Journal of Neural Engineering

Objective. Electroencephalography (EEG) analysis has been an important tool in neuroscience with applications in neuroscience, neural engineering (e.g. Brain–computer interfaces, BCI's), and even commercial applications. Many of the analytical tools used in EEG studies have used machine learning to uncover relevant information for neural classification and neuroimaging. Recently, the availability of large EEG data sets and advances in machine learning have both led to the deployment of deep learning architectures, especially in the analysis of EEG signals and in understanding the information it may contain for brain functionality. The robust automatic classification of these signals is an important step towards making the use of EEG more practical in many applications and less reliant on trained professionals. Towards this goal, a systematic review of the literature on deep learning applications to EEG classification was performed to address the following critical questions: (1) Which EEG classification tasks have been explored with deep learning? (2) What input formulations have been used for training the deep networks? (3) Are there specific deep learning network structures suitable for specific types of tasks? Approach. A systematic literature review of EEG classification using deep learning was performed on Web of Science and PubMed databases, resulting in 90 identified studies. Those studies were analyzed based on type of task, EEG preprocessing methods, input type, and deep learning architecture. Main results. For EEG classification tasks, convolutional neural networks, recurrent neural networks, deep belief networks outperform stacked auto-encoders and multi-layer perceptron neural networks in classification accuracy. The tasks that used deep learning fell into five general groups: emotion recognition, motor imagery, mental workload, seizure detection, event related potential detection, and sleep scoring. For each type of task, we describe the specific input formulation, major characteristics, and end classifier recommendations found through this review. Significance. This review summarizes the current practices and performance outcomes in the use of deep learning for EEG classification. Practical suggestions on the selection of many hyperparameters are provided in the hope that they will promote or guide the deployment of deep learning to EEG datasets in future research.

Objective. Brain machine interfaces (BMIs) that can restore speech have predominantly focused on decoding speech signals from the speech motor cortices. A few studies have shown some information outside the speech motor cortices, such as in parietal and temporal lobes, that also may be useful for BMIs. The ability to use information from outside the frontal lobe could be useful not only for people with locked-in syndrome, but also to people with frontal lobe damage, which can cause nonfluent aphasia or apraxia of speech. However, temporal and parietal lobes are predominantly involved in perceptive speech processing and comprehension. Therefore, to be able to use signals from these areas in a speech BMI, it is important to ascertain that they are related to production. Here, using intracranial recordings, we sought evidence for whether, when and where neural information related to speech intent could be found in the temporal and parietal cortices Approach. Using intracranial recordings, we examined neural activity across temporal and parietal cortices to identify signals associated with speech intent. We employed causal information to distinguish speech intent from resting states and other language-related processes, such as comprehension and working memory. Neural signals were analyzed for their spatial distribution and temporal dynamics to determine their relevance to speech production. Main results. Causal information enabled us to distinguish speech intent from resting state and other processes involved in language processing or working memory. Information related to speech intent was distributed widely across the temporal and parietal lobes, including superior temporal, medial temporal, angular, and supramarginal gyri. Significance. Loss of communication due to neurological diseases can be devastating. While speech BMIs have made strides in decoding speech from frontal lobe signals, our study reveals that the temporal and parietal cortices contain information about speech production intent that can be causally decoded prior to the onset of voice. This information is distributed across a large network. This information can be used to improve current speech BMIs and potentially expand the patient population for speech BMIs to include people with frontal lobe damage from stroke or traumatic brain injury.

Objective. Transcranial electrical stimulation (TES) is an effective technique to modulate brain activity and treat diseases. However, TES is primarily used to stimulate superficial brain regions and is unable to reach deeper targets. The spread of injected currents in the head is affected by volume conduction and the additional spreading of currents as they move through head layers with different conductivities, as is discussed in Forssell et al (2021 J. Neural Eng. 18 046042). In this paper, we introduce DeepFocus, a technique aimed at stimulating deep brain structures in the brain's 'reward circuit' (e.g. the orbitofrontal cortex, Brodmann area 25, amygdala, etc). Approach. To accomplish this, DeepFocus utilizes transnasal electrode placement (under the cribriform plate and within the sphenoid sinus) in addition to electrodes placed on the scalp, and optimizes current injection patterns across these electrodes. To quantify the benefit of DeepFocus, we develop the DeepROAST simulation and optimization platform. DeepROAST simulates the effect of complex skull-base bones' geometries on the electric fields generated by DeepFocus configurations using realistic head models. It also uses optimization methods to search for focal and efficient current injection patterns, which we use in our simulation and cadaver studies. Main results. In simulations, optimized DeepFocus patterns created larger and more focal fields in several regions of interest than scalp-only electrodes. In cadaver studies, DeepFocus patterns created large fields at the medial orbitofrontal cortex (OFC) with magnitudes comparable to stimulation studies, and, in conjunction with established cortical stimulation thresholds, suggest that the field intensity is sufficient to create neural response, e.g. at the OFC. Significance. This minimally invasive stimulation technique can enable more efficient and less risky targeting of deep brain structures to treat multiple neural conditions.

Enhancing speech perception in everyday noisy acoustic environments remains an outstanding challenge for hearing aids. Speech separation technology is improving rapidly, but hearing devices cannot fully exploit this advance without knowing which sound sources the user wants to hear. Even with high-quality source separation, the hearing aid must know which speech streams to enhance and which to suppress. Advances in EEG-based decoding of auditory attention raise the potential of neurosteering, in which a hearing instrument selectively enhances the sound sources that a hearing-impaired listener is focusing their attention on. Here, we present and discuss a real-time brain–computer interface system that combines a stimulus–response model based on canonical correlation analysis for real-time EEG attention decoding, coupled with a multi-microphone hardware platform enabling low-latency real-time speech separation through spatial beamforming. We provide an overview of the system and its various components, discuss prospects and limitations of the technology, and illustrate its application with case studies of listeners steering acoustic feedback of competing speech streams via real-time attention decoding. A software implementation code of the system is publicly available for further research and explorations.

