Predicting Motor Imagery Performance From Resting-State EEG Using Dynamic Causal Modeling

Abstract

Motor imagery-based brain–computer interfaces (MI-BCIs) send commands to a computer using the brain activity registered when a subject imagines—but does not perform—a given movement. However, inconsistent MI-BCI performance occurs in variations of brain signals across subjects and experiments; this is considered to be a significant problem in practical BCI. Moreover, some subjects exhibit a phenomenon referred to as “BCI-inefficiency,” in which they are unable to generate brain signals for BCI control. These subjects have significant difficulties in using BCI. The primary goal of this study is to identify the connections of the resting-state network that affect MI performance and predict MI performance using these connections. We used a public database of MI, which includes the results of psychological questionnaires and pre-experimental resting-state taken over two sessions on different days. A dynamic causal model was used to calculate the coupling strengths between brain regions with directionality. Specifically, we investigated the motor network in resting-state, including the dorsolateral prefrontal cortex, which performs motor planning. As a result, we observed a significant difference in the connectivity strength from the supplementary motor area to the right dorsolateral prefrontal cortex between the low- and high-MI performance groups. This coupling, measured in the resting-state, is significantly stronger in the high-MI performance group than the low-MI performance group. The connection strength is positively correlated with MI-BCI performance (Session 1: r = 0.54; Session 2: r = 0.42). We also predicted MI performance using linear regression based on this connection ( r-squared = 0.31). The proposed predictors, based on dynamic causal modeling, can develop new strategies for improving BCI performance. These findings can further our understanding of BCI-inefficiency and help BCI users to lower costs and save time.

Vividness of Visual Imagery and Personality Impact Motor-Imagery Brain Computer Interfaces

“…Future research should look into other EEG measures that account for BCI aptitude and performance. For instance, recent studies have proposed that connectivity measures can uncover the underlying brain activity in (in-)efficient users (Lee et al, 2020) and that coherence measures can improve accuracy for inefficient users as compared to CSP-dependent classifiers (Zhang et al, 2019). In addition, Nierhaus et al (2019) showed that functional connectivity in the brain networks increased already after 1 h of BCI training.…”

Deep Neural Regression Prediction of Motor Imagery Skills Using EEG Functional Connectivity Indicators

“…The next aspect refers to the assessment of resting-state activation on a reduced number of electrodes. To this end, we evaluate the DRN performance for the predictor sets extracted over the sensorimotor area, selecting the following electrodes, as suggested in [ 44 ]: (FC1, FC2, FC3, FC4, FC5, FC6, Cz, C1, C2, C3, C4, C5, C6, CPz, CP1, CP2, CP3, CP4, CP5, and CP6). In Table 5 , the lower part of each database presents the assessments computed for the sensorimotor zone (denoted with ⋆ ), showing that the channel selection strategy also improves the performance of every subject partition compared to the corresponding values in Table 4 obtained by the whole set of individuals.…”

“…Then, the coefficient of determination (noted as R ) is computed. Besides, a p -value is computed from a two-sided t-test whose null hypothesis is that the regression slope is zero [ 44 ]. It is worth noting that such a hypothesis testing is used, as in state-of-the-art works [ 38 , 44 ], because our Deep Learning Regressor aims to code the no consistency in the brain patterns among different subjects to favor a linear dependency between and .…”

“…Besides, a p -value is computed from a two-sided t-test whose null hypothesis is that the regression slope is zero [ 44 ]. It is worth noting that such a hypothesis testing is used, as in state-of-the-art works [ 38 , 44 ], because our Deep Learning Regressor aims to code the no consistency in the brain patterns among different subjects to favor a linear dependency between and . Moreover, to provide a comparison with Neural Network-based regression strategies, the real-valued measures of Mean Absolute Error (MAE), and Root Squared Error (RMSE) are also assessed, as carried out in [ 51 , 52 ]: where stands for the variance operator.…”

“…Obtained results show how our approach can achieve a high prediction of pretraining desynchronization and initial training synchronization with adequate physiological interpretability. We further compared the DRN predictor prediction performance (on average, 0.8) with the results obtained by linear regression models that are reported, at least for DBI, in the baseline work [ 44 ], presenting values of R-squared not exceeding 0.54.…”