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

TL;DR

This study presents an integrated framework for hospital readmission prediction that emphasizes explainability, fairness, and reliability, validated on the MIMIC-IV dataset with publicly available code.

Contribution

The paper introduces a comprehensive framework combining predictive modeling, explainability, and fairness assessment for hospital readmission prediction.

Findings

XGBoost achieved AUC-ROC 0.696, outperforming baseline models.

LightGBM provided the best calibration with Brier score 0.146.

All subgroups met predefined fairness thresholds.

Abstract

Objective: To propose and retrospectively validate an integrated framework addressing three barriers to clinical translation of readmission prediction: lack of explainability, absence of deployment reliability infrastructure, and inadequate demographic fairness evaluation. Materials and Methods: We constructed a cohort of 415231 adult admissions from the MIMIC-IV database (30-day readmission prevalence 18.0%), split 70/15/15. Logistic regression, XGBoost, and LightGBM models were trained on 26 features. SHAP provided per-patient explanations. Fairness was evaluated across 16 subgroups using AUC-ROC, false negative rate (FNR), and positive predictive value (PPV). Calibration was assessed using Brier scores and calibration curves. Results: XGBoost achieved AUC-ROC 0.696 (95% CI 0.691-0.701), outperforming or matching the LACE baseline (AUC 0.60-0.68). LightGBM achieved best calibration (Brier 0.146). Prior admissions were the dominant predictor. All subgroups met equity thresholds (delta AUC <= 0.05, delta FNR <= 0.10). Conclusion: This framework delivers competitive performance, clinically actionable explanations, and strong demographic equity. Code is publicly available at https://github.com/Tomisin92/readmission-prediction.