Context. Electroencephalography (EEG) is a complex signal and can require several years of training, as well as advanced signal processing and feature extraction methodologies to be correctly interpreted. Recently, deep learning (DL) has shown great promise in helping make sense of EEG signals due to its capacity to learn good feature representations from raw data. Whether DL truly presents advantages as compared to more traditional EEG processing approaches, however, remains an open question. Objective. In this work, we review 154 papers that apply DL to EEG, published between January 2010 and July 2018, and spanning different application domains such as epilepsy, sleep, brain–computer interfacing, and cognitive and affective monitoring. We extract trends and highlight interesting approaches from this large body of literature in order to inform future research and formulate recommendations. Methods. Major databases spanning the fields of science and engineering were queried to identify relevant studies published in scientific journals, conferences, and electronic preprint repositories. Various data items were extracted for each study pertaining to (1) the data, (2) the preprocessing methodology, (3) the DL design choices, (4) the results, and (5) the reproducibility of the experiments. These items were then analyzed one by one to uncover trends. Results. Our analysis reveals that the amount of EEG data used across studies varies from less than ten minutes to thousands of hours, while the number of samples seen during training by a network varies from a few dozens to several millions, depending on how epochs are extracted. Interestingly, we saw that more than half the studies used publicly available data and that there has also been a clear shift from intra-subject to inter-subject approaches over the last few years. About of the studies used convolutional neural networks (CNNs), while used recurrent neural networks (RNNs), most often with a total of 3–10 layers. Moreover, almost one-half of the studies trained their models on raw or preprocessed EEG time series. Finally, the median gain in accuracy of DL approaches over traditional baselines was across all relevant studies. More importantly, however, we noticed studies often suffer from poor reproducibility: a majority of papers would be hard or impossible to reproduce given the unavailability of their data and code. Significance. To help the community progress and share work more effectively, we provide a list of recommendations for future studies and emphasize the need for more reproducible research. We also make our summary table of DL and EEG papers available and invite authors of published work to contribute to it directly. A planned follow-up to this work will be an online public benchmarking portal listing reproducible results.

Objective. Most current electroencephalography (EEG)-based brain–computer interfaces (BCIs) are based on machine learning algorithms. There is a large diversity of classifier types that are used in this field, as described in our 2007 review paper. Now, approximately ten years after this review publication, many new algorithms have been developed and tested to classify EEG signals in BCIs. The time is therefore ripe for an updated review of EEG classification algorithms for BCIs. Approach. We surveyed the BCI and machine learning literature from 2007 to 2017 to identify the new classification approaches that have been investigated to design BCIs. We synthesize these studies in order to present such algorithms, to report how they were used for BCIs, what were the outcomes, and to identify their pros and cons. Main results. We found that the recently designed classification algorithms for EEG-based BCIs can be divided into four main categories: adaptive classifiers, matrix and tensor classifiers, transfer learning and deep learning, plus a few other miscellaneous classifiers. Among these, adaptive classifiers were demonstrated to be generally superior to static ones, even with unsupervised adaptation. Transfer learning can also prove useful although the benefits of transfer learning remain unpredictable. Riemannian geometry-based methods have reached state-of-the-art performances on multiple BCI problems and deserve to be explored more thoroughly, along with tensor-based methods. Shrinkage linear discriminant analysis and random forests also appear particularly useful for small training samples settings. On the other hand, deep learning methods have not yet shown convincing improvement over state-of-the-art BCI methods. Significance. This paper provides a comprehensive overview of the modern classification algorithms used in EEG-based BCIs, presents the principles of these methods and guidelines on when and how to use them. It also identifies a number of challenges to further advance EEG classification in BCI.

Neuromorphic computing covers a diverse range of approaches to information processing all of which demonstrate some degree of neurobiological inspiration that differentiates them from mainstream conventional computing systems. The philosophy behind neuromorphic computing has its origins in the seminal work carried out by Carver Mead at Caltech in the late 1980s. This early work influenced others to carry developments forward, and advances in VLSI technology supported steady growth in the scale and capability of neuromorphic devices. Recently, a number of large-scale neuromorphic projects have emerged, taking the approach to unprecedented scales and capabilities. These large-scale projects are associated with major new funding initiatives for brain-related research, creating a sense that the time and circumstances are right for progress in our understanding of information processing in the brain. In this review we present a brief history of neuromorphic engineering then focus on some of the principal current large-scale projects, their main features, how their approaches are complementary and distinct, their advantages and drawbacks, and highlight the sorts of capabilities that each can deliver to neural modellers.

Objective. Brain–computer interfaces (BCI) enable direct communication with a computer, using neural activity as the control signal. This neural signal is generally chosen from a variety of well-studied electroencephalogram (EEG) signals. For a given BCI paradigm, feature extractors and classifiers are tailored to the distinct characteristics of its expected EEG control signal, limiting its application to that specific signal. Convolutional neural networks (CNNs), which have been used in computer vision and speech recognition to perform automatic feature extraction and classification, have successfully been applied to EEG-based BCIs; however, they have mainly been applied to single BCI paradigms and thus it remains unclear how these architectures generalize to other paradigms. Here, we ask if we can design a single CNN architecture to accurately classify EEG signals from different BCI paradigms, while simultaneously being as compact as possible. Approach. In this work we introduce EEGNet, a compact convolutional neural network for EEG-based BCIs. We introduce the use of depthwise and separable convolutions to construct an EEG-specific model which encapsulates well-known EEG feature extraction concepts for BCI. We compare EEGNet, both for within-subject and cross-subject classification, to current state-of-the-art approaches across four BCI paradigms: P300 visual-evoked potentials, error-related negativity responses (ERN), movement-related cortical potentials (MRCP), and sensory motor rhythms (SMR). Main results. We show that EEGNet generalizes across paradigms better than, and achieves comparably high performance to, the reference algorithms when only limited training data is available across all tested paradigms. In addition, we demonstrate three different approaches to visualize the contents of a trained EEGNet model to enable interpretation of the learned features. Significance. Our results suggest that EEGNet is robust enough to learn a wide variety of interpretable features over a range of BCI tasks. Our models can be found at: https://github.com/vlawhern/arl-eegmodels.

Stroke is one of the leading causes of long-term disability among adults and contributes to major socio-economic burden globally. Stroke frequently results in multifaceted impairments including motor, cognitive and emotion deficits. In recent years, brain–computer interface (BCI)-based therapy has shown promising results for post-stroke motor rehabilitation. In spite of the success received by BCI-based interventions in the motor domain, non-motor impairments are yet to receive similar attention in research and clinical settings. Some preliminary encouraging results in post-stroke cognitive rehabilitation using BCI seem to suggest that it may also hold potential for treating non-motor deficits such as cognitive and emotion impairments. Moreover, past studies have shown an intricate relationship between motor, cognitive and emotion functions which might influence the overall post-stroke rehabilitation outcome. A number of studies highlight the inability of current treatment protocols to account for the implicit interplay between motor, cognitive and emotion functions. This indicates the necessity to explore an all-inclusive treatment plan targeting the synergistic influence of these standalone interventions. This approach may lead to better overall recovery than treating the individual deficits in isolation. In this paper, we review the recent advances in BCI-based post-stroke motor rehabilitation and highlight the potential for the use of BCI systems beyond the motor domain, in particular, in improving cognition and emotion of stroke patients. Building on the current results and findings of studies in individual domains, we next discuss the possibility of a holistic BCI system for motor, cognitive and affect rehabilitation which may synergistically promote restorative neuroplasticity. Such a system would provide an all-encompassing rehabilitation platform, leading to overarching clinical outcomes and transfer of these outcomes to a better quality of living. This is one of the first works to analyse the possibility of targeting cross-domain influence of post-stroke functional recovery enabled by BCI-based rehabilitation.

