Machine Learning Classification to Identify the Stage of Brain-Computer Interface Therapy for Stroke Rehabilitation Using Functional Connectivity

Abstract

Interventional therapy using brain-computer interface (BCI) technology has shown promise in facilitating motor recovery in stroke survivors; however, the impact of this form of intervention on functional networks outside of the motor network specifically is not well-understood. Here, we investigated resting-state functional connectivity (rs-FC) in stroke participants undergoing BCI therapy across stages, namely pre- and post-intervention, to identify discriminative functional changes using a machine learning classifier with the goal of categorizing participants into one of the two therapy stages. Twenty chronic stroke participants with persistent upper-extremity motor impairment received neuromodulatory training using a closed-loop neurofeedback BCI device, and rs-functional MRI (rs-fMRI) scans were collected at four time points: pre-, mid-, post-, and 1 month post-therapy. To evaluate the peak effects of this intervention, rs-FC was analyzed from two specific stages, namely pre- and post-therapy. In total, 236 seeds spanning both motor and non-motor regions of the brain were computed at each stage. A univariate feature selection was applied to reduce the number of features followed by a principal component-based data transformation used by a linear binary support vector machine (SVM) classifier to classify each participant into a therapy stage. The SVM classifier achieved a cross-validation accuracy of 92.5% using a leave-one-out method. Outside of the motor network, seeds from the fronto-parietal task control, default mode, subcortical, and visual networks emerged as important contributors to the classification. Furthermore, a higher number of functional changes were observed to be strengthening from the pre- to post-therapy stage than the ones weakening, both of which involved motor and non-motor regions of the brain. These findings may provide new evidence to support the potential clinical utility of BCI therapy as a form of stroke rehabilitation that not only benefits motor recovery but also facilitates recovery in other brain networks. Moreover, delineation of stronger and weaker changes may inform more optimal designs of BCI interventional therapy so as to facilitate strengthened and suppress weakened changes in the recovery process.

Brain Functional Networks Study of Subacute Stroke Patients With Upper Limb Dysfunction After Comprehensive Rehabilitation Including BCI Training

“…Furthermore, the study highlighted how machine learning can provide useful information by correlating neuro-function changes (i.e., rs-fMRI, EEG) to behavioral changes (i.e., Action Research Arm Test, Nine-Hole Peg Test, and Barthel Index). They also found that FCs related to the bilateral primary motor area were correlated to behavioral outcomes and clinical variables (33).…”

Predicting chemo‐brain in breast cancer survivors using multiple MRI features and machine‐learning

“…For example, 1 study of neural representations adopted Gaussian naïve Bayes as machine‐learning algorithms and fMRI image to classify subjects into HC groups and depression groups and reached 91% at the set of 17 suicidal ideators versus 17 controls. Former research adopted SVM classifiers to classify a data set of 20 chronic stroke participants who received brain‐computer interface therapy and a resting‐state functional connectivity scan at multiple time points (pre‐ and post‐therapy groups) to analyze functional changes during the therapy. In LOOCV, an accuracy of 92.5% was achieved.…”

MNE: Software for Acquiring, Processing, and Visualizing MEG/EEG Data

“…Brain-computer interfaces and hyperscanning. Two emerging approaches in rehabilitation science, social neuroscience, and computational psychiatry are BCIs (Höhne et al, 2014;Mohanty et al, 2018) and hyperscanning (Bilek et al, 2017;Ahn et al, 2018;Goldstein et al, 2018;Zhdanov et al, 2015). It is likely that soon new acquisition paradigms will emerge both for basic research and clinical practice in which BCI and hyperscanning will be combined, such that the stimulation will be driven by brain activity of several individuals (Rao et al, 2014;Jiang et al, 2018).…”