7 July 2021 in Journal of Neural Engineering
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.
5 October 2023 in APL Bioengineering
Neuroprosthetic devices used for the treatment of lower urinary tract dysfunction, such as incontinence or urinary retention, apply a pre-set continuous, open-loop stimulation paradigm, which can cause voiding dysfunctions due to neural adaptation. In the literature, conditional, closed-loop stimulation paradigms have been shown to increase bladder capacity and voiding efficacy compared to continuous stimulation. Current limitations to the implementation of the closed-loop stimulation paradigm include the lack of robust and real-time decoding strategies for the bladder fullness state. We recorded intraneural pudendal nerve signals in five anesthetized pigs. Three bladder-filling states, corresponding to empty, full, and micturition, were decoded using the Random Forest classifier. The decoding algorithm showed a mean balanced accuracy above 86.67% among the three classes for all five animals. Our approach could represent an important step toward the implementation of an adaptive real-time closed-loop stimulation protocol for pudendal nerve modulation, paving the way for the design of an assisted-as-needed neuroprosthesis.
1 August 2022 in Journal of Neural Engineering
Objective. Bioelectronic medicine is an emerging field that aims at developing closed-loop neuromodulation protocols for the autonomic nervous system (ANS) to treat a wide range of disorders. When designing a closed-loop protocol for real time modulation of the ANS, the computational execution time and the memory and power demands of the decoding step are important factors to consider. In the context of cardiovascular and respiratory diseases, these requirements may partially explain why closed-loop clinical neuromodulation protocols that adapt stimulation parameters on patient’s clinical characteristics are currently missing. Approach. Here, we developed a lightweight learning-based decoder for the classification of cardiovascular and respiratory functional challenges from neural signals acquired through intraneural electrodes implanted in the cervical vagus nerve (VN) of five anaesthetized pigs. Our algorithm is based on signal temporal windowing, nine handcrafted features, and random forest (RF) model for classification. Temporal windowing ranging from 50 ms to 1 s, compatible in duration with cardio-respiratory dynamics, was applied to the data in order to mimic a pseudo real-time scenario. Main results. We were able to achieve high balanced accuracy (BA) values over the whole range of temporal windowing duration. We identified 500 ms as the optimal temporal windowing duration for both BA values and computational execution time processing, achieving more than 86% for BA and a computational execution time of only ∼6.8 ms. Our algorithm outperformed in terms of BA and computational execution time a state of the art decoding algorithm tested on the same dataset (Vallone et al 2021 J. Neural Eng. 18 0460a2). We found that RF outperformed other machine learning models such as support vector machines, K-nearest neighbors, and multi-layer perceptrons. Significance. Our approach could represent an important step towards the implementation of a closed-loop neuromodulation protocol relying on a single intraneural interface able to perform real-time decoding tasks and selective modulation of the VN.