Knight Elizabeth, Oikonomou Evangelos K, Aminorroaya Arya, Pedroso Aline F, Khera Rohan
Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA.
Center for Outcomes Research and Evaluation (CORE), Yale New Haven Hospital, New Haven, CT, USA.
medRxiv. 2025 Jun 12:2025.06.10.25329163. doi: 10.1101/2025.06.10.25329163.
Artificial intelligence (AI) models can now detect patterns of structural heart diseases (SHDs) from electrocardiograms (ECGs), though scaling them requires the broader use of single-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 single-lead ECGs with information from echocardiographic text reports. Using 274,057 single-lead ECG-echo pairs from 77,378 adults (2015-2019), we contrastively pre-trained convolutional neural network (CNN) and RoBERTa 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 single-lead ECGs on echocardiographic text reduces label requirements for SHD screening on wearable and portable devices.
人工智能（AI）模型现在可以从心电图（ECG）中检测出结构性心脏病（SHD）的模式，不过要扩大其应用规模，需要更广泛地使用单导联心电图，而这种心电图在可穿戴设备和便携式设备中已很常见。然而，针对这些设备的模型开发受到可穿戴心电图缺乏SHD诊断标签的限制。在此，我们展示了可穿戴式回声调频模型（Wearable-Echo-FM），这是一种基础模型，它利用超声心动图文本报告中的信息对单导联心电图进行编码。我们使用了来自77378名成年人（2015 - 2019年）的274057个单导联心电图 - 回声对，对卷积神经网络（CNN）和RoBERTa编码器进行了对比预训练。心电图编码器在一个逐渐增大的不同心电图集（250至250260份心电图）上进行微调，以检测不同的心脏疾病：（i）左心室收缩功能障碍（LVSD），（ii）舒张功能障碍，以及（iii）复合性SHD。将其与随机初始化的CNN进行比较，两种方法都在一个独立的留出测试集中进行评估。在完整训练集的情况下，可穿戴式回声调频模型与基线CNN相当（LVSD的受试者工作特征曲线下面积分别为0.894对0.884；舒张功能障碍为0.849对0.843；复合性SHD为0.887对0.869）。仅使用0.5%（约1000份心电图）的数据时，它的表现就明显优于基线（分别为0.855对0.548；0.819对0.582；0.863对0.496）。在超声心动图文本上对单导联心电图进行对比预训练，可减少可穿戴和便携式设备上SHD筛查的标签需求。
