Machine Learning–Based Prediction Model for 30-Day Emergency Department Revisits in a Medically Underserved Tertiary Hospital: Formative Retrospective Cohort Study
JMIR Formative Research · 2026
DOI: 10.2196/87289 ↗Kurz gefasst
Kohortenstudie in der Zeitschrift JMIR Formative Research, 2026. Verfasst von Kyongmin Sun. Beteiligte Einrichtung: Department of Emergency Medicine, College of Medicine, Gangneung Asan Hospital, Gangneung, Gangwon-do, Republic of Korea. Hauptthemen laut MEDLINE: Emergency Service, Hospital, Machine Learning, Medically Underserved Area. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Emergency department (ED) revisits are critical quality indicators, particularly in medically underserved areas, where traditional prediction tools show limited performance. Machine learning (ML) approaches may offer improved predictive performance for identifying high-risk patients.
Objective
This formative study aimed to develop and validate an ML-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 retrospective cohort study analyzed 36,230 adult patients visiting the Gangneung Asan Hospital ED in 2023. We developed and compared 3 ML models (extreme gradient boosting [XGBoost], random forest, and ElasticNet) using electronic health records. Model interpretability was ensured through Shapley additive explanations (SHAP) analysis, and clinical utility was evaluated through 5-tier risk stratification.
Results
Among 36,230 patients, 798 (2.2%) revisited within 30 days. XGBoost achieved superior performance with an area under the receiver operating characteristic curve of 0.90 (95% CI 0.88‐0.92), a sensitivity of 0.94, and a specificity of 0.69. The SHAP analysis identified ED length of stay, oxygen saturation, systolic blood pressure, computed tomography performance, antibiotic use, and liver disease as key predictors. Risk stratification demonstrated a 25-fold difference in the actual revisit rates between the lowest (152/8450, 1.8%) and the highest (686/1500, 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 multicenter validation studies in similar medically underserved settings.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Emergency Medicine, College of Medicine, Gangneung Asan Hospital, Gangneung, Gangwon-do, Republic of Korea.
- Department of Health Administration, Graduate School, Yonsei University Mirae Campus, 1 Yonsedae-gil, Heungeop-myeon, Wonju, Gangwon-do, 26493, Republic of Korea, 82 337602418.
ORCID-Profile: Kyongmin Sun
Zitieren
APA
Sun, K. (2026). Machine Learning–Based Prediction Model for 30-Day Emergency Department Revisits in a Medically Underserved Tertiary Hospital: Formative Retrospective Cohort Study. JMIR Formative Research. https://doi.org/10.2196/87289
Vancouver
Sun K. Machine Learning–Based Prediction Model for 30-Day Emergency Department Revisits in a Medically Underserved Tertiary Hospital: Formative Retrospective Cohort Study. JMIR Formative Research. 2026. doi:10.2196/87289
BibTeX
@article{Sun2026,
author = {Sun, Kyongmin},
title = {Machine Learning–Based Prediction Model for 30-Day Emergency Department Revisits in a Medically Underserved Tertiary Hospital: Formative Retrospective Cohort Study},
journal = {JMIR Formative Research},
year = {2026},
doi = {10.2196/87289}
}
EUVIMED