Journal of Neural Engineering

Objective. This paper discusses a novel method for automating the curation of neural spike events detected from neural recordings using spike sorting methods. Spike sorting seeks to identify isolated neural events from extracellular recordings. This is critical for interpretation of electrophysiology recordings in neuroscience studies. Spike sorting analysis is vulnerable to errors because of non-neural events, such as experimental artifacts or electrical interference. To improve the specificity of spike sorting results, a manual postprocessing curation is typically used to examine the detected events and identify neural spikes based on their specific features. However, this manual curation process is subjective, prone to human errors and not scalable, especially for large datasets. Approach. To address these challenges, we introduce AECuration, a novel automatic curation method based on an autoencoder model trained on features of simulated extracellular spike waveforms. Using reconstruction error as a performance metric, our method classifies neural and non-neural events in experimental electrophysiology datasets. Main results. This paper demonstrates that AECuration can classify neural events with 97.46% accuracy on synthetic datasets. Moreover, our method can improve the sensitivity of different spike sorting pipelines on datasets with ground-truth recordings by up to 20%. The ratio of clustered units with low interspike interval violation rates is improved from 55.3% to 85.5% as demonstrated using our in-house experimental dataset. Significance. AEcuration is a time-domain evaluation method that automates the analysis of extracellular recordings based on learned time-domain features. Once trained on a synthetic dataset, this method can be applied to real extracellular datasets without the need for re-training. This highlights the generalizability of AECuration. It can be readily integrated with existing spike sorting pipelines as a preprocessing filtering or a postprocessing curation step to improve the overall accuracy and efficiency.

Objective. This work introduces Dareplane, a modular and broad technology-agnostic open source software platform for brain–computer interface (BCI) research with an application focus on adaptive deep brain stimulation (aDBS). One difficulty for investigating control approaches for aDBS resides with the complex setups required for aDBS experiments, a challenge Dareplane tries to address. Approach. The key features of the platform are presented and the composition of modules into a full experimental setup is discussed in the context of a Python-based orchestration module. The performance of a typical experimental setup on Dareplane for aDBS is evaluated in three benchtop experiments, covering (a) an easy-to-replicate setup using an Arduino microcontroller, (b) a setup with hardware of an implantable pulse generator, and (c) a setup using an established and CE certified external neurostimulator. The full technical feasibility of the platform in the aDBS context is demonstrated in a first closed-loop session with externalized leads on a patient with Parkinson's disease receiving DBS treatment and further in a non-invasive BCI speller application using code-modulated visual evoked potential (c-VEP). Main results. The platform is implemented and open-source accessible on https://github.com/bsdlab/Dareplane. Benchtop results show that performance of the platform is sufficient for current aDBS latencies, and the platform could successfully be used in the aDBS experiment. The timing-critical c-VEP speller could be successfully implemented on the platform achieving expected information transfer rates. Significance. The Dareplane platform supports aDBS setups, and more generally the research on neurotechnological systems such as BCIs. It provides a modular, technology-agnostic, and easy-to-implement software platform to make experimental setups more resilient and replicable.

Objective. Electroencephalogram (EEG) based brain–computer interfaces (BCIs) have shown tremendous promise in facilitating direct non-invasive brain-control over external devices. However, their practical application is hampered due to errors in command interpretation. A promising strategy for improving BCI accuracy is based on detecting error-related potentials (ErrPs), which are EEG potentials evoked in response to errors. Thus, performance can be improved by undoing actions that evoke potentials that the BCI detects as ErrPs. To achieve further improvement, we aimed to classify the type of error and correct, rather than just undo, erroneous actions. The objectives of this study are to develop an error classifier (EC) and to investigate the hypothesis that correcting the actions according to the EC decisions improves performance. Approach. To evaluate our hypothesis we developed a BCI application to control the pose of virtual hands with three possible commands: change the pose of either the right or left hand and maintain pose. Thus, when an action elicits an ErrP, the identity of the correct command is still undecided. The self-correcting BCI included an EC and was developed in three phases: hand control, initial brain control and self-correcting brain control. The first two phases were conducted by 22 participants, and half of them (n = 11) also completed the last phase. Main results. Detecting the type of error and correcting actions accordingly improved the success rate of the self-correcting BCI for each participant (n = 11), with a significant average improvement of 6.6$\%$ and best improvement of 13.5$\%$. Significance. Self-correction, based on an EC, was demonstrated to improve the accuracy of BCIs for three commands. Thus, our work presents a significant step toward the development of more reliable and user-friendly non-invasive BCIs.

