Estimation of cardiac stroke volume from radial pulse waveform by artificial neural network

Background and Objectives: Stroke volume (SV) and cardiac output (CO) are the key indicators for the evaluation of cardiac function and hemodynamic status during the perioperative period, which are very important in the detection and treatment of cardiovascular diseases. Traditional CO and SV measurement methods have problems such as complex operation, low precision and poor generalization ability. Methods: In this paper, a method for estimating stroke volume based on cascade artificial neural network (ANN) and time domain features of radial pulse waveform (SVANN) was proposed. The simulation datasets of 40 0 0 radial pulse waveforms and stroke volume (SVmeas) were generated by a 55 segment transmission line model of the human systemic vasculature and a recursive algorithm. The ANN was trained and tested by 10-fold cross-validation, and compared with 12 traditional models. Results: Experimental results showed that the Pearson correlation coefficients and mean difference between SVANN and SVmeas (R = 0.95, mean standard deviation (SD) = 0.00 +/- 6.45) were better than the best results of the 12 traditional models. Moreover, as increasing the number of training samples, the performance improvement of the ANN (R = 0.94(Delta+ 0.04), mean +/- SD = 0.00 +/- 6.38(Delta 2.02)) was better than the other best model, namely, multiple linear regression model (MLR) (R = 0.93(Delta+ 0.03), mean +/- SD = 0.00 +/- 6.99(Delta +/- 1.50)). Conclusions: A method is proposed to estimate cardiac stroke volume by the ANN with time domain features of radial pulse wave. It avoids the complicated modeling process based on hemodynamics within traditional models, improves the estimation accuracy of SV, and has a good generalization ability. (c) 2022 Elsevier B.V. All rights reserved.

Automated summary

This study proposed a new method to estimate cardiac stroke volume using artificial neural network and time domain features of radial pulse waveform, showing better accuracy and reliability compared to traditional models.