A novel practical algorithm using machine learning to differentiate outflow tract ventricular arrhythmia origins

INTRODUCTION

Diagnosis of outflow tract ventricular arrhythmia (OTVA) localization by an electrocardiographic complex is key to successful catheter ablation for OTVA. However, diagnosing the origin of OTVA with a precordial transition in lead V3 (V3TZ) is challenging. This study aimed to create the best practical electrocardiogram algorithm to differentiate the left ventricular outflow tract (LVOT) from the right ventricular outflow tract (RVOT) of OTVA origin with V3TZ using machine learning.

METHODS

Of 498 consecutive patients undergoing catheter ablation for OTVA, we included 104 patients who underwent ablation for OTVA with V3TZ and identified the origin of LVOT (n = 62) and RVOT (n = 42) from the results. We analyzed the standard 12-lead electrocardiogram preoperatively and measured 128 elements in each case. The study population was randomly divided into training group (70%) and testing group (30%), and decision tree analysis was performed using the measured elements as features. The performance of the algorithm created in the training group was verified in the testing group.

RESULTS

Four measurements were identified as important features: the aVF/II R-wave ratio, the V2S/V3R index, the QRS amplitude in lead V3, and the R-wave deflection slope in lead V3. Among them, the aVF/II R-wave ratio and the V2S/V3R index had a particularly strong influence on the algorithm. The performance of this algorithm was extremely high, with an accuracy of 94.4%, precision of 91.5%, recall of 100%, and an F1-score of 0.96.

CONCLUSIONS

The novel algorithm created using machine learning is useful in diagnosing the origin of OTVA with V3TZ.

A couplet of PVCs with different QRS morphologies arising from a single origin in the left ventricular outflow tract

A 59-year-old man with two different premature ventricular contractions (PVCs) forming a couplet underwent electrophysiological testing. Although pacing from the aorto-mitral continuity (AMC) produced an excellent pace map of one type of PVCs, a radiofrequency application within the right coronary cusp (RCC) eliminated all the PVCs. This case demonstrates that a single origin with two breakout sites in the left ventricular ostium (LVos) may result in a couplet consisting of different PVCs and preferential conduction from the RCC to AMC may also occur. These possibilities should be kept in our mind when predicting sites of origin of LVos ventricular arrhythmias.

QRS alternans during idiopathic ventricular tachycardia originating from the right coronary cusp of the aorta

A 77-year-old man underwent electrophysiological testing for idiopathic ventricular tachycardia (VT) with QRS alternans exhibiting a left bundle branch block and left inferior axis QRS morphology. Successful radiofrequency catheter ablation was achieved at the site of the earliest ventricular activation in the right coronary cusp. Pacing at this site reproduced an excellent pace map with QRS alternans. Pacing from other sites in the ventricular outflow tracts reproduced neither an excellent pace map nor QRS alternans. This case demonstrates that VT with a single origin and multiple exits in the aortic root may exhibit QRS alternans.

Idiopathic premature ventricular contractions exhibiting preferential conduction within the aortic root

A 65-year-old man with frequent premature ventricular contractions (PVCs) underwent electrophysiological testing. Although an excellent pace map was obtained from the right coronary cusp (RCC), radiofrequency ablation at that site interrupted the PVCs transiently. Successful ablation was achieved in the left coronary cusp with earlier local ventricular activation during the PVCs than that in the RCC. These findings suggest that preferential conduction within the aortic root may exist and cause ventricular arrhythmias (VAs) arising from this region to exhibit variable electrocardiographic features, thereby limiting the reliability of electrocardiographic algorithms and pace mapping to predict the site of the VA origin.