Objective. Electroencephalography (EEG) is a widely used neuroimaging technique known for its cost-effectiveness and user-friendliness. However, the presence of various artifacts leads to a poor signal-to-noise ratio, limiting the precision of analyses and applications. The proposed work focuses on the electromyography (EMG) artifacts, which are among the most challenging biological artifacts. The currently reported EMG artifact cleaning performance largely depends on the data used for validation, and in the case of machine learning approaches, also on the data used for training. The data are typically gathered either by recruiting subjects to perform specific EMG artifact tasks or by integrating existing datasets. Prevailing approaches, however, tend to rely on intuitive, concept-oriented data collection with minimal justification for the selection of artifacts and their quantities. Given the substantial costs associated with biological data collection and the pressing need for effective data utilization, we propose an optimization procedure for data-oriented data collection design using deep learning-based artifact detection. Approach. We apply a binary classification differentiating between artifact epochs (time intervals containing EMG artifacts) and non-artifact epochs (time intervals containing no EMG artifact) using three different neural architectures. Our aim is to minimize data collection efforts while preserving the cleaning efficiency. Main results. We were able to reduce the number of EMG artifact tasks from twelve to three and decrease repetitions of isometric contraction tasks from ten to three or sometimes even just one. Significance. Our work addresses the need for effective data utilization in biological data collection, offering a systematic and dynamic quantitative approach. By providing clear justifications for the choices of artifacts and their quantity, we aim to guide future studies toward more effective and economical data collection in EEG and EMG research.

Objective. In the field of brain–computer interface (BCI), achieving high information transfer rates (ITR) with a large number of targets remains a challenge. This study aims to address this issue by developing a novel code-modulated visual evoked potential (c-VEP) BCI system capable of handling an extensive instruction set while maintaining high performance. Approach. We propose a c-VEP BCI system that employs narrow-band random sequences as visual stimuli and utilizes a convolutional neural network (CNN)-based EEG2Code decoding algorithm. This algorithm predicts corresponding stimulus sequences from EEG data and achieves efficient and accurate classification. Main results. Offline experiments which conducted in a sequential paradigm, resulted in an average accuracy of 87.66% and a simulated ITR of 260.14 bits/min. In online experiments, the system demonstrated an accuracy of 76.27% and an ITR of 213.80 bits/min in a cued spelling task. Significance. This work represents an advancement in c-VEP BCI systems, offering one of the largest known instruction set in VEP-based BCIs and demonstrating robust performance metrics. The proposed system is potential for more practical and efficient BCI applications.

Objective. Sharing computational models offers many benefits, including increased scientific rigor during project execution, readership of the associated paper, resource usage efficiency, replicability, and reusability. In recognition of the growing practice and requirement of sharing models, code, and data, herein, we provide guidance to facilitate sharing of computational models by providing an accessible resource for regular reference throughout a project's stages. Approach. We synthesized literature on good practices in scientific computing and on code and data sharing with our experience in developing, sharing, and using models of neural stimulation, although the guidance will also apply well to most other types of computational models. Main results. We first describe the '6 R' characteristics of shared models, leaning on prior scientific computing literature, which enforce accountability and enable advancement: re-runnability, repeatability, replicability, reproducibility, reusability, and readability. We then summarize action items associated with good practices in scientific computing, including selection of computational tools during project planning, code and documentation design during development, and user instructions for deployment. We provide a detailed checklist of the contents of shared models and associated materials, including the model itself, code for reproducing published figures, documentation, and supporting datasets. We describe code, model, and data repositories, including a list of characteristics to consider when selecting a platform for sharing. We describe intellectual property (IP) considerations to balance permissive, open-source licenses versus software patents and bespoke licenses that govern and incentivize commercialization. Finally, we exemplify these practices with our ASCENT pipeline for modeling peripheral nerve stimulation. Significance. We hope that this paper will serve as an important and actionable reference for scientists who develop models—from project planning through publication—as well as for model users, institutions, IP experts, journals, funding sources, and repository platform developers.

