Estimation of cardiac stroke volume from radial pulse waveform by artificial neural network. (May 2022)

• Record Type: Journal Article
• Authors: Xiao, Hanguang; Liu, Daidai; Avolio, Alberto P; Chen, Kai; Li, Decai; Hu, Bo; Butlin, Mark
• Is Part Of: Computer methods and programs in biomedicine. Volume 218(2022)
• Publication Date: 2022-05
• Subjects: Cardiac stroke volume -- Artificial neural network -- Cardiac output -- Radial pulse waveform; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2022.106738
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: A novel method to estimate cardiac stroke volume from radial pulse wave is proposed. A multi-parameter fusion model of ANN is established to represent the relationship between time domain features of radial pressure waveform and SV. Time domain features as input simplify the procedure of the SV estimation and are more efficient. The method based on ANN and time domain features reduces the error of SV estimation against the 12 traditional methods. Abstract: 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 ( S V A N N ) was proposed. The simulation datasets of 4000 radial pulse waveforms and stroke volume ( S V m e a s ) 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 S V A N N and S V m e a s (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( Δ + 0.04), mean ± SD = 0.00 ± 6.38( Δ ± 2.02)) was better than the other best model, namely, multiple linear regression model (MLR) (R=0.93( Δ + 0.03), mean ± SD = 0.00 ± 6.99( Δ ± 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.