OBJECTIVE

To develop the models for assessing left ventricular (LV) systolic function based on electrocardiogram (ECG) and photoplethysmogram (PPG) parameters recorded by a single-channel ECG monitor with photoplethysmography function.

MATERIAL AND METHODS

There were 400 patients. All ones underwent echocardiography with analysis of LV ejection fraction (EF) and velocity time integral (VTI). After that, registration of ECG and PPG was performed using a single-channel ECG scanner with function of photoplethysmography. Then all data were transmitted to a single server, where ECG and PPG parameters were calculated. ECG- and PPG-based models for assessing LV systolic function were built using Lasso regression and random forest classifier (RFC).

RESULTS

Models were obtained for EF <55%, 40%, 30% and VTI <16 and 13 cm, respectively. For each model, we analyzed area under ROC curve (AUC), sensitivity and specificity. The following data were obtained using Lasso regression: for EF<55% AUC 0.857 (sensitivity 0.818, specificity 0.860); for EF<40% AUC 0.971; for EF<30% AUC 0.982; for VTI <13 AUC 0.754, for VTI <16 AUC 0.746. RFC revealed the following data: AUC for EF <55% was 0.913; for EF <40% — 0.955; for EF <30% — 0.962; for VTI <13 AUC was 0.776, for VTI <16 — 0.782.

CONCLUSION

ECG- and PPG-based models showed high accuracy in assessment of LV systolic function.