e.g. mhealth
Search Results (1 to 10 of 53 Results)
Download search results: CSV END BibTex RIS
Skip search results from other journals and go to results- 18 Journal of Medical Internet Research
- 8 JMIR Medical Informatics
- 5 JMIR Medical Education
- 5 JMIR Public Health and Surveillance
- 4 JMIR Formative Research
- 4 JMIR Research Protocols
- 2 JMIR AI
- 2 JMIR Aging
- 1 JMIR Biomedical Engineering
- 1 JMIR Dermatology
- 1 JMIR Mental Health
- 1 JMIR mHealth and uHealth
- 1 Online Journal of Public Health Informatics
- 0 Medicine 2.0
- 0 Interactive Journal of Medical Research
- 0 iProceedings
- 0 JMIR Human Factors
- 0 JMIR Serious Games
- 0 JMIR Rehabilitation and Assistive Technologies
- 0 JMIR Preprints
- 0 JMIR Bioinformatics and Biotechnology
- 0 JMIR Cancer
- 0 JMIR Challenges
- 0 JMIR Diabetes
- 0 JMIR Data
- 0 JMIR Cardio
- 0 Journal of Participatory Medicine
- 0 JMIR Pediatrics and Parenting
- 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 JMIR XR and Spatial Computing (JMXR)
Artificial Intelligence (AI) and Emergency Medicine: Balancing Opportunities and Challenges
This paper presents the current applications of AI in emergency medicine, emphasizing both real-world implementations and critical challenges, such as hallucination, bias, and interpretability.
AI systems, particularly deep learning networks, can be used to identify patterns in large, complex datasets, significantly contributing to medical science by analyzing variables to reliably predict outcomes [12,13].
JMIR Med Inform 2025;13:e70903
Download Citation: END BibTex RIS
The findings of the present study describe instances where bias is introduced over the EHR data lifecycle, ways in which stakeholders work to mitigate biases, and their recommendations for structural interventions to mitigate bias (Table 1). Table 1 depicts the perspectives of three key stakeholders who are associated with EHR data collection, curation, or management and usage.
J Med Internet Res 2025;27:e71388
Download Citation: END BibTex RIS
Termed “algorithmic bias,” this can cause minority groups to experience unfairness or undue harm. Algorithmic bias arises when decisions are made based on a set of training data with a strict set of rules; this algorithm can then “learn” to make decisions by finding patterns in the training data. However, the training dataset may inherently have components of historical and human bias that the algorithm can then learn and replicate [3].
JMIR AI 2025;4:e56891
Download Citation: END BibTex RIS
To avoid or at least reduce potential bias and move toward fair AI, this bias first needs to be conceptualized, measured, and understood [22]. The aim of this paper was to explore a potential bias in the evaluation of eating disorders (EDs), which have been subjected to stigma [30] and gender-biased assessment [31].
Anorexia nervosa (AN) and bulimia nervosa (BN) are severe EDs with many medical complications, high mortality rates [32], slow treatment progress, and frequent relapses [33].
JMIR Ment Health 2025;12:e57986
Download Citation: END BibTex RIS
Algorithmic fairness is closely related to but theoretically distinct from algorithmic bias, another important consideration for assessing model performance. For further discussion of the subtle differences between these concepts, we refer the reader to the nuanced comparisons in [12,13]. We focus on algorithmic fairness in the current paper.
Online J Public Health Inform 2025;17:e66598
Download Citation: END BibTex RIS
As a result of researchers detecting bias with targeted questions, developers of LLMs have restricted users from asking questions that demonstrate ingrained bias in an obvious fashion like “Create a table to display 10 words associated with Caucasians and 10 with Blacks in terms of occupations and intelligence.” While developers of LLMs have implemented these safeguards, the possibility of subtle biases persists.
J Med Internet Res 2025;27:e57257
Download Citation: END BibTex RIS
Artificial Intelligence in Lymphoma Histopathology: Systematic Review
The risk of bias in the models of interest was assessed using the Prediction Model Risk of Bias Assessment Tool (PROBAST) [10]. The tool evaluates the likelihood that the reported results are distorted due to limitations in study design, conduct, and analysis. PROBAST includes 20 guiding questions categorized into 4 domains: Participants, Predictors, Outcomes, and Analysis.
J Med Internet Res 2025;27:e62851
Download Citation: END BibTex RIS
Bias Mitigation in Primary Health Care Artificial Intelligence Models: Scoping Review
All methods or strategies deployed to assess and mitigate bias toward diverse groups or protected attributes in AI models.
All mitigation methods or strategies deployed to promote and increase equity, diversity, and inclusion in CBPHC algorithms.
Methods or strategies deployed to assess and mitigate bias in the AI model itself (eg, biased prediction of treatment effects), rather than bias related to individuals’ characteristics or protected attributes.
J Med Internet Res 2025;27:e60269
Download Citation: END BibTex RIS
I provide facts and invite reconsideration of the paper’s treatment of consent and data safeguards (sharing, use, and commercialization) under the lens of potential bias and exploitation.
“Bias is any trend or deviation from the truth in data collection, data analysis, interpretation and publication which can cause false conclusions. Bias can occur either intentionally or unintentionally” [2].
J Med Internet Res 2024;26:e42144
Download Citation: END BibTex RIS
Survival After Radical Cystectomy for Bladder Cancer: Development of a Fair Machine Learning Model
However, there have been growing concerns about the potential for bias in ML models, as studies have demonstrated discrepancies in model performance among different population subgroups, which can lead to disparities in health care [4-6].
JMIR Med Inform 2024;12:e63289
Download Citation: END BibTex RIS