Abstract

Hospital readmissions within 30 days remain a major quality and cost burden in the United States, costing Medicare more than $26 billion annually and triggering financial penalties under the Centers for Medicare & Medicaid Services Hospital Readmissions Reduction Program (HRRP). Traditional risk-adjustment models insufficiently account for social determinants of health (SDOH), potentially reinforcing inequities. This study developed an interpretable machine learning framework using 4.8 million Medicare fee-for-service discharges (2019–2022), linked with socioeconomic indicators, to predict 30-day all-cause readmissions and assess disparities. Five models were compared, with XGBoost incorporating SDOH achieving the highest performance (AUC = 0.871), outperforming both clinical-only models and the LACE+ baseline. Inclusion of SDOH variablessuch as area-level poverty, dual eligibility, and deprivation index improved predictive accuracy (ΔAUC = 0.024). SHAP analysis identified prior hospitalizations, length of stay, and comorbidity burden as the strongest predictors. However, lower model performance for Black and Hispanic patients and higher readmission rates in safety-net hospitals highlight persistent racial and socioeconomic disparities. These findings support integrating SDOH into equity-aware risk adjustment frameworks to improve fairness and policy effectiveness under HRRP.

References

• Jencks SF, Williams MV, Coleman EA. Rehospitalizations among patients in the Medicare fee-for-service program. New England Journal of Medicine. 2009;360(14):1418–1428. doi:10.1056/NEJMsa0803563
• Wadhera RK, Joynt Maddox KE, Wasfy JH, et al. Association of the Hospital Readmissions Reduction Program with mortality among Medicare beneficiaries hospitalized for heart failure, acute myocardial infarction, and pneumonia. JAMA. 2018;320(24):2542–2552. doi:10.1001/jama.2018.19232
• Lindenauer PK, Bernheim SM, Grady JN, et al. The performance of US hospitals as reflected in risk-standardized 30-day mortality and readmission rates for Medicare beneficiaries with pneumonia. Journal of Hospital Medicine. 2018;25(4):234–249. doi:10.1001/jama.2018.12306
• Khera R, Krumholz HM. With great power comes great responsibility: Big data research from the National Inpatient Sample. Circulation: Cardiovascular Quality and Outcomes. 2018;11(7):e005019. doi:10.1161/CIRCOUTCOMES.118.005019
• Frizzell JD, Liang L, Schulte PJ, et al. Prediction of 30-day all-cause readmissions in patients hospitalized for heart failure. JAMA Cardiology. 2017;2(2):204–209. doi:10.1001/jamacardio.2016.3956
• van Walraven C, Dhalla IA, Bell C, et al. Derivation and validation of an index to predict early death or unplanned readmission after discharge from hospital to the community. CMAJ. 2010;182(6):551–557. doi:10.1503/cmaj.091117
• Shameer K, Johnson KW, Glicksberg BS, Dudley JT, Sengupta PP. Machine learning in cardiovascular medicine: are we there yet? Heart. 2017;104(14):1156–1164. doi:10.1038/npjdigitalmed.2017.28
• Rajpurkar P, Chen E, Banerjee O, Topol EJ. AI in health and medicine. Nature Medicine. 2022;28(1):31–38. doi:10.1038/s41591-021-01614-0
• Lundberg SM, Lee SI. A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems. 2017;30. doi:10.5555/3295222.3295230
• Obermeyer Z, Powers B, Vogeli C, Mullainathan S. Dissecting racial bias in an algorithm used to manage the health of populations. Science. 2019;366(6464):447–453. doi:10.1126/science.aax2342
• Chen IY, Johansson FD, Sontag D. Why is my classifier discriminatory? Advances in Neural Information Processing Systems. 2019;31. doi:10.1186/s12916-019-1366-2
• Bernheim SM, Grady JN, Lucas L, et al. Race and ethnicity differences in characteristics of Medicare beneficiaries and readmissions. Medical Care. 2016;54(12):1023–1032. doi:10.1097/MLR.0000000000000507
• Ndugga N, Bhatt J. Health equity data and the social determinants of health. New England Journal of Medicine. 2021;384(3):211–219. doi:10.1056/NEJMp2031564
