Measuring and Reducing Racial Bias in a Pediatric Urinary Tract Infection Model.

Autor:	Anderson JW; Intelligent Systems Program, University of Pittsburgh, Pittsburgh, PA., Shaikh N; Department of Pediatrics, University of Pittsburgh, Pittsburgh, PA., Visweswaran S; Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA.
Jazyk:	angličtina
Zdroj:	AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science [AMIA Jt Summits Transl Sci Proc] 2024 May 31; Vol. 2024, pp. 488-497. Date of Electronic Publication: 2024 May 31 (Print Publication: 2024).
Abstrakt:	Clinical predictive models that include race as a predictor have the potential to exacerbate disparities in healthcare. Such models can be respecified to exclude race or optimized to reduce racial bias. We investigated the impact of such respecifications in a predictive model - UTICalc - which was designed to reduce catheterizations in young children with suspected urinary tract infections. To reduce racial bias, race was removed from the UTICalc logistic regression model and replaced with two new features. We compared the two versions of UTICalc using fairness and predictive performance metrics to understand the effects on racial bias. In addition, we derived three new models for UTICalc to specifically improve racial fairness. Our results show that, as predicted by previously described impossibility results, fairness cannot be simultaneously improved on all fairness metrics, and model respecification may improve racial fairness but decrease overall predictive performance. (©2024 AMIA - All rights reserved.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu