Galvanic Vestibular Stimulation Effects on EEG Biomarkers of Motor Vigor in Parkinson's Disease

Galvanic vestibular stimulation modulates EEG markers of voluntary movement in Parkinson's disease

We recently showed that vestibular stimulation can produce a long-lasting alleviation of motor features in Parkinson's disease. Here we investigated whether components of the motor related cortical response that are commonly compromised in Parkinson's - the Bereitschaftspotential and mu-rhythm event-related desynchronization - are modulated by concurrent, low frequency galvanic vestibular stimulation (GVS) during repetitive limb movement amongst 17 individuals with idiopathic Parkinson's disease. Relative to sham, GVS was favourably associated with higher amplitudes during the late and movement phases of the Bereitschaftspotential and with a more pronounced decrease in spectral power within the mu-rhythm range during finger-tapping. These data increase understanding of how GVS interacts with the preparation and execution of voluntary movement and give added impetus to explore its therapeutic effects on Parkinsonian motor features.

Deep Transfer Learning for Parkinson’s Disease Monitoring by Image-Based Representation of Resting-State EEG Using Directional Connectivity

Parkinson’s disease (PD) is characterized by abnormal brain oscillations that can change rapidly. Tracking neural alternations with high temporal resolution electrophysiological monitoring methods such as EEG can lead to valuable information about alterations observed in PD. Concomitantly, there have been advances in the high-accuracy performance of deep neural networks (DNNs) using few-patient data. In this study, we propose a method to transform resting-state EEG data into a deep latent space to classify PD subjects from healthy cases. We first used a general orthogonalized directed coherence (gOPDC) method to compute directional connectivity (DC) between all pairwise EEG channels in four frequency bands (Theta, Alpha, Beta, and Gamma) and then converted the DC maps into 2D images. We then used the VGG-16 architecture (trained on the ImageNet dataset) as our pre-trained model, enlisted weights of convolutional layers as initial weights, and fine-tuned all layer weights with our data. After training, the classification achieved 99.62% accuracy, 100% precision, 99.17% recall, 0.9958 F1 score, and 0.9958 AUC averaged for 10 random repetitions of training/evaluating on the proposed deep transfer learning (DTL) network. Using the latent features learned by the network and employing LASSO regression, we found that latent features (as opposed to the raw DC values) were significantly correlated with five clinical indices routinely measured: left and right finger tapping, left and right tremor, and body bradykinesia. Our results demonstrate the power of transfer learning and latent space derivation for the development of oscillatory biomarkers in PD.