将社会和生物因素与健康结果及公平性联系起来的数字路径。

Digital pathways connecting social and biological factors to health outcomes and equity.

作者信息

Cui Yan

机构信息

Department of Genetics, Genomics and Informatics, University of Tennessee Health Science Center, Memphis, TN, 38163, USA.

Center for Integrative and Translational Genomics, University of Tennessee Health Science Center, Memphis, TN, 38163, USA.

出版信息

NPJ Digit Med. 2025 Mar 20;8(1):172. doi: 10.1038/s41746-025-01564-8.

DOI:10.1038/s41746-025-01564-8

PMID:40113922

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11926183/

Abstract

Digital pathways extend conventional connections between social and biological factors and health outcomes, significantly influencing health equity. Data representation bias and distribution shifts are key mechanisms through which determinants of health impact generalizability of artificial intelligence (AI) models and subsequently affect health outcomes and equity. These mechanisms provide critical targets for algorithmic interventions, which can lead to Pareto improvements in AI model performance across diverse populations, thereby mitigating health disparities.

摘要

数字路径扩展了社会和生物因素与健康结果之间的传统联系，对健康公平性产生重大影响。数据表征偏差和分布变化是健康决定因素影响人工智能（AI）模型通用性并进而影响健康结果和公平性的关键机制。这些机制为算法干预提供了关键目标，算法干预可带来不同人群间人工智能模型性能的帕累托改进，从而减轻健康差距。