The impact of task context on predicting finger movements in a brain-machine interface
A key factor in the clinical translation of brain-machine interfaces (BMIs) for restoring hand motor function will be their robustness to changes in a task. With functional electrical stimulation (FES) for example, the patient’s own hand will be used to produce a wide range of forces in otherwise si...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
eLife Sciences Publications Ltd
2023-06-01
|
| Series: | eLife |
| Subjects: | |
| Online Access: | https://elifesciences.org/articles/82598 |
| _version_ | 1797797623966466048 |
|---|---|
| author | Matthew J Mender Samuel R Nason-Tomaszewski Hisham Temmar Joseph T Costello Dylan M Wallace Matthew S Willsey Nishant Ganesh Kumar Theodore A Kung Parag Patil Cynthia A Chestek |
| author_facet | Matthew J Mender Samuel R Nason-Tomaszewski Hisham Temmar Joseph T Costello Dylan M Wallace Matthew S Willsey Nishant Ganesh Kumar Theodore A Kung Parag Patil Cynthia A Chestek |
| author_sort | Matthew J Mender |
| collection | DOAJ |
| description | A key factor in the clinical translation of brain-machine interfaces (BMIs) for restoring hand motor function will be their robustness to changes in a task. With functional electrical stimulation (FES) for example, the patient’s own hand will be used to produce a wide range of forces in otherwise similar movements. To investigate the impact of task changes on BMI performance, we trained two rhesus macaques to control a virtual hand with their physical hand while we added springs to each finger group (index or middle-ring-small) or altered their wrist posture. Using simultaneously recorded intracortical neural activity, finger positions, and electromyography, we found that decoders trained in one context did not generalize well to other contexts, leading to significant increases in prediction error, especially for muscle activations. However, with respect to online BMI control of the virtual hand, changing either the decoder training task context or the hand’s physical context during online control had little effect on online performance. We explain this dichotomy by showing that the structure of neural population activity remained similar in new contexts, which could allow for fast adjustment online. Additionally, we found that neural activity shifted trajectories proportional to the required muscle activation in new contexts. This shift in neural activity possibly explains biases to off-context kinematic predictions and suggests a feature that could help predict different magnitude muscle activations while producing similar kinematics. |
| first_indexed | 2024-03-13T03:52:08Z |
| format | Article |
| id | doaj.art-c0e4f80894dd4d66af8bb495c8117fed |
| institution | Directory Open Access Journal |
| issn | 2050-084X |
| language | English |
| last_indexed | 2024-03-13T03:52:08Z |
| publishDate | 2023-06-01 |
| publisher | eLife Sciences Publications Ltd |
| record_format | Article |
| series | eLife |
| spelling | doaj.art-c0e4f80894dd4d66af8bb495c8117fed2023-06-22T13:01:10ZengeLife Sciences Publications LtdeLife2050-084X2023-06-011210.7554/eLife.82598The impact of task context on predicting finger movements in a brain-machine interfaceMatthew J Mender0https://orcid.org/0000-0003-1562-3289Samuel R Nason-Tomaszewski1Hisham Temmar2https://orcid.org/0000-0002-4464-4911Joseph T Costello3Dylan M Wallace4Matthew S Willsey5Nishant Ganesh Kumar6Theodore A Kung7Parag Patil8Cynthia A Chestek9https://orcid.org/0000-0002-9671-7051Department of Biomedical Engineering, University of Michigan, Ann Arbor, United StatesDepartment of Biomedical Engineering, University of Michigan, Ann Arbor, United StatesDepartment of Biomedical Engineering, University of Michigan, Ann Arbor, United StatesDepartment of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, United StatesDepartment of Robotics, University of Michigan, Ann Arbor, United StatesDepartment of Biomedical Engineering, University of Michigan, Ann Arbor, United States; Department of Neurosurgery, University of Michigan Medical School, Ann Arbor, United StatesSection of Plastic Surgery, Department of Surgery, University of Michigan, Ann Arbor, United StatesSection of Plastic Surgery, Department of Surgery, University of Michigan, Ann Arbor, United StatesDepartment of Biomedical Engineering, University of Michigan, Ann Arbor, United States; Department of Neurosurgery, University of Michigan Medical School, Ann Arbor, United StatesDepartment of Biomedical Engineering, University of Michigan, Ann Arbor, United States; Department of Robotics, University of Michigan, Ann