SavedAdd your journal

Journals / Fırat Üniversitesi Mühendislik Bilimleri Dergisi / 2026 / Cilt: 38 Sayı: 2

Development of Machine Learning Based Hospital Triage Decision Support System Application

Makine Öğrenme Tabanlı Hastane Triyaj Karar Destek Sistemi Uygulamasının Geliştirilmesi

Erhan Turan(Ardahan Üniversitesi Mühendislik Fakültesi Bİlgisayar Mühendisliği)0000-0003-4423-0118
Pages
541–554
Publication Date
2026-09-30
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The Random Forest and LGBM models achieved %96.1 test accuracy in the machine learning-based decision support system developed to correctly direct patients to the Green (under triage), Yellow (normal triage), and Red (over triage) areas.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:This study proposes a machine learning-based decision support system for the emergency department (ED), which is typically the most congested unit in hospitals.
📊
Key Findings & Data:In EDs, where the workspace is highly constrained by congestion, workload, stress, and human factors, the margin of error is significantly reduced.
💡
Conclusion & Impact:The Random Forest and LGBM models achieved %96.1 test accuracy in the machine learning-based decision support system developed to correctly direct patients to the Green (under triage), Yellow (normal triage), and Red (over triage) areas.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Triyaj · karar destek sistemi · makine öğrenmesi

Abstract

This study proposes a machine learning-based decision support system for the emergency department (ED), which is typically the most congested unit in hospitals. In EDs, where the workspace is highly constrained by congestion, workload, stress, and human factors, the margin of error is significantly reduced. Therefore, it is crucial to ensure that incoming patients are directed to the most appropriate unit for medical support. In emergency departments, incoming patients are directed to areas designated as Green, Yellow, and Red Zones. Accurate and rapid patient orientation is essential for the most efficient use of capacity in these congested areas and ensures that patients receive the most appropriate support according to their medical priorities. This study utilizes an open-source dataset obtained from the emergency departments of regional and local hospitals in Korea. Classification models were trained using Decision Trees, Gaussian Naive Bayes, K-Nearest Neighbors, LightGBM, Random Forests, and Support Vector Machines. These classification models, along with the training data, were developed with the Java Swing library to create a graphical interface for use in hospital emergency departments. The classification models themselves were compiled in Python. The entire application was run via the Java and Python command line, making it suitable for real-world testing. The Random Forest and LGBM models achieved %96.1 test accuracy in the machine learning-based decision support system developed to correctly direct patients to the Green (under triage), Yellow (normal triage), and Red (over triage) areas.

Özet

Bu çalışma ile hastanelerde yoğunluğun en fazla olduğu birim olan Acil bölümü için makine öğrenme tabanlı bir karar destek sistemi önerilmiştir. Yoğunluk, iş yükü, stres ve insan kaynaklı etkilerden dolayı çalışma alanının baskılandığı Acil birimi için hata payı azaltılarak gelen hastanın en doğru şekilde tıbbi destek alacağı birime yönlendirilme işlemleri yapılmaktadır. Acil birimlerinde gelen hastanın yeşil, sarı ve kırmızı alan olarak adlandırılan alanlara yönlendirilir. Hastaların doğru ve hızlı bir şekilde yönlendirilmesi bu alanlardaki yoğunluğun en verimli şekilde kullanılmasını ve hastaların tıbbi müdahale önceliklerine göre en doğru şekilde destek almasını sağlamaktadır. Bu çalışmada Kore’de bir bölgesel ve yerel hastanelerin acil bölümlerinden elde edilen açık kaynak veri seti kullanılmıştır. karar ağacı, Gaussian naif bayes, k-en yakın komşu, lightgbm, rasgele orman ve destek vektör makinesi kullanılarak sınıflandırma modelleri eğitilmiştir. Bu sınıflandırma modelleri ve eğitim setindeki verilerin girişinin yapıldığı ve hastanelerdeki acil birimlerinin kullanımına yönelik grafiksel arayüz Java swing kütüphanesi kullanılarak geliştirilmiştir. Sınıf modelleri ise Python ortamında derlenmiştir. Java ve Python komut satırı üzerinden haberleştirilerek uygulama bütün halinde çalıştırılarak gerçek ortam testlerine uygun hale getirilmiştir. Hastaların yeşil (under triage), sarı (normal triage) ve yeşil (over triage) alanlara doğru olarak yönlendirilmesinde geliştirilen makine öğrenme tabanlı karar destek sisteminde rasgele orman ağacı ve LGBM %96.1’luk test doğruluğuna ulaşmıştır.