Objective. Deep learning (DL) networks are increasingly attracting attention across various fields, including electroencephalography (EEG) signal processing. These models provide comparable performance to that of traditional techniques. At present, however, there is a lack of well-structured and standardized datasets with specific benchmark limit the development of DL solutions for EEG denoising. Approach. Here, we present EEGdenoiseNet, a benchmark EEG dataset that is suited for training and testing DL-based denoising models, as well as for performance comparisons across models. EEGdenoiseNet contains 4514 clean EEG segments, 3400 ocular artifact segments and 5598 muscular artifact segments, allowing users to synthesize contaminated EEG segments with the ground-truth clean EEG. Main results. We used EEGdenoiseNet to evaluate denoising performance of four classical networks (a fully-connected network, a simple and a complex convolution network, and a recurrent neural network). Our results suggested that DL methods have great potential for EEG denoising even under high noise contamination. Significance. Through EEGdenoiseNet, we hope to accelerate the development of the emerging field of DL-based EEG denoising. The dataset and code are available at https://github.com/ncclabsustech/EEGdenoiseNet.

Objective. Invasive brain-computer interfaces (iBCIs) have evolved significantly since the first neurotrophic electrode was implanted in a human subject three decades ago. Since then, both hardware and software advances have increased the iBCI performance to enable tasks such as decoding conversations in real-time and manipulating external limb prostheses with haptic feedback. In this systematic review, we aim to evaluate the advances in iBCI hardware, software and functionality and describe challenges and opportunities in the iBCI field. Approach. Medline, EMBASE, PubMed and Cochrane databases were searched from inception until 13 April 2024. Primary studies reporting the use of iBCI in human subjects to restore function were included. Endpoints extracted include iBCI electrode type, iBCI implantation, decoder algorithm, iBCI effector, testing and training methodology and functional outcomes. Narrative synthesis of outcomes was done with a focus on hardware and software development trends over time. Individual patient data (IPD) was also collected and an IPD meta-analysis was done to identify factors significant to iBCI performance. Main results. 93 studies involving 214 patients were included in this systematic review. The median task performance accuracy for cursor control tasks was 76.00% (Interquartile range [IQR] = 21.2), for motor tasks was 80.00% (IQR = 23.3), and for communication tasks was 93.27% (IQR = 15.3). Current advances in iBCI software include use of recurrent neural network architectures as decoders, while hardware advances such as intravascular stentrodes provide a less invasive alternative for neural recording. Challenges include the lack of standardized testing paradigms for specific functional outcomes and issues with portability and chronicity limiting iBCI usage to laboratory settings. Significance. Our systematic review demonstrated the exponential rate at which iBCIs have evolved over the past two decades. Yet, more work is needed for widespread clinical adoption and translation to long-term home-use.

Objective. Advances in electronics and materials science have led to the development of sophisticated components for clinical and research neurotechnology systems. However, instrumentation to easily evaluate how these components function in a complete system does not yet exist. In this work, we set out to design and validate a software-defined mixed-signal routing fabric, 'xDev', that enables neurotechnology system designers to rapidly iterate, evaluate, and deploy advanced multi-component systems. Approach. We developed a set of system requirements for xDev, and implemented a design based on a 16 × 16 analog crosspoint multiplexer. We then tested the impedance and switching characteristics of the design, assessed signal gain and crosstalk attenuation across biological and high-speed digital signaling frequencies, and evaluated the ability of xDev to flexibly reroute microvolt-scale amplitude and high-speed signals. Finally, we conducted an intraoperative in vivo deployment of xDev to rapidly conduct neuromodulation experiments using diverse neurotechnology submodules. Main results. The xDev system impedance matching, crosstalk attenuation, and frequency response characteristics accurately transmitted signals over a broad range of frequencies, encapsulating features typical of biosignals and extending into high-speed digital ranges. Microvolt-scale biosignals and 600 Mbps Ethernet connections were accurately routed through the fabric. These performance characteristics culminated in an in vivo demonstration of the flexibility of the system via implanted spinal electrode arrays in an ovine model. Significance. xDev represents a first-of-its-kind, low-cost, software-defined neurotechnology development accelerator platform. Through the public, open-source distribution of our designs, we lower the obstacles facing the development of future neurotechnology systems.

Objective. Obstructive sleep apnea (OSA) is a prevalent sleep disorder. Accurate sleep staging is one of the prerequisites in the study of sleep-related disorders and the evaluation of sleep quality. We introduce a novel GraphSleepFormer (GSF) network designed to effectively capture global dependencies and node characteristics in graph-structured data. Approach. The network incorporates centrality coding and spatial coding into its architecture. It employs adaptive learning of adjacency matrices for spatial encoding between channels located on the head, thereby encoding graph structure information to enhance the model's representation and understanding of spatial relationships. Centrality encoding integrates the degree matrix into node features, assigning varying degrees of attention to different channels. Ablation experiments demonstrate the effectiveness of these encoding methods. The Shapley Additive Explanations (SHAP) method was employed to evaluate the contribution of each channel in sleep staging, highlighting the necessity of using multimodal data. Main results. We trained our model on overnight polysomnography data collected from 28 OSA patients in a clinical setting and achieved an overall accuracy of 80.10%. GSF achieved performance comparable to state-of-the-art methods on two subsets of the ISRUC database. Significance. The GSF Accurately identifies sleep periods, providing a critical basis for diagnosing and treating OSA, thereby contributing to advancements in sleep medicine.

