The Use of Artificial Intelligence in Emergency Case Transport, Diagnosis, and Treatment

Abstract

Artificial intelligence (AI) is rapidly entering prehospital emergency care, where time-critical triage, transport, and early treatment decisions determine outcomes. We systematically reviewed original studies evaluating AI tools used before hospital arrival, focusing on prediction/triage, diagnostic support, and transport optimization, and synthesized insights from contemporary reviews to contextualize clinical adoption. Seven original studies met inclusion for quantitative results synthesis: an ensemble waveform-based triage model predicting lifesaving interventions in trauma; an AI-enhanced regional platform guiding hospital selection and first aid; two studies on prehospital ST-elevation myocardial infarction (STEMI) detection (mini-12-lead and smartphone capture); a randomized trial of AI dispatcher alerts for out-of-hospital cardiac arrest; a gradient-boosted model for dyspnea serious adverse events; and a deep-learning severity algorithm predicting need for critical care in EMS. Across studies, AI frequently achieved AUCs around or above 0.80, improved sensitivity or operational timeliness (faster ECG interpretation/feedback), and in specific subgroups reduced adverse outcomes (lower mortality when AI guided optimal hospital transfer). However, not all trials showed clinical recognition gains despite superior model sensitivity, underscoring implementation challenges. Current reviews emphasize the promise of AI alongside the need for rigorous prospective validation, workflow integration, transparency, and equity. AI can augment prehospital decision-making, but robust clinical pathways and governance remain essential.