Journal of electrocardiology, Volume 86, 5 1 2024, Pages 153768 Rationale and design of the artificial intelligence scalable solution for acute myocardial infarction (ASSIST) study. Domingo-Gardeta T, Montero-Cabezas JM, Jurado-Román A, Sabaté M, Aboal J, Baranchuk A, Carrillo X, García-Zamora S, Dores H, van der Valk V, Scherptong RWC, Andrés-Cordón JF, Vidal P, Moreno-Martínez D, Toribio-Fernández R, Lillo-Castellano JM, Cruz R, De Guio F, Marina-Breysse M, Martínez-Sellés M
Background
Acute coronary syndrome (ACS), specifically ST-segment elevation myocardial infarction is a major cause of morbidity and mortality throughout Europe. Diagnosis in the acute setting is mainly based on clinical symptoms and physician's interpretation of an electrocardiogram (ECG), which may be subject to errors. ST-segment elevation is the leading criteria to activate urgent reperfusion therapy, but a clear ST-elevation pattern might not be present in patients with coronary occlusion and ST-segment elevation might be seen in patients with normal coronary arteries.
Methods
The ASSIST project is a retrospective observational study aiming to improve the ECG-assisted assessment of ACS patients in the acute setting by incorporating an artificial intelligence platform, Willem™ to analyze 12‑lead ECGs. Our aim is to improve diagnostic accuracy and reduce treatment delays. ECG and clinical data collected during this study will enable the optimization and validation of Willem™. A retrospective multicenter study will collect ECG, clinical, and coronary angiography data from 10,309 patients. The primary outcome is the performance of this tool in the correct identification of acute myocardial infarction with coronary artery occlusion. Model performance will be evaluated internally with patients recruited in this retrospective study while external validation will be performed in a second stage.
Conclusion
ASSIST will provide key data to optimize Willem™ platform to detect myocardial infarction based on ECG-assessment alone. Our hypothesis is that such a diagnostic approach may reduce time delays, enhance diagnostic accuracy, and improve clinical outcomes.
