e.g. mhealth
Search Results (1 to 10 of 15 Results)
Download search results: CSV END BibTex RIS
Skip search results from other journals and go to results- 6 Journal of Medical Internet Research
- 2 Interactive Journal of Medical Research
- 2 JMIR Medical Informatics
- 1 Iproceedings
- 1 JMIR AI
- 1 JMIR Human Factors
- 1 JMIR Research Protocols
- 1 JMIR mHealth and uHealth
- 0 Medicine 2.0
- 0 iProceedings
- 0 JMIR Public Health and Surveillance
- 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 Neurotechnology
- 0 Asian/Pacific Island Nursing Journal
- 0 Online Journal of Public Health Informatics
- 0 JMIR XR and Spatial Computing (JMXR)
Building trustworthy machine learning models for clinical practice requires consideration of interpretability, explainability, as well as fairness. Interpretability—which refers to how easily a human can comprehend the mechanism by which a model makes predictions—is important in health care settings because of the need for clinicians and patients to understand and trust the Artificial Intelligence (AI)-involved decisions that directly impact patient care [1,2].
JMIR Med Inform 2025;13:e66200
Download Citation: END BibTex RIS
We also enhanced the ability of deep learning models by constructing a specialized knowledge graph that also increases the explainability of the decision-making process.
All study procedures were approved by the ethical committees of all the medical centers mentioned in this study. The patients involved in the study all signed informed consent forms before admission. All data involved in this study have been anonymized or deidentified. The case data involved in this study are part of a retrospective study.
J Med Internet Res 2025;27:e66055
Download Citation: END BibTex RIS
Interpretability refers to how a model arrives at a decision, and explainability refers to why the decision is reached [16]. While explainability in AI has been a topic of interest since the 1980s, the recent accelerations in the widespread use of AI have resulted in guidelines on the responsible use of AI. Responsible AI requires a robust model that conveys the confidence and degree of uncertainty in prediction [16-18].
JMIR Med Inform 2025;13:e64617
Download Citation: END BibTex RIS
To address interpretability, we applied two complementary explainability techniques: SHAP and Grad-CAM, each offering unique insights into model behavior.
SHAP provides a feature attribution approach, assigning precise numerical contributions to each input feature—such as latency or main frequency—to quantify its role in the prediction process.
J Med Internet Res 2025;27:e63937
Download Citation: END BibTex RIS
This system addresses nonlinearity assumptions and enhances explainability. In addition, we applied the EACH score to predict perioperative stroke to assess its performance in real-world clinical practice and examined its performance compared with traditional scores and other ML-based scoring systems.
Perioperative stroke significantly impacts postoperative morbidity and mortality.
J Med Internet Res 2025;27:e58021
Download Citation: END BibTex RIS
LLMs have been shown to excel in tasks such as text generation and summarization, but their application in sensitive fields such as mental health requires careful consideration of factors such as ethical concerns, privacy, and model explainability.
As generative AI becomes increasingly integrated into various tools and applications, its presence in our everyday lives grows.
JMIR Res Protoc 2025;14:e62865
Download Citation: END BibTex RIS
A crucial determinant for successfully implementing the human-AI collaboration approach is decision transparency [32,33], which is often referred to as explainability. Explainability is the concept that an ML model’s prediction can be explained in a way that human operators can comprehend and reconstruct the model’s reasoning [33].
JMIR Hum Factors 2024;11:e53378
Download Citation: END BibTex RIS
The Role of Artificial Intelligence Model Documentation in Translational Science: Scoping Review
Guidance for ethics and explainability is expected to meet the needs of a broad range of stakeholders, but what constitutes AI ethics and explainability best practices, who determines them, how principles are applied and regulated in practice, and how it is documented still needs to be defined [13,21,22,24,25,42].
Interact J Med Res 2023;12:e45903
Download Citation: END BibTex RIS
Nevertheless, explainability; transparency; and, most importantly, accountability and responsibility do not receive due consideration, in part because it remains difficult to transform these necessary concepts (eg, trust) into actual computational tools or metrics. Understanding why and how a particular model produced the observed predictions is of paramount importance, especially in health care applications.
J Med Internet Res 2023;25:e43838
Download Citation: END BibTex RIS
SHAP tool (version 0.40.0) was used to assess the explainability the model; that is, to identify factors protecting against chronic stress.
In addition to the performance evaluation, this study maximizes the interpretability of the underlying models. It focuses particularly on the explainability of the model, which can serve as an indispensable tool in the era of precision medicine.
JMIR AI 2023;2:e41868
Download Citation: END BibTex RIS