Neuroprosthesis enables conversational communication in amyotrophic lateral sclerosis
1. A participant with amyotrophic lateral sclerosis (ALS) and severe dysarthria underwent surgical implantation of microelectrode arrays set up to decode cortical activity as he attempted to speak.
2. The neuroprosthesis was calibrated rapidly through training to achieve a performance level sufficient for conversational communication by 8.4 months.
Evidence Rating Level: 4 (Below Average)
Study Rundown: Patients with neurologic disorders may develop difficulty and inability to communicate, which predisposes them to isolation, impairs quality of life, and impacts care decisions. Current assistive technologies, such as head or eye trackers, are limited by low information transfer rates and become unfeasible as patients lose voluntary motor control. Brain-computer interfaces to decode neural activity into intended speech are emerging as a promising alternative, with most being developed based on retrospective data from able-bodied speakers under electrophysiological monitoring. This was a case report of a 45-year-old man with ALS with tetraparesis and severe dysarthria who underwent implantation of microelectrode arrays into the left ventral precentral gyrus five years after disease onset. The neuroprosthesis system calibrated rapidly through usage and training data from the patient’s attempted speech, achieving 99.6% accuracy on a 50-word vocabulary on day one, 90.2% accuracy on a 125,000-word vocabulary on day two, and eventually sustaining 97.5% accuracy by 8.4 months after implantation. The participant could communicate in self-paced conversations at a rate of 32 words per minute in a voice modeled after his pre-ALS voice.
Click here to read the study in NEJMÂ
Relevant Reading: Neuroprosthesis for Decoding Speech in a Paralyzed Person with Anarthria
In-Depth [case report]: This was a case report of a 45-year-old man with ALS who had begun showing symptoms five years before enrollment. At enrollment, the participant was non-ambulatory, dependent on others for his activities of daily living, and had severe dysarthria. His ALS Functional Rating Scale-Revised score was 23 out of 48. He was cognitively intact, scoring 27 out of 27 on the modified Mini-Mental State Examination. The severity of dysarthria was stable throughout the study period. His neuro-implantation target was refined using the Human Connectome Project mapping to the language-related area 55b. Four microelectrode arrays, totaling 256 intracortical electrodes, were implanted in July 2023 into the participant’s left pre-central gyrus, a key cortical region for coordinating motor activities of speech. Each electrode was designed to record from one or a few cortical neurons. No serious adverse events were observed following the procedure. Data was collected across 84 sessions over 32 weeks, where the participant would perform attempts at speech through instruction video copy tasks and self-paced unstructured conversations. The computer outputs were limited to a 125,000-word dictionary. On the first day of use, the system demonstrated a 99.6% (95% confidence interval [CI] 98.6-100%) accuracy with a 50-word vocabulary. On the second day, with an additional 1.4 hours of training data, the neuroprosthesis achieved 90.2% (95% CI 84.0-95.9%) accuracy of a 125,000-word vocabulary. By session 84 at 8.4 months after implantation, the accuracy was maintained at approximately 97.5%, with the participant communicating at 31.6 words per minute (95% CI 31.2-32.0) in self-paced conversations. Compared to previous studies utilizing surface cortical neural signals, this current neuroprosthesis also demonstrated rapid calibration with significantly higher accuracy and lower training data requirements. Although whether similar results can be replicated and durability of this system as ALS progresses is unclear, this report showed the promise of intracortical neuroprosthesis in helping individuals with neurologic disorders and dysarthria communicate.
Image: PD
©2024 2 Minute Medicine, Inc. All rights reserved. No works may be reproduced without expressed written consent from 2 Minute Medicine, Inc. Inquire about licensing here. No article should be construed as medical advice and is not intended as such by the authors or by 2 Minute Medicine, Inc.