Objective. Localization of function within the brain and central nervous system is an essential aspect of clinical neuroscience. Classical descriptions of functional neuroanatomy provide a foundation for understanding the functional significance of identifiable anatomic structures. However, individuals exhibit substantial variation, particularly in the presence of disorders that alter tissue structure or impact function. Furthermore, functional regions do not always correspond to identifiable structural features. Understanding function at the level of individual patients—and diagnosing and treating such patients—often requires techniques capable of correlating neural activity with cognition, behavior, and experience in anatomically precise ways. Approach. Recent advances in brain–computer interface technology have given rise to a new generation of electrophysiologic tools for scalable, nondestructive functional mapping with spatial precision in the range of tens to hundreds of micrometers, and temporal resolutions in the range of tens to hundreds of microseconds. Here we describe our initial intraoperative experience with novel, thin-film arrays containing 1024 surface microelectrodes for electrocorticographic mapping in a first-in-human study. Main results. Eight patients undergoing standard electrophysiologic cortical mapping during resection of eloquent-region brain tumors consented to brief sessions of concurrent mapping (micro-electrocorticography) using the novel arrays. Four patients underwent motor mapping using somatosensory evoked potentials (SSEPs) while under general anesthesia, and four underwent awake language mapping, using both standard paradigms and the novel microelectrode array. SSEP phase reversal was identified in the region predicted by conventional mapping, but at higher resolution (0.4 mm) and as a contour rather than as a point. In Broca's area (confirmed by direct cortical stimulation), speech planning was apparent in the micro-electrocorticogram as high-amplitude beta-band activity immediately prior to the articulatory event. Significance. These findings support the feasibility and potential clinical utility of incorporating micro-electrocorticography into the intraoperative workflow for systematic cortical mapping of functional brain regions.

Objective. Humans spend a significant portion of their lives in sleep (an essential driver of body metabolism). Moreover, as sleep deprivation could cause various health complications, it is crucial to develop an automatic sleep stage detection model to facilitate the tedious manual labeling process. Notably, recently proposed sleep staging algorithms lack model explainability and still require performance improvement. Approach. We implemented multiscale neurophysiology-mimicking kernels to capture sleep-related electroencephalogram (EEG) activities at varying frequencies and temporal lengths; the implemented model was named 'multiscale temporal convolutional neural network (MTCNN).' Further, we evaluated its performance using an open-source dataset (Sleep-EDF Database Expanded comprising 153 d of polysomnogram data). Main results. By investigating the learned kernel weights, we observed that MTCNN detected the EEG activities specific to each sleep stage, such as the frequencies, K-complexes, and sawtooth waves. Furthermore, regarding the characterization of these neurophysiologically significant features, MTCNN demonstrated an overall accuracy (OAcc) of 91.12% and a Cohen kappa coefficient of 0.86 in the cross-subject paradigm. Notably, it demonstrated an OAcc of 88.24% and a Cohen kappa coefficient of 0.80 in the leave-few-days-out analysis. Our MTCNN model also outperformed the existing deep learning models in sleep stage classification even when it was trained with only 16% of the total EEG data, achieving an OAcc of 85.62% and a Cohen kappa coefficient of 0.75 on the remaining 84% of testing data. Significance. The proposed MTCNN enables model explainability and it can be trained with lesser amount of data, which is beneficial to its application in the real-world because large amounts of training data are not often and readily available.

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.

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition characterized by communication barriers, societal disengagement, and monotonous actions. Traditional diagnostic methods for ASD rely on clinical observations and behavioural assessments, which are time-consuming. In recent years, researchers have focused mainly on the early diagnosis of ASD due to the unavailability of recognised causes and the lack of permanent curative solutions. Electroencephalography (EEG) research in ASD offers insight into the neural dynamics of affected individuals. This comprehensive review examines the unique integration of EEG, machine learning, and statistical analysis for ASD identification, highlighting the promise of an interdisciplinary approach for enhancing diagnostic precision. The comparative analysis of publicly available EEG datasets for ASD, along with local data acquisition methods and their technicalities, is presented in this paper. This study also compares preprocessing techniques, and feature extraction methods, followed by classification models and statistical analysis which are discussed in detail. In addition, it briefly touches upon comparisons with other modalities to contextualize the extensiveness of ASD research. Moreover, by outlining research gaps and future directions, this work aims to catalyse further exploration in the field, with the main goal of facilitating more efficient and effective early identification methods that may be helpful to the lives of ASD individuals.

Objective. Intracellular patch-clamp electrophysiology, one of the most ubiquitous, high-fidelity techniques in biophysics, remains laborious and low-throughput. While previous efforts have succeeded at automating some steps of the technique, here we demonstrate a robotic 'PatcherBot' system that can perform many patch-clamp recordings sequentially, fully unattended. Approach. Comprehensive automation is accomplished by outfitting the robot with machine vision, and cleaning pipettes instead of manually exchanging them. Main results. the PatcherBot can obtain data at a rate of 16 cells per hour and work with no human intervention for up to 3 h. We demonstrate the broad applicability and scalability of this system by performing hundreds of recordings in tissue culture cells and mouse brain slices with no human supervision. Using the PatcherBot, we also discovered that pipette cleaning can be improved by a factor of three. Significance. The system is potentially transformative for applications that depend on many high-quality measurements of single cells, such as drug screening, protein functional characterization, and multimodal cell type investigations.

Objective. Most brain–computer interfaces (BCIs) based on functional near-infrared spectroscopy (fNIRS) require that users perform mental tasks such as motor imagery, mental arithmetic, or music imagery to convey a message or to answer simple yes or no questions. These cognitive tasks usually have no direct association with the communicative intent, which makes them difficult for users to perform. Approach. In this paper, a 3-class intuitive BCI is presented which enables users to directly answer yes or no questions by covertly rehearsing the word 'yes' or 'no' for 15 s. The BCI also admits an equivalent duration of unconstrained rest which constitutes the third discernable task. Twelve participants each completed one offline block and six online blocks over the course of two sessions. The mean value of the change in oxygenated hemoglobin concentration during a trial was calculated for each channel and used to train a regularized linear discriminant analysis (RLDA) classifier. Main results. By the final online block, nine out of 12 participants were performing above chance (p  <  0.001 using the binomial cumulative distribution), with a 3-class accuracy of 83.8%  ±  9.4%. Even when considering all participants, the average online 3-class accuracy over the last three blocks was 64.1 %  ±  20.6%, with only three participants scoring below chance (p  <  0.001). For most participants, channels in the left temporal and temporoparietal cortex provided the most discriminative information. Significance. To our knowledge, this is the first report of an online 3-class imagined speech BCI. Our findings suggest that imagined speech can be used as a reliable activation task for selected users for development of more intuitive BCIs for communication.

