Nathan E. Crone

Brain-computer interfaces can potentially restore autonomy to people with paralysis, including the ability to control their own environment via smart devices in the home. BCI applications for controlling smart devices to date have required visual displays or auditory cues, limiting the user’s ability to autonomously and privately issue commands. In this study, a clinical trial participant with amyotrophic lateral sclerosis (ALS) used a chronically implanted electrocorticographic (ECoG) BCI to control smart devices with self-paced silent speech commands. Across 18 experimental sessions, silently mimed speech commands were detected in real time and decoded with a median accuracy of 97.1% (chance: 7.14%) and the median correct decodes per minute was 11.86. These results demonstrate that silently attempted speech can be reliably decoded without exogenous timing cues, supporting the feasibility of reliable autonomous smart device control with an implantable BCI.

Objective. Achieving long-term decoding stability is a critical challenge for chronic intracranial brain-computer interfaces (BCIs). High-gamma (HG) activity from intracranial recordings is the standard signal for BCI control, and lower-frequency features can enhance HG decoding performance. This study evaluated the longitudinal stability of speech and hand-grasp detection models using individual and joint spectral features, and the local motor potential (LMP). Approach. Longitudinal data from a single participant implanted with two 64-channel ECoG arrays were used to evaluate the long-term stability of logistic regression models for speech and hand-grasp detection. Models were trained on individual frequency bands and on the LMP, a time-domain low-frequency feature, and evaluated over 21 months for speech and 13 months for grasp. The best-performing band features were then combined into multi-band models and analyzed for their spatial contributions. Main Results. The LMP yielded the most accurate single feature models in both tasks (speech 93.8%, grasp 99.4%) and showed little or no decline. Multi-band models combining HG with lower frequency bands were substantially more stable than HG-only models and outperformed the LMP models for speech but not grasp. HG accuracy degraded strongly for both tasks (speech:-4.3 percentage points per 100 days, or pp/100d, grasp:-3.4 pp/100d). HG+beta for speech showed a negligible decline (-0.5 pp/100d, 95.6% ±0.06% overall), and for grasp, delta alone showed remarkable stability (+0.5 pp/100d), while HG+beta+delta maintained 98.2 ±0.09% overall accuracy with flat performance (+0.0 pp/100d). The advantage of the multi-band models increased over time, reaching +20.6 pp for speech and +10.2 pp for grasp in the last 100 days. Significance. Incorporating lower-frequency neural activity yields more stable long-term speech and grasp detection than HG alone. These findings indicate that lower-frequency and multi-band features may reduce recalibration requirements for simple BCI tasks, and may complement the precision control provided by HG activity.

Summary: Passive language mapping using high-gamma modulation (HGM) has emerged as a valuable tool in both presurgical evaluation for epilepsy and neuroscientific discovery. HGM mapping leverages task-related synchronization in high-gamma frequencies to identify language areas without the risks associated with electrical stimulation mapping. This review outlines the principles and techniques used in the field of HGM-based mapping, including electrode types, referencing schemes, power analysis, and localization techniques. We survey a range of cognitive tasks—speech production, auditory processing, reading, and memory—that elicit language-related HGM responses and discuss their relevance to comprehensive language mapping. We examine perspectives on methodologic challenges, including artifact management, variability across patients, and spatial sampling. We assess validation studies comparing HGM with electrical stimulation mapping and neuropsychological outcomes, noting HGM's unique role in identifying language cortex in pediatric and cognitively impaired populations. Finally, we speculate on the future directions of the field, including integration with corticocortical evoked potentials and the potential for HGM-informed speech synthesis. As the field matures, HGM mapping is poised to contribute to improved clinical outcomes and enhance our understanding of the dynamics and development of the human language network.