The Tenth International brain–computer interface (BCI) meeting was held June 6–9, 2023, in the Sonian Forest in Brussels, Belgium. At that meeting, 21 master classes, organized by the BCI Society's Postdoc & Student Committee, supported the Society's goal of fostering learning opportunities and meaningful interactions for trainees in BCI-related fields. Master classes provide an informal environment where senior researchers can give constructive feedback to the trainee on their chosen and specific pursuit. The topics of the master classes span the whole gamut of BCI research and techniques. These include data acquisition, neural decoding and analysis, invasive and noninvasive stimulation, and ethical and transitional considerations. Additionally, master classes spotlight innovations in BCI research. Herein, we discuss what was presented within the master classes by highlighting each trainee and expert researcher, providing relevant background information and results from each presentation, and summarizing discussion and references for further study.

The brain is a highly complex physical system made of assemblies of neurons that work together to accomplish elaborate tasks such as motor control, memory and perception. How these parts work together has been studied for decades by neuroscientists using neuroimaging, psychological manipulations, and neurostimulation. Neurostimulation has gained particular interest, given the possibility to perturb the brain and elicit a specific response. This response depends on different parameters such as the intensity, the location and the timing of the stimulation. However, most of the studies performed so far used previously established protocols without considering the ongoing brain activity and, thus, without adaptively targeting the stimulation. In control theory, this approach is called open-loop control, and it is always paired with a different form of control called closed-loop, in which the current activity of the brain is used to establish the next stimulation. Recently, neuroscientists are beginning to shift from classical fixed neuromodulation studies to closed-loop experiments. This new approach allows the control of brain activity based on responses to stimulation and thus to personalize individual treatment in clinical conditions. Here, we review this new approach by introducing control theory and focusing on how these aspects are applied in brain studies. We also present the different stimulation techniques and the control approaches used to steer the brain. Finally, we explore how the closed-loop framework will revolutionize the way the human brain can be studied, including a discussion on open questions and an outlook on future advances.

Neurotechnologies are increasingly becoming integrated with our everyday lives, our bodies and our mental states. As the popularity and impact of neurotechnology grows, so does our responsibility to ensure we understand its particular implications on its end users, as well as broader ethical and societal implications. There are many different terms and frameworks to articulate the concept of involving end users in the technology development lifecycle, for example: 'Public and Patient Involvement and Engagement' (PPIE), 'lived experience', 'co-design' or 'co-production'. The objective of this tutorial is to utilise the PPIE framework to develop clear guidelines for implementing a robust involvement process of current and future end-users in neurotechnology, with emphasis on patient involvement. After an introduction that coveys the tangible and conceptual benefits of user involvement, we first guide the reader to develop a general strategy towards setting up their own PPIE process. We then help the reader map out their relevant stakeholders and provide advice on how to consider user diversity and representation. We also provide advice and tools on how to quantify the outcomes of the engagement. We consolidate advice from various online sources to orient individual teams (and their funders) to carve up their own approach to meaningful involvement. Key outputs include a stakeholder mapping tool, methods to measure the impact of engagement, and a structured checklist for transparent reporting. Enabling end-users and other stakeholders to participate in the development of neurotechnology, even at its earliest stages of conception, will help us better navigate our design around ethical, social, and usability considerations, and deliver more impactful technologies. The overall aim is the establishment of gold-standard methodologies for ensuring that patient and public insights are at the forefront of our scientific inquiry and product development.

Nanoparticle (NP)-based drug delivery systems hold immense potential for targeted therapy and diagnosis of neurological disorders, overcoming the limitations of conventional treatment modalities. This review explores the design considerations and functionalization strategies of NPs for precise targeting of the brain and central nervous system. This review discusses the challenges associated with drug delivery to the brain, including the blood–brain barrier and the complex heterogeneity of traumatic brain injury. We also examine the physicochemical properties of NPs, emphasizing the role of size, shape, and surface characteristics in their interactions with biological barriers and cellular uptake mechanisms. The review concludes by exploring the options of targeting ligands designed to augment NP affinity and retention to specific brain regions or cell types. Various targeting ligands are discussed for their ability to mimic receptor-ligand interaction, and brain-specific extracellular matrix components. Strategies to mimic viral mechanisms to increase uptake are discussed. Finally, the emergence of antibody, antibody fragments, and antibody mimicking peptides are discussed as promising targeting strategies. By integrating insights from these scientific fields, this review provides an understanding of NP-based targeting strategies for personalized medicine approaches to neurological disorders. The design considerations discussed here pave the way for the development of NP platforms with enhanced therapeutic efficacy and minimized off-target effects, ultimately advancing the field of neural engineering.