Objective. Optical techniques for recording and manipulating neural activity have traditionally been constrained to superficial brain regions due to light scattering. New techniques are needed to extend optical access to large 3D volumes in deep brain areas, while retaining local connectivity. Approach. We have developed a method to implant bundles of hundreds or thousands of optical microfibers, each with a diameter of 8 μm. During insertion, each fiber moves independently, following a path of least resistance. The fibers achieve near total internal reflection, enabling optically interfacing with the tissue near each fiber aperture. Main results. At a depth of 3 mm, histology shows fibers consistently splay over 1 mm in diameter throughout the target region. Immunohistochemical staining after chronic implants reveals neurons in close proximity to the fiber tips. Models of photon fluence indicate that fibers can be used as a stimulation light source to precisely activate distinct patterns of neurons by illuminating a subset of fibers in the bundle. By recording fluorescent beads diffusing in water, we demonstrate the recording capability of the fibers. Significance. Our histology, modeling and fluorescent bead recordings suggest that the optical microfibers may provide a minimally invasive, stable, bidirectional interface for recording or stimulating genetic probes in deep brain regions—a hyper-localized form of fiber photometry.

Objective. Stereotactic frame systems are the gold-standard for stereotactic surgeries, such as implantation of deep brain stimulation (DBS) devices for treatment of medically resistant neurologic and psychiatric disorders. However, frame-based systems require that the patient is awake with a stereotactic frame affixed to their head for the duration of the surgical planning and implantation of the DBS electrodes. While frameless systems are increasingly available, a reusable re-attachable frame system provides unique benefits. As such, we created a novel reusable MRI-compatible stereotactic frame system that maintains clinical accuracy through the detachment and reattachment of its stereotactic devices used for MRI-guided neuronavigation. Approach. We designed a reusable arc-centered frame system that includes MRI-compatible anchoring skull screws for detachment and re-attachment of its stereotactic devices. We validated the stability and accuracy of our system through phantom, in vivo mock-human porcine DBS-model and human cadaver testing. Main results. Phantom testing achieved a root mean square error (RMSE) of 0.94  ±  0.23 mm between the ground truth and the frame-targeted coordinates; and achieved an RMSE of 1.11  ±  0.40 mm and 1.33  ±  0.38 mm between the ground truth and the CT- and MRI-targeted coordinates, respectively. In vivo and cadaver testing achieved a combined 3D Euclidean localization error of 1.85  ±  0.36 mm (p  <  0.03) between the pre-operative MRI-guided placement and the post-operative CT-guided confirmation of the DBS electrode. Significance. Our system demonstrated consistent clinical accuracy that is comparable to conventional frame and frameless stereotactic systems. Our frame system is the first to demonstrate accurate relocation of stereotactic frame devices during in vivo MRI-guided DBS surgical procedures. As such, this reusable and re-attachable MRI-compatible system is expected to enable more complex, chronic neuromodulation experiments, and lead to a clinically available re-attachable frame that is expected to decrease patient discomfort and costs of DBS surgery.

Objective. Our purpose was to evaluate the ability of a dual electrode approach to remove motion artifact from electroencephalography (EEG) measurements. Approach. We used a phantom human head model and robotic motion platform to induce motion while collecting scalp EEG. We assembled a dual electrode array capturing (a) artificial neural signals plus noise from scalp EEG electrodes, and (b) electrically isolated motion artifact noise. We recorded artificial neural signals broadcast from antennae in the phantom head during continuous vertical sinusoidal movements (stationary, 1.00, 1.25, 1.50, 1.75, 2.00 Hz movement frequencies). We evaluated signal quality using signal-to-noise ratio (SNR), cross-correlation, and root mean square error (RMSE) between the ground truth broadcast signals and the recovered EEG signals. Main results. Signal quality was restored following noise cancellation when compared to single electrode EEG measurements collected with no phantom head motion. Significance. We achieved substantial motion artifact attenuation using secondary electrodes for noise cancellation. These methods can be applied to studying electrocortical signals during human locomotion to improve real-world neuroimaging using EEG.

Objective.&#xD;Machine learning's ability to capture intricate patterns makes it vital in neural engineering research. With its increasing use, ensuring the validity and reproducibility of machine learning methods is critical. Unfortunately, this has not always been the case in practice, as there have been recent retractions across various scientific fields due to the misuse of machine learning methods and validation procedures. To address these concerns, we propose the first version of the Neural Engineering Reproducibility and Validity Essentials for Machine Learning (NERVE-ML) checklist, a framework designed to promote the transparent, reproducible, and valid application of machine learning in neural engineering. &#xD;Approach. &#xD;We highlight some of the unique challenges of model validation in neural engineering, including the difficulties from limited subject numbers, repeated or non-independent samples, and high subject heterogeneity. Through detailed case studies, we demonstrate how different validation approaches can lead to divergent scientific conclusions, highlighting the importance of selecting appropriate procedures guided by the NERVE-ML checklist. Effectively addressing these challenges and properly scoping scientific conclusions will ensure that machine learning contributes to, rather than hinders, progress in neural engineering.&#xD;Main Results. &#xD;Our case studies demonstrate that improper validation approaches can result in flawed studies or overclaimed scientific conclusions, complicating the scientific discourse. The (NERVE-ML) checklist effectively addresses these concerns by providing guidelines to ensure that machine learning approaches in neural engineering are reproducible and lead to valid scientific conclusions. &#xD;Significance. &#xD;By effectively addressing these challenges and properly scoping scientific conclusions guided by the NERVE-ML checklist, we aim to help pave the way for a future where machine learning reliably enhances the quality and impact of neural engineering research.&#xD;

Introduction&#xD;Evoked compound action potentials (ECAPs) during spinal cord stimulation (SCS) may be useful in the treatment of chronic pain as a control signal for closed-loop neuromodulation. However, considerable inter-individual variability in evoked responses requires robust methods in order to realize effective, personalized pain management. These methods include artifact removal, feature extraction, classification, and prediction.&#xD;&#xD;Methods&#xD;We recorded ECAPs from eight participants with chronic pain undergoing an externalized trial with two percutaneous leads. The two most caudal electrodes were used for stimulation and the remaining electrodes were used for recording. Artifact-cleaned waveforms were clustered using principal component analysis (PCA) and classified using a K-Nearest Neighbors (KNN) classifier as non-ECAPs, ECAPs, or outlier (i.e. artifacts) to determine how well different features, including area under the curve (AUC) and peak-to-peak amplitude (P2P), discriminate between waveform classes. Finally, we used generalized linear mixed effects models (GLMEs) to predict evoked response features and the probability of observing artifacts or ECAPs following individual stimulation pulses for different stimulation amplitudes, pulse widths, and polarities.&#xD;&#xD;Results&#xD;AUC was better at discriminating between ECAPs and non-ECAPs than P2P (d' = 2.44 vs d' = 2.27) while most features were good at discriminating between ECAPs and artifacts (d' > 1.5). The application of an optimal AUC threshold was then used to analyze individual ECAPs at different stimulation amplitudes, pulse widths, and polarities. Interestingly, ECAPs could be evoked using ~1.25 mA less current when using participant-specific, preferred stimulation polarities. Conversely, N1 latency consistently correlated with the location of the cathode.&#xD;&#xD;Conclusion&#xD;We developed an automated analysis pipeline for individual ECAPs during SCS. AUC was better than the widely used P2P for characterizing evoked responses. Furthermore, our modeling results provide a method for predicting how various stimulation parameters affect SCS responses in individual participants.&#xD;

Objective. Despite remarkable advances in EMG-based hand motor decoding, developing a practical and reliable decoder for robotic prosthetic hands remains unsolved. This study highlights inter-individual, inter-session, and intra-session variabilities of EMG signals as practical challenges and introduces a novel personalized and adaptive motor decoding framework, designed to mitigate their impact and improve hand motor decoding.&#xD;Approach. A dataset was collected from twelve participants (8 male, 4 female), incorporating EMG signals from three forearm muscles during 20 repetitions of 9 distinct hand motions. This data was used to conduct a number of tests for analyzing variabilities of EMG signals, followed by the evaluation of the proposed framework using various classifier models, including MLP, SVM, CNN, and KAN, as well as different feature extraction methods, some of which were suggested in previous studies. &#xD;Main Results. For feature extraction, a window size of 100 ms proved optimal, balancing the trade-off between time and accuracy. Focusing on EMG signal variabilities, this study highlights the impact of intra-session variability on classification accuracy, alongside inter-individual and inter-session variabilities. For all models, accuracy declines from an initial average of 92.33±6.17% to 80.56±9.57% after only 17 repetitions without adaptation. However, the framework, which is designed based on unsupervised adaptation, enhances this degradation to 88.88±8.72%, achieving statistically significant improvements, regardless of the classifier structure and feature extraction method used.&#xD;Significance. Considering the variabilities of EMG signals, the proposed framework is modular and integrates components such as a motion classifier and a feature extractor, which can be selected based on suggestions from prior studies. These are extended by additional elements, including a finite-state machine (FSM) to identify hand rest and action states and manage state transitions, and a Softmax module designed to ensure the consistency of performed motions and minimize the likelihood of misclassification.

In recent years, electroencephalogram (EEG)-based emotion recognition technology has made remarkable advances. However, a subtle but crucial problem caused by the sliding window method has long been overlooked, which is the serious quantity mismatch between stimuli and short-term EEG frames. This may be an important factor limiting the performance of the emotion recognition systems. We name this mismatch as quantity-independence imbalance (Q/I imbalance) and propose the weak independence hypothesis to explain it. To validate this hypothesis and explore the effects of the Q/I imbalance on short-term EEG frames, we design four experiments from four perspectives, which are visualization, cross-validation, randomness test, and redundancy test. Furthermore, inspired by the redundancy of the short-term EEG samples, we propose an inference correction (IC), which uses the majority of the classifier's outputs to correct the prediction. The proposed IC is tested in the two datasets, including 60 subjects, using the intra- and inter-subject validations. Our IC achieves a significant improvement of 14.97% in classification accuracy. This study promotes the understanding of the time-dependent nature of EEG signals.

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. Method. 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.&#xD;Machine learning's ability to capture intricate patterns makes it vital in neural engineering research. With its increasing use, ensuring the validity and reproducibility of machine learning methods is critical. Unfortunately, this has not always been the case in practice, as there have been recent retractions across various scientific fields due to the misuse of machine learning methods and validation procedures. To address these concerns, we propose the first version of the Neural Engineering Reproducibility and Validity Essentials for Machine Learning (NERVE-ML) checklist, a framework designed to promote the transparent, reproducible, and valid application of machine learning in neural engineering. &#xD;Approach. &#xD;We highlight some of the unique challenges of model validation in neural engineering, including the difficulties from limited subject numbers, repeated or non-independent samples, and high subject heterogeneity. Through detailed case studies, we demonstrate how different validation approaches can lead to divergent scientific conclusions, highlighting the importance of selecting appropriate procedures guided by the NERVE-ML checklist. Effectively addressing these challenges and properly scoping scientific conclusions will ensure that machine learning contributes to, rather than hinders, progress in neural engineering.&#xD;Main Results. &#xD;Our case studies demonstrate that improper validation approaches can result in flawed studies or overclaimed scientific conclusions, complicating the scientific discourse. The (NERVE-ML) checklist effectively addresses these concerns by providing guidelines to ensure that machine learning approaches in neural engineering are reproducible and lead to valid scientific conclusions. &#xD;Significance. &#xD;By effectively addressing these challenges and properly scoping scientific conclusions guided by the NERVE-ML checklist, we aim to help pave the way for a future where machine learning reliably enhances the quality and impact of neural engineering research.&#xD;

Introduction&#xD;Evoked compound action potentials (ECAPs) during spinal cord stimulation (SCS) may be useful in the treatment of chronic pain as a control signal for closed-loop neuromodulation. However, considerable inter-individual variability in evoked responses requires robust methods in order to realize effective, personalized pain management. These methods include artifact removal, feature extraction, classification, and prediction.&#xD;&#xD;Methods&#xD;We recorded ECAPs from eight participants with chronic pain undergoing an externalized trial with two percutaneous leads. The two most caudal electrodes were used for stimulation and the remaining electrodes were used for recording. Artifact-cleaned waveforms were clustered using principal component analysis (PCA) and classified using a K-Nearest Neighbors (KNN) classifier as non-ECAPs, ECAPs, or outlier (i.e. artifacts) to determine how well different features, including area under the curve (AUC) and peak-to-peak amplitude (P2P), discriminate between waveform classes. Finally, we used generalized linear mixed effects models (GLMEs) to predict evoked response features and the probability of observing artifacts or ECAPs following individual stimulation pulses for different stimulation amplitudes, pulse widths, and polarities.&#xD;&#xD;Results&#xD;AUC was better at discriminating between ECAPs and non-ECAPs than P2P (d' = 2.44 vs d' = 2.27) while most features were good at discriminating between ECAPs and artifacts (d' > 1.5). The application of an optimal AUC threshold was then used to analyze individual ECAPs at different stimulation amplitudes, pulse widths, and polarities. Interestingly, ECAPs could be evoked using ~1.25 mA less current when using participant-specific, preferred stimulation polarities. Conversely, N1 latency consistently correlated with the location of the cathode.&#xD;&#xD;Conclusion&#xD;We developed an automated analysis pipeline for individual ECAPs during SCS. AUC was better than the widely used P2P for characterizing evoked responses. Furthermore, our modeling results provide a method for predicting how various stimulation parameters affect SCS responses in individual participants.&#xD;

