Artificial Intelligence-Powered Electrocardiogram Detecting Culprit Vessel Blood Flow Abnormality: AI-ECG TIMI Study...

Area of Science:

• Cardiology
• Medical Imaging
• Artificial Intelligence

Background:

• The 12-lead electrocardiogram (ECG) is crucial for identifying patients with occlusive myocardial infarction (OMI) needing revascularization.
• Acute coronary syndromes (ACS) present dynamically, with many OMI patients lacking typical ECG changes before invasive coronary angiography (ICA).
• Existing AI models for OMI detection are limited to retrospective ECG analysis.

Purpose of the Study:

• To prospectively validate an artificial intelligence (AI) model for detecting acute coronary artery occlusion using 12-lead ECGs.
• To assess the AI model's performance in identifying patients with TIMI 0-1 flow at the time of ICA.
• To characterize ECG findings associated with acute myocardial ischemia and abnormal perfusion.

Main Methods:

• The AI-ECG Thrombolysis in Myocardial Infarction (TIMI) study is a prospective, multicenter registry.
• Over 700 consecutive patients with ACS undergoing ICA across 9 European centers will be enrolled.
• A standard 12-lead ECG will be recorded for each participant at the time of ICA, with standardized angiograms serving as the reference standard.

Main Results:

• Primary endpoint is the AI model's accuracy in identifying actively occluded culprit coronary arteries (TIMI 0-1 flow) using only ECG data.
• The study will provide prospective data on the AI model's real-world performance.
• Analysis will correlate ECG findings with angiographic results to understand myocardial perfusion abnormalities.

Conclusions:

• AI-ECG TIMI is the first prospective registry to record standard 12-lead ECGs concurrently with ICA in ACS patients.
• This study will prospectively validate an AI model's capability to detect acute ischemia via ECG.
• Findings will enhance understanding of ECG markers for abnormal myocardial perfusion during acute events.