November 14, 2026 · European heart journal · DOI: 10.1093/eurheartj/ehag917

Artificial intelligence-enhanced electrocardiography for detection and prediction of dilated cardiomyopathy.

Listen to this summary

An AI model trained on over 330,000 paired ECG-echocardiogram records was developed to detect dilated cardiomyopathy (DCM) and predict its future onset, asking whether a low-cost ECG could identify disease before it manifests. The model achieved AUROCs of 0.87-0.97 for prevalent DCM, outperformed traditional ECG parameters, and matched echocardiography for predicting incident disease across external cohorts. In genetically at-risk familial cohorts, it showed high 5-year negative predictive values (91.5-95.5%), suggesting it could help exclude short- to mid-term disease and reduce surveillance burden, though positive predictive values were modest (39-42%).

Ewa Sieliwonczyk, Arunashis Sau, Yixiu Liang, Konstantinos Patlatzoglou, Kathryn A McGurk, Libor Pastika, Pantazis Theotokis, Joseph Barker, Boroumand Zeidaabadi, Upasana Tayal, Brian P Halliday, Sanjay Prasad, Declan P O'Regan, Nicholas S Peters, Nina J Beelen, Job A J Verdonschot, Johan Saenen, Olivier Van Leuven, Peter Gorissen, Bart Loeys, Junbo Ge, Daniel B Kramer, Jonathan W Waks, James S Ware, Fu Siong Ng

This is one of 33,000+ journals available on OSLR. Try it free for 14 days.

Free 14-day trial. 33,000+ journals. Cancel anytime.

14-day free trial. No commitment.

“

"Oslr has become part of my weekly routine on my day off. The clinical relevance of the summaries is outstanding — I'd rate it 9/10. Being able to consume research hands-free is a huge advantage for busy physicians."

Dr. Jennifer Thompson

Dr. Jennifer Thompson

Portland, OR

Stay current without falling behind

33,000+ journals. 3-minute audio summaries. Free for 14 days.

Download on the App StoreGet it on Google Play