Preprint
Balancing Fairness and Performance in Healthcare AI: A Gradient Reconciliation Approach
arXiv.org
19 Apr 2025
Abstract
The rapid growth of healthcare data and advances in computational power have accelerated the adoption of artificial intelligence (AI) in medicine. However, AI systems deployed without explicit fairness considerations risk exacerbating existing healthcare disparities, potentially leading to inequitable resource allocation and diagnostic disparities across demographic subgroups. To address this challenge, we propose FairGrad, a novel gradient reconciliation framework that automatically balances predictive performance and multi-attribute fairness optimization in healthcare AI models. Our method resolves conflicting optimization objectives by projecting each gradient vector onto the orthogonal plane of the others, thereby regularizing the optimization trajectory to ensure equitable consideration of all objectives. Evaluated on diverse real-world healthcare datasets and predictive tasks - including Substance Use Disorder (SUD) treatment and sepsis mortality - FairGrad achieved statistically significant improvements in multi-attribute fairness metrics (e.g., equalized odds) while maintaining competitive predictive accuracy. These results demonstrate the viability of harmonizing fairness and utility in mission-critical medical AI applications.
Metrics
8 Record Views
Details
- Title
- Balancing Fairness and Performance in Healthcare AI: A Gradient Reconciliation Approach
- Creators
- Xiaoyang Wang - Drexel UniversityChristopher C Yang - Drexel University
- Publication Details
- arXiv.org
- Number of pages
- 10
- Resource Type
- Preprint
- Language
- English
- Academic Unit
- Information Science; School of Computer and Information Sciences
- Other Identifier
- 991022048223204721