e.g. mhealth
Search Results (1 to 7 of 7 Results)
Download search results: CSV END BibTex RIS
Skip search results from other journals and go to results- 3 Journal of Medical Internet Research
- 2 JMIR Medical Informatics
- 1 JMIR AI
- 1 JMIR Formative Research
- 0 Medicine 2.0
- 0 Interactive Journal of Medical Research
- 0 iProceedings
- 0 JMIR Research Protocols
- 0 JMIR Human Factors
- 0 JMIR Public Health and Surveillance
- 0 JMIR mHealth and uHealth
- 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 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)
Survival After Radical Cystectomy for Bladder Cancer: Development of a Fair Machine Learning Model
In-processing techniques incorporate fairness constraints within the model training process. These techniques aim to steer the model toward producing fair predictions. One such example is the exponentiated gradient method, which implements a reduction approach. In reduction approaches, the model is treated as a black box optimizer. The algorithm iteratively reweights the training data points based on the current model’s predictions and a chosen fairness metric.
JMIR Med Inform 2024;12:e63289
Download Citation: END BibTex RIS
Increasing the size of the tree can enhance the NPT’s expressivity; however, a larger tree leads to a more complex decision-making process, which reduces the classifier’s interpretability and can impact its performance and fairness. Investigating the relationship between interpretability, performance, and fairness will provide the basis for future studies to better align these 3 dimensions within the NPT classifier for CXR pathology detection.
JMIR Form Res 2024;8:e59045
Download Citation: END BibTex RIS
However, the development process of health AI and the generalization and fairness of the resulting models face significant challenges due to the inherent biases, uncertainty, variability, and quality levels of real-world data (RWD). These challenges include variable information across different settings and over time, biases affecting underrepresented groups, uncertainty from lacking or overlapping information, or data quality (DQ) issues such as incomplete or implausible information.
J Med Internet Res 2024;26:e50295
Download Citation: END BibTex RIS
Thus, the Ethics and Equity Workgroup (EEWG) was formed within the AIM-AHEAD Consortium to ensure that ethics and fairness are at the forefront of AI and ML applications to build equity in biomedical research, education, and health care. Activities within the workgroup have included deliberations and discussions to develop and reach consensus on actionable guiding principles, a glossary of key terms, and other engagement tools to encourage greater attention to ethics and equity in AI and ML development.
JMIR AI 2023;2:e52888
Download Citation: END BibTex RIS
The definition of fairness in ML is 2-fold: statistical notions of fairness and individual notions of fairness [13]. Statistical definitions of fairness refer to a guarantee of parity across protected demographic groups based on statistical measures, whereas individual definitions of fairness require equal treatment for individuals with similar features [13,14].
J Med Internet Res 2023;25:e46547
Download Citation: END BibTex RIS
Sharing Data With Shared Benefits: Artificial Intelligence Perspective
From an economic perspective, fairness could be defined as receiving a return commensurate with the investments made. Therefore, when it comes to AI, it would be desirable for organizations to obtain AI models that perform proportionally to the amount of cost they incur. Generally, the process of data collection, preparation, and analysis is not a trivial one [20,21].
J Med Internet Res 2023;25:e47540
Download Citation: END BibTex RIS
Evaluation and Mitigation of Racial Bias in Clinical Machine Learning Models: Scoping Review
Fairness in ML is achieved when algorithmic decision-making does not favor an individual or group based on protected attributes. Research efforts have emphasized group fairness over individual fairness, given the need for algorithms that consider existing differences between populations—whether intrinsic or extrinsic—while preventing discrimination between groups [13,21]. Crucially, improving model fairness does not necessarily require compromising accuracy overall [22].
JMIR Med Inform 2022;10(5):e36388
Download Citation: END BibTex RIS