Patients with chest pain and persistent ST segment elevation (STE) may not have acute coronary occlusions or serum troponin curves suggestive of acute necrosis. Our objective is the validation and cost-effectiveness analysis of a diagnostic model assisted by artificial intelligence (AI). Our hypothesis is that an AI analysis of the surface electrocardiogram allows a better distinction of patients with STE due to acute myocardial ischemia, from those with another etiology. This is a prospective multicenter study with two groups of patients with STE: I) coronary arteries without significant lesions and without serum troponin curve suggestive of acute necrosis, II) myocardial infarction with acute coronary occlusion. A manual centralized electrocardiographic analysis and another by AI algorithms will be performed.
This is a prospective multicenter study promoted by the Ischemic Heart Disease and Acute Cardiovascular Care Section of the Spanish Society of Cardiology. Following institutional ethical approval, the surface ECG prior to the activation of the Infarction Code, and the ECGs before and after (up to a maximum of 20) the Infarction Code along with other clinical data will be collected across the different enrolled hospitals. Sites will securely transfer the data to a centralized repository for processing. Willem AI platform will automatically analyze the ECGs in parallel to an experienced observer. The results of the study will provide new information for the improvement in the stratification of patients with ST segment elevation.
Study Type
OBSERVATIONAL
Enrollment
420
A clinical decision support software as a medical device that detects whether a patient has ST elevation due to acute myocardial ischemia or due to another etiology based upon the input of one or more ECGs and other clinical data obtained at the point-of-care.
Hospital Universitario de Canarias
San Cristóbal de La Laguna, Santa Cruz De Tenerife, Spain
Hospital de Basurto
Bilbao, Vizcaya, Spain
Hospital Vall D' Hebron
Barcelona, Spain
Idoven
Madrid, Spain
Servicio Cardiología Hospital Universitario Gregorio Marañón
Madrid, Spain
Hospital Clínico San Carlos
Madrid, Spain
Hospital Clínico Universitario de Valladolid
Valladolid, Spain
Clinical validation of a screening model assisted by AI
The detection performance of acute myocardial ischemia will be evaluated for the AI platform in comparison to standard manual analysis.
Time frame: 6 months after the last enrolled patient
Cost-effectiveness analysis of a screening model assisted by AI
The benefits of the screening model assisted by the AI platform will be evaluated using a hybrid decision tree/ Markov model.
Time frame: 1 year after the last enrolled patient
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.