A Bayesian Model for Triage Decision Support

Author: Sarmad Sadeghi, MD; Afsaneh Barzi, MD (co-author)

Primary Advisor: Craig W. Johnson, PhD

Committee Members: Brent King, MD (co-author)

Masters thesis, The University of Texas School of Health Information Sciences at Houston.

OBJECTIVE: An automated triage decision support system developed by the authors is evaluated in a retrospective clinical study. METHODS: We compared the triage decisions of this system with triage decisions made by an emergency medicine specialist. The final disposition and diagnoses of the physicians who visited the patient as reflected in the medical records were used as control. Appropriateness of dispositions is analyzed using Chi square test. The ability of the physician or the triage system to predict the actual disposition in the ED is analyzed using a binary logistic regression model. RESULTS: The triage system successfully predicted the Admit decisions made in the ED whereas the emergency medicine specialist decisions could not predict the ED disposition. Additionally, the emergency medicine specialist in this study under-disposed more patients than the triage system and the triage system over disposed more patients than the emergency medicine specialist; both effects were statistically significant. CONCLUSION: The triage system studied here shows promise as a triage decision support tool to be used for telephone triage and triage in the EDs. This technology may also be useful to the patients as a self-triage tool. However, the efficiency of this particular application of this technology is unclear.