Decoding force from deep brain electrodes in Parkinsonian patients
Limitations of many Brain Machine Interface (BMI) systems using invasive electrodes include reliance on single neurons and decoding limited to kinematics only. This study investigates whether force-related information is present in the local field potential (LFP) recorded with deep brain electrodes...
| Main Authors: | , , |
|---|---|
| Format: | Conference item |
| Published: |
IEEE
2016
|
| _version_ | 1797102904865193984 |
|---|---|
| author | Shah, S Tan, H Brown, P |
| author_facet | Shah, S Tan, H Brown, P |
| author_sort | Shah, S |
| collection | OXFORD |
| description | Limitations of many Brain Machine Interface (BMI) systems using invasive electrodes include reliance on single neurons and decoding limited to kinematics only. This study investigates whether force-related information is present in the local field potential (LFP) recorded with deep brain electrodes using data from 14 patients with Parkinson’s disease. A classifier based on logistic regression (LR) is developed to classify various force stages, using 10-fold cross validation. Least Absolute and Shrinkage Operator (Lasso) is then employed in order to identify the features with the most predictivity. The results show that force-related information is present in the LFP, and it is possible to distinguish between various force stages using certain frequency-domain (delta, beta, gamma) and time-domain (mobility) features in real-time. |
| first_indexed | 2024-03-07T06:12:27Z |
| format | Conference item |
| id | oxford-uuid:effe64b1-ad5c-4f43-bcdb-be5412a00d89 |
| institution | University of Oxford |
| last_indexed | 2024-03-07T06:12:27Z |
| publishDate | 2016 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:effe64b1-ad5c-4f43-bcdb-be5412a00d892022-03-27T11:44:18ZDecoding force from deep brain electrodes in Parkinsonian patientsConference itemhttp://purl.org/coar/resource_type/c_5794uuid:effe64b1-ad5c-4f43-bcdb-be5412a00d89Symplectic Elements at OxfordIEEE2016Shah, STan, HBrown, PLimitations of many Brain Machine Interface (BMI) systems using invasive electrodes include reliance on single neurons and decoding limited to kinematics only. This study investigates whether force-related information is present in the local field potential (LFP) recorded with deep brain electrodes using data from 14 patients with Parkinson’s disease. A classifier based on logistic regression (LR) is developed to classify various force stages, using 10-fold cross validation. Least Absolute and Shrinkage Operator (Lasso) is then employed in order to identify the features with the most predictivity. The results show that force-related information is present in the LFP, and it is possible to distinguish between various force stages using certain frequency-domain (delta, beta, gamma) and time-domain (mobility) features in real-time. |
| spellingShingle | Shah, S Tan, H Brown, P Decoding force from deep brain electrodes in Parkinsonian patients |
| title | Decoding force from deep brain electrodes in Parkinsonian patients |
| title_full | Decoding force from deep brain electrodes in Parkinsonian patients |
| title_fullStr | Decoding force from deep brain electrodes in Parkinsonian patients |
| title_full_unstemmed | Decoding force from deep brain electrodes in Parkinsonian patients |
| title_short | Decoding force from deep brain electrodes in Parkinsonian patients |
| title_sort | decoding force from deep brain electrodes in parkinsonian patients |
| work_keys_str_mv | AT shahs decodingforcefromdeepbrainelectrodesinparkinsonianpatients AT tanh decodingforcefromdeepbrainelectrodesinparkinsonianpatients AT brownp decodingforcefromdeepbrainelectrodesinparkinsonianpatients |