Objective. Advances in electronics and materials science have led to the development of sophisticated components for clinical and research neurotechnology systems. However, instrumentation to easily evaluate how these components function in a complete system does not yet exist. In this work, we set out to design and validate a software-defined mixed-signal routing fabric, 'xDev', that enables neurotechnology system designers to rapidly iterate, evaluate, and deploy advanced multi-component systems. Approach. We developed a set of system requirements for xDev, and implemented a design based on a 16 × 16 analog crosspoint multiplexer. We then tested the impedance and switching characteristics of the design, assessed signal gain and crosstalk attenuation across biological and high-speed digital signaling frequencies, and evaluated the ability of xDev to flexibly reroute microvolt-scale amplitude and high-speed signals. Finally, we conducted an intraoperative in vivo deployment of xDev to rapidly conduct neuromodulation experiments using diverse neurotechnology submodules. Main results. The xDev system impedance matching, crosstalk attenuation, and frequency response characteristics accurately transmitted signals over a broad range of frequencies, encapsulating features typical of biosignals and extending into high-speed digital ranges. Microvolt-scale biosignals and 600 Mbps Ethernet connections were accurately routed through the fabric. These performance characteristics culminated in an in vivo demonstration of the flexibility of the system via implanted spinal electrode arrays in an ovine model. Significance. xDev represents a first-of-its-kind, low-cost, software-defined neurotechnology development accelerator platform. Through the public, open-source distribution of our designs, we lower the obstacles facing the development of future neurotechnology systems.

Objective. There is limited work investigating Brain-Computer Interface (BCI) technology in people with Multiple Sclerosis (pwMS), a neurodegenerative disorder of the central nervous system. Present work is limited to recordings at the scalp, which may be significantly altered by changes within the cortex due to volume conduction. The recordings obtained from the sensors, therefore, combine disease-related alterations and task-relevant neural signals, as well as signals from other regions of the brain that are not relevant. The current study aims to unmix signals affected by MS progression and BCI task-relevant signals using estimated source activity to improve classification accuracy.&#xD;Approach. Data was collected from eight participants with a range of MS severity and ten neurotypical participants. This dataset was used to report the classification accuracy of imagined movements of the hands and feet at the sensor-level and the source-level in the current study. K-means clustering of equivalent current dipoles was conducted to unmix temporally independent signals. The location of these dipoles was compared between MS and control groups and used for classification of imagined movement. Linear discriminant analysis classification was performed at each time-frequency point to highlight differences in frequency band delay.&#xD;Main Results. Source-level signal acquisition significantly improved decoding accuracy of imagined movement vs. rest and movement vs. movement classification in pwMS and controls. There was no significant difference found in alpha (7-13 Hz) and beta (13-30 Hz) band classification delay between the neurotypical control and MS group, including imagery of limbs with weakness or paralysis.&#xD;Significance. This study is the first to demonstrate the advantages of source-level analysis for BCI applications in pwMS. The results highlight the potential for enhanced clinical outcomes and emphasize the need for longitudinal studies to assess the impact of MS progression on BCI performance, which is crucial for effective clinical translation of BCI technology.&#xD;

Objective. Localization of function within the brain and central nervous system is an essential aspect of clinical neuroscience. Classical descriptions of functional neuroanatomy provide a foundation for understanding the functional significance of identifiable anatomic structures. However, individuals exhibit substantial variation, particularly in the presence of disorders that alter tissue structure or impact function. Furthermore, functional regions do not always correspond to identifiable structural features. Understanding function at the level of individual patients—and diagnosing and treating such patients—often requires techniques capable of correlating neural activity with cognition, behavior, and experience in anatomically precise ways. Approach. Recent advances in brain–computer interface technology have given rise to a new generation of electrophysiologic tools for scalable, nondestructive functional mapping with spatial precision in the range of tens to hundreds of micrometers, and temporal resolutions in the range of tens to hundreds of microseconds. Here we describe our initial intraoperative experience with novel, thin-film arrays containing 1024 surface microelectrodes for electrocorticographic mapping in a first-in-human study. Main results. Eight patients undergoing standard electrophysiologic cortical mapping during resection of eloquent-region brain tumors consented to brief sessions of concurrent mapping (micro-electrocorticography) using the novel arrays. Four patients underwent motor mapping using somatosensory evoked potentials (SSEPs) while under general anesthesia, and four underwent awake language mapping, using both standard paradigms and the novel microelectrode array. SSEP phase reversal was identified in the region predicted by conventional mapping, but at higher resolution (0.4 mm) and as a contour rather than as a point. In Broca's area (confirmed by direct cortical stimulation), speech planning was apparent in the micro-electrocorticogram as high-amplitude beta-band activity immediately prior to the articulatory event. Significance. These findings support the feasibility and potential clinical utility of incorporating micro-electrocorticography into the intraoperative workflow for systematic cortical mapping of functional brain regions.

Virtual Reality (VR) serves as a modern and powerful tool to enrich neurofeedback (NF) and brain-computer interface (BCI) applications as well as to achieve higher user motivation and adherence to training. However, between 20-80% of all the users develop symptoms of cybersickness (CS), such as nausea, oculomotor problems or disorientation during VR interaction, which influence user performance and behaviour in VR. Hence, we investigated whether CS-inducing VR paradigms influence the success of a NF training task. We tested 39 healthy participants (20 female) in a single-session VR-based NF study. One half of the participants was presented with a high CS-inducing VR-environment where movement speed, field of view and camera angle were varied in a CS-inducing fashion throughout the session and the other half underwent NF training in a less CS-inducing VR environment, where those parameters were held constant. The NF training consisted of 6 runs of 3 min each, in which participants should increase their sensorimotor rhythm (SMR, 12-15 Hz) while keeping artifact control frequencies constant (Theta 4-7 Hz, Beta 16-30 Hz). Heart rate and subjectively experienced CS were also assessed. The high CS-inducing condition tended to lead to more subjectively experienced CS nausea symptoms than the low CS-inducing condition. Further, women experienced more CS, a higher heart rate and showed a worse NF performance compared to men. However, the SMR activity during the NF training was comparable between both the high and low CS-inducing groups. Both groups were able to increase their SMR across feedback runs, although, there was a tendency of higher SMR power for male participants in the low CS group. Hence, sickness symptoms in VR do not necessarily impair NF/BCI training success. This takes us one step further in evaluating the practicability of VR in BCI and NF applications. Nevertheless, inter-individual differences in CS susceptibility should be taken into account for VR-based NF applications.

