ORCID Identifier(s)

0009-0001-4858-6069

Document Type

Honors Thesis

Abstract

Triage in emergent situations occurs when patients are assigned to areas of the hospital with different levels of care according to the perceived risks determined by their signs and symptoms. The variability of current triage protocols substantially increases the proportion of lower acuity patients who die unexpectedly due to improper risk stratification. However, recent artificial intelligence (AI) developments have been applied to trauma triage situations to improve accuracy and patient outcomes. To further evaluate the effectiveness of this new tool, this study used various AI models to assess the presenting assessments of multiple situations and determine the appropriate level of care required. These models were compared according to accuracy, mortality rates, disposition after discharge, applicability to the dynamics of care, integration in diagnostic tools, and efficiency. The results show that the AI-integrated KATE triage model improves accurate risk stratification by ~4.96% compared to triage nurses and reduces the risk of mortality by ~47.45%. It was the top performer among the AI models, which also included Gemini, Pi AI, Copilot, and ChatGPT. KATE may be implemented in more emergency departments and used as an effective adjunct to interpretation by healthcare professionals.

Disciplines

Critical Care | Critical Care Nursing | Emergency Medicine | Investigative Techniques | Trauma

Publication Date

5-2025

Language

English

Faculty Mentor of Honors Project

Paula Wyman

Download

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.