In a recent study conducted by the Cardiovascular Data Science (CarDS) Lab at Yale School of Medicine, researchers created an artificial intelligence (AI) tool that identifies individuals at high risk for developing heart failure by analyzing electrocardiogram (ECG) images. This innovative tool allows for earlier detection of heart failure, which could lead to a decrease in hospitalizations and premature deaths, according to the researchers. The findings from the study were published online in the European Heart Journal. ECGs are noninvasive examinations that assess the electrical activity of the heart using electrodes placed on the skin. As these tests are often performed and readily accessible, they serve as an excellent platform for large-scale heart failure screening. Heart failure is a prevalent cardiovascular condition that affects millions globally. Currently, identifying individuals at high risk of heart failure typically involves a combination of clinical evaluations, including comprehensive clinical history, physical exams, and blood tests, which may not always be accessible, notes first author Lovedeep Singh Dhingra, MBBS, a postdoctoral fellow in the CarDS Lab. According to Dhingra, the AI-driven tool signifies a major advancement in heart failure risk assessment. “Our model, which utilizes a photograph of a 12-lead ECG as input, was able to effectively assess heart failure risk across varied populations in the United States, United Kingdom, and Brazil, ” he stated.

“We can now foresee who might be at risk of developing heart failure in the future, even before they exhibit clear symptoms. ” The study’s senior author, Rohan Khera, MD, MS, an assistant professor of medicine (cardiovascular medicine) and director of the CarDS Lab, highlighted the significant public health implications of this research. “Every time a clinician performs an ECG—a procedure that is already part of standard clinical care—our straightforward tool provides an opportunity for screening and risk assessment for cardiovascular disease, ” Khera explained. “The widespread availability of ECG technology, even in resource-limited settings, allows for early intervention and improved outcomes for patients who might otherwise remain undiagnosed. ” As part of the CarDS Lab’s global initiative, the AI model was tested across various international populations, emphasizing its potential for broad implementation. “Our goal is to ensure the wide and equitable integration of AI-based health technologies into everyday medical practice, ” Khera added. “This is our next challenge. ” This research received funding from grants provided by the National Heart, Lung, and Blood Institute, the National Institute on Aging of the National Institutes of Health (NIH), and the Doris Duke Charitable Foundation. Other authors affiliated with Yale include Arya Aminorroaya, MD, PhD, Veer Sangha, Aline Pedroso, PhD, Harlan Krumholz, MD, SM, and Evangelos Oikonomou, MD, DPhil. For further information, read the article titled “Heart failure risk stratification using artificial intelligence applied to electrocardiogram images: a multinational study. ” The Department of Internal Medicine at Yale School of Medicine stands among the country’s leading departments, uniting an elite group of clinicians, researchers, educators, and staff within one of the world’s top medical schools. To learn more, visit Internal Medicine.