AI-powered ECG assessments may improve heart transplant rejection warnings
Researchers with NYU Langone Health may have identified a new way to predict heart transplant rejection without the need for an invasive biopsy. Their findings were recently published in the Journal of Heart and Lung Transplantation.[1]
The study combined blood biomarkers with electrocardiogram (ECG) heart rhythm recordings into an artificial intelligence (AI) model and then compared the results directly against the gold-standard myocardial biopsy results. The team found the AI accurately identified when a transplant patient’s body starts attacking a donated heart.
“Our results highlight that electrocardiograms contain an abundance of physiological information that can be used to substantially improve the accuracy of detection and enable earlier diagnosis and treatment for patients with cardiac transplant rejection,” senior author Lior Jankelson, MD, PhD, said in a statement. He is an associate professor in the Leon H. Charney Division of Cardiology in NYU Grossman School of Medicine’s Department of Medicine and an associate professor of biomedical engineering at NYU Tandon School of Engineering.
The researchers trained AI models to recognize patterns in more than 5,300 ECG readings from 389 adult heart transplant recipients between 2018 and 2024. One AI model was trained on ECG data alone. A second AI model used ECG data and the results from two blood tests, AlloMap, AlloSure, traditionally used to predict rejection risk. Blood biomarkers measure gene activity linked to cellular rejection and fragments of donor heart DNA in the recipient’s bloodstream. While this test does spot rejection, it also comes with a high false-positive rate.
The team then applied their AI models to a test group of 38 heart transplant recipients and found the combined model performed better. Two patients experienced rejection. The AI model correctly identified 97% of patients who were not experiencing rejection. However, the model based only on the combination of both blood tests incorrectly indicated that 19 patients needed a biopsy. The researchers said the combined model would have spared these patients from the biopsy procedure.
“Heart transplantation is a major, resource-intensive procedure, and rejection is common but treatable if caught in time,” Jankelson said. “Based on our findings, combining the availability of EKGs with the support of AI may help identify rejection earlier and save more lives.”
As a next step, the researchers said they plan to test the AI model in more patients at several transplant centers.
Dave Fornell has covered healthcare for more than 17 years, with a focus in cardiology and radiology. Fornell is a 5-time winner of a Jesse H. Neal Award, the most prestigious editorial honors in the field of specialized journalism. The wins included best technical content, best use of social media and best COVID-19 coverage. Fornell was also a three-time Neal finalist for best range of work by a single author. He produces more than 100 editorial videos each year, most of them interviews with key opinion leaders in medicine. He also writes technical articles, covers key trends, conducts video hospital site visits, and is very involved with social media. E-mail: [email protected]