A multi-channel masked autoencoder (MCMA) successfully reconstructed 12-lead ECGs from arbitrary single-lead ECGs, achieving average diagnostic F1-scores of 0.8233 and 0.8410.
Does a multi-channel masked autoencoder accurately reconstruct a 12-lead ECG from an arbitrary single-lead ECG?
The proposed multi-channel masked autoencoder successfully reconstructs 12-lead ECGs from arbitrary single-lead inputs, potentially enhancing the diagnostic utility of single-lead wearable devices.
Electrocardiogram (ECG) has emerged as a widely accepted diagnostic instrument for cardiovascular diseases (CVD). The standard clinical 12-lead ECG configuration causes considerable inconvenience and discomfort, while wearable devices offers a more practical alternative. To reduce information gap between 12-lead ECG and single-lead ECG, this study proposes a multi-channel masked autoencoder (MCMA) for reconstructing 12-Lead ECG from arbitrary single-lead ECG, and a comprehensive evaluation benchmark, ECGGenEval, encompass the signal-level, feature-level, and diagnostic-level evaluations. MCMA can achieve the state-of-the-art performance. In the signal-level evaluation, the mean square errors of 0.0175 and 0.0654, Pearson correlation coefficients of 0.7772 and 0.7287. In the feature-level evaluation, the average standard deviation of the mean heart rate across the generated 12-lead ECG is 1.0481, the coefficient of variation is 1.58%, and the range is 3.2874. In the diagnostic-level evaluation, the average F1-score with two generated 12-lead ECG from different single-lead ECG are 0.8233 and 0.8410.
Chen et al. (Wed,) conducted a other in Cardiovascular diseases. Multi-channel masked autoencoder (MCMA) was evaluated on Signal-level, feature-level, and diagnostic-level evaluations (ECGGenEval benchmark). A multi-channel masked autoencoder (MCMA) successfully reconstructed 12-lead ECGs from arbitrary single-lead ECGs, achieving average diagnostic F1-scores of 0.8233 and 0.8410.