This Project Grant from the National Institute for Minority Health and Health Disparities, part of the Department of Health and Human Services National Institutes of Health, provides $769,755 to develop an unbiased machine learning tool for the prediction of acute coronary syndrome. The tool aims to minimize bias in predictions between patient demographic groups, as measured by equal opportunity difference and the Zemel statistic, to ensure machine learning algorithms do not exacerbate existing health inequities. Specifically, Dascena, Inc. will develop an algorithm for early acute coronary syndrome prediction through aim one and compare its performance to commonly used risk stratification scores through aim two. The algorithm will be evaluated for accuracy and bias when predicting outcomes for white versus non-white and male versus female emergency department patients. This work supports the goals of the Minority Health and Health Disparities Research program to reduce health disparities through research, information dissemination, and community outreach.
Generated 1/6/24, 1:53 PM