Machine learning to classify left ventricular hypertrophy using ECG feature extraction by variational autoencoder

Traditional ECG criteria for left ventricular hypertrophy (LVH) have modest diagnostic yield. Develop and validate machine learning models for LVH diagnosis from ECG. ECG summary features (rate, intervals, axis), R-wave, S-wave and overall-QRS amplitudes, and QRS voltage-time integrals (VTIQRS) were extracted from 12-lead, vectorcardiographic X-Y-Z-lead, and 3D (L2 norm) representative-beat ECGs. Latent features (30 per ECG) were extracted using a variational autoencoder (trained on unselected >1 million ECGs) from X-Y-Z-lead representative-beat ECG signals. Logistic regression, random forest, light gradient boosted machine (LGBM), residual network (ResNet) and multilayer perceptron network (MLP) models using ECG features and sex, and a convolutional neural network (CNN) using ECG signals alone, were trained to predict LVH (left ventricular mass indexed in women >95 g/m2, men >115 g/m2) on 482,734 adult ECG-echocardiogram (within 45 days) pairs. ROC-AUCs for LVH classification are reported from a separate hold-out test set. In the test set (n=54,984), AUC for LVH classification was higher for ML models using ECG features (LGBM 0.794, MLP 0.793, ResNet 0.795) compared with the best individual ECG variable (VTIQRS-Z 0.707), the best traditional criterion (Cornell voltage-duration product 0.716), and the CNN using ECG signals (0.788). Among patients without LVH who had a follow-up echocardiogram >1 (closest to 5) year later, LGBM false positives, compared to true negatives, had a 3.07 (95% CI 2.44, 3.86)-fold higher odds of developing future LVH (p<0.0001). ML models are superior to traditional ECG criteria to classify LVH. Models trained on extracted ECG features, including latent variational autoencoder representations, can outperform CNN models directly trained on ECG signals.