wei %+ School of Nursing, College of Nursing, Taipei Medical University, 250, Wuxing Street,, Taipei City, 11031, Taiwan, 886 2 27361661 ext 6350, tsaiwei@tmu.edu.tw %K cancer-related fatigue %K heart rate variability %K LF-HF ratio %K photoplethysmography %K wearables %K chemotherapy %D 2021 %7 5.7.2021 %9 Original Paper %J J Med Internet Res %G English %X Background: Cancer-related fatigue is a serious side effect of cancer, and its treatment can disrupt the quality of life of patients. Clinically, the standard method for assessing cancer-related fatigue relies on subjective experience retrieved from patient self-reports, such as the Brief Fatigue Inventory (BFI). However, most patients do not self-report their fatigue levels. Objective: In this study, we aim to develop an objective cancer-related fatigue assessment method to track and monitor fatigue in patients with cancer. Methods: In total, 12 patients with lung cancer who were undergoing chemotherapy or targeted therapy were enrolled. We developed frequency-domain parameters of heart rate variability (HRV) and BFI based on a wearable-based HRV measurement system. All patients completed the BFI-Taiwan version questionnaire and wore the device for 7 consecutive days to record HRV parameters such as low frequency (LF), high frequency (HF), and LF-HF ratio (LF-HF). Statistical analysis was used to map the correlation between subjective fatigue and objective data. Results: A moderate positive correlation was observed between the average LF-HF ratio and BFI in the sleep phase (ρ=0.86). The mapped BFI score derived by the BFI mapping method could approximate the BFI from the patient self-report. The mean absolute error rate between the subjective and objective BFI scores was 3%. Conclusions: LF-HF is highly correlated with the cancer-related fatigue experienced by patients with lung cancer undergoing chemotherapy or targeted therapy. Beyond revealing fatigue levels objectively, continuous HRV recordings through the photoplethysmography watch device and the defined parameters (LF-HF) can define the active phase and sleep phase in patients with lung cancer who undergo chemotherapy or targeted chemotherapy, allowing a deduction of their sleep patterns. %M 36260384 %R 10.2196/25791 %U https://www.jmir.org/2021/7/e25791 %U https://doi.org/10.2196/25791 %U http://www.ncbi.nlm.nih.gov/pubmed/36260384 %0 Journal Article %@ 2561-326X %I JMIR Publications %V 5 %N 6 %P e28952 %T A Web-Based Intervention to Increase Smokers’ Intentions to Participate in a Cessation Study Offered at the Point of Lung Screening: Factorial Randomized Trial %A Neil,Jordan M %A Chang,Yuchiao %A Goshe,Brett %A Rigotti,Nancy %A Gonzalez,Irina %A Hawari,Saif %A Ballini,Lauren %A Haas,Jennifer S %A Marotta,Caylin %A Wint,Amy %A Harris,Kim %A Crute,Sydney %A Flores,Efren %A Park,Elyse R %+ Health Promotion Research Center, Stephenson Cancer Center, University of Oklahoma Health Sciences Center, 655 Research Parkway, 1404, Oklahoma City, OK, 73104, United States, 1 6034430743, jordan-neil@ouhsc.edu %K clinical trials recruitment %K digital outreach %K message design experiment %K smoking cessation %K lung cancer screening %K prospect theory %D 2021 %7 30.6.2021 %9 Original Paper %J JMIR Form Res %G English %X Background: Screen ASSIST is a cessation trial offered to current smokers at the point of lung cancer screening. Because of the unique position of promoting a prevention behavior (smoking cessation) within the context of a detection behavior (lung cancer screening), this study employed prospect theory to design and formatively evaluate a targeted recruitment video prior to trial launch. Objective: The aim of this study was to identify which message frames were most effective at promoting intent to participate in a smoking cessation study. Methods: Participants were recruited from a proprietary opt-in online panel company and randomized to a 2 (benefits of quitting vs risks of continuing to smoke at the time of lung screening; BvR) × 2 (gains of participating vs losses of not participating in a cessation study; GvL) message design experiment (N=314). The primary