e.g. mhealth
Search Results (1 to 10 of 254 Results)
Download search results: CSV END BibTex RIS
Skip search results from other journals and go to results- 69 Journal of Medical Internet Research
- 49 JMIR Medical Informatics
- 34 JMIR Public Health and Surveillance
- 23 JMIR Formative Research
- 16 JMIRx Med
- 12 JMIR Research Protocols
- 7 JMIR Aging
- 7 JMIR Bioinformatics and Biotechnology
- 6 JMIR AI
- 5 JMIR mHealth and uHealth
- 4 JMIR Human Factors
- 4 JMIR Mental Health
- 3 Interactive Journal of Medical Research
- 3 Online Journal of Public Health Informatics
- 2 JMIR Cardio
- 2 JMIR Pediatrics and Parenting
- 1 JMIR Biomedical Engineering
- 1 JMIR Cancer
- 1 JMIR Dermatology
- 1 JMIR Diabetes
- 1 JMIR Medical Education
- 1 JMIR Neurotechnology
- 1 JMIR Perioperative Medicine
- 1 JMIR Rehabilitation and Assistive Technologies
- 0 Medicine 2.0
- 0 iProceedings
- 0 JMIR Serious Games
- 0 JMIR Preprints
- 0 JMIR Challenges
- 0 JMIR Data
- 0 Journal of Participatory Medicine
- 0 JMIR Nursing
- 0 JMIRx Bio
- 0 JMIR Infodemiology
- 0 Transfer Hub (manuscript eXchange)
- 0 Asian/Pacific Island Nursing Journal
- 0 JMIR XR and Spatial Computing (JMXR)

Health care providers use AI for patient disease prediction and data anonymization, addressing the growing health care costs associated with increasing chronic diseases and life expectancy [2]. Recent studies have increasingly applied advanced machine learning and explainable artificial intelligence (XAI) methods to improve disease survival prediction.
JMIR Med Inform 2025;13:e75022
Download Citation: END BibTex RIS

In summary, most “prediction” studies predominantly explain the relationships between variables and outcomes within existing data, rather than establishing generalizable prediction through rigorous validation with new data. Even among studies using appropriate ML prediction models with both training and validation components, most implement only basic predictive methodologies, focusing on prediction with retrospective modeling and lacking external validation.
J Med Internet Res 2025;27:e66100
Download Citation: END BibTex RIS

Additionally, it reduces model complexity and boosts prediction accuracy by eliminating irrelevant or unnecessary data in ML. Models based on the most impactful clinical features, such as BMI, age, low-density lipoprotein cholesterol (LDL-C), and high-density lipoprotein cholesterol (HDL-C), can capture underlying patterns linked with prediabetes [6].
JMIR Bioinform Biotech 2025;6:e70621
Download Citation: END BibTex RIS

However, efforts to quantitatively evaluate fairness in prediction models for clinical practice are still scarce [15].
A model with high predictive accuracy does not guarantee the best clinical usage, as it might display unfavorable biases [16]. As a result, it is important to understand and quantify the trade-offs between accuracy and fairness in model selection.
JMIR Med Inform 2025;13:e66200
Download Citation: END BibTex RIS

We then incorporated a range of different observation periods and prediction windows (Figure 2) to test our prediction algorithms, considering the different use cases. We considered 4 different prediction windows: 0 years, 1 year, 3 years, and 5 years before CRC diagnosis.
Visualization of the observation and prediction windows. For the prediction task. The index date for CRC cases is the date of diagnosis.
JMIR Cancer 2025;11:e64506
Download Citation: END BibTex RIS

The reporting of the model development and validation followed the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD [37]) guidelines (Table S4 in Multimedia Appendix 1).
The strongest statistically significant unadjusted linear relationships between baseline predictors and mental health at follow-up are shown in Figure 4 and coefficients of all predictors can be found in Tables S1 and S2 in Multimedia Appendix 1.
JMIR Public Health Surveill 2025;11:e60125
Download Citation: END BibTex RIS

Prediction models that can identify infants with a high risk of ROP reactivation are needed in clinical practice.
Artificial intelligence has recently optimized medical practice [15-17]. Artificial intelligence has been mainly applied to ROP diagnosis and prediction based on imaging [17-19]. To our knowledge, studies on ROP reactivation after treatment are very limited, and there is no successful prediction model for clinical application.
J Med Internet Res 2025;27:e60367
Download Citation: END BibTex RIS
Go back to the top of the page Skip and go to footer section

Uncertainty-aware AI models present the model’s uncertainty, or confidence in its decision, alongside its prediction [11], thus providing a metric for the user to assess the AI’s reliability [12]. CDSS reliability is an essential component of human evaluation of AI’s trustworthiness which determines the user’s acceptability of a technology [7].
JMIR Med Inform 2025;13:e64902
Download Citation: END BibTex RIS
Go back to the top of the page Skip and go to footer section