Arbor, United StatesA key factor in the clinical translation of brain-machine interfaces (BMIs) for restoring hand motor function will be their robustness to changes in a task. With functional electrical stimulation (FES) for example, the patient’s own hand will be used to produce a wide range of forces in otherwise similar movements. To investigate the impact of task changes on BMI performance, we trained two rhesus macaques to control a virtual hand with their physical hand while we added springs to each finger group (index or middle-ring-small) or altered their wrist posture. Using simultaneously recorded intracortical neural activity, finger positions, and electromyography, we found that decoders trained in one context did not generalize well to other contexts, leading to significant increases in prediction error, especially for muscle activations. However, with respect to online BMI control of the virtual hand, changing either the decoder training task context or the hand’s physical context during online control had little effect on online performance. We explain this dichotomy by showing that the structure of neural population activity remained similar in new contexts, which could allow for fast adjustment online. Additionally, we found that neural activity shifted trajectories proportional to the required muscle activation in new contexts. This shift in neural activity possibly explains biases to off-context kinematic predictions and suggests a feature that could help predict different magnitude muscle activations while producing similar kinematics.https://elifesciences.org/articles/82598motor controlbrain-machine interfacespinal cord injuryhandEMGfingers |
| spellingShingle | Matthew J Mender Samuel R Nason-Tomaszewski Hisham Temmar Joseph T Costello Dylan M Wallace Matthew S Willsey Nishant Ganesh Kumar Theodore A Kung Parag Patil Cynthia A Chestek The impact of task context on predicting finger movements in a brain-machine interface eLife motor control brain-machine interface spinal cord injury hand EMG fingers |
| title | The impact of task context on predicting finger movements in a brain-machine interface |
| title_full | The impact of task context on predicting finger movements in a brain-machine interface |
| title_fullStr | The impact of task context on predicting finger movements in a brain-machine interface |
| title_full_unstemmed | The impact of task context on predicting finger movements in a brain-machine interface |
| title_short | The impact of task context on predicting finger movements in a brain-machine interface |
| title_sort | impact of task context on predicting finger movements in a brain machine interface |
| topic | motor control brain-machine interface spinal cord injury hand EMG fingers |
| url | https://elifesciences.org/articles/82598 |
| work_keys_str_mv | AT matthewjmender theimpactoftaskcontextonpredictingfingermovementsinabrainmachineinterface AT samuelrnasontomaszewski theimpactoftaskcontextonpredictingfingermovementsinabrainmachineinterface AT hishamtemmar theimpactoftaskcontextonpredictingfingermovementsinabrainmachineinterface AT josephtcostello theimpactoftaskcontextonpredictingfingermovementsinabrainmachineinterface AT dylanmwallace theimpactoftaskcontextonpredictingfingermovementsinabrainmachineinterface AT matthewswillsey theimpactoftaskcontextonpredictingfingermovementsinabrainmachineinterface AT nishantganeshkumar theimpactoftaskcontextonpredictingfingermovementsinabrainmachineinterface AT theodoreakung theimpactoftaskcontextonpredictingfingermovementsinabrainmachineinterface AT paragpatil theimpactoftaskcontextonpredictingfingermovementsinabrainmachineinterface AT cynthiaachestek theimpactoftaskcontextonpredictingfingermovementsinabrainmachineinterface AT matthewjmender impactoftaskcontextonpredictingfingermovementsinabrainmachineinterface AT samuelrnasontomaszewski impactoftaskcontextonpredictingfingermovementsinabrainmachineinterface AT hishamtemmar impactoftaskcontextonpredictingfingermovementsinabrainmachineinterface AT josephtcostello impactoftaskcontextonpredictingfingermovementsinabrainmachineinterface AT dylanmwallace impactoftaskcontextonpredictingfingermovementsinabrainmachineinterface AT matthewswillsey impactoftaskcontextonpredictingfingermovementsinabrainmachineinterface AT nishantganeshkumar impactoftaskcontextonpredictingfingermovementsinabrainmachineinterface AT theodoreakung impactoftaskcontextonpredictingfingermovementsinabrainmachineinterface AT paragpatil impactoftaskcontextonpredictingfingermovementsinabrainmachineinterface AT cynthiaachestek impactoftaskcontextonpredictingfingermovementsinabrainmachineinterface |