Tanveer Ahmed Yadgir
Fatima College of Health Sciences, UAE
Title: High-sensitivity self-triage systems for public health in case of emergency
Biography
Biography: Tanveer Ahmed Yadgir
Abstract
Objective: Ambulance over-triage is wasteful and can cause delayed treatment for serious emergencies. Existing prehospital triage systems have limited accuracy in the absence of physi- ological measurements prior to arriving at the scene. This study proposes two new computerized models in a prehospital self-triage setting, based on information available to patients themselves, investigates safety and accuracy in terms of under- and over-triage rates, and compares them with established scores such as the Modified (MEWS) or National Early Warning System (NEWS) and the Emergency Severity Index (ESI).
Study Design: This was a retrospective cohort study.
Results: Among the 433,498 missions considered, 17.6% were classified as serious and 3.9% life-threatening. Both self-triage models, based on a decision tree (DT) and Neural Network (NN), showed better discriminative power between serious and non-serious calls compared to established scoring systems, with a sensitivity of 98.3% (DT) / 88.2% (NN) and negative predic- tive value of 96.7% (DT) / 95.0% (NN), compared to physiological scoring systems with sensi- tivities of 98.0% (MEWS), 74.7% (NEWS), 51.8% (ESI), negative predictive values of 82.6% (MEWS), 90.2% (NEWS), and 84.7% (ESI). The safer model (DT) has the potential to reduce current call load by 13.5% at only 1.7% risk of misclassifying serious calls and less than half the rate of under-triage of existing scores.
Conclusion: While scoring systems for emergency triage have shown limited discrimination ability in a prehospital setting, we present supporting evidence for the feasibility, safety, and util- ity of high-sensitivity patient self-triage systems using computational methods, without requiring either training or diagnostic devices.