• Leppin AL, Gionfriddo MR, Kessler M, et al. Preventing 30-day hospital readmissions: A systematic review and meta-analysis of randomized trials. JAMA Internal Medicine. 2014;174(7):1095–1107. doi:10.1001/jamainternmed.2014.1608
• Vest JR, Gamm LD, Oxford BA, Gonzalez MI, Slawson KM. Determinants of preventable readmissions in the United States: A systematic review. Implementation Science. 2011;6:88. doi:10.1186/1748-5908-6-88
• Herrin J, St Andre J, Kenward K, Joshi MS, Audet AM, Hines SC. Community factors and hospital readmission rates. Health Services Research. 2015;50(1):20–39. doi:10.1111/1475-6773.12177
• Bhatt DL, Bhatt BK. New strategies to reduce 30-day readmissions in patients with heart failure. JAMA Cardiology. 2020;5(12):1399–1400. doi:10.1001/jamacardio.2020.4251
• Voss R, Gardner R, Baier R, Butterfield K, Lehrman S, Gravenstein S. The care transitions intervention: Translating from efficacy to effectiveness. Archives of Internal Medicine. 2011;171(14):1232–1237. doi:10.1001/archinternmed.2011.278
• Finlay GD, Rothman MJ, Smith RA. Measuring the modified early warning score and the Rothman Index: Advantages of utilizing the electronic medical record in an early warning system. Journal of Hospital Medicine. 2019;9(2):116–119. doi:10.1002/jhm.2019.9.issue-2
• Austin PC, Rothwell DM, Tu JV. A comparison of statistical modeling strategies for analyzing length of stay after CABG surgery. Health Services and Outcomes Research Methodology. 2010;2(2):107–133. doi:10.1023/A:1020823529282
• Rosen AK, Chen Q, Shin MH, et al. Use of the Elixhauser comorbidity index for risk adjustment of health outcomes. Medical Care. 2021;59(11):e96–e105. doi:10.1097/MLR.0000000000001633
• National Academies of Sciences, Engineering, and Medicine (NASEM). Integrating Social Care into the Delivery of Health Care: Moving Upstream to Improve the Nation's Health. Washington, DC: National Academies Press; 2020. doi:10.17226/25467
• Wager S, Hastie T, Efron B. Confidence intervals for random forests: The jackknife and the infinitesimal jackknife. Journal of Machine Learning Research. 2014;15(1):1625–1651.
• Chen T, Guestrin C. XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016:785–794. doi:10.1145/2939672.2939785
• Rubin DB. Multiple Imputation for Nonresponse in Surveys. New York: Wiley; 1987. doi:10.1002/9780470316696
• Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research. 2002;16:321–357. doi:10.1613/jair.953
• Elixhauser A, Steiner C, Harris DR, Coffey RM. Comorbidity measures for use with administrative data. Medical Care. 1998;36(1):8–27. doi:10.1097/00005650-199801000-00004
• Singh GK, Siahpush M. Increasing rural-urban gradients in US suicide mortality and the accompanying polarization of socioeconomic characteristics, 1996–2020. International Journal of Epidemiology. 2021;50(5):1452–1465. doi:10.1093/ije/dyab012
• Krumholz HM, Lin Z, Drye EE, et al. An administrative claims measure suitable for profiling hospital performance on the basis of 30-day all-cause readmission rates among patients with acute myocardial infarction. Circulation: Cardiovascular Quality and Outcomes. 2011;4(2):243–252. doi:10.1161/CIRCOUTCOMES.110.957498
• Charlson ME, Pompei P, Ales KL, MacKenzie CR. A new method of classifying prognostic comorbidity in longitudinal studies: Development and validation. Journal of Chronic Diseases. 1987;40(5):373–383. doi:10.1016/0021-9681(87)90171-8
• Durfey SNM, Kind AJH, Buckingham WR, DuGoff EH, Trivedi AN. Neighborhood disadvantage and chronic disease management. Health Services Research. 2019;54(S1):206–216. doi:10.1111/1475-6773.13092
• Goff SL, Mazor KM, Ting HH, Kleppel R, Rothberg MB. How cardiologists present the benefits of percutaneous coronary interventions to patients with stable angina. JAMA Internal Medicine. 2019;174(10):1614–1621. doi:10.1001/jamainternmed.2014.1897
• Goodfellow I, Bengio Y, Courville A. Deep Learning. Cambridge, MA: MIT Press; 2016. ISBN: 9780262035613
• Hardt M, Price E, Srebro N. Equality of opportunity in supervised learning. Advances in Neural Information Processing Systems. 2016;29.
