A click-based electrocorticographic brain-computer interface enables long-term high-performance switch scan spelling

Abstract Background Brain-computer interfaces (BCIs) can restore communication for movement- and/or speech-impaired individuals by enabling neural control of computer typing applications. Single command click detectors provide a basic yet highly functional capability. Methods We sought to test the p...

Full description

Saved in:
Bibliographic Details
Main Authors: Daniel N. Candrea, Samyak Shah, Shiyu Luo, Miguel Angrick, Qinwan Rabbani, Christopher Coogan, Griffin W. Milsap, Kevin C. Nathan, Brock A. Wester, William S. Anderson, Kathryn R. Rosenblatt, Alpa Uchil, Lora Clawson, Nicholas J. Maragakis, Mariska J. Vansteensel, Francesco V. Tenore, Nicolas F. Ramsey, Matthew S. Fifer, Nathan E. Crone
Format: Article
Language:English
Published: Nature Portfolio 2024-10-01
Series:Communications Medicine
Online Access:https://doi.org/10.1038/s43856-024-00635-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850202389806579712
author Daniel N. Candrea
Samyak Shah
Shiyu Luo
Miguel Angrick
Qinwan Rabbani
Christopher Coogan
Griffin W. Milsap
Kevin C. Nathan
Brock A. Wester
William S. Anderson
Kathryn R. Rosenblatt
Alpa Uchil
Lora Clawson
Nicholas J. Maragakis
Mariska J. Vansteensel
Francesco V. Tenore
Nicolas F. Ramsey
Matthew S. Fifer
Nathan E. Crone
author_facet Daniel N. Candrea
Samyak Shah
Shiyu Luo
Miguel Angrick
Qinwan Rabbani
Christopher Coogan
Griffin W. Milsap
Kevin C. Nathan
Brock A. Wester
William S. Anderson
Kathryn R. Rosenblatt
Alpa Uchil
Lora Clawson
Nicholas J. Maragakis
Mariska J. Vansteensel
Francesco V. Tenore
Nicolas F. Ramsey
Matthew S. Fifer
Nathan E. Crone
author_sort Daniel N. Candrea
collection DOAJ
description Abstract Background Brain-computer interfaces (BCIs) can restore communication for movement- and/or speech-impaired individuals by enabling neural control of computer typing applications. Single command click detectors provide a basic yet highly functional capability. Methods We sought to test the performance and long-term stability of click decoding using a chronically implanted high density electrocorticographic (ECoG) BCI with coverage of the sensorimotor cortex in a human clinical trial participant (ClinicalTrials.gov, NCT03567213) with amyotrophic lateral sclerosis. We trained the participant’s click detector using a small amount of training data (<44 min across 4 days) collected up to 21 days prior to BCI use, and then tested it over a period of 90 days without any retraining or updating. Results Using a click detector to navigate a switch scanning speller interface, the study participant can maintain a median spelling rate of 10.2 characters per min. Though a transient reduction in signal power modulation can interrupt usage of a fixed model, a new click detector can achieve comparable performance despite being trained with even less data (<15 min, within 1 day). Conclusions These results demonstrate that a click detector can be trained with a small ECoG dataset while retaining robust performance for extended periods, providing functional text-based communication to BCI users.
format Article
id doaj-art-5c5b61fc56574dd6b4b5cc7132cd8687
institution OA Journals
issn 2730-664X
language English
publishDate 2024-10-01
publisher Nature Portfolio
record_format Article
series Communications Medicine
spelling doaj-art-5c5b61fc56574dd6b4b5cc7132cd86872025-08-20T02:11:47ZengNature PortfolioCommunications Medicine2730-664X2024-10-014111410.1038/s43856-024-00635-3A click-based electrocorticographic brain-computer interface enables long-term high-performance switch scan spellingDaniel N. Candrea0Samyak Shah1Shiyu Luo2Miguel Angrick3Qinwan Rabbani4Christopher Coogan5Griffin W. Milsap6Kevin C. Nathan7Brock A. Wester8William S. Anderson9Kathryn R. Rosenblatt10Alpa Uchil11Lora Clawson12Nicholas J. Maragakis13Mariska J. Vansteensel14Francesco V. Tenore15Nicolas F. Ramsey16Matthew S. Fifer17Nathan E. Crone18Department of Biomedical Engineering, Johns Hopkins University School of MedicineDepartment of Neurology, Johns Hopkins University School of MedicineDepartment of Biomedical Engineering, Johns Hopkins University School of MedicineDepartment of Neurology, Johns Hopkins University School of MedicineDepartment of Electrical and Computer Engineering, Johns Hopkins UniversityDepartment of Neurology, Johns Hopkins University School of MedicineResearch and Exploratory Development Department, Johns Hopkins University Applied Physics LaboratoryDepartment of Neurology, Johns Hopkins University School of MedicineResearch and Exploratory Development Department, Johns Hopkins University Applied Physics LaboratoryDepartment of Neurosurgery, Johns Hopkins University School of MedicineDepartment of Anesthesiology and Critical Care Medicine, Johns Hopkins University School of MedicineDepartment of Neurology, Johns Hopkins University School of MedicineDepartment of Neurology, Johns Hopkins University School of MedicineDepartment of Neurology, Johns Hopkins University School of MedicineDepartment of Neurology and Neurosurgery, UMC Utrecht Brain CenterResearch and Exploratory Development Department, Johns Hopkins University Applied Physics LaboratoryDepartment of Neurology and Neurosurgery, UMC Utrecht Brain CenterResearch and Exploratory Development Department, Johns Hopkins University Applied Physics LaboratoryDepartment of Neurology, Johns Hopkins University School of MedicineAbstract Background Brain-computer interfaces (BCIs) can restore communication for