Effects of neighborhood-level data on performance and algorithmic equity of a model that predicts 30-day heart failure readmissions at an urban academic medical center.

Abstract

BACKGROUND\nSocioeconomic data may improve predictions of clinical events. However, due to structural racism, algorithms may not perform equitably across racial subgroups. Therefore, we sought to compare the predictive performance overall, and by racial subgroup, of commonly used predictor variables for heart failure readmission with and without the Area Deprivation Index (ADI), a neighborhood-level socioeconomic measure.\n\n\nMETHODS\nWe conducted a retrospective cohort study of 1,316 Philadelphia residents discharged with a primary diagnosis of congestive heart failure from the University of Pennsylvania Health System between April 1, 2015 and March 31, 2017. We trained a regression model to predict the probability of a 30-day readmission using clinical and demographic variables. A second model also included the ADI as a predictor variable. We measured predictive performance with the Brier Score (BS) in a held-out test set.\n\n\nRESULTS\nThe baseline model had moderate performance overall (BS 0.13, 95% CI 0.13 to 0.14), and among white (BS 0.12, 95% CI 0.12 to 0.13) and non-white (BS 0.13, 95% CI 0.13 to 0.14) patients. Neither performance nor algorithmic equity were significantly changed with the addition of the ADI.\n\n\nCONCLUSIONS\nThe inclusion of neighborhood-level data may not reliably improve performance or algorithmic equity.