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

arXiv cs.LG / 4/27/2026

📰 NewsDeveloper Stack & InfrastructureIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper proposes an integrated framework for hospital readmission prediction that targets explainability, deployment reliability/observability, and demographic fairness evaluation barriers to clinical translation.
Using a retrospective cohort of 415,231 adult admissions from MIMIC-IV, the authors train logistic regression, XGBoost, and LightGBM models on 26 features and apply SHAP to generate per-patient explanations.
Model performance is assessed with AUC-ROC, subgroup fairness metrics (AUC-ROC, false negative rate, and positive predictive value across 16 subgroups), and calibration using Brier scores and calibration curves.
XGBoost reaches AUC-ROC of 0.696 (95% CI 0.691–0.701) and compares favorably with the LACE baseline, while LightGBM shows the best calibration (Brier 0.146), and equity thresholds are met across subgroups.
The study concludes that the approach provides clinically actionable explanations with competitive accuracy and strong demographic equity, and it releases code publicly on GitHub.

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.