Search Results (1 to 10 of 2531 Results)
Download search results: CSV END BibTex RIS
Skip search results from other journals and go to results- 721 Journal of Medical Internet Research
- 427 JMIR Research Protocols
- 307 JMIR Formative Research
- 216 JMIR mHealth and uHealth
- 105 JMIR Public Health and Surveillance
- 97 Online Journal of Public Health Informatics
- 88 JMIR Mental Health
- 69 JMIR Medical Informatics
- 68 JMIR Human Factors
- 52 JMIR Pediatrics and Parenting
- 44 JMIR Cancer
- 42 JMIR Aging
- 36 JMIR Dermatology
- 34 JMIR Serious Games
- 28 Iproceedings
- 28 JMIR Medical Education
- 24 JMIR Cardio
- 21 JMIR Diabetes
- 20 Interactive Journal of Medical Research
- 18 JMIR Rehabilitation and Assistive Technologies
- 17 JMIR Infodemiology
- 17 JMIR Perioperative Medicine
- 10 Journal of Participatory Medicine
- 9 JMIR Nursing
- 8 JMIR AI
- 8 JMIRx Med
- 5 JMIR Biomedical Engineering
- 5 JMIR Neurotechnology
- 3 JMIR XR and Spatial Computing (JMXR)
- 2 Medicine 2.0
- 1 Asian/Pacific Island Nursing Journal
- 1 JMIR Bioinformatics and Biotechnology
- 0 iProceedings
- 0 JMIR Preprints
- 0 JMIR Challenges
- 0 JMIR Data
- 0 JMIRx Bio
- 0 Transfer Hub (manuscript eXchange)
Go back to the top of the page Skip and go to footer section
Go back to the top of the page Skip and go to footer section
Go back to the top of the page Skip and go to footer section
Go back to the top of the page Skip and go to footer section
Go back to the top of the page Skip and go to footer section
Go back to the top of the page Skip and go to footer section
All machine learning procedures were conducted using the caret package in R (R Foundation for Statistical Computing) [30].
As the dataset was naturally imbalanced, with more tweets from high-mortality states, we used multiple strategies to mitigate potential classification bias. To enhance model learning, SMOTE was applied only to the training data, preventing overfitting while allowing the models to better distinguish between high- and low-mortality states based on linguistic features.
J Med Internet Res 2025;27:e67506
Download Citation: END BibTex RIS
Propensity matching was conducted using the Match IT package [52] in R (R Foundation) with the “nearest neighbor” methodology (average treatment effect in treated patients), matching for propensity score on a one-to-one ratio. Comparator groups showed high similarity with the digital program sample (see Table S2 in Multimedia Appendix 1).
J Med Internet Res 2025;27:e69351
Download Citation: END BibTex RIS
Go back to the top of the page Skip and go to footer section
Cocreating the Visualization of Digital Mobility Outcomes: Delphi-Type Process With Patients
JMIR Form Res 2025;9:e68782
Download Citation: END BibTex RIS