Gary E Weissman1, Stephanie Teeple2, Nwamaka D Eneanya3, Rebecca A Hubbard4, Shreya Kangovi5. 1. Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA; Palliative and Advanced Illness Research (PAIR) Center, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA; Leonard Davis Institute for Health Economics, University of Pennsylvania, Philadelphia, Pennsylvania, USA. Electronic address: Gary.weissman@pennmedicine.upenn.edu. 2. Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA; Department of Biostatistics, Epidemiology, & Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA. 3. Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA; Palliative and Advanced Illness Research (PAIR) Center, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA; Leonard Davis Institute for Health Economics, University of Pennsylvania, Philadelphia, Pennsylvania, USA; Department of Biostatistics, Epidemiology, & Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA. 4. Department of Biostatistics, Epidemiology, & Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA. 5. Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA; Leonard Davis Institute for Health Economics, University of Pennsylvania, Philadelphia, Pennsylvania, USA; Penn Center for Community Health Workers, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
Abstract
BACKGROUND: Socioeconomic data may improve predictions of clinical events. However, owing 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. METHODS AND RESULTS: We conducted a retrospective cohort study of 1316 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. The baseline model had moderate performance overall (BS 0.13, 95% CI 0.13-0.14), and among White (BS 0.12, 95% CI 0.12-0.13) and non-White (BS 0.13, 95% CI 0.13-0.14) patients. Neither performance nor algorithmic equity were significantly changed with the addition of the ADI. CONCLUSIONS: The inclusion of neighborhood-level data may not reliably improve performance or algorithmic equity.
BACKGROUND: Socioeconomic data may improve predictions of clinical events. However, owing 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. METHODS AND RESULTS: We conducted a retrospective cohort study of 1316 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. The baseline model had moderate performance overall (BS 0.13, 95% CI 0.13-0.14), and among White (BS 0.12, 95% CI 0.12-0.13) and non-White (BS 0.13, 95% CI 0.13-0.14) patients. Neither performance nor algorithmic equity were significantly changed with the addition of the ADI. CONCLUSIONS: The inclusion of neighborhood-level data may not reliably improve performance or algorithmic equity.
Authors: Alvin Rajkomar; Michaela Hardt; Michael D Howell; Greg Corrado; Marshall H Chin Journal: Ann Intern Med Date: 2018-12-04 Impact factor: 25.391
Authors: Amy J H Kind; Steve Jencks; Jane Brock; Menggang Yu; Christie Bartels; William Ehlenbach; Caprice Greenberg; Maureen Smith Journal: Ann Intern Med Date: 2014-12-02 Impact factor: 25.391
Authors: Donald M Lloyd-Jones; Peter W F Wilson; Martin G Larson; Alexa Beiser; Eric P Leip; Ralph B D'Agostino; Daniel Levy Journal: Am J Cardiol Date: 2004-07-01 Impact factor: 2.778
Authors: Agostina J Larrazabal; Nicolás Nieto; Victoria Peterson; Diego H Milone; Enzo Ferrante Journal: Proc Natl Acad Sci U S A Date: 2020-05-26 Impact factor: 11.205
Authors: Jacob A Martin; Andrew Crane-Droesch; Folasade C Lapite; Joseph C Puhl; Tyler E Kmiec; Jasmine A Silvestri; Lyle H Ungar; Bruce P Kinosian; Blanca E Himes; Rebecca A Hubbard; Joshua M Diamond; Vivek Ahya; Michael W Sims; Scott D Halpern; Gary E Weissman Journal: J Am Med Inform Assoc Date: 2021-12-28 Impact factor: 4.497