Appearance
An Accurate and Rapidly Calibrating Speech Neuroprosthesis.
Literature Information
| DOI | 10.1056/NEJMoa2314132 |
|---|---|
| PMID | 39141853 |
| Journal | The New England journal of medicine |
| Impact Factor | 78.5 |
| JCR Quartile | Q1 |
| Publication Year | 2024 |
| Times Cited | 38 |
| Keywords | Brain-computer interface, Neuroprosthesis, Amyotrophic lateral sclerosis, Speech recognition, Calibration |
| Literature Type | Journal Article, Case Reports, Research Support, U.S. Gov't, Non-P.H.S., Research Support, N.I.H., Extramural |
| ISSN | 0028-4793 |
| Pages | 609-618 |
| Issue | 391(7) |
| Authors | Nicholas S Card, Maitreyee Wairagkar, Carrina Iacobacci, Xianda Hou, Tyler Singer-Clark, Francis R Willett, Erin M Kunz, Chaofei Fan, Maryam Vahdati Nia, Darrel R Deo, Aparna Srinivasan, Eun Young Choi, Matthew F Glasser, Leigh R Hochberg, Jaimie M Henderson, Kiarash Shahlaie, Sergey D Stavisky, David M Brandman |
TL;DR
This study demonstrates that an intracortical speech neuroprosthesis can effectively restore conversational communication in a 45-year-old man with ALS, achieving up to 99.6% accuracy after minimal training and allowing for sustained communication at 32 words per minute over 8.4 months. The findings highlight the potential of brain-computer interfaces to improve the quality of life for individuals with severe speech impairments by facilitating naturalistic communication.
Search for more papers on MaltSci.com
Brain-computer interface · Neuroprosthesis · Amyotrophic lateral sclerosis · Speech recognition · Calibration
Abstract
BACKGROUND Brain-computer interfaces can enable communication for people with paralysis by transforming cortical activity associated with attempted speech into text on a computer screen. Communication with brain-computer interfaces has been restricted by extensive training requirements and limited accuracy.
METHODS A 45-year-old man with amyotrophic lateral sclerosis (ALS) with tetraparesis and severe dysarthria underwent surgical implantation of four microelectrode arrays into his left ventral precentral gyrus 5 years after the onset of the illness; these arrays recorded neural activity from 256 intracortical electrodes. We report the results of decoding his cortical neural activity as he attempted to speak in both prompted and unstructured conversational contexts. Decoded words were displayed on a screen and then vocalized with the use of text-to-speech software designed to sound like his pre-ALS voice.
RESULTS On the first day of use (25 days after surgery), the neuroprosthesis achieved 99.6% accuracy with a 50-word vocabulary. Calibration of the neuroprosthesis required 30 minutes of cortical recordings while the participant attempted to speak, followed by subsequent processing. On the second day, after 1.4 additional hours of system training, the neuroprosthesis achieved 90.2% accuracy using a 125,000-word vocabulary. With further training data, the neuroprosthesis sustained 97.5% accuracy over a period of 8.4 months after surgical implantation, and the participant used it to communicate in self-paced conversations at a rate of approximately 32 words per minute for more than 248 cumulative hours.
CONCLUSIONS In a person with ALS and severe dysarthria, an intracortical speech neuroprosthesis reached a level of performance suitable to restore conversational communication after brief training. (Funded by the Office of the Assistant Secretary of Defense for Health Affairs and others; BrainGate2 ClinicalTrials.gov number, NCT00912041.).
MaltSci.com AI Research Service
Intelligent ReadingAnswer any question about the paper and explain complex charts and formulas
Locate StatementsFind traces of a specific claim within the paper
Add to KBasePerform data extraction, report drafting, and advanced knowledge mining
Primary Questions Addressed
- How does the accuracy of the speech neuroprosthesis compare to traditional speech therapy methods for patients with ALS?
- What are the potential long-term effects of using a speech neuroprosthesis on cognitive function in patients with severe dysarthria?
- How can the calibration process of the neuroprosthesis be optimized for different types of speech impairments beyond ALS?
- What advancements in neural decoding technology could further enhance the performance of speech neuroprostheses in the future?
- How does the integration of text-to-speech software impact the user's emotional and psychological well-being during communication?
Key Findings
Background and Objectives
Brain-computer interfaces (BCIs) offer potential communication avenues for individuals with paralysis by translating cortical activity related to speech attempts into text. However, traditional BCIs have faced challenges due to extensive training needs and limited accuracy. This study aims to evaluate the effectiveness of an intracortical speech neuroprosthesis in a patient with amyotrophic lateral sclerosis (ALS), focusing on its ability to facilitate communication through decoded neural signals.
