Are you at risk of a silent heart attack? Now, AI can detect the disease in the blink of an eye.

News Topical, Digital Desk : Heart attack cases are rising rapidly worldwide. Artificial intelligence (AI)-based methods for interpreting ECGs outperformed standard methods in detecting occlusive myocardial infarction (MI), according to a study presented at ESC Acute Cardiovascular Care 2026, a conference of the Association for Acute Cardiovascular Care (ACVC), a branch of the European Society of Cardiology (ESC).

Blockage in the patient's coronary artery

In patients suspected of having acute coronary syndrome elevation infarction (ACS), a characteristic change in the ESC, called ST elevation, indicates a possible blockage in a coronary artery. This type of heart attack is known as ST myocardial infarction (SEMI) and requires immediate percutaneous coronary intervention to restore blood flow to the heart. In patients who do not have ST elevation, the cause of chest pain may be less certain.

"Many patients who do not have an ST elevation have an occlusive MI, but it can be difficult for doctors to recognize it quickly and accurately, leading to delays in emergency treatment," explained Dr. Federico Nani of the Central Hospital of Bolzano, Italy. "We investigated whether AI-based interpretation of initial ECGs could improve the accuracy of detecting occlusive MI."

Study done on 1,490 patients

This single-center, prospective study included 1,490 patients who presented with symptoms of ACS but did not have ST elevation on their initial ECG. Their average age was 63 years, and 42 percent were women. Doctors reviewed the initial ECG, checked the cardiac biomarker troponin levels, and, if necessary, performed coronary angiography to rule out occlusive MI based on ESC guidelines. The initial ECG was also evaluated by a smartphone-based, CE-certified AI ECG algorithm.

Correctly identified occlusive MI in 42% of cases

AI-based ECG interpretation ruled out occlusive MI in 1,382 patients and detected it in 108 patients (7%). The AI-based method correctly identified obstructive MI in 84% of cases. Its sensitivity for correct identification was 77%, specificity was 99%, and negative predictive value was 98%. There were 27 false negatives (2%) and 17 false positives (1%). In 1,207 patients, occlusive MI was ruled out based on troponin levels, and 283 patients underwent coronary angiography to confirm or rule out the diagnosis. ECG interpretation correctly identified occlusive MI in 42% of cases.

Read More: Are you at risk of a silent heart attack? Now, AI can detect the disease in the blink of an eye.