e.g. mhealth
Search Results (1 to 10 of 220 Results)
Download search results: CSV END BibTex RIS
Skip search results from other journals and go to results- 42 JMIR Medical Informatics
- 38 Journal of Medical Internet Research
- 27 JMIR Formative Research
- 12 JMIR AI
- 12 JMIR mHealth and uHealth
- 11 JMIR Public Health and Surveillance
- 10 JMIR Research Protocols
- 9 JMIR Aging
- 8 JMIRx Med
- 7 JMIR Dermatology
- 6 JMIR Cardio
- 6 JMIR Mental Health
- 5 JMIR Human Factors
- 4 JMIR Biomedical Engineering
- 4 JMIR Pediatrics and Parenting
- 3 JMIR Bioinformatics and Biotechnology
- 2 JMIR Cancer
- 2 JMIR Diabetes
- 2 JMIR Medical Education
- 2 JMIR Nursing
- 1 Asian/Pacific Island Nursing Journal
- 1 Interactive Journal of Medical Research
- 1 Iproceedings
- 1 JMIR Infodemiology
- 1 JMIR Perioperative Medicine
- 1 JMIR Rehabilitation and Assistive Technologies
- 1 Journal of Participatory Medicine
- 1 Online Journal of Public Health Informatics
- 0 Medicine 2.0
- 0 iProceedings
- 0 JMIR Serious Games
- 0 JMIR Preprints
- 0 JMIR Challenges
- 0 JMIR Data
- 0 JMIRx Bio
- 0 Transfer Hub (manuscript eXchange)
- 0 JMIR Neurotechnology
- 0 JMIR XR and Spatial Computing (JMXR)
The Right to Explanation in AI: In a Lonely Place
There are several types of explanations related to ADM; for example, some explanations are more technical and describe the mechanisms that an algorithm uses to generate an output. In a clinical context, explanations are often transmitted between clinicians and patients to ensure that patients have the information they need to understand their health and make informed decisions about it.
J Med Internet Res 2025;27:e64482
Download Citation: END BibTex RIS
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
Dermatology, in particular, poses a unique challenge due to the diversity of skin tones, which requires a varied dataset for effective algorithm training [38].
Moreover, this review has also underscored a remarkable deficiency in studies investigating the aspect of equity in AI applications. This observation highlights the necessity for more inclusive research focused on equity-related issues.
Interact J Med Res 2025;14:e56240
Download Citation: END BibTex RIS
Leveraging AI to Drive Timely Improvements in Patient Experience Feedback: Algorithm Validation
This study demonstrates the broader implementation and iteration of this algorithm in different hospital settings in England that use FFT to capture patient feedback.
The implementation of the FFT free-text algorithm demands thorough testing to ensure robustness, accuracy, and applicability.
JMIR Med Inform 2025;13:e60900
Download Citation: END BibTex RIS
Based on the predictive quality approach further described by Tercan et al [12] and Schmitt et al [13], this research aimed to identify a predictive model-based quality algorithm for clinical data, including RWD, and provide automated quality inspection. The goal of this paper is to demonstrate the varying quality of medical data in primary clinical source systems and to inform researchers about data reliability using machine learning techniques.
JMIR Med Inform 2025;13:e60204
Download Citation: END BibTex RIS
The platform’s “For You” tab was used, which curates content using Tik Tok’s in-house recommendation algorithm based on popular topics, user engagement, and relevance, to gather the sample of 1000 Tik Tok videos. This strategy was chosen to represent the kind of content that users are most likely to come across naturally.
J Med Internet Res 2025;27:e64225
Download Citation: END BibTex RIS
“Alert fatigue” is an important barrier when developing a telemonitoring algorithm [10]. In hypertension management, for example, it is known that health care providers, on average, only respond to around 60% of generated off-target blood pressure (BP) alerts [11]. To improve the efficiency of a telemonitoring program, technical improvements or algorithm enhancement, such as designing more sophisticated alerts or refining threshold values, can be initiated [12,13].
JMIR Med Inform 2025;13:e66066
Download Citation: END BibTex RIS
Minibatch gradient descent with the ADAM optimization algorithm was used with a weighted categorical cross-entropy loss (batch size=1×100 consecutive frames, learning rate 10−4, beta1=.9, beta2=.999, epsilon=10−8). To mitigate the effects of unbalanced category distributions, each frame’s error in the loss functions was weighted with the inverse probability of the target class occurrence.
JMIR Mhealth Uhealth 2025;13:e58078
Download Citation: END BibTex RIS
From the included studies, the following data elements were then extracted: study design; sample size; skin types included; length of study for each participant; location of study; materials used (such as types of allergen panels and imaging equipment); type of AI algorithm and its performance in the study; limitations and challenges of the study; and future directions.
JMIR Dermatol 2025;8:e67154
Download Citation: END BibTex RIS