🔖

Cite This Article

Turan, E. (2026). Development of Machine Learning Based Hospital Triage Decision Support System Application. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, Cilt: 38 Sayı: 2, 541–554. https://doi.org/10.35234/fumbd.1781412

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (25)

  1. N. Akyolcu, “Acil Birimlerde Triyaj,” Florence Nightingale J. Nurs., vol. 15, no. 58, 2014.
  2. H. Kırmızıgül, A. Erciyas, N. Görmeli Kurt, and Y. Kavak, “Acil Bakım Hemşirelerinin Triyaj Karar Verme Becerilerinin Değerlendirilmes,” İnönü Üniversitesi Sağlık Hizmetleri Mesl. Yüksek Okulu Derg., vol. 12, no. 3, pp. 967–978, 2024.
  3. Bracken J, Triage. Newberry L (Ed). Emergency Nursing, 5th ed. 2003.
  4. D. Öner Şimşek, “TRİAJ SİSTEMLERİNE GENEL BAKIŞ VE TÜRKİYE’DE ACİL SERVİS BAŞVURULARINI ETKİLEYEN FAKTÖRLERİN LOJİSTİK REGRESYON İLE BELİRLENMESİ,” Sos. Güvence, no. 13, pp. 84–115, 2018.
  5. R. M. Williams, “Triage and emergency department services.,” Annals of emergency medicine, vol. 27, no. 4. United States, pp. 506–508, Apr-1996.
  6. Ş. Bora et al., “Machine Learning for E-triage,” Int. J. Multidiscip. Stud. Innov. Technol., vol. 6, no. 1, pp. 86–90, 2022.
  7. Y.-H. Chang et al., “Machine learning–based triage to identify low-severity patients with a short discharge length of stay in emergency department,” BMC Emerg. Med., vol. 22, no. 1, p. 88, 2022.
  8. S. Levin et al., “Machine-Learning-Based Electronic Triage More Accurately Differentiates Patients With Respect to Clinical Outcomes Compared With the Emergency Severity Index.,” Ann. Emerg. Med., vol. 71, no. 5, pp. 565-574.e2, May 2018.
  9. S. B. Çetin, F. Cebeci, and O. Eray, “The effect of computer-based decision support system on emergency department triage: Non-randomised controlled trial,” Int. Emerg. Nurs., vol. 70, p. 101341, 2023.
  10. Y.-H. Chang et al., “Using machine learning and natural language processing in triage for prediction of clinical disposition in the emergency department,” BMC Emerg. Med., vol. 24, no. 1, p. 237, 2024.
  11. H. Mutegeki, A. Nahabwe, J. Nakatumba-Nabende, and G. Marvin, “Interpretable Machine Learning-Based Triage For Decision Support in Emergency Care,” in 2023 7th International Conference on Trends in Electronics and Informatics (ICOEI), 2023, pp. 983–990.
  12. R. Inokuchi, M. Iwagami, Y. Sun, A. Sakamoto, and N. Tamiya, “Machine learning models predicting undertriage in telephone triage,” Ann. Med., vol. 54, no. 1, pp. 2989–2996, 2022.
  13. İ. Yıldız, “Triage Application with Machine Learning Models.” [Online]. Available: https://www.kaggle.com/code/ilkeryildiz/triage-application-with-machine-learning-models/data.
  14. S. W. Choi, T. Ko, K. J. Hong, and K. H. Kim, “Machine Learning-Based Prediction of Korean Triage and Acuity Scale Level in Emergency Department Patients.,” Healthc. Inform. Res., vol. 25, no. 4, pp. 305–312, Oct. 2019.
  15. A. Kantarci et al., “Machine Learning for E-triage,” Int. J. Multidiscip. Stud. Innov. Technol., vol. 6, Jun. 2022.
  16. E. Turan, B. Dandıl, and C. Bal, “Grafiksel Arayüz Tabanlı Mermer Sınıflandırma Uygulaması Geliştirme,” Gazi Üniversitesi Fen Bilim. Derg. Part C Tasarım ve Teknol., vol. 8, no. 4, pp. 1034–1050, 2020.
  17. M. A. Halwani et al., “Predicting triage of pediatric patients in the emergency department using machine learning approach.,” Int. J. Emerg. Med., vol. 18, no. 1, p. 51, Mar. 2025.
  18. E. Alpaydin, Introduction to machine learning. MIT Press, 2010.
  19. Scikit-Learn, “RandomForestClassifier.” [Online]. Available: https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html.
  20. M. Osman, J. He, F. Mokbal, N. Zhu, and S. Qureshi, “ML-LGBM: A Machine Learning Model based on Light Gradient Boosting Machine for the Detection of Version Number Attacks in RPL-Based Networks,” IEEE Access, vol. PP, p. 1, Jun. 2021.
  21. Y. Raita, T. Goto, M. K. Faridi, D. F. M. Brown, C. A. J. Camargo, and K. Hasegawa, “Emergency department triage prediction of clinical outcomes using machine learning models.,” Crit. Care, vol. 23, no. 1, p. 64, Feb. 2019.
  22. Z. Gao et al., “Developing and Validating an Emergency Triage Model Using Machine Learning Algorithms with Medical Big Data.,” Risk Manag. Healthc. Policy, vol. 15, pp. 1545–1551, 2022.
  23. W. A. Sulaiman et al., “Emergency Department Triage Hospitalization Prediction Based on Machine Learning and Rule Extraction,” in 2023 IEEE EMBS Special Topic Conference on Data Science and Engineering in Healthcare, Medicine and Biology, 2023, pp. 147–148.
  24. N. Seesuwan, N. Phetkub, A. Rojanasumapong, and N. Chuenjai, Comparison of the Performance of Machine Learning Models in Predicting ESI Triage Levels Using Data of Non‐Traumatic Patients from the Triage Point at the Emergency Medicine Department of Lampang Hospital. 2024.
  25. W. S. Hong, A. D. Haimovich, and R. A. Taylor, “Predicting hospital admission at emergency department triage using machine learning.,” PLoS One, vol. 13, no. 7, p. e0201016, 2018.