Main Methods/Materials/Experimental Design
The study involved a 45-year-old male patient with ALS who exhibited tetraparesis and severe dysarthria. The following methods were employed:
- Surgical Procedure: Four microelectrode arrays were implanted into the left ventral precentral gyrus, enabling the recording of neural activity from 256 intracortical electrodes.
- Data Collection: The patient attempted to speak in both prompted and unstructured conversational settings. Neural signals were recorded during these attempts.
- Decoding Process: The recorded neural activity was processed to decode speech attempts, with the results displayed on a screen and vocalized using text-to-speech software that mimicked the patient's voice prior to ALS.
The technical workflow can be summarized as follows:
Key Results and Findings
- On the first day of usage, the neuroprosthesis achieved a remarkable 99.6% accuracy with a vocabulary of 50 words after 30 minutes of calibration.
- After an additional 1.4 hours of training on the second day, accuracy was maintained at 90.2% with a vocabulary expanded to 125,000 words.
- Over an 8.4-month period, the neuroprosthesis sustained an accuracy of 97.5%, enabling the participant to engage in self-paced conversations at a rate of approximately 32 words per minute, accumulating over 248 hours of use.
| Day | Vocabulary Size | Accuracy (%) | Training Time (hours) |
|---|---|---|---|
| 1 | 50 | 99.6 | 0.5 |
| 2 | 125,000 | 90.2 | 1.4 |
| 8.4 months | - | 97.5 | - |
Main Conclusions/Significance/Innovativeness
The study demonstrates that an intracortical speech neuroprosthesis can effectively restore conversational communication in a patient with ALS and severe dysarthria after minimal training. This advancement suggests that BCIs can significantly enhance the quality of life for individuals with speech impairments, providing a promising avenue for future research and clinical applications in neuroprosthetics.
Research Limitations and Future Directions
- Limitations: The study is limited by its single-case design, which may affect the generalizability of the results. Additionally, the long-term stability of the device's performance over time and in varied contexts remains to be established.
- Future Directions: Further research should involve larger sample sizes and diverse patient populations to validate the findings. Additionally, exploring the integration of machine learning algorithms for improved decoding accuracy and vocabulary expansion could enhance the neuroprosthesis's effectiveness.
In conclusion, this research provides a significant step forward in the development of BCIs for speech restoration, highlighting both the potential benefits and the need for continued exploration in this innovative field.
References
- A Neurosurgical Functional Dissection of the Middle Precentral Gyrus during Speech Production. - Alexander B Silva;Jessie R Liu;Lingyun Zhao;Deborah F Levy;Terri L Scott;Edward F Chang - The Journal of neuroscience : the official journal of the Society for Neuroscience (2022)
- Stable Decoding from a Speech BCI Enables Control for an Individual with ALS without Recalibration for 3 Months. - Shiyu Luo;Miguel Angrick;Christopher Coogan;Daniel N Candrea;Kimberley Wyse-Sookoo;Samyak Shah;Qinwan Rabbani;Griffin W Milsap;Alexander R Weiss;William S Anderson;Donna C Tippett;Nicholas J Maragakis;Lora L Clawson;Mariska J Vansteensel;Brock A Wester;Francesco V Tenore;Hynek Hermansky;Matthew S Fifer;Nick F Ramsey;Nathan E Crone - Advanced science (Weinheim, Baden-Wurttemberg, Germany) (2023)
- New and emerging access technologies for adults with complex communication needs and severe motor impairments: State of the science. - Susan Koch Fager;Melanie Fried-Oken;Tom Jakobs;David R Beukelman - Augmentative and alternative communication (Baltimore, Md. : 1985) (2019)
- In pursuit of off-task thought: mind wandering-performance trade-offs while reading aloud and color naming. - David R Thomson;Derek Besner;Daniel Smilek - Frontiers in psychology (2013)
