An Integrated Framework for Explainable, Fair, and Observable Hospital Readmission Prediction: Development and Validation on MIMIC-IV

Objective: To propose and retrospectively validate an integrated framework that simultaneously addresses three barriers to clinical translation of readmission prediction: lack of explainability, absence of deployment reliability infrastructure, and inadequate demographic fairness evaluation. Materials and Methods: A cohort of 415,231 adult admissions from the MIMIC-IV clinical database (30-day readmission prevalence 18.0%) was split chronologically 70/15/15. Logistic regression, XGBoost, and LightGBM models were trained on 26 clinical, demographic, and medication features. SHAP TreeExplainer provided per-patient feature attributions. Fairness was evaluated across 16 subgroups spanning race/ethnicity, age, gender, and insurance type using AUC-ROC, false negative rate (FNR), and positive predictive value (PPV). Calibration was assessed via Brier scores and calibration curves. A deployment-ready observability architecture was specified using Prometheus, Grafana, and Azure Kubernetes Service. Results: XGBoost achieved AUC-ROC 0.696 (95% CI: 0.691-0.701), outperforming or matching the LACE clinical baseline (AUC 0.60-0.68). LightGBM achieved the best calibration (Brier score 0.146). Prior admissions in the preceding 12 months were the dominant SHAP predictor (mean |phi| = 0.085). All 16 demographic subgroups met equity thresholds (ΔAUC ≤ 0.05, ΔFNR ≤ 0.10) without post-processing. Discussion: The framework jointly addresses explainability, fairness, and deployment reliability - requirements not previously integrated in published readmission prediction systems. Conclusion: This integrated framework delivers competitive discriminative performance, clinically actionable per-patient explanations, and strong demographic equity simultaneously. All code is publicly available at https://github.com/Tomisin92/readmission-prediction

hospital readmission, machine learning, explainable AI, health equity, clinical decision support

1. Centers for Medicare & Medicaid Services. (2023). National Health Expenditure Data. Retrieved from https://www.cms.gov/NationalHealthExpenditureData [Google Scholar] [Crossref]

2. Jencks, S. F., Williams, M. V., & Coleman, E. A. (2009). Rehospitalizations among patients in the Medicare fee-for-service program. New England Journal of Medicine, 360(14), 1418-1428. [Google Scholar] [Crossref]

3. Centers for Medicare & Medicaid Services. (2023). Hospital Readmissions Reduction Program. Retrieved from https://www.cms.gov/medicare/quality/value-based-programs/hrrp [Google Scholar] [Crossref]

4. Dharmarajan, K., Hsieh, A. F., Lin, Z., et al. (2013). Diagnoses and timing of 30-day readmissions after hospitalization for heart failure, acute myocardial infarction, or pneumonia. JAMA, 309(4), 355-363. [Google Scholar] [Crossref]

5. Desai, N. R., Ross, J. S., Kwon, J. Y., et al. (2016). Association between hospital penalty status under the hospital readmissions reduction program and readmission rates for target and nontarget conditions. JAMA, 316(24), 2647-2656. [Google Scholar] [Crossref]

6. Herrin, J., St Andre, J., Kenward, K., et al. (2015). Community factors and hospital readmission rates. Health Services Research, 50(1), 20-39. [Google Scholar] [Crossref]

7. Kansagara, D., Englander, H., Salanitro, A., et al. (2011). Risk prediction models for hospital readmission: a systematic review. JAMA, 306(15), 1688-1698. [Google Scholar] [Crossref]

8. Frizzell, J. D., Liang, L., Schulte, P. J., et al. (2017). Prediction of 30-day all-cause readmissions in patients hospitalized for heart failure. JAMA Cardiology, 2(2), 204-209. [Google Scholar] [Crossref]

9. Zheng, B., Zhang, J., Yoon, S. W., et al. (2015). Predictive modeling of hospital readmissions using metaheuristics and data mining. Expert Systems with Applications, 42(20), 7110-7120. [Google Scholar] [Crossref]

10. Tonekaboni, S., Joshi, S., McCradden, M. D., et al. (2019). What clinicians want: contextualizing explainable machine learning for clinical end use. Proceedings of Machine Learning Research, 106, 359-380. [Google Scholar] [Crossref]

11. Sculley, D., Holt, G., Golovin, D., et al. (2015). Hidden technical debt in machine learning systems. Advances in Neural Information Processing Systems, 28, 2503-2511. [Google Scholar] [Crossref]

12. Obermeyer, Z., Powers, B., Vogeli, C., et al. (2019). Dissecting racial bias in an algorithm used to manage the health of populations. Science, 366(6464), 447-453. [Google Scholar] [Crossref]

13. Vyas, D. A., Eisenstein, L. E., & Jones, D. S. (2020). Hidden in plain sight - reconsidering the use of race correction in clinical algorithms. New England Journal of Medicine, 383(9), 874-882. [Google Scholar] [Crossref]

14. Hardt, M., Price, E., & Srebro, N. (2016). Equality of opportunity in supervised learning. Advances in Neural Information Processing Systems, 29, 3315-3323. [Google Scholar] [Crossref]

15. van Walraven, C., Dhalla, I. A., Bell, C., et al. (2010). Derivation and validation of an index to predict early death or unplanned readmission after discharge from hospital to the community. CMAJ, 182(6), 551-557. [Google Scholar] [Crossref]

16. Donze, J., Aujesky, D., Williams, D., et al. (2013). Potentially avoidable 30-day hospital readmissions in medical patients: derivation and validation of a prediction model. JAMA Internal Medicine, 173(8), 632-638. [Google Scholar] [Crossref]

17. Rajkomar, A., Oren, E., Chen, K., et al. (2018). Scalable and accurate deep learning with electronic health records. NPJ Digital Medicine, 1, 18. [Google Scholar] [Crossref]

18. Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30, 4765-4774. [Google Scholar] [Crossref]

19. Lundberg, S. M., Erion, G., Chen, H., et al. (2020). From local explanations to global understanding with explainable AI for trees. Nature Machine Intelligence, 2, 56-67. [Google Scholar] [Crossref]

20. Caruana, R., Lou, Y., Gehrke, J., et al. (2015). Intelligible models for healthcare: predicting pneumonia risk and hospital 30-day readmission. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1721-1730. [Google Scholar] [Crossref]

21. Johnson, A. E. W., Bulgarelli, L., Shen, L., et al. (2023). MIMIC-IV, a freely accessible electronic health record dataset. Scientific Data, 10, 1. [Google Scholar] [Crossref]

22. Chen, T., & Guestrin, C. (2016). XGBoost: a scalable tree boosting system. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785-794. [Google Scholar] [Crossref]

23. Ke, G., Meng, Q., Finley, T., et al. (2017). LightGBM: a highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems, 30, 3146-3154. [Google Scholar] [Crossref]

24. Beyer, B., Jones, C., Petoff, J., et al. (2016). Site Reliability Engineering: How Google Runs Production Systems. O'Reilly Media [Google Scholar] [Crossref]

• Exploring the Ethical Dimensions of Artificial Intelligence