Improving Emergency Telephone Triage Using Artificial Intelligence to Detect Critical Conditions Like Cardiac Arrest, Respiratory Distress, Chest Pain, and Stroke at the Andalusia Emergency Coordination Center

What this Trial Is About

Researchers are evaluating how to improve telephone triage for emergency calls using advanced Artificial Intelligence AI methods. The study focuses on four critical emergency situations unconsciousness or cardiac arrest, difficulty breathing, non-traumatic chest pain, and stroke symptoms. The goal is to help emergency call operators make faster and more accurate decisions to prioritize serious cases and improve patient outcomes. The project analyzes historical call data from the Emergency Coordination Center in Andalusia. This includes both structured data like answers to standard questions and unstructured data such as free-text notes. A hybrid AI approach combining traditional machine learning and generative AI techniques will be used to develop predictive models. Various algorithms like decision trees, random forests, and neural networks will be tested to find the most accurate model. Participants will not be directly involved since the study uses anonymized past call data. Researchers will evaluate the AI models using key performance metrics such as accuracy, sensitivity, specificity, and false positive and negative rates. The primary outcome is detecting critical severity within 24 hours from call receipt to medical team dispatch. The study aims to lay the foundation for integrating this AI model into the emergency system to enhance response times and care quality.

Evaluation and Optimization of Telephone Triage Using Artificial Intelligence (AI) Models for the Detection of Demands for Time-dependent Pathology at the Emergency and Urgent Care Coordination Center (CCUE).