An automated machine learning algorithm using 12-lead ECG features predicted right versus left ventricular outflow tract origins of ventricular tachycardia with an AUC of 98.99%.
Observational (n=420)
No
Does a machine learning algorithm using automatically extracted 12-lead ECG features improve the prediction of LVOT vs. RVOT origins of ventricular arrhythmias compared to conventional criteria and human cardiologists?
A novel machine learning algorithm utilizing over 1.6 million automated ECG features achieved clinical-grade precision (>97% accuracy) in localizing outflow tract ventricular arrhythmias, significantly outperforming conventional criteria and human experts.
Absolute Event Rate: 98.99% vs 95.62%
p-value: p=0.035
Introduction Multiple algorithms based on 12-lead ECG measurements have been proposed to identify the right ventricular outflow tract (RVOT) and left ventricular outflow tract (LVOT) locations from which ventricular tachycardia (VT) and frequent premature ventricular complex (PVC) originate. However, a clinical-grade machine learning algorithm that automatically analyzes characteristics of 12-lead ECGs and predicts RVOT or LVOT origins of VT and PVC is not currently available. The effective ablation sites of RVOT and LVOT, confirmed by a successful ablation procedure, provide evidence to create RVOT and LVOT labels for the machine learning model. Methods We randomly sampled training, validation, and testing data sets from 420 patients who underwent successful catheter ablation (CA) to treat VT or PVC, containing 340 (81%), 38 (9%), and 42 (10%) patients, respectively. We iteratively trained a machine learning algorithm supplied with 1,600,800 features extracted via our proprietary algorithm from 12-lead ECGs of the patients in the training cohort. The area under the curve (AUC) of the receiver operating characteristic curve was calculated from the internal validation data set to choose an optimal discretization cutoff threshold. Results The proposed approach attained the following performance: accuracy (ACC) of 97.62 (87.44–99.99), weighted F1-score of 98.46 (90–100), AUC of 98.99 (96.89–100), sensitivity (SE) of 96.97 (82.54–99.89), and specificity (SP) of 100 (62.97–100). Conclusions The proposed multistage diagnostic scheme attained clinical-grade precision of prediction for LVOT and RVOT locations of VT origin with fewer applicability restrictions than prior studies.
Zheng et al. (Thu,) conducted a observational in Outflow tract ventricular tachycardia (OTVT) (n=420). Automated machine learning algorithm (XGBoost) vs. Conventional QRS morphological feature extraction was evaluated on Area under the curve (AUC) for predicting RVOT vs LVOT origins (95% CI 96.89-100, p=0.035). An automated machine learning algorithm using 12-lead ECG features predicted right versus left ventricular outflow tract origins of ventricular tachycardia with an AUC of 98.99%.