Researchers at the Mount Sinai Kravis Children's Heart Center have developed and validated an artificial intelligence (AI) tool capable of analyzing a standard electrocardiogram (ECG) to identify patients with repaired tetralogy of Fallot who may be at risk for harmful heart changes typically detected by cardiac MRI. The study, funded by the National Institutes of Health and published in the European Heart Journal: Digital Health, represents a significant step toward improving lifelong monitoring for individuals born with this congenital heart defect. Tetralogy of Fallot, a complex heart condition, requires surgical repair in childhood but demands ongoing surveillance throughout life to detect subtle changes in heart structure and function. Cardiac MRI remains the gold standard for follow-up, yet it is costly, time-intensive, and not always accessible, leading many patients to miss recommended imaging appointments. In this multicenter study, scientists trained an AI model using ECG and MRI data from patients with repaired tetralogy of Fallot, then validated its performance across five additional hospitals in North America. The AI learned to recognize patterns in ECG signals associated with ventricular remodeling—abnormal changes in heart size and pumping ability that may indicate progressive disease. Key findings show that the AI-ECG tool can effectively flag patients who may need urgent cardiac MRI, potentially reducing unnecessary scans while ensuring timely detection of clinically significant changes. “This research shows how artificial intelligence can unlock new value from a routine ECG,” said Son Duong, MD, MS, lead author and Assistant Professor of Pediatrics and Artificial Intelligence and Human Health at Icahn School of Medicine at Mount Sinai. “Our goal is to make lifelong heart monitoring more accessible and efficient for people born with congenital heart disease.” The researchers stress that the AI model is not designed to replace cardiac MRI. Instead, it serves as a screening tool to help clinicians prioritize which patients need imaging, improving care efficiency and reducing delays. “As AI becomes more integrated into health care, it is critical to rigorously validate these tools across diverse clinical settings,” said Girish Nadkarni, MD, MPH, co-senior author and Barbara T. Murphy Chair of the Windreich Department of Artificial Intelligence and Human Health at Mount Sinai Health System. “Our findings show both the promise of AI-enabled screening and the importance of testing performance at each site before real-world implementation.” Dr. Nadkarni also serves as Director of the Hasso Plattner Institute for Digital Health and Chief AI Officer at Icahn School of Medicine at Mount Sinai. The implications are significant. Patients with congenital heart disease often face lifelong medical follow-up, and access to advanced imaging can be a barrier. By leveraging AI with a widely available and low-cost test like the ECG, the team aims to bridge gaps in care. Moving forward, the research team plans to conduct prospective clinical trials to further evaluate the AI-ECG approach and refine the model for use in younger patients. The long-term vision is to integrate the tool into routine clinical practice, enabling earlier detection of heart changes and better long-term outcomes for patients with repaired tetralogy of Fallot.