Emerging algorithmic bias: fairness drift as the next dimension of model maintenance and sustainability.

IF 4.7 2区 医学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS Journal of the American Medical Informatics Association Pub Date : 2025-03-13 DOI:10.1093/jamia/ocaf039
Sharon E Davis, Chad Dorn, Daniel J Park, Michael E Matheny
{"title":"Emerging algorithmic bias: fairness drift as the next dimension of model maintenance and sustainability.","authors":"Sharon E Davis, Chad Dorn, Daniel J Park, Michael E Matheny","doi":"10.1093/jamia/ocaf039","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>While performance drift of clinical prediction models is well-documented, the potential for algorithmic biases to emerge post-deployment has had limited characterization. A better understanding of how temporal model performance may shift across subpopulations is required to incorporate fairness drift into model maintenance strategies.</p><p><strong>Materials and methods: </strong>We explore fairness drift in a national population over 11 years, with and without model maintenance aimed at sustaining population-level performance. We trained random forest models predicting 30-day post-surgical readmission, mortality, and pneumonia using 2013 data from US Department of Veterans Affairs facilities. We evaluated performance quarterly from 2014 to 2023 by self-reported race and sex. We estimated discrimination, calibration, and accuracy, and operationalized fairness using metric parity measured as the gap between disadvantaged and advantaged groups.</p><p><strong>Results: </strong>Our cohort included 1 739 666 surgical cases. We observed fairness drift in both the original and temporally updated models. Model updating had a larger impact on overall performance than fairness gaps. During periods of stable fairness, updating models at the population level increased, decreased, or did not impact fairness gaps. During periods of fairness drift, updating models restored fairness in some cases and exacerbated fairness gaps in others.</p><p><strong>Discussion: </strong>This exploratory study highlights that algorithmic fairness cannot be assured through one-time assessments during model development. Temporal changes in fairness may take multiple forms and interact with model updating strategies in unanticipated ways.</p><p><strong>Conclusion: </strong>Equitable and sustainable clinical artificial intelligence deployments will require novel methods to monitor algorithmic fairness, detect emerging bias, and adopt model updates that promote fairness.</p>","PeriodicalId":50016,"journal":{"name":"Journal of the American Medical Informatics Association","volume":" ","pages":""},"PeriodicalIF":4.7000,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of the American Medical Informatics Association","FirstCategoryId":"91","ListUrlMain":"https://doi.org/10.1093/jamia/ocaf039","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

Abstract

Objectives: While performance drift of clinical prediction models is well-documented, the potential for algorithmic biases to emerge post-deployment has had limited characterization. A better understanding of how temporal model performance may shift across subpopulations is required to incorporate fairness drift into model maintenance strategies.

Materials and methods: We explore fairness drift in a national population over 11 years, with and without model maintenance aimed at sustaining population-level performance. We trained random forest models predicting 30-day post-surgical readmission, mortality, and pneumonia using 2013 data from US Department of Veterans Affairs facilities. We evaluated performance quarterly from 2014 to 2023 by self-reported race and sex. We estimated discrimination, calibration, and accuracy, and operationalized fairness using metric parity measured as the gap between disadvantaged and advantaged groups.

Results: Our cohort included 1 739 666 surgical cases. We observed fairness drift in both the original and temporally updated models. Model updating had a larger impact on overall performance than fairness gaps. During periods of stable fairness, updating models at the population level increased, decreased, or did not impact fairness gaps. During periods of fairness drift, updating models restored fairness in some cases and exacerbated fairness gaps in others.

Discussion: This exploratory study highlights that algorithmic fairness cannot be assured through one-time assessments during model development. Temporal changes in fairness may take multiple forms and interact with model updating strategies in unanticipated ways.

Conclusion: Equitable and sustainable clinical artificial intelligence deployments will require novel methods to monitor algorithmic fairness, detect emerging bias, and adopt model updates that promote fairness.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
求助全文
约1分钟内获得全文 去求助
来源期刊
Journal of the American Medical Informatics Association
Journal of the American Medical Informatics Association 医学-计算机:跨学科应用
CiteScore
14.50
自引率
7.80%
发文量
230
审稿时长
3-8 weeks
期刊介绍: JAMIA is AMIA''s premier peer-reviewed journal for biomedical and health informatics. Covering the full spectrum of activities in the field, JAMIA includes informatics articles in the areas of clinical care, clinical research, translational science, implementation science, imaging, education, consumer health, public health, and policy. JAMIA''s articles describe innovative informatics research and systems that help to advance biomedical science and to promote health. Case reports, perspectives and reviews also help readers stay connected with the most important informatics developments in implementation, policy and education.
期刊最新文献
Patient and clinician acceptability of automated extraction of social drivers of health from clinical notes in primary care. Unmet social needs and diverticulitis: a phenotyping algorithm and cross-sectional analysis. A call for the informatics community to define priority practice and research areas at the intersection of climate and health: report from 2023 mini-summit. Emerging algorithmic bias: fairness drift as the next dimension of model maintenance and sustainability. Optimizing the efficiency and effectiveness of data quality assurance in a multicenter clinical dataset.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1