• Chouldechova A. Fair prediction with disparate impact: A study of bias in recidivism prediction instruments. Big Data. 2017;5(2):153–163. doi:10.1089/big.2016.0047
• Kind AJH, Buckingham WR. Making neighborhood-disadvantage metrics accessible: The neighborhood atlas. New England Journal of Medicine. 2018;378(26):2456–2458. doi:10.1056/NEJMp1802313
• Lipsitz SR, Leong T, Ibrahim J, Lipshultz S. A partial correlation coefficient for survival data. Statistics in Medicine. 2001;20(6):851–857. doi:10.1002/sim.687
• Amarasingham R, Moore BJ, Tabak YP, et al. An automated model to identify heart failure patients at risk for 30-day readmission or death using electronic medical record data. Medical Care. 2010;48(11):981–988. doi:10.1097/MLR.0b013e3181ef60d9
• Kansagara D, Englander H, Salanitro A, et al. Risk prediction models for hospital readmission: A systematic review. JAMA. 2011;306(15):1688–1698. doi:10.1001/jama.2011.1515
• Horwitz LI, Partovian C, Lin Z, et al. Hospital-wide all-cause unplanned readmission measure. Technical Report, Yale University-Yale New Haven Hospital Center for Outcomes Research and Evaluation; 2012.
• Tibshirani R. Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society: Series B. 1996;58(1):267–288. doi:10.1111/j.2517-6161.1996.tb02080.x
• Bates DM, Maechler M, Bolker BM, Walker SC. Fitting linear mixed-effects models using lme4. Journal of Statistical Software. 2015;67(1):1–48. doi:10.18637/jss.v067.i01
• Rabe-Hesketh S, Skrondal A. Multilevel and Longitudinal Modeling Using Stata. 3rd ed. College Station, TX: Stata Press; 2012.
• Saito T, Rehmsmeier M. The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLOS ONE. 2015;10(3):e0118432. doi:10.1371/journal.pone.0118432
• Guo C, Pleiss G, Sun Y, Weinberger KQ. On calibration of modern neural networks. Proceedings of the 34th International Conference on Machine Learning. 2017;70:1321–1330.
• Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research. 2011;12:2825–2830.
• DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: A nonparametric approach. Biometrics. 1988;44(3):837–845. doi:10.2307/2531595
• Berwick DM, Nolan TW, Whittington J. The triple aim: Care, health, and cost. Health Affairs. 2008;27(3):759–769. doi:10.1377/hlthaff.27.3.759
• Steyerberg EW, Vickers AJ, Cook NR, et al. Assessing the performance of prediction models: A framework for traditional and novel measures. Epidemiology. 2010;21(1):128–138. doi:10.1097/EDE.0b013e3181c30fb2
• Collins GS, Reitsma JB, Altman DG, Moons KG. Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD): The TRIPOD statement. Annals of Internal Medicine. 2015;162(1):55–63. doi:10.7326/M14-0697
• Ekine, E. U., Onyekwuluje, T. P., &Uwaezuoke, E. C. (2024). Analysis of a Microcontroller using ML Algorithms for Two-Way Digital Telemetry. International Journal of Modern Science and Research Technology, 2(7).
• Alozie, C. E., Umeanozie, C. P., Onyekwuleje, T. P., & Ekine, E. U. (2026). Compliance Challenges in AI-Driven IT Infrastructure: A Framework for Mitigation and Governance. International Journal of Computer Applications, 187(78).