What question did this study set out to answer?

To develop a predictive framework for identifying high-risk diabetes patients prone to hospital readmissions.

March 23, 20260 citationsOpen Access

Predictive Risk Stratification for Preventable Diabetes Readmissions in U.S. Hospitals

Key Points

To develop a predictive framework for identifying high-risk diabetes patients prone to hospital readmissions.
Utilized UCI Diabetes dataset of over 101,000 hospital encounters.
Developed Random Forest and XGBoost models to predict readmissions.
Performed feature importance and SHAP analysis to identify key predictors.
Achieved a recall of 76% at an optimized threshold.
Identified key predictors include prior inpatient visits and medication burden.
Proposed a CDC HI-5 aligned intervention to incorporate risk stratification and care coordination.

Abstract

This study presents a machine learning–based predictive framework for identifying patients at high risk of 30-day hospital readmission among individuals with diabetes. Using the UCI Diabetes dataset comprising over 101,000 hospital encounters, we developed and evaluated Random Forest and XGBoost models, achieving a recall of 76% at an optimized threshold. Feature importance and SHAP analysis identified key predictors including prior inpatient visits, medication burden, and length of stay. Building on these findings, we propose a CDC HI-5 aligned intervention incorporating risk stratification, care coordination, medication management, and a real-time clinical dashboard. The results demonstrate the feasibility of integrating predictive analytics into population health strategies to reduce preventable readmissions.

KI fragen

Bookmark

View Full Paper