Multi-Channel Masked Autoencoder and Comprehensive Evaluations for Reconstructing 12-Lead ECG from Arbitrary Single-Lead ECG

TL;DR

This work tackles the challenge of bridging wearable single-lead ECG sensing with the diagnostic richness of a standard 12-lead ECG. It introduces the Multi-Channel Masked Autoencoder (MCMA) that can reconstruct a full 12-lead ECG from any single input lead, paired with ECGGenEval, a three-level benchmark for signal-, feature-, and diagnostic-level evaluation. Across internal PTB-XL and external CPSC2018 CODE-test datasets, MCMA achieves high fidelity reconstructions (low MSE, high PCC) and preserves clinically relevant information, including heart-rate consistency and arrhythmia classification performance. The study demonstrates practical potential for wearable-based cardiac monitoring and provides open data and code to support further research and clinical translation.

Abstract

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 0.0317 and 0.1034, Pearson correlation coefficients of 0.7885 and 0.7420. 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.

Figures (6)

• Figure 1: The 12-lead ECG generation process with single-lead ECG, the input single-lead ECG can be arbitrary, including I, II, III, aVR, aVL, avF, V1, V2, V3, V4, V5, V6, and this case takes lead I as an example
• Figure 2: The detailed model architecture, the proposed model mainly includes MCBlock and MCTBlock.
• Figure 3: The mean square error and Pearson correlation coefficient in the training process. The red circle means training loss, the blue star is validation loss, the black circle means training Pearson correlation coefficient ($PCC$), and the black star means validation Pearson correlation coefficient ($PCC$).
• Figure 4: The 12-lead ECG reconstruction performance in the internal testing set PTB-XL, the red lines are the real signals while the blue lines represent the generated signals.
• Figure 5: The 12-lead ECG reconstruction performance in the external testing set CPSC2018, the red lines are the real signals while the blue lines represent the generated signals.