Developing a Machine Learning Decision Support System for Ambulance Nurses to Assess Patients With Chest Pain

What this Trial Is About

This research aims to develop and improve a decision support system for patients experiencing chest pain before they reach the hospital. It focuses on evaluating how well a machine learning model can assist emergency medical services in assessing these patients. The study addresses the challenge of safely directing patients to the right level of care, balancing timely treatment for serious conditions like heart attacks or strokes with avoiding unnecessary hospital visits that may cause delays or overcrowding. Participants will be asked questions at the scene about their medical history and pain details, and a blood sample for troponin and glucose will be taken and analyzed immediately. The study collects routine medical record data and scene measurements to validate and further develop the decision support model. Participants will continue to receive standard care according to guidelines, typically transport to an emergency department if needed. Throughout the study, researchers will monitor clinical outcomes including time-sensitive conditions, deaths within seven days, and adverse events within 72 hours after ambulance service inclusion. Data from the initial assessment, blood tests, and medical records will help evaluate the models predictive performance. The study is observational, and participant involvement includes answering questions and consenting to data and sample collection. The total duration extends from emergency contact through hospital discharge and follow-up periods up to 100 days.

Digital Decision Support in the Management of Patients With Chest Pain