movement- and/or speech-impaired individuals by enabling neural control of computer typing applications. Single command click detectors provide a basic yet highly functional capability. Methods We sought to test the performance and long-term stability of click decoding using a chronically implanted high density electrocorticographic (ECoG) BCI with coverage of the sensorimotor cortex in a human clinical trial participant (ClinicalTrials.gov, NCT03567213) with amyotrophic lateral sclerosis. We trained the participant’s click detector using a small amount of training data (<44 min across 4 days) collected up to 21 days prior to BCI use, and then tested it over a period of 90 days without any retraining or updating. Results Using a click detector to navigate a switch scanning speller interface, the study participant can maintain a median spelling rate of 10.2 characters per min. Though a transient reduction in signal power modulation can interrupt usage of a fixed model, a new click detector can achieve comparable performance despite being trained with even less data (<15 min, within 1 day). Conclusions These results demonstrate that a click detector can be trained with a small ECoG dataset while retaining robust performance for extended periods, providing functional text-based communication to BCI users.https://doi.org/10.1038/s43856-024-00635-3
spellingShingle Daniel N. Candrea
Samyak Shah
Shiyu Luo
Miguel Angrick
Qinwan Rabbani
Christopher Coogan
Griffin W. Milsap
Kevin C. Nathan
Brock A. Wester
William S. Anderson
Kathryn R. Rosenblatt
Alpa Uchil
Lora Clawson
Nicholas J. Maragakis
Mariska J. Vansteensel
Francesco V. Tenore
Nicolas F. Ramsey
Matthew S. Fifer
Nathan E. Crone
A click-based electrocorticographic brain-computer interface enables long-term high-performance switch scan spelling
Communications Medicine
title A click-based electrocorticographic brain-computer interface enables long-term high-performance switch scan spelling
title_full A click-based electrocorticographic brain-computer interface enables long-term high-performance switch scan spelling
title_fullStr A click-based electrocorticographic brain-computer interface enables long-term high-performance switch scan spelling
title_full_unstemmed A click-based electrocorticographic brain-computer interface enables long-term high-performance switch scan spelling
title_short A click-based electrocorticographic brain-computer interface enables long-term high-performance switch scan spelling
title_sort click based electrocorticographic brain computer interface enables long term high performance switch scan spelling
url https://doi.org/10.1038/s43856-024-00635-3
work_keys_str_mv AT danielncandrea aclickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT samyakshah aclickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT shiyuluo aclickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT miguelangrick aclickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT qinwanrabbani aclickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT christophercoogan aclickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT griffinwmilsap aclickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT kevincnathan aclickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT brockawester aclickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT williamsanderson aclickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT kathrynrrosenblatt aclickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT alpauchil aclickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT loraclawson aclickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT nicholasjmaragakis aclickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT mariskajvansteensel aclickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT francescovtenore aclickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT nicolasframsey aclickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT matthewsfifer aclickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT nathanecrone aclickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT danielncandrea clickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT samyakshah clickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT shiyuluo clickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT miguelangrick clickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT qinwanrabbani clickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT christophercoogan clickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT griffinwmilsap clickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT kevincnathan clickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT brockawester clickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT williamsanderson clickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT kathrynrrosenblatt clickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT alpauchil clickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT loraclawson clickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT nicholasjmaragakis clickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT mariskajvansteensel clickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT francescovtenore clickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT nicolasframsey clickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT matthewsfifer clickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling
AT nathanecrone clickbasedelectrocorticographicbraincomputerinterfaceenableslongtermhighperformanceswitchscanspelling