Simultaneous decoding of cardiovascular and respiratory functional changes from pig intraneural vagus nerve signals

Abstract

Objective. Bioelectronic medicine is opening new perspectives for the treatment of some major chronic diseases through the physical modulation of autonomic nervous system activity. Being the main peripheral route for electrical signals between central nervous system and visceral organs, the vagus nerve (VN) is one of the most promising targets. Closed-loop VN stimulation (VNS) would be crucial to increase effectiveness of this approach. Therefore, the extrapolation of useful physiological information from VN electrical activity would represent an invaluable source for single-target applications. Here, we present an advanced decoding algorithm novel to VN studies and properly detecting different functional changes from VN signals. Approach. VN signals were recorded using intraneural electrodes in anaesthetized pigs during cardiovascular and respiratory challenges mimicking increases in arterial blood pressure, tidal volume and respiratory rate. We developed a decoding algorithm that combines discrete wavelet transformation, principal component analysis, and ensemble learning made of classification trees. Main results. The new decoding algorithm robustly achieved high accuracy levels in identifying different functional changes and discriminating among them. Interestingly our findings suggest that electrodes positioning plays an important role on decoding performances. We also introduced a new index for the characterization of recording and decoding performance of neural interfaces. Finally, by combining an anatomically validated hybrid neural model and discrimination analysis, we provided new evidence suggesting a functional topographical organization of VN fascicles. Significance. This study represents an important step towards the comprehension of VN signaling, paving the way for the development of effective closed-loop VNS systems.

Closed-Loop Vagus Nerve Stimulation for the Treatment of Cardiovascular Diseases: State of the Art and Future Directions

“…Neural interfaces used for stimulation can also be used to record neural signals and monitor ANS activity in real-time ( 13 ). While innovative neural interfaces with multiple contacts are designed to improve the quality and information content of neural recordings ( 148 – 151 ), comparable efforts are being made to develop advanced signal processing and data analysis methods ( 152 , 153 ). Several studies recently focused on the extrapolation of neural markers from spontaneous or physiologically enhanced VN activity, employing various decoding techniques.…”

“…The TIME has shown higher selectivity at low stimulation intensities than the single LIFE and multipolar cuffs ( 46 , 148 , 149 ). Our group combined the use of multichannel intrafascicular electrodes, machine learning principles and hybrid models ( 136 ) to study high frequency (>1,500 Hz) VN activity of anesthetized pigs during artificially produced alterations of physiological parameters, simulating increases in respiratory rate, tidal volume and arterial blood pressure ( Figure 6A ) ( 152 ). Using a new decoding algorithm that combines wavelet decomposition, dimensionality reduction, and ensemble learning classifiers, we could associate VN signals to specific functional changes ( Figure 6B ).…”

“…Different from epineural electrodes that can only provide a global picture of neural signal trafficking ( 147 , 171 ), we employed intraneural electrodes to enhance selectivity ( 147 , 169 ) and to map a possible spatial functional organization of VN fascicles. Thus, we employed a hybrid modeling framework based on histological analysis combined with electrode discrimination ability properties measured via a novel quantitative measure called Discriminative Field Potential (DFP) and we obtained distinct spatial configurations of discriminative patterns generated by fascicles during the various functional challenges ( Figure 6C ) ( 152 ). This is extremely important for the development not only of timely, but also spatially selective stimulation protocols in a complex nerve with multiple fascicles like the human or porcine VN ( 152 ).…”

“…Thus, we employed a hybrid modeling framework based on histological analysis combined with electrode discrimination ability properties measured via a novel quantitative measure called Discriminative Field Potential (DFP) and we obtained distinct spatial configurations of discriminative patterns generated by fascicles during the various functional challenges ( Figure 6C ) ( 152 ). This is extremely important for the development not only of timely, but also spatially selective stimulation protocols in a complex nerve with multiple fascicles like the human or porcine VN ( 152 ). In this perspective, the precise knowledge of cardiovascular fibers arrangement within the cervical vagal trunk would be crucial to establish effective VNS protocols for the treatment of CVDs.…”

“… Schematic representation of the experimental setup and decoding algorithm from Vallone et al ( 152 ). (A) Recording apparatus, electrode implantation and summary of the in vivo protocol and functional challenges comparisons.…”