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

Vagus nerve stimulation: Novel concept for the treatment of glioblastoma and solid cancers by cytokine (interleukin-6) reduction, attenuating the SASP, enhancing tumor immunity

Immuno-oncology, specifically immune checkpoint inhibitors (ICIs), has revolutionized cancer care with dramatic, long-term responses and increased survival, including patients with metastatic cancer to the brain. Glioblastomas, and other primary brain tumors, are refractory to ICIs as monotherapy or in combination with standard therapy. The tumor microenvironment (TME) poses multiple biological hurdles: blood-brain barrier, immune suppression, heterogeneity, and tumor infiltration. Genomic analysis of the senescence-associated secretory phenotype (SASP) and preclinical models of glioma suggest that an exciting approach would entail reprogramming of the glioma microenvironment, attenuating the pro-inflammatory, pro-tumorigenic cytokines of the SASP, especially interleukin-6 (IL-6). A testable hypothesis now proposed is to modulate the immune system by harnessing the body's 'inflammatory reflex' to reduce cytokines. Vagus nerve stimulation can activate T cell immunity by the cholinergic, α7nicotinic acetylcholine receptor agonist (α7nAchR), and suppress IL-6 systemically, as well as other pro-inflammatory cytokines of the SASP, interleukin -1β (IL-1β) and tumor necrosis factor-alpha (TNF-α). The hypothesis predicts that electrical activation of the vagus nerve, with cytokine reduction, in combination with ICIs, would convert an immune resistant ("cold") tumor to an immune responsive ("hot") tumor, and halt glioma progression. The hypothesis also envisions cancer as an immune "dysautonomia" whereby a therapeutic intervention, vagus nerve stimulation (VNS), resets the systemic and local cytokine levels. A prospective, randomized, phase II clinical trial, to confirm the hypothesis, is a logical, exigent, next step. Cytokine reduction by VNS could also be useful for other forms of human cancer, e.g., breast, colorectal, head and neck, lung, melanoma, ovarian, pancreatic, and prostate cancer, as the emerging field of "cancer neuroscience" shows a role for neural regulation of multiple tumor types. Because IL-6, and companion pro-inflammatory cytokines, participate in the initiation, progression, spread and recurrence of cancer, minimally invasive VNS could be employed to suppress glioma or cancer progression, while also mitigating depression and/or seizures, thereby enhancing quality of life. The current hypothesis reimagines glioma pathophysiology as a dysautonomia with the therapeutic objective to reset the autonomic nervous system and form an immune responsive state to halt tumor progression and prevent recurrence. VNS, as a novel method to control cancer, can be administered with ICIs, standard therapy, or in clinical trials, combined with emerging immunotherapy: dendritic cell, mRNA, or chimeric antigen receptor (CAR) T cell vaccines.

Treating heart failure by targeting the vagus nerve

Increased sympathetic and reduced parasympathetic nerve activity is associated with disease progression and poor outcomes in patients with chronic heart failure. The demonstration that markers of autonomic imbalance and vagal dysfunction, such as reduced heart rate variability and baroreflex sensitivity, hold prognostic value in patients with chronic heart failure despite modern therapies encourages the research for neuromodulation strategies targeting the vagus nerve. However, the approaches tested so far have yielded inconclusive results. This review aims to summarize the current knowledge about the role of the parasympathetic nervous system in chronic heart failure, describing the pathophysiological background, the methods of assessment, and the rationale, limits, and future perspectives of parasympathetic stimulation either by drugs or bioelectronic devices.

Vagus nerve stimulation in Parkinson's disease: a scoping review of animal studies and human subjects research

Parkinson's Disease (PD) is a prevalent, progressive neurodegenerative disease with motor and non-motor symptoms. Vagus Nerve Stimulation (VNS) has emerged as a potential therapeutic approach for PD, but published research on this topic varies widely. This scoping review maps existing literature on VNS for PD, highlighting stimulation methods, operational parameters, safety profiles, neurophysiological mechanisms, and clinical outcomes in human and animal models. Online databases were used to identify 788 papers published between 2013 and 2023, from which 17 publications on invasive and non-invasive VNS in PD were selected. Studies showed high variability in VNS parameters and study design. Evidence in animal models and human subjects suggests potential neurophysiological effects on PD-related pathology and motor function improvements. However, significant gaps in the literature remain. Future research should include rigorous reporting of study design, standardization of stimulation parameters, and larger sample sizes to ultimately facilitate translation of VNS into clinical practice.

