EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Interpretable Machine Learning for Emergency Department Triage: Clinical Insights from 133,198 Patients Using the Korean Triage and Acuity Scale (KTAS)

MyoungJe Song iD, Jongsun Kim iD, Eun-Chul Jang, SoonChan Kwon iD

Diagnostics · 23.03.2026 · 16 (6) · 954

DOI: 10.3390/diagnostics16060954 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 23.03.2026. Verfasst von MyoungJe Song und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Emergency Medicine, International St. Mary's Hospital, Catholic Kwandong University, Incheon 22711, Republic of Korea. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Catholic Kwandong University International St. Mary’s Hospital.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: Emergency room severity classification (KTAS) is essential for patient safety but has limitations due to its reliance on subjective judgment. Existing machine learning models have not been trusted in clinical settings due to their opaque ‘black box’ nature in decision-making processes. To overcome this, this study aims to develop an explainable machine learning framework that provides a transparent basis for judgment with high accuracy.

Method

We retrospectively analyzed 133,198 emergency room visits from 2022 to 2024. We trained Random Forest (RF) and XGBoost models using vital signs and pain scores and applied explainable AI (XAI) techniques to ensure model transparency.

Results

Although XGBoost showed the highest predictive performance (94.7% accuracy within a ±1 error margin), we ultimately selected the RF model, which provides a good balance of predictive power (91.6%) and interpretability for clinical use. The results of the XAI analysis confirmed that pain score, age, and systolic blood pressure were the key variables in prediction, strongly aligning with clinical logic.

Conclusions

This study demonstrates that explainable AI can provide transparent insights for KTAS prediction beyond the limitations of traditional black-box models. These models may support emergency department triage by improving consistency and assisting clinicians in identifying potentially high-risk patients. However, further external validation is required before routine clinical implementation.

Schlagwörter

Stichwörter der Autor:innen

Korean triage and acuity scale (KTAS)decision-makingemergency department triageexplainable artificial intelligence (XAI)machine learning

Autor:innen und Institutionen

  • Department of Emergency Medicine, International St. Mary's Hospital, Catholic Kwandong University, Incheon 22711, Republic of Korea.
  • Department of Occupational and Environmental Medicine, Soonchunhyang University Cheonan Hospital, Cheonan 31151, Republic of Korea.

ORCID-Profile: MyoungJe Song, Jongsun Kim, SoonChan Kwon

Förderung

  • Catholic Kwandong University International St. Mary’s Hospital

Zitieren

APA

Song, M., Kim, J., Jang, E. C., & Kwon, S. (2026). Interpretable Machine Learning for Emergency Department Triage: Clinical Insights from 133,198 Patients Using the Korean Triage and Acuity Scale (KTAS). Diagnostics, 16(6), 954. https://doi.org/10.3390/diagnostics16060954

Vancouver

Song M, Kim J, Jang EC, Kwon S. Interpretable Machine Learning for Emergency Department Triage: Clinical Insights from 133,198 Patients Using the Korean Triage and Acuity Scale (KTAS). Diagnostics. 2026;16(6):954. doi:10.3390/diagnostics16060954

BibTeX
@article{Song2026,
  author = {Song, MyoungJe and Kim, Jongsun and Jang, Eun-Chul and Kwon, SoonChan},
  title = {Interpretable Machine Learning for Emergency Department Triage: Clinical Insights from 133,198 Patients Using the Korean Triage and Acuity Scale (KTAS)},
  journal = {Diagnostics},
  year = {2026},
  volume = {16},
  number = {6},
  pages = {954},
  doi = {10.3390/diagnostics16060954}
}
Kostenlos starten →