Objective:&#xD;Freely moving thought is a type of thinking that shifts from one topic to another without any overarching direction or aim. The ability to detect when freely moving thought occurs may help us promote its beneficial outcomes, such as for creative thinking and positive mood. Thus far, no studies have used machine learning to detect freely moving thought on the basis of "objective" (e.g. neural or behavioral) data. &#xD;Approach:&#xD;Our study addresses this gap, using event-related potential (ERP) and spectral features of electroencephalogram (EEG) signals as well as behavioral measures during a simple attention task and machine learning to detect freely moving thought. EEG features were first examined with both inter-subject and intra-subject strategies. Specifically, the statistical and entropy features of the P3 ERP and alpha spectral measures were entered as inputs to the support vector machine (SVM). The best combination of EEG features achieving higher classification performance in both strategies were then selected to combine with behavioral features to further enhance classification performance. &#xD;Results:&#xD;Our best performing model has a Matthew's Correlation Coefficient (MCC) and Area Under the Curve (AUC) of 0.3105 and 0.6665 for inter-subject models and 0.2815 and 0.6407 for intra-subject models respectively. &#xD;Significance:&#xD;The above chance level performance in both strategies using EEG and behavioral features shows great promise for machine learning approaches to detect freely moving thought and highlights their potential for real-time prediction in the real world. This has important implications for enhancing creative processes and mood associated with freely moving thought.

Objective: This study examined the strength and stability of motor signals in low gamma and high gamma bands of vascular electrocorticograms (VECoG) recorded with endovascular stent-electrode arrays (Stentrodes) implanted in the superior sagittal sinus of two participants with severe paralysis due to Amyotrophic Lateral Sclerosis. &#xD;Methods: VECoG signals were recorded from two participants in the COMMAND trial, an Early Feasibility Study of the Stentrode brain-computer interface (BCI) (NCT05035823). The participants performed attempted movements of their ankles or hands. The signals were band-pass filtered to isolate low gamma (30-70 Hz) and high gamma (70-200 Hz) components. The strength of VECoG motor activity was measured as signal-to-noise ratio (SNR) and the percentage change in signal amplitude between the rest and attempted movement epochs, which we termed depth of modulation (DoM). We trained and tested classifiers to evaluate the accuracy and stability of detecting motor intent.&#xD;Results: Both low gamma and high gamma were modulated during attempted movements. For Participant 1, the average DoM across channels and sessions was 125.41 ± 17.53 % for low gamma and 54.23 ± 4.52 % for high gamma, with corresponding SNR values of 6.75 ± 0.37 dB and 3.69 ± 0.28 dB. For Participant 2, the average DoM was 22.77 ± 4.09 % for low gamma and 22.53 ± 2.04 % for high gamma, with corresponding SNR values of 1.72 ± 0.25 dB and 1.73 ± 0.13 dB. VECoG amplitudes remained significantly different between rest and move periods over the 3 - month testing period, with > 90 % accuracy in discriminating attempted movement from rest epochs for both participants. For Participant 1, the average DoM was strongest during attempted movements of both ankles, while for Participant 2, the DoM was greatest for attempted movement of the right hand. The overall classification accuracy was 91.43 % for Participant 1 and 70.37 % for Participant 2 in offline decoding of multiple attempted movements and rest conditions.&#xD;Significance: By eliminating the need for open brain surgery, the Stentrode offers a promising BCI alternative, potentially enhancing access to BCIs for individuals with severe motor impairments. This study provides preliminary evidence that the Stentrode can detect discriminable signals indicating motor intent, with motor signal modulation observed over the 3 - month testing period reported here.

Objective: The notion of a somatotopically organized motor cortex, with movements of different body parts being controlled by spatially distinct areas of cortex, is well known. However, recent studies have challenged this notion and suggested a more distributed representation of movement control. This shift in perspective has significant implications, particularly when considering the implantation location of electrode arrays for intracortical brain–computer interfaces (iBCIs). We sought to evaluate whether the location of neural recordings from the precentral gyrus, and thus the underlying somatotopy, has any impact on the imagery strategies that can enable successful iBCI control. Approach: Three individuals with a spinal cord injury were enrolled in an ongoing clinical trial of an iBCI. Participants had two intracortical microelectrode arrays implanted in the arm and/or hand areas of the precentral gyrus based on presurgical functional imaging. Neural data were recorded while participants attempted to perform movements of the hand, wrist, elbow, and shoulder. Main results: We found that electrode arrays that were located more medially recorded significantly more activity during attempted proximal arm movements (elbow, shoulder) than did lateral arrays, which captured more activity related to attempted distal arm movements (hand, wrist). We also evaluated the relative contribution from the two arrays implanted in each participant to decoding accuracy during calibration of an iBCI decoder for translation and grasping tasks. For both task types, imagery strategy (e.g. reaching vs wrist movements) had a significant impact on the relative contributions of each array to decoding. Overall, we found some evidence of broad tuning to arm and hand movements; however, there was a clear bias in the amount of information accessible about each movement type in spatially distinct areas of cortex. Significance: These results demonstrate that classical concepts of somatotopy can have real consequences for iBCI use, and highlight the importance of considering somatotopy when planning iBCI implantation.

Objective.&#xD;Decoding algorithms used in invasive brain-computer interfaces (iBCIs) typically convert neural activity into continuously varying velocity commands. We hypothesized that putting constraints on which decoded velocity commands are permissible could improve user performance. To test this hypothesis, we designed the discrete direction selection (DDS) decoder, which uses neural activity to select among a small menu of preset cursor velocities.&#xD;Approach.&#xD;We tested DDS in a closed-loop cursor control task against many common continuous velocity decoders in both a human-operated real-time iBCI simulator (the jaBCI) and in a monkey using an iBCI. In the jaBCI, we compared performance across four visits by each of 48 naïve, able-bodied human subjects using either DDS, direct regression with assist (an affine map from neural activity to cursor velocity, DR-A), ReFIT, or the velocity Kalman Filter (vKF). In a follow up study to verify the jaBCI results, we compared a monkey's performance using an iBCI with either DDS or the Wiener filter decoder (a direct regression decoder that includes time history, WF).&#xD;Main Result.&#xD;In the jaBCI, DDS substantially outperformed all other decoders with 93% mean targets hit per day compared to DR-A, ReFIT, and vKF with 56%, 39%, and 26% mean targets hit, respectively. With the iBCI, the monkey achieved a 61% success rate with DDS and a 37% success rate with WF.&#xD;Significance.&#xD;Discretizing the decoded velocity with DDS effectively traded high resolution velocity commands for less tortuous and lower noise trajectories, highlighting the potential benefits of discretization in simplifying online BCI control.&#xD;