Background: The efficient performance of an Emergency Department (ED) relies heavily on an effective triage system that prioritizes patients based on the severity of their medical conditions. Traditional triage systems, including those using the Canadian Triage and Acuity Scale (CTAS), may involve subjective assessments by healthcare providers, leading to potential inconsistencies and delays in patient care. Objective: This study aimed to evaluate six Machine Learning (ML) models K-Nearest Neighbors (KNN), Support Vector Machine (SCM), Decision Tree (DT), Random Forest (RF), Gaussian Naïve Bayes (GNB), and Light GBM (Light Gradient Boosting Machine) for triage prediction in the King Abdulaziz University Hospital using the CTAS framework. Methodology: We followed three essential phases: data collection (7125 records of ED patients), data exploration and processing, and the development of machine learning predictive models for ED triage at King Abdulaziz University Hospital. Results and conclusion: The overall predictive performance of CTAS was the highest using GNB = 0.984 accuracy. The CTAS-level model performance indicated that SVM, RF, and LGBM achieved the highest performance regarding the consistency of precision and recall values across all CTAS levels.
25 May 2021 in Saudi Journal of Emergency Medicine
Background: In response to the coronavirus disease 19 (COVID-19) pandemic, a new set of rapid measures for containment was necessary to deal with the medical emergency, and emergency services are a vital part of this response. However, if poorly handled, it can facilitate transmission to patients and healthcare workers. Yet, the practice-based exercises required to evaluate the preparedness of healthcare facilities in face of the current pandemic are lacking. We aim to assess the applicability of emergency procedures for respiratory pathogens for tertiary medical center in Saudi Arabia. Methods: Suitability and rapidity of the response were measured by conducting the "Homeland Security Exercise and Evaluation Program" simulation in which six medical evaluators observe the admission procedures of four mock victims of COVID-19 to the Emergency Department in King Abdulaziz University Hospital, Jeddah. Results: A total of 27 healthcare workers participated in the exercise during March 2020. The simulation drills gave the hospital the tool to test the preparedness to the COVID-19 pandemic. It uncovered the strengths and mostly the area of development in the clinical protocols and proficiency in personal protective equipment use. Conclusion: Simulation exercises can be beneficial in examining the readiness of the hospitals, including infrastructures, protocols, surge capacity, and staff competencies to deal with real-time health emergencies and to find solutions to fill the gaps. This study provided valuable feedback and opportunities for healthcare staff to practice before the peak of the COVID-19 pandemic was reached in Saudi Arabia. Establishing an out emergency department respiratory illness facility for initial screening of potential COVID-19 patients is recommended for proper containment while still providing the standard assessment, triage, and management practices.