5L3DVCG-AI for identification of cardiovascular risk in females is superior to cardiovascular risk factor scoring

Caroline Schmidt-Lucke (Berlin)1, B. Lischke (Berlin)1, E. Weber (Frankfurt am Main)2, S. Deiß (Frankfurt am Main)2, A. Schomöller (Berlin)1, J. A. Schmidt-Lucke (Berlin)3

1MEDIACC GmbH Berlin, Deutschland; 2Cardisio GmbH Frankfurt am Main, Deutschland; 3Internal Medicine Practice Berlin, Deutschland


Introduction: Artificial Intelligence-based 5-lead 3D-vectorcardiography (5L3DVCG-AI) offers additional information over 12-lead electrocardiography (ECG) identifying coronary vascular disease (CVD) in need for coronary intervention in a mixed population. Early detection of cardiovascular risk in females still is a challenge.

Hypothesis: We, thus, tested the hypothesis of 5L3DVCG-AI being able to detect mild to overt signs and / or history of CVD in women.

Methods: In this monocentric retrospective study, consecutive data of 118 female patients with 5L3DVCG-AI for detection of CVD were included. The Perfusion (P)-Factor for cardiac ischaemic pathologies, based on the CSG-Index including 731 parameters and in-house features calculated in time and frequency domains (e.g. beat moments), classified patients as normal, slightly conspicuous or conspicuous for CVD. Diagnosis of CVD was based upon current guidelines by 2 independent blinded cardiologists and categorised as exclusion of CVD (control), mild signs or overt CVD. The P-Factor was validated against clinical CVD. Cardiovascular risk factors (CVRF) were quantified with modified PROCAM-Score.

Results: Of 118 patients (58 ± 16 years) of mixed ethnicity and moderate CVRF (1.5 ± 1.2), 86 were controls, 27 had mild signs of CVD and 3 overt CVD. Follow-up period was 16.2 ± 7.5 months. CVRF-Score was significantly higher in CVD compared to controls (2.1 ± 1.1 vs. 1.4 ± 1.1, p<0.01), and P-Factor correlated with number of CVRF (p<0.01), with significantly higher CVRF in higher P-Factor (KW p<0.01). P-Factor indicated significantly more often higher risk in CHD compared to controls (CVRF-Score: 1.8 ± 1.2 vs. 1.3 ± 1.1, p<0.01). CSG-Index from 5L3DVCG-AI at rest was a better predictor for CVD in females than CVRF-Score (ß=0.24, T=2.6, p<0.01) than CVRF-Score. ECG at rest was not able to differentiate between CVD and controls.

Conclusions: These data extend the previous findings of 5L3DVCG-AI identifying CVD with cardiac ischaemia from those without to now differentiating healthy controls from CVD and those with higher risk for CVD in a female population. 5L3DVCG-AI is superior to CVRF-Scores and offers the opportunity to identify women at risk for CVD in need for further cardiac diagnosis and in need for risk modification. Ongoing prospective large-scale clinical trials will have to confirm these data to verify diagnostic accuracy.

Diese Seite teilen