Organ Neuroprosthetics: Connecting Transplanted and Artificial Organs with the Nervous System

Implantable neural interfaces with the central and peripheral nervous systems are currently used to restore sensory, motor, and cognitive functions in disabled people with very promising results. They have also been used to modulate autonomic activities to treat diseases such as diabetes or hypertension. Here, this study proposes to extend the use of these technologies to (re-)establish the connection between new (transplanted or artificial) organs and the nervous system in order to increase the long-term efficacy and the effective biointegration of these solutions. In this perspective paper, some clinically relevant applications of this approach are briefly described. Then, the choices that neural engineers must implement about the type, implantation location, and closed-loop control algorithms to successfully realize this approach are highlighted. It is believed that these new "organ neuroprostheses" are going to become more and more valuable and very effective solutions in the years to come.

Ablation of myocardial autonomic ganglion plexus in the treatment of bradyarrhythmia A one-arm interventional study

OBJECTIVES

To study the complications and effectiveness of the treatment of chronic arrhythmias with cardiac Ganglion Plexus (GP) ablation, and to explore the value of the treatment of chronic arrhythmias with GP ablation.

METHODS

This study was a one-arm interventional study of patients from the first hospital of Xinjiang Medical University and the People's Hospital of Xuancheng City admitted (09/2018-08/2021) because of bradyarrhythmia. The left atrium was modeled using the Carto3 mapping system. The ablation endpoint was the absence of a vagal response under anatomically localized and high-frequency stimulation guidance. Postoperative routine follow-up was conducted. Holter data at 3-, 6-, and 12-months were recorded.

RESULTS

Fifty patients (25 male, mean age 33.16 ± 7.89 years) were induced vagal response by either LSGP, LIGP, RAGP, or RIGP. The heart rate was stable at 76 bpm, SNRT 1.092s. DC, DR, HR, SDNN, RMSSD values were lower than that before ablation. AC, SSR, TH values were higher than those before ablation, mean heart rate and the slowest heart rate were significantly increased. There were significant differences in follow-up data between the preoperative and postoperative periods (all p < 0.05). All the patients were successfully ablated, and their blood pressure decreased significantly. No complications such as vascular damage, vascular embolism and pericardial effusion occurred.

CONCLUSIONS

Left Atrial GP ablation has good long-term clinical results and can be used as a treatment option for patients with bradyarrhythmia.

Neuroimmune circuits in the plaque and bone marrow regulate atherosclerosis

Atherosclerosis remains the leading cause of death globally. Although its focal pathology is atheroma that develops in arterial walls, atherosclerosis is a systemic disease involving contributions by many organs and tissues. It is now established that the immune system causally contributes to all phases of atherosclerosis. Recent and emerging evidence positions the nervous system as a key modulator of inflammatory processes that underly atherosclerosis. This neuro-immune crosstalk, we are learning, is bidirectional, and immune regulated afferent signaling is becoming increasingly recognized in atherosclerosis. Here, we summarize data and concepts that link the immune and nervous systems in atherosclerosis by focusing on two important sites, the arterial vessel and the bone marrow.

Reinforcement learning for closed-loop regulation of cardiovascular system with vagus nerve stimulation: a computational study

Objective. Vagus nerve stimulation (VNS) is being investigated as a potential therapy for cardiovascular diseases including heart failure, cardiac arrhythmia, and hypertension. The lack of a systematic approach for controlling and tuning the VNS parameters poses a significant challenge. Closed-loop VNS strategies combined with artificial intelligence (AI) approaches offer a framework for systematically learning and adapting the optimal stimulation parameters. In this study, we presented an interactive AI framework using reinforcement learning (RL) for automated data-driven design of closed-loop VNS control systems in a computational study.Approach.Multiple simulation environments with a standard application programming interface were developed to facilitate the design and evaluation of the automated data-driven closed-loop VNS control systems. These environments simulate the hemodynamic response to multi-location VNS using biophysics-based computational models of healthy and hypertensive rat cardiovascular systems in resting and exercise states. We designed and implemented the RL-based closed-loop VNS control frameworks in the context of controlling the heart rate and the mean arterial pressure for a set point tracking task. Our experimental design included two approaches; a general policy using deep RL algorithms and a sample-efficient adaptive policy using probabilistic inference for learning and control.Main results.Our simulation results demonstrated the capabilities of the closed-loop RL-based approaches to learn optimal VNS control policies and to adapt to variations in the target set points and the underlying dynamics of the cardiovascular system. Our findings highlighted the trade-off between sample-efficiency and generalizability, providing insights for proper algorithm selection. Finally, we demonstrated that transfer learning improves the sample efficiency of deep RL algorithms allowing the development of more efficient and personalized closed-loop VNS systems.Significance.We demonstrated the capability of RL-based closed-loop VNS systems. Our approach provided a systematic adaptable framework for learning control strategies without requiring prior knowledge about the underlying dynamics.

