Evaluation of Parkinsons disease with early diagnosis using single-channel EEG features and auditory cognitive assessment
원문 초록
Parkinsons disease (PD) diagnosis is challenging due to subtle early clinical signs. F-DOPA PET is commonly used for early PD diagnosis. We explore the potential of machine-learning (ML) based EEG features extracted from single-channel EEG during auditory cognitive assessment as a noninvasive, low-cost support for PD diagnosis. The study included data collected from 32 participants who underwent an F-DOPA PET scan as part of their standard treatment and 20 cognitively healthy controls. Participants performed an auditory cognitive assessment recorded with Neurosteer EEG device. Data processing involved wavelet-packet decomposition and ML. First, a prediction model was developed to predict 1/3 of the undisclosed F-DOPA results. Then, generalized linear mixed models were calculated to distinguish between PD and non-PD subjects on the frequency bands and ML-based EEG features (A0 and L1) previously associated with cognitive functions. The prediction model accurately labeled patients with unrevealed scores as positive F-DOPA. Novel EEG feature A0 and the Delta band showed significant separation between study groups, with healthy controls exhibiting higher activity than PD patients. EEG feature L1 activity was significantly lower in resting state compared to high-cognitive load. This effect was absent in the PD group, suggesting that lower activity in resting state is lacking in PD patients. This study successfully demonstrated the ability to separate patients with positive vs. negative F-DOPA PET results with an easy-to-use single-channel EEG during an auditory cognitive assessment. Future longitudinal studies should further explore the potential utility of this tool for early PD diagnosis and as a potential biomarker in PD.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
eegFloss: A Python package for refining sleep EEG recordings using machine learning models
DBConformer: Dual-Branch Convolutional Transformer for EEG Decoding
AGTCNet: A Graph-Temporal Approach for Principled Motor Imagery EEG Classification
Cross-Modal Epileptic Signal Harmonization: Frequency Domain Mapping Quantization for Pre-training a Unified Neurophysiological Transformer
Efficient and faithful reconstruction of dynamical attractors using homogeneous differentiators
On using AI for EEG-based BCI applications: problems, current challenges and future trends
토론
이 논문과 연결된 포럼 글이 아직 없습니다.