SC Connecticut News

Yale investigators from the section of cardiovascular medicine have identified a new artificial intelligence (AI)-based video biomarker for aortic stenosis development and progression. The research, published in JAMA Cardiology on April 6, 2024, introduces the Digital AS Severity index (DASSi) as a predictive tool for identifying patients at risk of severe aortic stenosis.

Lead author of the study, Evangelos K. Oikonomou, MD, DPhil, emphasized the significance of this breakthrough, stating, "So far, we have not had a way to know who develops aortic stenosis or who gets worse. This is foundational research that we believe will facilitate further study of new treatments to address the progression of aortic stenosis and, eventually, help prevent bad outcomes."

The senior author of the paper, Rohan Khera, MD, MS, highlighted the versatility of DASSi, stating, "DASSi can convert cardiac MRIs, point of care ECGs, and cardiac ultrasound all using the same model." This adaptability across multiple modalities is crucial in flagging distinct myocardial and valvular phenotypic signatures for aortic stenosis.

Eric J. Velazquez, MD, co-author of the study, commended the research's innovative use of AI, stating, "This research shows how creatively using AI can help us better understand a common heart disease and ultimately help us identify new approaches to stem the progression of the disease so that fewer patients develop severe aortic stenosis."

The study's findings also advocate for the use of DASSi in opportunistic screening of aortic stenosis on ECGs. Khera expressed his belief in the potential impact of this research on clinical practice, stating, "This research shows that it’s possible to diagnose aortic stenosis and prognosticate risk of aortic stenosis using cardiac ultrasounds and cardiac MRI. That’s potentially practice-changing."

Looking ahead, Khera and the CarDS lab colleagues plan to launch a multi-randomized clinical trial to confirm the role of AI in diagnosing aortic stenosis and identifying individuals at risk of disease progression. Khera emphasized their commitment to advancing beyond tool development, stating, "We want to see whether these tools and discoveries can change practice and help cardiologists better identify each patient’s potential risk factors."

The study, which was also presented at the 2024 American College of Cardiology’s Scientific Sessions by Oikonomou, involved a team of Yale researchers including Gregory Holste, Andreas Coppi, Robert L. McNamara, Norrisa Haynes, Amit N. Vora, Fan Li, Thomas Gill, and Harlan M. Krumholz.