Importance of cardiac-synchronized vagus nerve stimulation parameters on the provoked chronotropic response for different levels of cardiac innervation

Introduction

The influence of vagus nerve stimulation (VNS) parameters on provoked cardiac effects in different levels of cardiac innervation is not well understood yet. This study examines the effects of VNS on heart rate (HR) modulation across a spectrum of cardiac innervation states, providing data for the potential optimization of VNS in cardiac therapies.

Materials and Methods

Utilizing previously published data from VNS experiments on six sheep with intact innervation, and data of additional experiments in five rabbits post bilateral rostral vagotomy, and four isolated rabbit hearts with additionally removed sympathetic influences, the study explored the impact of diverse VNS parameters on HR.

Results

Significant differences in physiological threshold charges were identified across groups: 0.09 ± 0.06 μC for intact, 0.20 ± 0.04 μC for vagotomized, and 9.00 ± 0.75 μC for isolated hearts. Charge was a key determinant of HR reduction across all innervation states, with diminishing correlations from intact (r = 0.7) to isolated hearts (r = 0.44). An inverse relationship was observed for the number of pulses, with its influence growing in conditions of reduced innervation (intact r = 0.11, isolated r = 0.37). Frequency and stimulation delay showed minimal correlations (r < 0.17) in all conditions.

Conclusion

Our study highlights for the first time that VNS parameters, including stimulation intensity, pulse width, and pulse number, crucially modulate heart rate across different cardiac innervation states. Intensity and pulse width significantly influence heart rate in innervated states, while pulse number is key in denervated states. Frequency and delay have less impact impact across all innervation states. These findings suggest the importance of customizing VNS therapy based on innervation status, offering insights for optimizing cardiac neuromodulation.

Digitalomics, digital intervention, and designing future: The next frontier in cardiology

The discipline of cardiology stands at a transformative juncture, primarily influenced by the surge in digital health technologies. These innovations hold the promise to redefine the realms of cardiovascular research and patient care, ushering in an era of individualized and data-driven treatments. This review delves into the heart of this evolution, introducing a comprehensive design for the future of cardiology. Emphasizing the emerging domains of "digitalomics" and "digital intervention", it explores how the integration of patient data, artificial intelligence-enabled diagnostics, and telehealth can lead to more streamlined and personalized cardiovascular health. The "digital-twin" model, a highlight of this approach, encapsulates individual patient characteristics, allowing for targeted treatments. The role of interdisciplinary collaboration in cardiovascular medicine is also underlined, emphasizing the importance of merging traditional cardiology with technological advancements. The convergence of traditional cardiology methods and digital health technologies, facilitated by a transdisciplinary approach, is set to chart a new course in cardiovascular health, emphasizing individualized care and improved clinical outcomes.

Dorsal motor vagal neurons can elicit bradycardia and reduce anxiety-like behavior

Cardiovagal neurons (CVNs) innervate cardiac ganglia through the vagus nerve to control cardiac function. Although the cardioinhibitory role of CVNs in nucleus ambiguus (CVNNA) is well established, the nature and functionality of CVNs in dorsal motor nucleus of the vagus (CVNDMV) is less clear. We therefore aimed to characterize CVNDMV anatomically, physiologically, and functionally. Optogenetically activating cholinergic DMV neurons resulted in robust bradycardia through peripheral muscarinic (parasympathetic) and nicotinic (ganglionic) acetylcholine receptors, but not beta-1-adrenergic (sympathetic) receptors. Retrograde tracing from the cardiac fat pad labeled CVNNA and CVNDMV through the vagus nerve. Using whole-cell patch-clamp, CVNDMV demonstrated greater hyperexcitability and spontaneous action potential firing ex vivo despite similar resting membrane potentials, compared to CVNNA. Chemogenetically activating DMV also caused significant bradycardia with a correlated reduction in anxiety-like behavior. Thus, DMV contains uniquely hyperexcitable CVNs and is capable of cardioinhibition and robust anxiolysis.

