Physiological and descriptive variables as predictors for the Emergency Severity Index

Abstract

Many hospital emergency departments (EDs) in the United States have implemented the use of the five-level Emergency Severity Index (ESI) as their clinical decision support method to enhance clinical decision making in the triage process. The ESI designates the most acutely ill patients as level 1 or 2 and those who do not meet these criteria are assigned to levels 3–5 based on estimated resource utilization. Although the number of resources is the primary decision rule to determine levels 3–5, physiological and descriptive variables can also be used to predict the ESI level. This study uses several physiological and descriptive variables as predictors to determine the ESI value. The physiological variables include heart rate, blood pressure, temperature, respiration rate, and oxygen level, whereas the descriptive variables include age, gender, pain level, and patient complaint. An ordered probit model was developed for ESI prediction. In addition, a linear regression model was also developed to demonstrate the necessity of having a decision making tool that allows for non-integer values. The results of this research can be used to enhance the precision of the ESI and the nurse's ability to prioritize treatment based on triage acuity. The decision making tool can also be used to stratify patients who are classified in the same priority group and may eliminate the necessity of grouping patients into different categories.