Estimation of pulse transit time from radial pressure waveform alone by artificial neural network

Objective: To validate the feasibility of the estimation of pulse transit time (PTT) by artificial neural network (ANN) from radial pressure waveform alone. Methods: A cascade ANN with ten-fold cross validation was applied to invasively and simultaneously recorded aortic and radial pressure waveforms during rest and nitroglycerin infusion (n=62) for the estimation of mean and beat-to-beat PTT. The results of the ANN models were compared to a multiple linear regression (LR) model when the features of radial arterial pressure waveform in time and frequency domains were used as the predictors of the models. Results: For the estimation of mean PTT and beat-to-beat PTT by ANN (PTT_ANN), the correlation coefficient between the PTT_ANN and the measured PTT (PTT_measured) (mean: r=0.73; beat-to-beat: r=0.85) is higher than that between the PTT estimated by LR (PTT_LR) and PTT_measured (mean: r=0.46; beat-to-beat: r=0.79). The standard deviation (SD) of the difference between the PTT_ANN and PTT_measured (mean: SD=10 ms; beat-to-beat: SD=8 ms) is significantly less than that between the PTT_LR and PTT_measured (mean: SD=17 ms; beat-to-beat: 10 ms), but no significant difference exists between their mean (p=0.92). The lack of frequency features of radial pressure waveform caused obvious reduction in the correlation coefficient (Δr=0.16) and SD of the difference (ΔSD=6 ms) between the PTT_ANN and PTT_measured. The performance of the ANN was improved by increasing the sample number but not by increasing the neuron number. Conclusion: ANN is a potential method of PTT estimation from a single pressure measurement at radial artery.