Design and validation of a low-cost photomodulator for in vivo photoactivation of a mGluR5 inhibitor

Purpose: Severe side effects prevent the utilization of otherwise promising drugs in treatments. These side effects arise when drugs affect untargeted tissues due to poor target specificity. In photopharmacology, light controls the timing and the location of drug delivery, improving treatment specificity and pharmacokinetic control. Photopharmaceuticals have not seen widespread adoption in part because researchers do not always have access to reliable and reproducible light delivery devices at prices which fit within the larger research budget. Method: In this work, we present a customizable photomodulator for use in both wearable and implantable devices. For experimental validation of the photomodulator, we photolyse JF-NP-26 in rats. Results: We successfully drive in vivo photopharmacology with a tethered photomodulator and demonstrate modifications which enable the photomodulator to operate wirelessly. Conclusion: By documenting our photomodulator development, we hope to introduce researchers to a simple solution which significantly lowers the engineering barriers to photopharmacology research.

Graphical abstract

Researchers present a photomodulator, a device designed to facilitate in vivo photopharmacology. They demonstrate the in vivo capabilities of the photomodulator by photoreleasing raseglurant, an mGluR5 inhibitor, to treat pain in an acute rat model and follow this study by showing how to reconfigure the photomodulator to work wirelessly and interface with other biomedical devices.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13534-023-00334-3.

Enhancing Motor Sequence Learning via Transcutaneous Auricular Vagus Nerve Stimulation (taVNS): An EEG Study

Motor learning plays a crucial role in human life, and various neuromodulation methods have been utilized to strengthen or improve it. Transcutaneous auricular vagus nerve stimulation (taVNS) has gained increasing attention due to its non-invasive nature, affordability and ease of implementation. Although the potential of taVNS on regulating motor learning has been suggested, its actual regulatory effect has yet been fully explored. Electroencephalogram (EEG) analysis provides an in-depth understanding of cognitive processes involved in motor learning so as to offer methodological support for regulation of motor learning. To investigate the effect of taVNS on motor learning, this study recruited 22 healthy subjects to participate a single-blind, sham-controlled, and within-subject serial reaction time task (SRTT) experiment. Every subject involved in two sessions at least one week apart and received a 20-minute active/sham taVNS in each session. Behavioral indicators as well as EEG characteristics during the task state, were extracted and analyzed. The results revealed that compared to the sham group, the active group showed higher learning performance. Additionally, the EEG results indicated that after taVNS, the motor-related cortical potential amplitudes and alpha-gamma modulation index decreased significantly and functional connectivity based on partial directed coherence towards frontal lobe was enhanced. These findings suggest that taVNS can improve motor learning, mainly through enhancing cognitive and memory functions rather than simple movement learning. This study confirms the positive regulatory effect of taVNS on motor learning, which is particularly promising as it offers a potential avenue for enhancing motor skills and facilitating rehabilitation.

Advances in Non-Invasive Neuromodulation: Designing Closed-Loop Devices for Respiratory-Controlled Transcutaneous Vagus Nerve Stimulation

Studies suggest non-invasive transcutaneous auricular vagus nerve stimulation (taVNS) as a potential therapeutic option for various pathological conditions, such as epilepsy and depression. Exhalation-controlled taVNS, which synchronizes stimulation with internal body rhythms, holds promise for enhanced neuromodulation, but there is no closed-loop system in the literature capable of performing such integration in real time. In this context, the objective was to develop real-time signal processing techniques and an integrated closed-loop device with sensors to acquire physiological data. After a conditioning stage, the signal is processed and delivers synchronized electrical stimulation during the patient's expiratory phase. Additional modules were designed for processing, software-controlled selectors, remote and autonomous operation, improved analysis, and graphical visualization. The signal processing method effectively extracted respiratory cycles and successfully attenuated signal noise. Heart rate variability was assessed in real time, using linear statistical evaluation. The prototype feedback stimulator device was physically constructed. Respiratory peak detection achieved an accuracy of 90%, and the real-time processing resulted in a small delay of up to 150 ms in the detection of the expiratory phase. Thus, preliminary results show promising accuracy, indicating the need for additional tests to optimize real-time processing and the application of the prototype in clinical studies.

