The abstract is read at the publisher; the summary is JClub's.
An explainable AI-ECG model detects the echocardiographic DCM phenotype with AUCs of .87–.97, outperforming traditional ECG parameters across external validation cohorts.
- Why it matters: Early identification of people at risk for dilated cardiomyopathy is a key care challenge, especially for genetically predisposed individuals before echocardiographic disease appears.
- What they did: A deep learning model was trained on 330 000+ ECG-echocardiogram pairs from Beth Israel Deaconess Medical Center, then validated in UK Biobank, Zhongshan Hospital, and Antwerp University Hospital, with comparisons to traditional ECG and echocardiographic traits.
- The result: In familial cohorts, 5-year negative predictive values were 95.5% (Antwerp) and 91.5% (Maastricht), and high-risk scores were linked to a 5.1–6.4-fold increased risk of incident DCM.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.