outcome was self-assessed intent to participate in a smoking cessation study. Message effectiveness and lung cancer risk perception measures were also collected. Analysis of variance examined the main effect of the 2 message factors and a least absolute shrinkage and selection operator (LASSO) approach identified predictors of intent to participate in a multivariable model. A mediation analysis was conducted to determine the direct and indirect effects of message factors on intent to participate in a cessation study. Results: A total of 296 participants completed the intervention. There were no significant differences in intent to participate in a smoking cessation study between message frames (P=.12 and P=.61). In the multivariable model, quit importance (P<.001), perceived message relevance (P<.001), and affective risk response (ie, worry about developing lung cancer; P<.001) were significant predictors of intent to participate. The benefits of quitting frame significantly increased affective risk response (Meanbenefits 2.60 vs Meanrisk 2.40; P=.03), which mediated the relationship between message frame and intent to participate (b=0.24; 95% CI 0.01-0.47; P=.03). Conclusions: This study provides theoretical and practical guidance on how to design and evaluate proactive recruitment messages for a cessation trial. Based on our findings, we conclude that heavy smokers are more responsive to recruitment messages that frame the benefits of quitting as it increased affective risk response, which predicted greater intention to participate in a smoking cessation study. %M 34255651 %R 10.2196/28952 %U https://formative.jmir.org/2021/6/e28952 %U https://doi.org/10.2196/28952 %U http://www.ncbi.nlm.nih.gov/pubmed/34255651 %0 Journal Article %@ 2369-1999 %I JMIR Publications %V 7 %N 2 %P e23161 %T Data Integration to Improve Real-world Health Outcomes Research for Non–Small Cell Lung Cancer in the United States: Descriptive and Qualitative Exploration %A Grabner,Michael %A Molife,Cliff %A Wang,Liya %A Winfree,Katherine B %A Cui,Zhanglin Lin %A Cuyun Carter,Gebra %A Hess,Lisa M %+ HealthCore Inc, 123 Justison Street, Wilmington, DE, 19801, United States, 1 3022302000, mgrabner@healthcore.com %K non–small cell lung cancer %K cancer %K data aggregation %K real-world data %K administrative claims data %K medical records %K electronic health record %K retrospective study %K population health %K health services research %D 2021 %7 12.4.2021 %9 Original Paper %J JMIR Cancer %G English %X Background: The integration of data from disparate sources could help alleviate data insufficiency in real-world studies and compensate for the inadequacies of single data sources and short-duration, small sample size studies while improving the utility of data for research. Objective: This study aims to describe and evaluate a process of integrating data from several complementary sources to conduct health outcomes research in patients with non–small cell lung cancer (NSCLC). The integrated data set is also used to describe patient demographics, clinical characteristics, treatment patterns, and mortality rates. Methods: This retrospective cohort study integrated data from 4 sources: administrative claims from the HealthCore Integrated Research Database, clinical data from a Cancer Care Quality Program (CCQP), clinical data from abstracted medical records (MRs), and mortality data from the US Social Security Administration. Patients with lung cancer who initiated second-line (2L) therapy between November 01, 2015, and April 13, 2018, were identified in the claims and CCQP data. Eligible patients were 18 years or older and received atezolizumab, docetaxel, erlotinib, nivolumab, pembrolizumab, pemetrexed, or ramucirumab in the 2L setting. The main analysis cohort included patients with claims data and data from at least one additional data source (CCQP or MR). Patients without integrated data (claims only) were reported separately. Descriptive and univariate statistics were reported. Results: Data integration resulted in a main analysis cohort of 2195 patients with NSCLC; 2106 patients had CCQP and 407 patients