Abstract

Introduction

In emergency medicine, accurate triage is vital for patient outcomes and resource management. The Canadian Triage and Acuity Scale (CTAS) has been essential in training healthcare providers to make prompt and precise triage decisions.1 With the rise of artificial intelligence (AI), chatbots are being considered for their potential to support or even replace human decision-making in various medical situations. This study aims to assess the agreement between AI chatbot triage decisions and those made by experienced emergency physicians using CTAS.

Methods

This study involved a comparative analysis between an AI chatbot and two expert emergency physicians, each with over ten years of experience. We used a dataset of 60 emergency case scenarios, which have been utilized for over 8-10 years to train medical personnel at the start of their careers.1 The AI chatbot received training materials on CTAS and triage before being tasked with assigning appropriate triage levels for each scenario. Meanwhile, the expert physicians independently triaged the same cases. Scenarios where the two experts disagreed on the triage level were excluded, leaving 35 case scenarios for the final analysis.

To evaluate the agreement between the AI chatbot and the expert physicians, we used the Cohen’s Kappa coefficient. This included determining the Cohen’s Kappa coefficient value, the p-value, and the 95% confidence interval (CI) to assess the statistical significance and reliability of the agreement.

Results

The Cohen’s Kappa coefficient value between the AI chatbot and the expert physicians was 0.721, indicating a substintial level of agreement. The p-value was

Key words: Triage, AI, Health Informatics, Emergency Department.