Direct electrocortical stimulation (ECS) is a well-established brain mapping technique that helps achieve safe and effective resection of epileptic foci, tumors or vascular malformations. Recent studies using electrocorticography (ECoG) suggest that ECS' exerted effects on brain sites are determined by the roles of those sites in larger networks. However, ECoG has limited spatial coverage. Here, we used functional magnetic resonance imaging from eighteen participants during performance of five language tasks to assess the functional network signatures of cortical sites defined as critical for speech and language by ECS. We found that critical sites causing speech arrests (SA) and language errors (LE) exhibited lower local and global connectivity than non-critical sites. LE sites showed greater connectivity across sub-networks (communities) than both non-critical and SA sites, indicating their role as connectors across functional networks. This connector profile of LE sites was most robust when considering network connectivity across the entire brain. Connector sites were concentrated primarily in temporal and inferior parietal cortices. Finally, these network features accurately predicted which sites were critical in machine learning models. These findings provide a preoperative framework for predicting cortical sites critical for speech and language function, which may ultimately help accelerate or improve brain mapping.

Millions of people worldwide are living with movement and sensory impairments owing to spinal cord injury, stroke and other neurological conditions. Here we report a double neural bypass (DNB), a hybrid neuroprosthetic system designed to restore both immediate and lasting gains in movement and sensation after a severe, complete spinal cord injury. The DNB links an intracortical brain–computer interface with targeted and patterned neuromodulation of the spinal cord and cortex. This allows brain signals associated with movement intention to directly control the movement of the user’s own hand in real time while also promoting long-term sensorimotor recovery—even after the system is turned off. The DNB system uses recurrent artificial neural networks and reinforcement learning for fine grasp control, together with patterned spinal cord stimulation and activity-informed intracortical microstimulation (‘cortical mirroring’) to promote neuroplasticity and durable recovery of function. In a participant with chronic C4 sensory/C5 motor complete tetraplegia, this hybrid approach enabled recovery of functional abilities including self-feeding and manipulation of delicate objects, while also producing significant and persistent improvements in elbow flexion and wrist tactile sensation. These findings demonstrate the potential of combining a sensorimotor neuroprosthesis with targeted brain and spinal neuromodulation to restore clinically relevant function in severe paralysis.

Background Electrocorticographic (ECoG) speech brain-computer interfaces (BCIs) show promise for restoring communication in amyotrophic lateral sclerosis (ALS), but the long-term stability of speech-related neural signals and decoding performance during disease progression remains unclear. We tracked signal characteristics and decoding over 25 months in a participant with ALS to determine how high-gamma (HG, 70–170 Hz) activity changes over time and whether these changes affect offline speech decoding. Methods We implanted two 8×8 subdural ECoG grids over left sensorimotor cortex (SMC) in a participant with slowly progressive bulbar variant ALS. Across 25 months, the participant performed an overt syllable-repetition task (12 consonant-vowel tokens) during simultaneous ECoG and audio recording. We quantified HG activation ratio (ActR), spectral signal-to-noise ratio (SNR; HG/HF, where HF = 300–499 Hz), and peak z-scored HG responses. Speech acoustics were evaluated using first/second formants (F1/F2) and the triangular vowel space area (tVSA). Offline EEGNet-based decoders were assessed in two stages: models trained on post-implant months 1–6 were tested on months 7–25, while models trained on stabilized data (months 7–11) were tested on the remaining period (months 12–25). Electrode-level saliency assessed spatial contributions to decoding. Results Acoustic analyses showed a significant reduction in tVSA over two years (-44.6 Hz²/day; P < 10 ⁻ ⁷), consistent with mild intelligibility decline. Neural metrics (ActR and SNR) followed a biphasic trajectory: increasing during the first 6 months, after which ActR stabilized (0.041%/day; P = 0.13), and SNR declined gradually (-0.46%/day, P < 10 ^− 4 ). The model trained on months 1–6 achieved 55.7% accuracy (chance: 8.33%), but performance declined over time (-0.019%/day; P = 2.1×10 ⁻ ⁴). Conversely, the model trained on months 7–11 achieved higher accuracy (65.9%) on subsequent data with no significant temporal decline ( P = 0.23). Conclusions Speech-related HG features exhibited an initial unstable period followed by a long-term gradual SNR reduction, potentially reflecting disease progression. Models trained after signal stabilization generalized robustly to data recorded over a year later. These findings confirm that despite reduced absolute HG power and mild acoustic degradation of speech, cortical features remain stable enough to support durable ECoG speech BCIs without frequent recalibration. These findings will motivate future adaptive calibration algorithms that account for slow signal changes while leveraging stable spatial representations in ventral SMC. ClinicalTrials.gov Identifier NCT03567213