Introduction: Spinal cord injury (SCI) affects over 250,000 individuals in the US. Brain-computer interfaces (BCIs) may improve quality of life by controlling external devices. Invasive intracortical BCIs have shown promise in clinical trials but degrade in the chronic period and tether patients to acquisition hardware. Alternatively, electrocorticography (ECoG) records data from electrodes on the cortex, and studies evaluating fully implanted BCI-ECoG systems are scarce. Thus, we seek to address this need using a fully implanted ECoG-based BCI that allows for home use in SCI. Method: The patient used a long-term BCI system, initially controlling an FES orthosis in the lab and later using an external mechanical orthosis at home. To evaluate its long-term viability, electrode contact impedance, signal quality, and decoder performance were measured. Signal quality was assessed using signal-to-noise ratio and maximum bandwidth of the signal. Decoder performance was monitored using the area under the receiver operator characteristic curve (AUROC). Results: The study analyzed data from the patient's home environment over 54 months, revealing that the device was used at home for 38 ± 24 minutes on average daily. After six months, we observed stable event-related desynchronization that aided in determining the onset of motor intention. The decoder's average AUROC across months was 0.959. Importantly, 40 months of the data collected was gather from the subject's home or community environment. The results indicate long-term ECoG recordings were stable for motor-imagery classification and motor control in the environment in a case of an individual with SCI. Conclusion: This study presents the long-term feasibility and viability of an ECoG-based BCI system that persists in the home environment in a case of SCI. Future research should explore larger electrode counts with more participants to confirm this stability. Understanding these trends is crucial for clinical utility and chronic viability in broader patient populations.

Objective. Predicting performance in Brain-Computer Interfaces (BCI) is crucial for enhancing user experience, optimizing training and identifying the most efficient BCI approach for each individual. Approach. This study explores the use of Median Nerve Stimulation (MNS) as a predictor of Motor Imagery (MI)-BCI performance. MNS induces Event Related (De)Synchronization (ERD/ERS) patterns in the brain that are similar to those generated during MI tasks, providing a non-invasive, user-independent, and easy-to-setup method for performance prediction. Main results. Our proposed predictor, based on the minimum value of the ERD induced by the MNS, not only exhibits a robust correlation with the MI-BCI performance accuracy (rho = -0.71, p < 0.001), but also effectively predicts this performance with a significant correlation (rho = 0.61, mean absolute error = 9.0, p < 0.01). These results demonstrate its validity as a reliable predictor of MI-BCI performance. Significance. By systematically analyzing patterns induced by MNS and correlating them with subsequent MI-BCI task performance, we aim to establish a robust predictive method of motor activity to each individual only based on MNS, making it possible, among other things, to passively predict BCI deficiency or proficiency, and to potentially adapt BCI parameters for an efficient BCI experience or BCI-based recovery.

Non-stationarity in EEG signals poses significant challenges for the performance and implementation of brain computer– interfaces (BCIs). In this study, we propose a novel method for cross-session BCI tasks that employs a supervised autoencoder to reduce session-specific information while preserving task-related signals. Our approach compresses high-dimensional EEG inputs and reconstructs them, thereby mitigating non-stationary variability in the data. In addition to unsupervised minimization of the reconstruction error, the objective function of the network includes two supervised terms to ensure that the latent representations exclude session identity information and are optimized for subsequent classification. Evaluation across three different motor imagery datasets demonstrates that our approach effectively addresses domain adaptation challenges, outperforming both naïve cross-session and within-session methods. Our method eliminates the need for data from new sessions, making it fully unsupervised concerning new session data and reducing the necessity for recalibration with each session. Furthermore, the reduction of session-specific information in the reconstructed signals indicates that our approach effectively denoises non-stationary signals, thereby enhancing the accuracy of BCI models. Future applications could extend this model to a broader range of BCI tasks and explore the residual signals to investigate sources of non-stationary brain components and other cognitive processes.&#xD;

