EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Proactive forecasting of emergency department crowding through explainable machine learning and temporal feature dynamics

Sujeong Lee, Taerim Kim, Hansol Chang, Seong Young Choi

Hong Kong Journal of Emergency Medicine · 2026-04 · 33 (2)

DOI: 10.1002/hkj2.70093 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Hong Kong Journal of Emergency Medicine, online erschienen am 21.04.2026. Verfasst von Sujeong Lee und 3 weiteren Autor:innen. Die Arbeit nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Emergency department (ED) crowding is a major global challenge that adversely affects patient safety and care quality. Conventional NEDOCS‐based approaches are largely reactive and provide limited support for proactive decision‐making.

Methods

We conducted a retrospective observational study using ED operational and clinical data from the Clinical Data Warehouse of Samsung Medical Center (2017–2025). A total of 292,033 ED visits were included. Time‐series datasets with 19 variables were constructed across five forecasting horizons ( t + 1 to t + 5). XGBoost‐based models were developed using two NEDOCS thresholds (≥141 and ≥ 101) with strict temporal validation. Model performance was evaluated using sensitivity, F1‐score, balanced accuracy, and AUC‐ROC. Model interpretability was assessed using SHAP.

Results

The nedocs1 model showed stable but conservative prediction behavior with low sensitivity (0.14–0.29). In contrast, the nedocs2 model demonstrated improved sensitivity (0.39–0.48) and F1‐score, particularly at t + 3. SHAP analysis revealed that waiting time and patient volume were key drivers, with increased contributions from hospitalization and acuity‐related variables at longer horizons.

Conclusion

Explainable time‐series machine learning enables early prediction of ED crowding with interpretable insights. The nedocs2 model showed superior performance for proactive operational alerting and may support timely resource allocation in emergency care settings.

Zitieren

APA

Lee, S., Kim, T., Chang, H., & Choi, S. Y. (2026). Proactive forecasting of emergency department crowding through explainable machine learning and temporal feature dynamics. Hong Kong Journal of Emergency Medicine, 33(2). https://doi.org/10.1002/hkj2.70093

Vancouver

Lee S, Kim T, Chang H, Choi SY. Proactive forecasting of emergency department crowding through explainable machine learning and temporal feature dynamics. Hong Kong Journal of Emergency Medicine. 2026;33(2). doi:10.1002/hkj2.70093

BibTeX
@article{Lee2026,
  author = {Lee, Sujeong and Kim, Taerim and Chang, Hansol and Choi, Seong Young},
  title = {Proactive forecasting of emergency department crowding through explainable machine learning and temporal feature dynamics},
  journal = {Hong Kong Journal of Emergency Medicine},
  year = {2026},
  volume = {33},
  number = {2},
  doi = {10.1002/hkj2.70093}
}
Kostenlos starten →