Quantitative identification of blood pressure information through directly decoding intrafascicular vagal activities

Abstract

The cervical vagus nerve is closely involved in blood pressure (BP) regulation, and the closed-loop vagus nerve stimulation (VNS) could mitigate concerns for neural adaptation by feeding back BP information to accomplish adaptive stimulation, making BP quantification significant. In this present study, BPs were directly decoded from vagal activities. The cervical left vagus nerves (LVNs) in eight normal Sprague-Dawley rats were intrafascicularly implanted with axon-like carbon nanotube yarn electrodes for vagal recording. Phenylephrine was intravenously injected to elevate the BPs, and LVN and systolic BP waveforms were synchronously recorded in real time. Then we quantitatively reconstructed beat-to-beat systolic BP waveforms from vagal activities using convolutional neural networks (CNNs). Three CNN models with different inputs and network structures were separately trained and tested for each rat including (1) Time–Frequency Sub-band CNN (TFS-CNN) with decomposed LVN sub-bands post wavelet transform as input and 1D convolutional layers, (2) Spectrogram-Spectral CNN (SS-CNN) with the 2D time–frequency spectrogram post Short Time Fourier Transform as input and 2D convolutional layers, and (3) Dilated Causal CNN (DC-CNN) with the same input as that in TFS-CNN and seven 1D dilated convolutional layers. It was found that the SS-CNN outperformed the other two models considering the reconstruction performance of BPs. The R² of SS-CNN (0.78 ± 0.08, mean$\pm$sd) exceeded those of TFS-CNN (0.70 ± 0.13) (P < 0.05) and DC-CNN (0.53 ± 0.26) (P < 0.05). The SS-CNN model also presented the least training (4.83 ± 1.98 mmHg) and testing loss (9.91 ± 3.89 mmHg). These findings would shed some light on clinical application of the closed-loop VNS in BP regulation.