JMIR Publications

ABSTRACT

Background:

Emergency department (ED) revisits are critical quality indicators, particularly in medically underserved areas, where traditional prediction tools show limited performance. Machine learning approaches may offer improved predictive performance for identifying high-risk patients.

Objective:

This formative study aimed to develop and validate a machine learning-based model for predicting 30-day ED revisits using electronic health records from a tertiary hospital serving a medically underserved area in South Korea, and to evaluate its clinical utility through interpretability analysis and risk stratification.

Methods:

This formative study aimed to develop and validate a machine learning-based model for predicting 30-day ED revisits using electronic health records from a tertiary hospital serving a medically underserved area in South Korea, and to evaluate its clinical utility through interpretability analysis and risk stratification.

Results:

Among 36,230 patients, 798 (2.2%) revisited within 30 days. XGBoost achieved superior performance with AUROC 0.90 (95% CI: 0.88-0.92), sensitivity 0.94, and specificity 0.69. The SHAP analysis identified ED length of stay, oxygen saturation, systolic blood pressure, CT performance, antibiotic use, and liver disease as key predictors. Risk stratification demonstrated a 25-fold difference in the actual revisit rates between the lowest (1.8%) and highest (45.7%) risk groups.

Conclusions:

The XGBoost model demonstrated excellent predictive performance with high interpretability for 30-day ED revisit predictions. The implementation of this model could enable risk-stratified interventions and more efficient resource allocation in medically underserved settings, potentially reducing unnecessary revisits and improving patient outcomes. This formative study establishes feasibility and provides a foundation for future multi-center validation studies in similar medically underserved settings.