Dorsal Motor Vagal Neurons Can Elicit Bradycardia and Reduce Anxiety-Like Behavior

Cardiovagal neurons (CVNs) innervate cardiac ganglia through the vagus nerve to control cardiac function. Although the cardioinhibitory role of CVNs in nucleus ambiguus (CVNNA) is well established, the nature and functionality of CVNs in dorsal motor nucleus of the vagus (CVNDMV) is less clear. We therefore aimed to characterize CVNDMV anatomically, physiologically, and functionally. Optogenetically activating cholinergic DMV neurons resulted in robust bradycardia through peripheral muscarinic (parasympathetic) and nicotinic (ganglionic) acetylcholine receptors, but not beta-1-adrenergic (sympathetic) receptors. Retrograde tracing from the cardiac fat pad labeled CVNNA and CVNDMV through the vagus nerve. Using whole cell patch clamp, CVNDMV demonstrated greater hyperexcitability and spontaneous action potential firing ex vivo despite similar resting membrane potentials, compared to CVNNA. Chemogenetically activating DMV also caused significant bradycardia with a correlated reduction in anxiety-like behavior. Thus, DMV contains uniquely hyperexcitable CVNs capable of cardioinhibition and robust anxiolysis.

Importance of timing optimization for closed-loop applications of vagus nerve stimulation

In recent decades, vagus nerve stimulation (VNS) therapy has become widely used for clinical applications including epilepsy, depression, and enhancing the effects of rehabilitation. However, several questions remain regarding optimization of this therapy to maximize clinical outcomes. Although stimulation parameters such as pulse width, amplitude, and frequency are well studied, the timing of stimulation delivery both acutely (with respect to disease events) and chronically (over the timeline of a disease's progression) has generally received less attention. Leveraging such information would provide a framework for the implementation of next generation closed-loop VNS therapies. In this mini-review, we summarize a number of VNS therapies and discuss (1) general timing considerations for these applications and (2) open questions that could lead to further therapy optimization.

Vagus Nerve Stimulation and Its Cardioprotective Abilities: A Systematic Review

Despite the vagus nerve stimulator (VNS) being used in neuroscience, it has recently been highlighted that it has cardioprotective functions. However, many studies related to VNS are not mechanistic in nature. This systematic review aims to focus on the role of VNS in cardioprotective therapy, selective vagus nerve stimulators (sVNS), and their functional capabilities. A systemic review of the current literature was conducted on VNS, sVNS, and their ability to induce positive effects on arrhythmias, cardiac arrest, myocardial ischemia/reperfusion injury, and heart failure. Both experimental and clinical studies were reviewed and assessed separately. Of 522 research articles retrieved from literature archives, 35 met the inclusion criteria and were included in the review. Literature analysis proves that combining fiber-type selectivity with spatially-targeted vagus nerve stimulation is feasible. The role of VNS as a tool for modulating heart dynamics, inflammatory response, and structural cellular components was prominently seen across the literature. The application of transcutaneous VNS, as opposed to implanted electrodes, provides the best clinical outcome with minimal side effects. VNS presents a method for future cardiovascular treatment that can modulate human cardiac physiology. However, continued research is needed for further insight.

Wireless optoelectronic devices for vagus nerve stimulation in mice

Objective.Vagus nerve stimulation (VNS) is a promising approach for the treatment of a wide variety of debilitating conditions, including autoimmune diseases and intractable epilepsy. Much remains to be learned about the molecular mechanisms involved in vagus nerve regulation of organ function. Despite an abundance of well-characterized rodent models of common chronic diseases, currently available technologies are rarely suitable for the required long-term experiments in freely moving animals, particularly experimental mice. Due to challenging anatomical limitations, many relevant experiments require miniaturized, less invasive, and wireless devices for precise stimulation of the vagus nerve and other peripheral nerves of interest. Our objective is to outline possible solutions to this problem by using nongenetic light-based stimulation.Approach.We describe how to design and benchmark new microstimulation devices that are based on transcutaneous photovoltaic stimulation. The approach is to use wired multielectrode cuffs to test different stimulation patterns, and then build photovoltaic stimulators to generate the most optimal patterns. We validate stimulation through heart rate analysis.Main results.A range of different stimulation geometries are explored with large differences in performance. Two types of photovoltaic devices are fabricated to deliver stimulation: photocapacitors and photovoltaic flags. The former is simple and more compact, but has limited efficiency. The photovoltaic flag approach is more elaborate, but highly efficient. Both can be used for wireless actuation of the vagus nerve using light impulses.Significance.These approaches can enable studies in small animals that were previously challenging, such as long-termin vivostudies for mapping functional vagus nerve innervation. This new knowledge may have potential to support clinical translation of VNS for treatment of select inflammatory and neurologic diseases.

