Artificial intelligence algorithm to predict the need for critical care in prehospital emergency medical services

Abstract

Background: In emergency medical services (EMSs), accurately predicting the severity of a patient's medical condition is important for the early identification of those who are vulnerable and at high-risk. In this study, we developed and validated an artificial intelligence (AI) algorithm based on deep learning to predict the need for critical care during EMS. Methods: We conducted a retrospective observation cohort study. The algorithm was established using development data from the Korean national emergency department information system, which were collected during visits in real time from 151 emergency departments (EDs). We validated the algorithm using EMS run sheets from two EDs. The study subjects comprised adult patients who visited EDs. The endpoint was critical care, and we used age, sex, chief complaint, symptom onset to arrival time, trauma, and initial vital signs as the predicted variables. Results: The number of patients in the development data was 8,981,181, and the validation data comprised 2604 EMS run sheets from two hospitals. The area under the receiver operating characteristic curve of the algorithm to predict the critical care was 0.867 (95% confidence interval, [0.864-0.871]). This result outperformed the Emergency Severity Index (0.839 [0.831-0.846]), Korean Triage and Acuity System (0.824 [0.815-0.832]), National Early Warning Score (0.741 [0.734-0.748]), and Modified Early Warning Score (0.696 [0.691-0.699]). Conclusions: The AI algorithm accurately predicted the need for the critical care of patients using information during EMS and outperformed the conventional triage tools and early warning scores.

A short guide for medical professionals in the era of artificial intelligence

“…It is crucial to be able to predict how severe a patient’s medical condition is to support the early identification of those who are vulnerable and at high-risk, especially in emergency medical services. In a study, authors developed and validated an A.I.-based algorithm using deep learning that accurately predicted the need for the critical care of patients and outperformed the conventional triage tools and early warning scores 23 . In another study, authors analyzed online triage tools from more than 150 000 patient interactions with a chatbot, and they found a decreased level of the urgency of patients’ intended level of care in more than one-quarter of the cases 24 .…”

Prehospital shock index outperforms hypotension alone in predicting significant injury in trauma patients

“…This could be close to reality with recent advances in artificial intelligence and portable technologies. 26 This has major implications on best utilization of regional trauma systems and hospitals, as well as when generalizing recommendations to other countries and regions with variable resources, where individualized criteria are likely to have a stronger impact. Future prospective investigations, such as pretriage and post-triage protocol adjustments, as well as a cost-effectiveness analysis of such adjustment should address some of the limitations in our study and provide further insight into the full benefits of modifying trauma triage criteria.…”

A Decision Support Method for Prehospital Emergency Care Based on Ranking the Importance of Physiological Variables

“…In Swedish PEC, the majority of adverse events originate as a result of deviations from the normal standard of care and incomplete documentation [15]. In EMSs, accurately predicting the severity of a patient's medical condition with an AI algorithm could overcome the limitations of conventional statistical methods and have recently achieved state-of-the-art performance [5]. Decisions made by paramedics during PEC have the potential to impact patient health outcomes and represent both a professional risk for individual staff members, and a reputational risk to with regards to patient trust [16].…”

“…Some studies are beginning to investigate the feasibility of checklists in improving prehospital emergency care [3,4]. For instance, Kang et al proposed an artificial intelligence (AI) algorithm based on deep learning to predict the severity of a patient's medical condition in emergency medical services (EMSs) [5]. However, obtaining the checklists for emergency conditions using AI is still a big problem.…”