Objective Neural prosthetics represent a significant opportunity for control of external effectors like artificial limbs and computer devices as well as a means for interacting with virtual reality. Prior studies have shown posterior parietal cortex to be a viable source of signals for the purposes of decoding motor intentions given its representation of both visual inputs and motor outputs. Additionally, signals in parietal cortex have been shown known to be associated with tool use the body schema. We investigated if more realistic movement effectors in virtual reality might elicit stronger signals at the single neuron level in parietal cortex. Approach A quadriplegic human subject was implanted with multi-electrode recording arrays in the posterior parietal cortex. Neural spiking recorded during attempted movement in a computer-rendered, stereoscopic, 3D virtual environment. Tuning to different movement effectors was examined using a first-person, movement generation task in addition to closed loop control performance. Results We found single neurons and simultaneously recorded field potentials in a quadriplegic patient exhibited enhanced responses during attempted (rather than passively observed) movement of a realistic and "attached" 3D arm relative to either a visually similar but "detached" 2D arm or a non-anthropomorphic abstract effector. These preferences were found despite the patient having lost motor function years prior. These differences did not effect performance during closed loop brain control of the movement effectors. Significance In human parietal cortex, these signals responded preferentially to visually guided attempted movement of a realistic arm rather than abstract effector. However, by choosing a text-only training paradigm, this tuning did not seem to effect closed loop brain control in a virtual reality environment. Additionally, single-unit driven brain control of a body in virtual reality is reported here for the first time.

Background:&#xD;The vestibular implant is a potential treatment approach for bilateral vestibulopathy patients. To restore gaze stabilization, the implant should elicit vestibulo-ocular reflexes over a wide range of eye velocities. Different stimulation strategies to achieve this goal were previously described. Vestibular information can be encoded by modulating stimulation amplitude, rate,  or a combination of both. In this study, combined rate and amplitude modulation was compared with amplitude modulation, to evaluate their potential for vestibular implant stimulation.&#xD;Methods:&#xD;Nine subjects with a vestibulo-cochlear implant participated in this study. Three stimulation strategies were tested. The combined rate and amplitude modulation setting (baseline rate 50%) was compared with amplitude modulation (baseline rate 50%, and baseline rate equal to the maximum rate).  The resulting vestibulo-ocular reflex was evaluated.&#xD;Results:&#xD;Combining rate and amplitude modulation, or using amplitude modulation with a baseline equal to the maximum rate, both significantly increased peak eye velocities. Misalignment increased with higher peak eye velocities and higher pulse rate. No significant differences were found in peak eye velocities and misalignment, between both stimulation strategies. Amplitude modulation with a baseline rate at 50%, demonstrated the lowest peak eye velocities.&#xD;Conclusion:&#xD;Combining rate and amplitude modulation, or amplitude modulation with a baseline equal to the maximum rate, can both be considered for future vestibular implant fitting.&#xD;

Objective. This paper discusses a novel method for automating the curation of neural spike events detected from neural recordings using spike sorting methods. Spike sorting seeks to identify isolated neural events from extracellular recordings. This is critical for interpretation of electrophysiology recordings in neuroscience studies. Spike sorting analysis is vulnerable to errors because of non-neural events, such as experimental artifacts or electrical interference. To improve the specificity of spike sorting results, a manual postprocessing curation is typically used to examine the detected events and identify neural spikes based on their specific features. However, this manual curation process is subjective, prone to human errors and not scalable, especially for large datasets. Approach. To address these challenges, we introduce AECuration, a novel automatic curation method based on an autoencoder model trained on features of simulated extracellular spike waveforms. Using reconstruction error as a performance metric, our method classifies neural and non-neural events in experimental electrophysiology datasets. Main results. This paper demonstrates that AECuration can classify neural events with 97.46% accuracy on synthetic datasets. Moreover, our method can improve the sensitivity of different spike sorting pipelines on datasets with ground-truth recordings by up to 20%. The ratio of clustered units with low interspike interval violation rates is improved from 55.3% to 85.5% as demonstrated using our in-house experimental dataset. Significance. AEcuration is a time-domain evaluation method that automates the analysis of extracellular recordings based on learned time-domain features. Once trained on a synthetic dataset, this method can be applied to real extracellular datasets without the need for re-training. This highlights the generalizability of AECuration. It can be readily integrated with existing spike sorting pipelines as a preprocessing filtering or a postprocessing curation step to improve the overall accuracy and efficiency.

