Decision Making at Triage Classification using SVM with SMOTE Technique

Authors

• Mehanas Shahul, Mahatma Gandhi University, KottayamFollow
• Pushpalatha KP, Mahatma Gandhi University, KottayamFollow

Author ORCID Identifier

Mehanas Shahul: 0009-0005-0349-8056

Pushpalatha KP: 0000-0002-0044-5507

Abstract

The efficient functioning of triage gates in overcrowded emergency departments (EDs) occurs in the context of the complex adaptive system (CAS) framework, where diverse system elements – patients, medical personnel, resources, patients’ inflow patterns, and patients themselves – simultaneously and dynamically influence the decision process. This study addresses the automated incorporation of machine learning triage algorithms as part of the system triage process to support automated classified risk-level recognition based on a limited set of vital signs. Patients are dynamically subsumed under high and low-risk categories enhanced by sensitivity, which enables optimal diagnosis and triage response to the critical clinician decision time. Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Naive Bayes (NB), and Decision Tree (DT) constitute the conventional machine learning model set, and are vastly used as decision support agents and evaluated in the context of the system relevant metrics: Accuracy, Precision, Recall, F1 Score, Specificity, and  Sensitivity. The Synthetic Minority Oversampling Technique (SMOTE) addresses patients’ risk-level triage imbalance. SVM is presented to the system as a member of the highest performing models.

Recommended Citation

Shahul, Mehanas and KP, Pushpalatha (2026) "Decision Making at Triage Classification using SVM with SMOTE Technique," Northeast Journal of Complex Systems (NEJCS): Vol. 8 : No. 3 , Article 1.
DOI: https://doi.org/10.63562/2577-8439.1139
Available at: https://orb.binghamton.edu/nejcs/vol8/iss3/1