Abstract 16473: Validation of the Artificial Intelligence-Based 5-Lead 3D Vectorcardiography in Comparison to the 12-Lead ECG in a Mixed Population

Abstract

Introduction: Artificial Intelligence-based 5-lead 3D-vectorcardiography (5L3DVCG-AI) offers additional information over 12-lead electrocardiography (ECG) in the detection of significant coronary stenoses. 5L3DVCG-AI is under investigation as a new screening tool for coronary vascular disease (CVD). Hypothesis: We tested the hypothesis of variables from the reconstructed “12-lead ECG” (5L12L-ECG, modified Dower transformation) corresponding with the standard 12-lead ECG (ECG). Methods: In this monocentric exploratory retrospective study, raw data of 331 patients with 5L3DVCG-AI and ECG were included. Cardiac pathology (CP) was categorised as exclusion of any CP (control), mild CP or overt CP by 2 independent cardiologists. The following variables were compared: RR-interval, P, PQ, QRS, QT, QTcB, QTcF, QRS-morphology, and ST-morphology. Cardiovascular risk factors (CVRF) were quantified with the modified PROCAM score. Results: From 331 patients (m:w 60:40%, 50.0 ± 19.8 years) of mixed ethnicity and moderate CVRF (2.1 ± 1.2), 70% were controls, 21% had mild CP and 9% overt CP. All variables from reconstructed 5L12L-ECG correlated to the corresponding individual variables from ECG (r= 0.49 to 0.7, p<0.001). With identical RR-intervals in both methods, all defined variables were significantly, but irrelevantly or mildly (Cohen’s d) different in 5L12L-ECG compared to ECG (P 106 ± 12 vs. 109 ±20 ( d =0.3), PQ 152 ± 24 vs. 159 ± 26 ( d =0.3), QRS 105 ± 16 vs. 97 ± 14 ( d =0.7), QT 380 ± 33 vs. 396 ± 27 ( d =0.46), QTcB 432 ± 31 vs. 426 ± 25 ( d =0.57), QTcF 414 ± 26 vs. 416 ± 19 ( d =0.53). 5L3DVCG-AI was able to distinguish between controls and patients with CVD (Sensitivity 78%, Specificity 66%, p=0.01). Comparing heart axis, there was a small, but significant difference with a significant correlation between methods (r=0.30, p<0.01). Conclusions: The easy to use 5-lead ECG may thus be used in clinical practice to reconstruct valid 12-lead ECG curves without major training or expertise. Additionally, 5L3DVCG-AI can identify persons at risk for CVD. Shorter values for the defined variable will have to be considered when interpreting 5L12L-ECG and separate “normal” value ranges will be given and validated in the ongoing prospective large-scale performance clinical trials.