Brain-computer interfaces (BCIs) have the potential to preserve or restore communication and device control in people with paralysis from a variety of causes. For people living with amyotrophic lateral sclerosis (ALS), however, the progressive loss of cortical motor neurons could theoretically pose a challenge to the stability of BCI performance. Here we tested the stability of gesture decoding with a chronic electrocorticographic (ECoG) BCI in a man living with ALS and participating in a clinical trial ( ClinicalTrials.gov , NCT03567213 ). We evaluated offline decoding performance of attempted gestures over two periods: a 5-week period beginning roughly 2 years post-implant and a 6-week period ending roughly 5 months later. Decoder sensitivity was high in both periods (90 - 98%), while classification accuracy was 37 - 68% in the first period and worsened to 23 - 39% in the second. We investigated multiple frequency bands that were used as model features in both periods, and we observed reductions in high gamma band power (70 - 110 Hz) and between-class separation during the second period compared to the first. Over the 5-month period motor function did not appreciably decline. These results, albeit preliminary, suggest that declines in the neural population responses that drive ECoG BCI performance can occur without overt signs of disease progression in people living with ALS, and could serve as a biomarker for disease progression in the future.

Objective. Brain–computer interfaces hold significant promise for restoring communication in individuals with partial or complete loss of the ability to speak due to paralysis from amyotrophic lateral sclerosis (ALS), brainstem stroke, and other neurological disorders. Many of the approaches to speech decoding reported in the BCI literature have required time-aligned target representations to allow successful training—a major challenge when translating such approaches to people who have already lost their voice. Approach. In this pilot study, we made a first step toward scenarios in which no ground truth is available. We utilized a graph-based clustering approach to identify temporal segments of speech production from electrocorticographic (ECoG) signals alone. We then used the estimated speech segments to train a voice activity detection (VAD) model using only ECoG signals. We evaluated our approach using a leave-one-day-out cross-validation on open-loop recordings of a single dysarthric clinical trial participant living with ALS, and we compared the resulting performance to previous solutions trained with ground truth acoustic voice recordings. Main results. Our approach achieves a median timing error of around 530 ms with respect to the actual spoken speech. Embedded into a real-time BCI, our approach is capable of providing VAD results with a latency of only 10 ms. Significance. To the best of our knowledge, our results show for the first time that speech activity can be predicted purely from unlabeled ECoG signals, a crucial step toward individuals who cannot provide this information anymore due to their neurological condition, such as patients with locked-in syndrome. Clinical Trial Information. ClinicalTrials.gov, registration number NCT03567213.

Spinal cord injury (SCI) affects millions worldwide, with over half of all cases resulting in tetraplegia, where a complete injury can cause profound motor and sensory loss in all four limbs ¹ . Here, we demonstrate an artificial ‘double neural bypass’ (DNB) that integrates a bidirectional intracortical brain-computer interface with targeted spinal and brain stimulation to promote restoration of upper limb function in severe, complete paralysis. This hybrid assistive-therapeutic approach restores both hand movement and tactile sensation simultaneously via cortical mediation while promoting significant persistent sensorimotor improvements. The DNB uses a stable nested neural decoding architecture with deep reinforcement learning for fine grasping, along with patterned brain microstimulation (‘cortical mirroring’) and spinal cord stimulation to promote real-time and long-term functional recovery. Using the DNB, our participant with chronic C4 sensory/C5 motor complete tetraplegia regained the ability to self-feed, grasp delicate objects, and experienced persistent recovery of arm flexion and wrist tactile sensation. These findings represent a major advance in restoring meaningful function after severe, complete SCI, demonstrating that bidirectional neuroprostheses combined with targeted brain and spinal neuromodulation can drive durable sensorimotor recovery and improve independence and quality of life.