A video-based AI biomarker (Digital Aortic Stenosis [AS] Severity index [DASSi]) can detect severe AS development and progression in patients undergoing echocardiography or cardiac MRI, according to a study published in JAMA Cardiology. Evangelos K. Oikonomou, MD, DPhil, and colleagues deployed DASSi to patients with no AS or mild-to-moderate AS at baseline. The study included 12,599 participants: 8,798 from the Yale New Haven Health System (YNHHS) and 3,801 from the Cedars-Sinai Medical Center (CSMC). Higher baseline DASSi was associated with faster progression in aortic valve velocity (AV-Vmax; per 0.1 DASSi increment, 0.033 and 0.082 m/s per year in YNHHS and CSMC, respectively), with values of 0.2 or greater associated with a 4- to 5-fold higher aortic valve replacement risk compared with values of less than 0.2 (adjusted hazard ratios [95 percent confidence intervals], 4.97 [2.71 to 5.82] and 4.04 [0.92 to 17.70] for YNHHS and CSMC, respectively). This finding was independent of confounding variables such as age, sex, race, ethnicity, ejection fraction, and AV-Vmax. The findings were reproduced in 45,474 participants undergoing cardiac MRI in the UK Biobank.
