(A) ECoG, STN, and gripping force were recorded simultaneously during performance of a Go / No-Go task. (B) Individual ECoG and STN electrodes were localized and transformed into in Montreal …
ECoG and STN electrode localizations.
Mean ECoG and STN spectral power.
Mean ECoG and STN features.
(A) All used normalized and baseline corrected grip force traces. (B) Maximum peak amplitude histogram (C) All movement trace velocities.
(A) Multivariable linear model coefficients trained only from the instantaneous sample (0 time lag with respect to decoded target sample) including all frequency bands from best channels per patient …
Best channel Linear Model coefficients trained from instantaneous sample.
Univariate Linear Model coefficients of single frequency band and time lag.
Wiener Filter multiple time-step comparison.
Based on the presented real-time compatible signal processing pipeline Neural Networks, Elastic - Net regularized Linear Models, Wiener Filters and extreme Gradient Boosting (XGBOOST) regression …
Cross-validated ECoG and STN machine learning model performances for single channels.
Cross-validated combined and best-channel XGBOOST performances for best ECoG and STN channels.
Cross-validated XGBOOST performances for multichannel models based on ECoG, LFP and combined ECoG-LFP channels.
UPDRS-III scores show significant negative correlations with patient-wise XGBOOST grip-force decoding performance averages for (A) ECoG (ρ=–0.55, p=0.039) and (B) STN-LFP signals (ρ=–0.55, p=0.042) …
ECoG and STN single channel performances and UPDRS ratings.
ECoG and STN Force prediction UPDRS correlation.
UPDRS-III scores are significantly correlated with time spent in subthalamic low-beta bursts in the motor preparation period (A) and during movement (not shown). Average XGBOOST decoding performance …
Time spend in low-beta burst performance and UPDRS correlation.
Movement onset aligned low-beta bursts for two subjects.
(A) Channels are color coded for individual XGBOOST grip-force regression performances per channel. Performance differences shown are in favor of ECoG over STN and contralateral over ipsilateral …
Single channel XGBOOST coordinates and performances.
(A) Visualization of fibers originating from the ECoG recording locations of subject 1. (B) Decoding performance across all subjects and channels significant fiber tracts are displayed. All ECoG …
Fiber Tracking network decoding performance prediction.
fMRI network decoding performance prediction.
(A) Functional connectivity ‘Fingerprints’ are estimated using fMRI resting state correlations of the Volume of Tissue Activated (VTA) voxels correlation to all other voxels. (B) The correlation of …
N | Gender | UPDRS total | Hemisphere | Age | Movements | Disease duration [years] | ECoG Strip Contact Number Left | ECoG Strip Contact Number Right |
---|---|---|---|---|---|---|---|---|
0 | Male | 28 | R | 60.3 | 128 | 10.7 | 0 | 6 |
1 | Male | 27 | L+R | 51.2 | 464 | 14 | 28 | 28 |
2 | Male | 33 | L+R | 53.8 | 213 | 7.2 | 8 | 8 |
3 | Male | 31 | L+R | 44.2 | 285 | 10.1 | 8 | 8 |
4 | Male | 32 | 2L+2 R | 63.6 | 381 | 13.1 | 28+8 | 28+8 |
5 | Male | 52 | L | 59.6 | 84 | 5.9 | 6 | 0 |
6 | Male | 55 | L | 71.6 | 161 | 1.4 | 6 | 0 |
7 | Male | 50 | L | 52.5 | 131 | 8.7 | 6 | 0 |
8 | Male | 62 | L+R | 66.8 | 547 | 9.8 | 6 | 6 |
9 | Male | 48 | L | 67.9 | 86 | 17.1 | 6 | 0 |
10 | Female | 31 | R | 69 | 205 | 10.4 | 0 | 6 |
Electrode details, Bayesian optmization hyperparemeters and best subject performances.
(a) Electrode Details (b) Bayesian Optimization Hyperparameters (c) Best channel performances.