had MR data. The claims-only cohort included 931 eligible patients. For the main analysis cohort, the mean age was 62.1 (SD 9.27) years, 48.56% (1066/2195) were female, the median length of follow-up was 6.8 months, and for 37.77% (829/2195), death was observed. For the claims-only cohort, the mean age was 66.6 (SD 12.69) years, 52.1% (485/931) were female, the median length of follow-up was 8.6 months, and for 29.3% (273/931), death was observed. The most frequent 2L treatment was immunotherapy (1094/2195, 49.84%), followed by platinum-based regimens (472/2195, 21.50%) and single-agent chemotherapy (441/2195, 20.09%); mean duration of 2L therapy was 5.6 (SD 4.9, median 4) months. We describe challenges and learnings from the data integration process, and the benefits of the integrated data set, which includes a richer set of clinical and outcome data to supplement the utilization metrics available in administrative claims. Conclusions: The management of patients with NSCLC requires care from a multidisciplinary team, leading to a lack of a single aggregated data source in real-world settings. The availability of integrated clinical data from MRs, health plan claims, and other sources of clinical care may improve the ability to assess emerging treatments. %M 33843600 %R 10.2196/23161 %U https://cancer.jmir.org/2021/2/e23161 %U https://doi.org/10.2196/23161 %U http://www.ncbi.nlm.nih.gov/pubmed/33843600 %0 Journal Article %@ 2369-1999 %I JMIR Publications %V 7 %N 1 %P e26911 %T Development and Early Feasibility of Chatbots for Educating Patients With Lung Cancer and Their Caregivers in Japan: Mixed Methods Study %A Kataoka,Yuki %A Takemura,Tomoyasu %A Sasajima,Munehiko %A Katoh,Naoki %+ Department of Respiratory Medicine, Hyogo Prefectural Amagasaki General Medical Center, Higashi-Naniwa-Cho 2-17-77, Amagasaki, 660-8550, Japan, 81 6480 7000, youkiti@gmail.com %K cancer %K caregivers %K chatbot %K lung cancer %K mixed methods approach %K online health %K patients %K symptom management education %K web-based platform %D 2021 %7 10.3.2021 %9 Original Paper %J JMIR Cancer %G English %X Background: Chatbots are artificial intelligence–driven programs that interact with people. The applications of this technology include the collection and delivery of information, generation of and responding to inquiries, collection of end user feedback, and the delivery of personalized health and medical information to patients through cellphone- and web-based platforms. However, no chatbots have been developed for patients with lung cancer and their caregivers. Objective: This study aimed to develop and evaluate the early feasibility of a chatbot designed to improve the knowledge of symptom management among patients with lung cancer in Japan and their caregivers. Methods: We conducted a sequential mixed methods study that included a web-based anonymized questionnaire survey administered to physicians and paramedics from June to July 2019 (phase 1). Two physicians conducted a content analysis of the questionnaire to curate frequently asked questions (FAQs; phase 2). Based on these FAQs, we developed and integrated a chatbot into a social network service (phase 3). The physicians and paramedics involved in phase I then tested this chatbot (α test; phase 4). Thereafter, patients with lung cancer and their caregivers tested this chatbot (β test; phase 5). Results: We obtained 246 questions from 15 health care providers in phase 1. We curated 91 FAQs and their corresponding responses in phase 2. In total, 11 patients and 1 caregiver participated in the β test in phase 5. The participants were asked 60 questions, 8 (13%) of which did not match the appropriate categories. After the β test, 7 (64%) participants responded to the postexperimental questionnaire. The mean satisfaction score was 2.7 (SD 0.5) points out of 5. Conclusions: Medical staff providing care to patients with lung cancer can use the categories specified in this chatbot to educate patients on how they can manage their symptoms. Further studies are required to improve chatbots in terms of interaction with patients. %M 33688839 %R 