Wearable-Echo-FM: an ECG echo foundation model for 1-lead electrocardiography

Artificial intelligence (AI) models can now detect patterns of structural heart diseases (SHDs) from electrocardiograms (ECGs), though scaling them requires the broader use of 1-lead ECGs that are now ubiquitous in wearable and portable devices. However, model development for these devices is limited by a lack of diagnostic labels for SHDs for wearable ECGs.

Here, we present Wearable-Echo-FM, a foundation model that encodes 1-lead ECGs with information from echocardiographic text reports. Using 194 551 1-lead ECG-echo pairs from 77 378 adults (2015-2018), we contrastively pre-trained ECG convolutional neural network (CNN) and RoBERTa text encoders. The ECG encoder was fine-tuned on a distinct progressively larger ECG set (250 to 250 260 ECGs) to detect different cardiac disorders: (i) left-ventricular systolic dysfunction (LVSD), (ii) diastolic dysfunction, and (iii) a composite SHD. This was compared with a randomly initialized CNN, with both approaches evaluated in an independent held-out test set. With the full training set, Wearable-Echo-FM matched the baseline CNN (AUROC 0.894 vs. 0.884 for LVSD; 0.849 vs. 0.843 diastolic dysfunction; 0.887 vs. 0.869 composite). With only 0.5% (∼1000 ECGs) of data, it markedly outperformed baseline (0.855 vs. 0.548; 0.819 vs. 0.582; 0.863 vs. 0.496, respectively).

Contrastive pre-training of 1-lead ECGs on echocardiographic text reduces label requirements for label-efficient development of SHD screening models on 1-lead ECGs, providing a foundation for future validation on wearable and portable devices.