Examines age bias in machine learning applications, suggesting a framework for improvement in healthcare outcomes.
Key Points
The central aim is to investigate the existence of age bias in machine learning systems and to evaluate the effectiveness of bias mitigation strategies.
Utilized the AI Fairness 360 framework
Analyzed machine learning algorithms in healthcare applications
Investigated the effects of age bias during patient treatment evaluations
Compared bias mitigation strategies
Identified significant age bias within existing machine learning models
Demonstrated that the AI Fairness 360 framework can effectively mitigate age bias
Improved fairness in patient treatment predictions after implementing bias mitigation strategies
Cite This Study
Maclean-Milner et al. (2026) studied this question.