Search Results (1 to 8 of 8 Results)
Download search results: CSV END BibTex RIS
Skip search results from other journals and go to results- 4 Journal of Medical Internet Research
- 3 JMIR Medical Informatics
- 1 Interactive Journal of Medical Research
- 0 Medicine 2.0
- 0 iProceedings
- 0 JMIR Research Protocols
- 0 JMIR Human Factors
- 0 JMIR Public Health and Surveillance
- 0 JMIR mHealth and uHealth
- 0 JMIR Serious Games
- 0 JMIR Mental Health
- 0 JMIR Rehabilitation and Assistive Technologies
- 0 JMIR Preprints
- 0 JMIR Bioinformatics and Biotechnology
- 0 JMIR Medical Education
- 0 JMIR Cancer
- 0 JMIR Challenges
- 0 JMIR Diabetes
- 0 JMIR Biomedical Engineering
- 0 JMIR Data
- 0 JMIR Cardio
- 0 JMIR Formative Research
- 0 Journal of Participatory Medicine
- 0 JMIR Dermatology
- 0 JMIR Pediatrics and Parenting
- 0 JMIR Aging
- 0 JMIR Perioperative Medicine
- 0 JMIR Nursing
- 0 JMIRx Med
- 0 JMIRx Bio
- 0 JMIR Infodemiology
- 0 Transfer Hub (manuscript eXchange)
- 0 JMIR AI
- 0 JMIR Neurotechnology
- 0 Asian/Pacific Island Nursing Journal
- 0 Online Journal of Public Health Informatics
- 0 JMIR XR and Spatial Computing (JMXR)
Multimedia Appendix 9 summarizes the 9 laboratory test predictors used in the model: (1) coagulation assay, (2) glomerular filtration rate, (3) carboxyhemoglobin in blood, (4) cardiac troponin T antibodies in blood, (5) blood glucose, (6) creatine kinase, (7) reticulocytes in blood, (8) n-terminal prohormone B-type natriuretic peptide in serum or plasma, and (9) estimated average glucose level.
JMIR Med Inform 2021;9(2):e23606
Download Citation: END BibTex RIS
To avoid overfitting, the model at the t-th iteration was trained to minimize the following item,
where
was the prediction of the i-th instance at the t-1-th iteration, and l is a differentiable convex loss function. The term Ω indicates the penalty of the model complexity and is defined as
where γ and are parameters controlling penalty for the number of leaves T and magnitude of leaf weights w, respectively.
J Med Internet Res 2019;21(5):e13260
Download Citation: END BibTex RIS
The sum term at the t iteration was as seen in Figure 3, where l was a differentiable convex loss function that not only measured the difference between the target yi and the prediction ŷi(t-1) of the i instance at the t-1 iteration but also took the ft to improve the model most into account. The term Ω was set to penalize the complexity of the regression tree functions in avoid of overfitting.
J Med Internet Res 2018;20(6):e10311
Download Citation: END BibTex RIS
The model at the t- th iteration was trained to minimize the following objective, where l is a differentiable convex loss function that not only measures the difference between the target yi and the prediction ŷi(t-1) of the i-th instance at the t-1- th iteration but also takes the ƒt that improves the model most into account:
L(t)= ∑ni=1l( yi, ŷi(t-1)+ ƒt(xi)) + Ω (ƒt) (2)
The term Ω penalizes the complexity of the regression tree functions to avoid issues of overfitting.
J Med Internet Res 2018;20(1):e22
Download Citation: END BibTex RIS
Sum of the loss function and the overfitting control term at the t iteration.
A workflow chart for the study is shown in Figure 1. To improve computational efficiency, a feature selection process was carried out to determine the features that would go into the model prior to the derivation phase. The selection process was divided into 2 stages: literature review and variance analysis. Features recognized to have an association with CKD in previous literature were extracted as risk factors.
JMIR Med Inform 2017;5(3):e21
Download Citation: END BibTex RIS
As a result, the inference of DM diagnosis for a codified note was only dependent on the ICD code noted in the structured data, whereas for uncodified notes we trained a random forest model [33,38] to obtain T(f) (Figure 3 (g)), where tn was the n th decision tree in the random forest.
At the perspective of hierarchical tree, the model could be considered as a combination of a predetermined tree-based model and a random forest-based model.
JMIR Med Inform 2016;4(4):e37
Download Citation: END BibTex RIS
Go back to the top of the page Skip and go to footer section
We obtained two thresholds, T
h
,T
m
, from this mapping. The intent of the model was to stratify the patients from low to high risk allowing the clinicians to target different risk levels for personalized intervention. Field care providers can target different risk groups with different threshold settings as a continuous variable for active case finding.
Interact J Med Res 2015;4(1):e2
Download Citation: END BibTex RIS