Objective. This work introduces Dareplane, a modular and broad technology-agnostic open source software platform for brain–computer interface (BCI) research with an application focus on adaptive deep brain stimulation (aDBS). One difficulty for investigating control approaches for aDBS resides with the complex setups required for aDBS experiments, a challenge Dareplane tries to address. Approach. The key features of the platform are presented and the composition of modules into a full experimental setup is discussed in the context of a Python-based orchestration module. The performance of a typical experimental setup on Dareplane for aDBS is evaluated in three benchtop experiments, covering (a) an easy-to-replicate setup using an Arduino microcontroller, (b) a setup with hardware of an implantable pulse generator, and (c) a setup using an established and CE certified external neurostimulator. The full technical feasibility of the platform in the aDBS context is demonstrated in a first closed-loop session with externalized leads on a patient with Parkinson's disease receiving DBS treatment and further in a non-invasive BCI speller application using code-modulated visual evoked potential (c-VEP). Main results. The platform is implemented and open-source accessible on https://github.com/bsdlab/Dareplane. Benchtop results show that performance of the platform is sufficient for current aDBS latencies, and the platform could successfully be used in the aDBS experiment. The timing-critical c-VEP speller could be successfully implemented on the platform achieving expected information transfer rates. Significance. The Dareplane platform supports aDBS setups, and more generally the research on neurotechnological systems such as BCIs. It provides a modular, technology-agnostic, and easy-to-implement software platform to make experimental setups more resilient and replicable.

Objective. Electroencephalogram (EEG) based brain–computer interfaces (BCIs) have shown tremendous promise in facilitating direct non-invasive brain-control over external devices. However, their practical application is hampered due to errors in command interpretation. A promising strategy for improving BCI accuracy is based on detecting error-related potentials (ErrPs), which are EEG potentials evoked in response to errors. Thus, performance can be improved by undoing actions that evoke potentials that the BCI detects as ErrPs. To achieve further improvement, we aimed to classify the type of error and correct, rather than just undo, erroneous actions. The objectives of this study are to develop an error classifier (EC) and to investigate the hypothesis that correcting the actions according to the EC decisions improves performance. Approach. To evaluate our hypothesis we developed a BCI application to control the pose of virtual hands with three possible commands: change the pose of either the right or left hand and maintain pose. Thus, when an action elicits an ErrP, the identity of the correct command is still undecided. The self-correcting BCI included an EC and was developed in three phases: hand control, initial brain control and self-correcting brain control. The first two phases were conducted by 22 participants, and half of them (n = 11) also completed the last phase. Main results. Detecting the type of error and correcting actions accordingly improved the success rate of the self-correcting BCI for each participant (n = 11), with a significant average improvement of 6.6$\%$ and best improvement of 13.5$\%$. Significance. Self-correction, based on an EC, was demonstrated to improve the accuracy of BCIs for three commands. Thus, our work presents a significant step toward the development of more reliable and user-friendly non-invasive BCIs.

Introduction: Spinal cord injury (SCI) affects over 250,000 individuals in the US. Brain-computer interfaces (BCIs) may improve quality of life by controlling external devices. Invasive intracortical BCIs have shown promise in clinical trials but degrade in the chronic period and tether patients to acquisition hardware. Alternatively, electrocorticography (ECoG) records data from electrodes on the cortex, and studies evaluating fully implanted BCI-ECoG systems are scarce. Thus, we seek to address this need using a fully implanted ECoG-based BCI that allows for home use in SCI. Method: The patient used a long-term BCI system, initially controlling an FES orthosis in the lab and later using an external mechanical orthosis at home. To evaluate its long-term viability, electrode contact impedance, signal quality, and decoder performance were measured. Signal quality was assessed using signal-to-noise ratio and maximum bandwidth of the signal. Decoder performance was monitored using the area under the receiver operator characteristic curve (AUROC). Results: The study analyzed data from the patient's home environment over 54 months, revealing that the device was used at home for 38 ± 24 minutes on average daily. After six months, we observed stable event-related desynchronization that aided in determining the onset of motor intention. The decoder's average AUROC across months was 0.959. Importantly, 40 months of the data collected was gather from the subject's home or community environment. The results indicate long-term ECoG recordings were stable for motor-imagery classification and motor control in the environment in a case of an individual with SCI. Conclusion: This study presents the long-term feasibility and viability of an ECoG-based BCI system that persists in the home environment in a case of SCI. Future research should explore larger electrode counts with more participants to confirm this stability. Understanding these trends is crucial for clinical utility and chronic viability in broader patient populations.

