Exploring Electroencephalography-Based Affective Analysis and Detection of Parkinson’s Disease

Abstract

While Parkinson’s disease (PD) is typically characterized by motor disorder, there is also evidence of diminished emotion perception in PD patients. This study examines the utility of electroencephalography (EEG) signals to understand emotional differences between PD and healthy controls (HCs), and for automated PD detection. Employing traditional machine learning and deep learning methods on multiple EEG descriptors, we explore (a) dimensional and categorical emotion recognition and (b) PD versus HC classification from multiple descriptors characterizing emotional EEG signals. Our results reveal that PD patients comprehend arousal better than valence and, among emotion categories, fear, disgust, and surprise less accurately, and sadness most accurately. Mislabeling analyses confirm confounds among opposite-valence emotions for PD data. Emotional EEG responses also achieve near-perfect PD versus HC recognition. Cumulatively, our study demonstrates that (a) examining implicit responses alone enables (i) discovery of valence-related impairments in PD patients and (ii) differentiation of PD from HC and that (b) emotional EEG analysis is an ecologically valid, effective, practical, and sustainable tool for PD diagnosis vis-à-vis self-reports, expert assessments, and resting-state analysis.