Abstract 13157: Multivariable ECG Machine Learning is Superior to QRS Duration and Traditional ECG Criteria for Detecting Left Ventricular Hypertrophy in Patients With Left Bundle Branch Block

Abstract

Introduction: The utility of ECG to diagnose left ventricular hypertrophy (LVH) in patients with left bundle branch block (LBBB) is limited. We sought to compare the diagnostic yield of ECG using (i) QRS duration, (ii) published LVH criteria, and (iii) machine learning (ML) models to detect increased left ventricular mass indexed (LVMi) in the setting of LBBB. Hypothesis: ML is superior to QRS duration and LVH criteria to detect LVH among LBBB. Methods: 12-lead ECGs were processed to reconstruct orthogonal X, Y, Z leads using Kors’s matrix and obtain root-mean-squared (3D) ECG. R wave, S wave and overall amplitudes, voltage-time-integrals (VTIs), and other ECG features were extracted from all ECG leads. ML algorithms [logistic regression (LR), support vector classifier (SVC), decision trees (DT), random forest (RF), gradient boosted machine (GBM) and boosted trees (BT)] were trained to predict increased LVMi (women >95 g/m 2 , men >115 g/m 2 ) from ECG features on a training set of 2668 ECGs with typical LBBB and echocardiogram within 45 days before or after ECG. LVM was calculated using the ASE formula. We obtained ROC AUCs for prediction of increased LVMi by (i) QRS duration, (ii) published LVH criteria, and (iii) ML models in a separate validation set of adults with typical LBBB. Results: Among the validation set of 413 adults (53% women, age 73±12 yr) with LBBB, QRS duration alone had a higher AUC (women 0.657, men 0.703) for diagnosing increased LVMi compared to standard LVH criteria (Table). RF (women 0.688, men 0.738), GBM and DT models had better AUCs than QRS duration alone. Conclusions: In patients with LBBB, QRS duration ≥150 in women and ≥160 in men is a superior predictor of LVH than traditional voltage-based ECG criteria, but ML methods outperform all traditional ECG criteria and QRS duration.