Right vagus nerve stimulation improves motor behavior by exerting neuroprotective effects in Parkinson's disease rats

Background

Parkinson's disease (PD) is a common movement disorder disease. Left vagus nerve stimulation (LVNS) is a potential treatment option for PD. Compared with the left vagus nerve, the right vagus nerve is more closely connected with the midbrain dopaminergic neurons, which are the lesion locations of PD. However, whether right vagus nerve stimulation (RVNS) has a therapeutic effect on PD has not yet been studied. Therefore, in this study, we studied the therapeutic effect and underlying mechanism of RVNS using a PD rat model.

Methods

To establish the PD rat model, 8-week-old male Sprague-Dawley rats were intraperitoneally injected with rotenone for 21 days. The cuff electrodes were implanted into the right cervical vagal carotid sheaths of the rats. The right vagus nerve was continuously stimulated for 14 days using a radio stimulation system. Behavioral tests were performed before and after stimulation. Finally, tyrosine hydroxylase (TH), vesicular monoamine transporter 2 (VMAT2), and α-synuclein in the midbrain, including the substantia nigra (SN) and ventral tegmental area (VTA), were detected by immunofluorescence.

Results

A markedly lower distance traveled and rearing number was observed in the rotenone, rotenone + sham, and rotenone + RVNS groups compared to the vehicle group. After the stimulation days, the distance traveled and rearing number were both higher in the rotenone + RVNS group compared to the rotenone and rotenone + sham groups (P<0.01, P<0.0001). A remarkable increase in distance traveled and rearing number was observed in the rotenone + RVNS group after stimulation. TH expression in the vehicle group was significantly up-regulated than the other groups. RVNS markedly up-regulated TH expression level. A significantly higher expression of α-synuclein was observed in the rotenone, rotenone + sham, and rotenone + RVNS groups compared to the vehicle group. The expression of α-synuclein was lower in the rotenone + RVNS group compared to the rotenone and rotenone + sham groups. A markedly higher VMAT2 expression was observed in the vehicle group compared to other groups. RVNS significantly up-regulated VMAT2 expression.

Conclusions

The improved motor behavior and neuroprotective effects on the midbrain dopaminergic neurons in the PD rat model suggest that RVNS could be used as a potential treatment for PD.

Structure and Functions of the Vagus Nerve in Mammals

We review the structure and function of the vagus nerve, drawing on information obtained in humans and experimental animals. The vagus nerve is the largest and longest cranial nerve, supplying structures in the neck, thorax, and abdomen. It is also the only cranial nerve in which the vast majority of its innervation territory resides outside the head. While belonging to the parasympathetic division of the autonomic nervous system, the nerve is primarily sensory-it is dominated by sensory axons. We discuss the macroscopic and microscopic features of the nerve, including a detailed description of its extensive territory. Histochemical and genetic profiles of afferent and efferent axons are also detailed, as are the central nuclei involved in the processing of sensory information conveyed by the vagus nerve and the generation of motor (including parasympathetic) outflow via the vagus nerve. We provide a comprehensive review of the physiological roles of vagal sensory and motor neurons in control of the cardiovascular, respiratory, and gastrointestinal systems, and finish with a discussion on the interactions between the vagus nerve and the immune system. © 2022 American Physiological Society. Compr Physiol 12: 1-49, 2022.

A lightweight learning-based decoding algorithm for intraneural vagus nerve activity classification in pigs

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 5 anaesthetized pigs. Our algorithm is based on signal temporal windowing, 9 handcrafted features, and Random Forest (RF) model for classification. Temporal windowing ranging from 50 ms to 1 sec, 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 balanced accuracy and computational execution time a state of the art decoding algorithm tested on the same dataset [1]. 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.