提出梯度重整方法，让医疗AI同时提升公平性与预测准确率。
Balancing Fairness and Performance in Healthcare AI: A Gradient Reconciliation Approach
- 通过梯度正交投影，自动调和预测性能与多维度公平性的冲突
- 在药物滥用治疗和败血症死亡预测任务中，公平性指标显著提升
- 适合关注医疗AI公平性、需兼顾诊断准确性的人群
医疗数据激增与算力进步加速了人工智能在医学领域的应用。然而，缺乏显式公平性考量的AI系统可能加剧现有医疗不平等，导致资源分配与诊断结果在不同人口群体间出现差异。为此，我们提出FairGrad——一种新型梯度重整框架，可自动平衡医疗AI模型的预测性能与多属性公平性优化。该方法通过将每个梯度向量投影到其他梯度的正交平面，规整优化轨迹，确保所有目标得到均衡考虑。在涵盖物质使用障碍（SUD）治疗与败血症死亡率预测等真实世界医疗数据集上的评估显示，FairGrad在多属性公平性指标（如等校正机会）上实现统计显著提升，同时保持竞争性预测精度。结果表明，在关键医疗AI应用中实现公平性与效用的协同优化具有可行性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。