Non-stationarity in EEG signals poses significant challenges for the performance and implementation of brain computer– interfaces (BCIs). In this study, we propose a novel method for cross-session BCI tasks that employs a supervised autoencoder to reduce session-specific information while preserving task-related signals. Our approach compresses high-dimensional EEG inputs and reconstructs them, thereby mitigating non-stationary variability in the data. In addition to unsupervised minimization of the reconstruction error, the objective function of the network includes two supervised terms to ensure that the latent representations exclude session identity information and are optimized for subsequent classification. Evaluation across three different motor imagery datasets demonstrates that our approach effectively addresses domain adaptation challenges, outperforming both naïve cross-session and within-session methods. Our method eliminates the need for data from new sessions, making it fully unsupervised concerning new session data and reducing the necessity for recalibration with each session. Furthermore, the reduction of session-specific information in the reconstructed signals indicates that our approach effectively denoises non-stationary signals, thereby enhancing the accuracy of BCI models. Future applications could extend this model to a broader range of BCI tasks and explore the residual signals to investigate sources of non-stationary brain components and other cognitive processes.&#xD;

Background:&#xD;The vestibular implant is a potential treatment approach for bilateral vestibulopathy patients. To restore gaze stabilization, the implant should elicit vestibulo-ocular reflexes over a wide range of eye velocities. Different stimulation strategies to achieve this goal were previously described. Vestibular information can be encoded by modulating stimulation amplitude, rate,  or a combination of both. In this study, combined rate and amplitude modulation was compared with amplitude modulation, to evaluate their potential for vestibular implant stimulation.&#xD;Methods:&#xD;Nine subjects with a vestibulo-cochlear implant participated in this study. Three stimulation strategies were tested. The combined rate and amplitude modulation setting (baseline rate 50%) was compared with amplitude modulation (baseline rate 50%, and baseline rate equal to the maximum rate).  The resulting vestibulo-ocular reflex was evaluated.&#xD;Results:&#xD;Combining rate and amplitude modulation, or using amplitude modulation with a baseline equal to the maximum rate, both significantly increased peak eye velocities. Misalignment increased with higher peak eye velocities and higher pulse rate. No significant differences were found in peak eye velocities and misalignment, between both stimulation strategies. Amplitude modulation with a baseline rate at 50%, demonstrated the lowest peak eye velocities.&#xD;Conclusion:&#xD;Combining rate and amplitude modulation, or amplitude modulation with a baseline equal to the maximum rate, can both be considered for future vestibular implant fitting.&#xD;

Objective: Transcutaneous electrical stimulation aims to restore sensation and function in individuals with sensory or motor deficits. However, limited selectivity and unintended nerve recruitment often result in discomfort. Temporal interference (TI) stimulation has been proposed as a novel approach to non-invasive nerve stimulation, hypothesising that low-frequency modulation of kilohertz carriers reduces activation thresholds. Prior studies have produced conflicting results regarding comfort in kilohertz-frequency stimulation, and the practical applicability of TI remains unclear. This study addresses these gaps by systematically analysing the role of depth of modulation in activation thresholds and comfort, focusing on peripheral nerves and clinically relevant stimulation levels.&#xD;&#xD;Approach: This study uses a dual-method approach combining computational and psychophysical experiments targeting the median nerve. Computational modelling involved nine MRI-informed finite element models to account for anatomical variability and biophysical neural activation predictions using NEURON. Psychophysical experiments with 19 participants determined stimulation thresholds and comfort levels. Statistical analysis using the Friedman test and Bonferroni correction assessed the impact of carrier and beat frequencies, and depth of modulation on activation thresholds and comfort.&#xD;&#xD;Main results: The results showed that the activation thresholds did not vary with the depth of modulation, challenging the core assumption underlying temporal interference stimulation. Despite that, comfort significantly increased with carrier frequencies as low as 500 Hz, with no further significant changes at higher frequencies. Computational modelling results showed an association between increased comfort and asynchronous nerve activation patterns, providing a possible explanation for the observed improvement in comfort. &#xD;&#xD;Significance: By challenging a core assumption of TI stimulation, this study shifts the focus from threshold modulation to optimising comfort in peripheral nerve stimulation. These findings establish a foundation for developing kilohertz-frequency stimulation protocols prioritising user comfort, particularly in applications such as functional electrical stimulation for rehabilitation or sensory feedback for prostheses. &#xD;

