arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.01906stat.MLcs.CYcs.LG
收藏

医疗保健中算法公平性的净效益、校准、阈值选择和训练目标

Net benefit, calibration, threshold selection, and training objectives for algorithmic fairness in healthcare

Stanford Center for Biomedical Informatics Research(斯坦福生物医学信息学研究中心);Stanford University(斯坦福大学)

Stephen R. Pfohl, Yizhe Xu, Agata Foryciarz, Nikolaos Ignatiadis, Julian Genkins, Nigam H. Shah

摘要:

越来越多的工作使用算法公平性的范式来构建技术的发展,以预测和主动缓解可能因使用模型指导决策而导致的健康不公平的引入或加剧。我们评估了模型性能,公平性和决策的预期效用之间的相互作用,为医疗保健预测模型的开发和评估算法公平性原则的可操作性提供了实用的建议。我们通过开发模型进行了一项经验性病例研究,以估计动脉粥样硬化性心血管疾病的十年风险,从而根据临床实践指南告知他汀类药物的启动。我们证明,将公平性考虑纳入模型训练目标的方法通常不会提高模型性能,也不会为任何研究的患者人群提供更大的净收益,而不是使用标准学习范式,然后选择与患者偏好一致的阈值,干预有效性的证据和模型校准。当测量结果不受患者人群之间差异测量误差的影响且阈值选择不受约束时,这些结果成立,无论模型性能指标是否存在差异,例如真阳性和假阳性错误率。最后,我们主张将模型开发工作的重点放在开发校准模型上,这些模型可以很好地预测所有患者人群的结果,同时强调这些努力是对透明报告,参与式设计和推理模型知情干预措施的影响的补充。

英文摘要:

A growing body of work uses the paradigm of algorithmic fairness to frame the development of techniques to anticipate and proactively mitigate the introduction or exacerbation of health inequities that may follow from the use of model-guided decision-making. We evaluate the interplay between measures of model performance, fairness, and the expected utility of decision-making to offer practical recommendations for the operationalization of algorithmic fairness principles for the development and evaluation of predictive models in healthcare. We conduct an empirical case-study via development of models to estimate the ten-year risk of atherosclerotic cardiovascular disease to inform statin initiation in accordance with clinical practice guidelines. We demonstrate that approaches that incorporate fairness considerations into the model training objective typically do not improve model performance or confer greater net benefit for any of the studied patient populations compared to the use of standard learning paradigms followed by threshold selection concordant with patient preferences, evidence of intervention effectiveness, and model calibration. These results hold when the measured outcomes are not subject to differential measurement error across patient populations and threshold selection is unconstrained, regardless of whether differences in model performance metrics, such as in true and false positive error rates, are present. In closing, we argue for focusing model development efforts on developing calibrated models that predict outcomes well for all patient populations while emphasizing that such efforts are complementary to transparent reporting, participatory design, and reasoning about the impact of model-informed interventions in context.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