- Direct speech reconstruction from sensorimotor brain activity with optimized deep learning models. - Julia Berezutskaya;Zachary V Freudenburg;Mariska J Vansteensel;Erik J Aarnoutse;Nick F Ramsey;Marcel A J van Gerven - Journal of neural engineering (2023)
- Generalizable spelling using a speech neuroprosthesis in an individual with severe limb and vocal paralysis. - Sean L Metzger;Jessie R Liu;David A Moses;Maximilian E Dougherty;Margaret P Seaton;Kaylo T Littlejohn;Josh Chartier;Gopala K Anumanchipalli;Adelyn Tu-Chan;Karunesh Ganguly;Edward F Chang - Nature communications (2022)
- Speech synthesis from neural decoding of spoken sentences. - Gopala K Anumanchipalli;Josh Chartier;Edward F Chang - Nature (2019)
- Plug-and-Play Stability for Intracortical Brain-Computer Interfaces: A One-Year Demonstration of Seamless Brain-to-Text Communication. - Chaofei Fan;Nick Hahn;Foram Kamdar;Donald Avansino;Guy H Wilson;Leigh Hochberg;Krishna V Shenoy;Jaimie M Henderson;Francis R Willett - Advances in neural information processing systems (2023)
- Decoding spoken words using local field potentials recorded from the cortical surface. - Spencer Kellis;Kai Miller;Kyle Thomson;Richard Brown;Paul House;Bradley Greger - Journal of neural engineering (2010)
- Brain-to-text: decoding spoken phrases from phone representations in the brain. - Christian Herff;Dominic Heger;Adriana de Pesters;Dominic Telaar;Peter Brunner;Gerwin Schalk;Tanja Schultz - Frontiers in neuroscience (2015)
Literatures Citing This Work
- A flexible intracortical brain-computer interface for typing using finger movements. - Nishal P Shah;Matthew S Willsey;Nick Hahn;Foram Kamdar;Donald T Avansino;Chaofei Fan;Leigh R Hochberg;Francis R Willett;Jaimie M Henderson - bioRxiv : the preprint server for biology (2024)
- The speech neuroprosthesis. - Alexander B Silva;Kaylo T Littlejohn;Jessie R Liu;David A Moses;Edward F Chang - Nature reviews. Neuroscience (2024)
- Targeted deep brain stimulation of the motor thalamus improves speech and swallowing motor functions after cerebral lesions. - Elvira Pirondini;Erinn Grigsby;Lilly Tang;Arianna Damiani;Jonathan Ho;Isabella Montanaro;Sirisha Nouduri;Sara Trant;Theodora Constantine;Gregory Adams;Kevin Franzese;Bradford Mahon;Julie Fiez;Donald Crammond;Kaila Stipancic;Jorge Gonzalez-Martinez - Research square (2024)
- Brain Function, Learning, and Role of Feedback in Complete Paralysis. - Stefano Silvoni;Chiara Occhigrossi;Marco Di Giorgi;Dorothée Lulé;Niels Birbaumer - Sensors (Basel, Switzerland) (2024)
- Non-invasive brain-machine interface control with artificial intelligence copilots. - Johannes Y Lee;Sangjoon Lee;Abhishek Mishra;Xu Yan;Brandon McMahan;Brent Gaisford;Charles Kobashigawa;Mike Qu;Chang Xie;Jonathan C Kao - bioRxiv : the preprint server for biology (2024)
- Artificial Intelligence in Communication Sciences and Disorders: Introduction to the Forum. - Jordan R Green - Journal of speech, language, and hearing research : JSLHR (2024)
- Decoding the brain: From neural representations to mechanistic models. - Mackenzie Weygandt Mathis;Adriana Perez Rotondo;Edward F Chang;Andreas S Tolias;Alexander Mathis - Cell (2024)
- Reducing power requirements for high-accuracy decoding in iBCIs. - Brianna M Karpowicz;Bareesh Bhaduri;Samuel R Nason-Tomaszewski;Brandon G Jacques;Yahia H Ali;Robert D Flint;Payton H Bechefsky;Leigh R Hochberg;Nicholas AuYong;Marc W Slutzky;Chethan Pandarinath - Journal of neural engineering (2024)
- Speech motor cortex enables BCI cursor control and click. - Tyler Singer-Clark;Xianda Hou;Nicholas S Card;Maitreyee Wairagkar;Carrina Iacobacci;Hamza Peracha;Leigh R Hochberg;Sergey D Stavisky;David M Brandman - bioRxiv : the preprint server for biology (2024)
- Enabling electric field model of microscopically realistic brain. - Zhen Qi;Gregory M Noetscher;Alton Miles;Konstantin Weise;Thomas R Knösche;Cameron R Cadman;Alina R Potashinsky;Kelu Liu;William A Wartman;Guillermo Nunez Ponasso;Marom Bikson;Hanbing Lu;Zhi-De Deng;Aapo R Nummenmaa;Sergey N Makaroff - Brain stimulation (2025)
... (28 more literatures)
© 2025 MaltSci - We reshape scientific research with AI technology