AHA Scientific Sessions 2026 Abstract
Heart-trace models trained apart did slightly better on new data
Average absolute age-estimation error was 7.74 years with federated training versus 8.04 years with pooled training in external testing.Average absolute age-estimation error was 7.74 years with federated training versus 8.04 years with pooled training in external testing.
Computational studyBiomarkers
Who was studied1,202,162 ECGs, against pooled training
What changedAverage absolute age-estimation error was lower with federated training: 7.74 years versus 8.04 years with pooled training
The catchThe federated setup was simulated; operation across institutions was not measured