Objective:&#xD; Seizure detection algorithms enable clinicians to accurately assess seizure burden for epilepsy diagnosis and long-term management. State-of-the-art algorithms rely on electroencephalography (EEG) data to identify electrographic seizures. Previous research that used non-EEG signals, such as electrocardiography (ECG) and wristband data, were collected in epilepsy monitoring units. We aimed to investigate the feasibility of ECG seizure detection in ambulatory settings. &#xD;Approach:&#xD;We developed a patient-independent, machine learning-based seizure detector using ambulatory long-term ECG monitoring data. The model was trained on long-term studies of 47 patients and evaluated pseudoprospectively using event detection on a hold-out test set of 18 patients. &#xD;Main results:&#xD; In the hold-out test set, the seizure detector performed better than chance for 14 out of 18 patients. The average sensitivity was 72% and the average specificity was 68% for the whole test cohort. Overall, across training and test sets, the performance was better for patients diagnosed with focal epilepsy and for patients who were identified as responders (had substantial heart rate changes during seizures). &#xD; Significance:&#xD; Key contributions of this study include the development of a patient-independent seizure detector using ambulatory data and the introduction of a pseudoprospective evaluation framework, which can benefit chronic ambulatory seizure monitoring.

Objective. Epidural electrical stimulation (EES) has shown promise as both a clinical therapy and research tool for studying nervous system function. However, available clinical EES paddles are limited to using a small number of contacts due to the burden of wires necessary to connect each contact to the therapeutic delivery device, limiting the treatment area or density of epidural electrode arrays. We aimed to eliminate this burden using advanced on-paddle electronics. Approach. We developed a smart EES paddle with a 60-electrode programmable array, addressable using an active electronic multiplexer embedded within the electrode paddle body. The electronics are sealed in novel, ultra-low profile hermetic packaging. We conducted extensive reliability testing on the novel array, including a battery of ISO 10993-1 biocompatibility tests and determination of the hermetic package leak rate. We then evaluated the EES device in vivo, placed on the epidural surface of the ovine lumbosacral spinal cord for 15 months. Main results. The active paddle array performed nominally when implanted in sheep for over 15 months and no device-related malfunctions were observed. The onboard multiplexer enabled bespoke electrode arrangements across, and within, experimental sessions. We identified stereotyped responses to stimulation in lower extremity musculature, and examined local field potential responses to EES using high-density recording bipoles. Finally, spatial electrode encoding enabled machine learning models to accurately perform EES parameter inference for unseen stimulation electrodes, reducing the need for extensive training data in future deep models. Significance. We report the development and chronic large animal in vivo evaluation of a high-density EES paddle array containing active electronics. Our results provide a foundation for more advanced computation and processing to be integrated directly into devices implanted at the neural interface, opening new avenues for the study of nervous system function and new therapies to treat neural injury and dysfunction.

Objective. Transcranial focused ultrasound (tFUS) is a promising neuromodulation technique able to target shallow and deep brain structures with high precision. Previous studies have demonstrated that tFUS stimulation responses are cell-type specific, and specifically tFUS can elicit time-locked neural activity in regular spiking units (RSUs) that is sensitive to increases in pulse repetition frequency (PRF), while time-locked responses are not seen in fast spiking units (FSUs). These findings suggest a unique capability of tFUS to alter circuit network dynamics with cell-type specificity; however, these results could be biased by the use of anesthesia, which significantly modulates neural activities. Approach. In this study, we developed an awake head-fixed rat model specifically designed for simultaneous tFUS stimulation using a customized 128-element ultrasound array transducer, and recording of spiking data. Using this novel animal model, we examined a series of PRFs and burst duty cycles (DCs) to determine their effects on neuronal subpopulations without anesthesia. Main results. We observed cell type specific responses to varying PRF and DC in the awake setting as well as the anesthetized setting, with time locked responses observed in RSU and delayed responses in FSU. Anesthesia broadly was found to dampen responses to tFUS, and affected the latency of delayed responses. Preferred parameters for inducing time-locked responses appear to be 1500 Hz PRF and 60% DC. Significance. We conclude that despite some differences in response, isoflurane anesthesia is not a major confound in studying the cell-type specificity of ultrasound neuromodulation, but may affect studies of circuit dynamics and FSU. Our developed awake model will allow for future investigations without this confound.