10.2196/26911 %U https://cancer.jmir.org/2021/1/e26911 %U https://doi.org/10.2196/26911 %U http://www.ncbi.nlm.nih.gov/pubmed/33688839 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 8 %N 6 %P e17821 %T End-to-End Models to Imitate Traditional Chinese Medicine Syndrome Differentiation in Lung Cancer Diagnosis: Model Development and Validation %A Liu,Ziqing %A He,Haiyang %A Yan,Shixing %A Wang,Yong %A Yang,Tao %A Li,Guo-Zheng %+ School of Artifical Intelligence and Information Techology, Nanjing University of Chinese Medicine, Nanjing, China, 86 13405803341, taoyang1111@126.com %K traditional Chinese medicine %K syndrome differentiation %K lung cancer %K medical record %K deep learning %K model fusion %D 2020 %7 16.6.2020 %9 Original Paper %J JMIR Med Inform %G English %X 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. %M 32543445 %R 10.2196/17821 %U https://medinform.jmir.org/2020/6/e17821 %U https://doi.org/10.2196/17821 %U http://www.ncbi.nlm.nih.gov/pubmed/32543445 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 22 %N 3 %P e17695 %T Identifying Lung Cancer Risk Factors in the Elderly Using Deep Neural Networks: Quantitative Analysis of Web-Based Survey Data %A Chen,Songjing %A Wu,Sizhu %+ Institute of Medical Information and Library, Chinese Academy of Medical Sciences / Peking Union Medical College, No 3, Yabao Road, Chaoyang District, Beijing, China, 86 01052328761, chen.songjing@imicams.ac.cn %K deep learning %K lung cancer %K risk factors %K aged %K primary prevention %D 2020 %7 17.3.2020 %9 Original Paper %J J Med Internet Res %G English %X Background: Lung cancer is one of the most dangerous malignant tumors, with the fastest-growing morbidity and mortality, especially in the elderly. With a rapid growth of the elderly population in recent years, lung cancer prevention and control are increasingly of fundamental importance, but are complicated by the fact that the pathogenesis of lung cancer is a complex process involving a variety of risk factors. Objective: This study aimed at identifying key risk factors of lung cancer incidence in the elderly and quantitatively analyzing these risk factors’ degree of influence using a deep learning method. Methods: Based on Web-based survey data, we integrated multidisciplinary risk factors, including behavioral risk factors, disease history factors, environmental factors, and demographic factors, and then preprocessed these integrated data. We trained deep neural network models in a stratified elderly population. We then extracted risk factors of lung cancer in the elderly and conducted quantitative analyses of the degree of influence using the deep neural network models. Results: The proposed model quantitatively identified risk factors based on 235,673 adults. The proposed deep neural network models of 4 groups (age ≥65 years, women ≥65 years old, men ≥65 years old, and the whole population) achieved good performance in identifying lung cancer risk factors, with accuracy ranging from 0.927 (95% CI 0.223-0.525; P=.002) to 0.962 (95% CI 0.530-0.751; P=.002) and the area under curve ranging from 0.913 (95% CI 0.564-0.803) to 0.931(95% CI 0.499-0.593). Smoking frequency was the leading risk factor for lung cancer in men 65 years and older. Time since quitting and smoking at least 100 cigarettes in their lifetime were the main risk factors for lung cancer in women 65 years and older. Men 65 years and older had the highest lung cancer incidence among the stratified groups, particularly non–small cell lung cancer incidence. Lung cancer incidence decreased more obviously in men than in women with smoking rate decline. Conclusions: This study demonstrated a quantitative method to identify risk factors of lung cancer in the elderly. The proposed models provided intervention indicators to prevent lung cancer, especially in older men. This approach might be used as a risk factor identification tool to apply in other cancers and help physicians make decisions on cancer prevention. %M 32181751 %R 10.2196/17695 %U http://www.jmir.org/2020/3/e17695/ %U https://doi.org/10.2196/17695 %U http://www.ncbi.nlm.nih.gov/pubmed/32181751