EEG-Based Classification of Parkinson's Disease With Freezing of Gait Using Midfrontal Beta Oscillations

Abstract

Background: Freezing of gait (FOG) is a debilitating motor symptom of Parkinson's disease (PD) that significantly affects patient mobility and quality of life. Identifying reliable biomarkers to distinguish between PD patients with freezing of gait (PDFOG+) and those without FOG (PDFOG-) is essential for early intervention and treatment planning. This study investigates the potential of electroencephalographic (EEG) signals, focusing on well-studied midfrontal beta oscillatory feature, to classify PDFOG+ and PDFOG- using machine learning (ML) and deep learning (DL) approaches.

Methods: Resting-state EEG data were collected from the midfrontal 'Cz' and nearby channels (Cz-cluster) from 41 PDFOG+ and 41 PDFOG- subjects. A range of ML and DL models, including logistic regression (LR), random forest (RF), extreme gradient boosting (XGBoost), categorical boosting (CatBoost), and long short-term memory (LSTM) models were evaluated using leave-one-subject-out (LOSO), 10-fold, and stratified cross-validation (CV).

Results: Outcomes demonstrate that while LR achieved an area under the receiver-operating characteristic (AUC-ROC) score of 0.63, LSTM outperformed all models, achieving an AUC-ROC of 0.68 and accuracy of 0.63, particularly with the Cz-cluster configuration.

Conclusions: These findings support the potential of midfrontal beta oscillations, particularly in combination with LSTM temporal modeling, a promising EEG-based biomarker for distinguishing PDFOG+ from PDFOG-. This work contributes to the development of more effective diagnostic tools and treatment strategies for PD-related gait impairments.

Keywords: Parkinson disease; beta rhythm; deep learning; electroencephalography; freezing of gait; machine learning.