Parkinson's disease tremor prediction using EEG data analysis-A preliminary and feasibility study

Tremor is one of the hallmarks of Parkinson's disease (PD) that does not respond effectively to conventional medications. In this regard, as a complementary solution, methods such as deep brain stimulation have been proposed. To apply the intervention with minimal side effects, it is necessary to predict tremor initiation. The purpose of the current study was to propose a novel methodology for predicting resting tremors using analysis of EEG time-series.

A modified algorithm for tremor onset detection from accelerometer data was proposed. Furthermore, a machine learning methodology for predicting PD hand tremors from EEG time-series was proposed. The most discriminative features extracted from EEG data based on statistical analyses and post-hoc tests were used to train the classifier for distinguishing pre-tremor conditions.

Statistical analyses with post-hoc tests showed that features such as form factor and statistical features were the most discriminative features. Furthermore, limited numbers of EEG channels (F3, F7, P4, CP2, FC6, and C4) and EEG bands (Delta and Gamma) were sufficient for an accurate tremor prediction based on EEG data. Based on the selected feature set, a KNN classifier obtained the best pre-tremor prediction performance with an accuracy of 73.67%.

This feasibility study was the first attempt to show the predicting ability of EEG time-series for PD hand tremor prediction. Considering the limitations of this study, future research with longer data, and different brain dynamics are needed for clinical applications.