Using artificial intelligence (AI) to analyze electrocardiograms (ECG) has significantly improved the detection of severe heart attacks, particularly those presenting with unconventional symptoms or atypical ECG patterns. This advancement also reduces false positives, according to a study published in JACC: Cardiovascular Interventions and presented at TCT 2025 in San Francisco.
ST-segment elevation myocardial infarction (STEMI) is a critical type of heart attack where a major coronary artery is blocked, cutting off blood supply to the heart muscle. Rapid restoration of blood flow, known as reperfusion, is crucial and typically achieved through percutaneous coronary intervention (PCI). However, delays in meeting the guideline-recommended time for reperfusion remain a challenge, especially in non-specialized hospitals and rural areas. A delay exceeding 90 minutes can lead to a threefold increase in mortality rates.
AI-Driven ECG Analysis: A Game Changer
“AI-driven ECG interpretation can bring the best of both worlds – identify true heart attacks early while reducing unnecessary activations,” said Robert Herman, MD, PhD, lead author of the study and a cardiovascular researcher at AZORG Hospital in Aalst, Belgium. “Improving the accuracy of triage at the first medical contact can streamline emergency care, reduce fatigue and strain on clinical teams, and ensure that patients who truly need urgent intervention receive it without delay.”
In one of the first large-scale, real-world evaluations of an AI-based ECG model for STEMI triage in emergency settings, researchers retrospectively analyzed data from 1,032 patients with suspected STEMI who triggered emergency reperfusion protocols. This data was collected from three geographically diverse primary PCI centers between January 2020 and May 2024. Each patient’s initial ECG was analyzed by the STEMI AI ECG Model, known as “Queen of Hearts,” which is trained to detect acute coronary occlusion, including STEMI equivalents, and differentiate them from benign mimics.
Remarkable Results and Expert Insights
Angiography and biomarkers confirmed that out of the 1,032 cases, 601 (58%) were true STEMIs, while 431 (42%) were false positives. The AI ECG model outperformed standard triage methods, detecting 553 of the 601 confirmed STEMIs compared to 427 detected by standard triage on the initial ECG. The AI ECG model achieved a false positive rate of 7.9%, compared to 41.8% for standard triage, representing a fivefold reduction.
“These results indicate that AI-enhanced STEMI diagnosis at the first medical contact has the potential to shorten time to treatment and reduce false activations,” said Timothy D. Henry, MD, FACC, senior author of the study, and Medical Director of The Carl and Edyth Lindner Center for Research and Education at The Christ Hospital in Cincinnati.
In an accompanying editorial comment, Mohamad Alkhouli, MD, MBA, a cardiologist at the Mayo Clinic, praised the researchers for developing an operational AI model aimed at addressing one of the most complex and error-prone aspects of interventional cardiology practice—STEMI activation. However, he cautioned that the AI model was originally developed to detect occluded arteries rather than STEMI and requires further prospective validation across diverse patient populations.
Implications for the Future of Cardiac Care
The implications of AI-enhanced ECG analysis are profound, particularly for optimizing the transfer of STEMI patients from non-PCI centers to ensure timely and appropriate care. The technology promises to streamline emergency protocols, reduce unnecessary strain on healthcare resources, and potentially save lives by ensuring quicker and more accurate diagnosis and treatment.
“The true challenge is not proof of accuracy alone, but readiness—to integrate, regulate, and interpret AI as a complement to human judgment, particularly in high-stakes, time-sensitive clinical settings,” Alkhouli emphasized.
The American College of Cardiology (ACC), a global leader in cardiovascular care, continues to support advancements in medical technology and research. For over 75 years, the ACC has empowered a community of over 60,000 cardiovascular professionals worldwide with cutting-edge education and advocacy, rigorous professional credentials, and trusted clinical guidance.
The ACC’s JACC Journals are among the top cardiovascular journals globally for scientific impact, publishing peer-reviewed research on all aspects of cardiovascular disease. These efforts underscore the commitment to creating a world where science, knowledge, and innovation optimize patient care and outcomes.
As AI continues to evolve, its integration into medical diagnostics holds the promise of transforming emergency cardiac care, offering hope for more efficient and effective treatment pathways in the future.
