Benchmarking of EEG Analysis Techniques for Parkinson's Disease Diagnosis: A Comparison between Traditional ML Methods and Foundation DL Methods

Parkinson's Disease (PD) is a progressive neurodegen-erative disorder that affects motor and cognitive functions, with early diagnosis being critical for effective clinical intervention. Electroencephalography (EEG) offers a noninvasive and cost-effective means of detecting PD-related neural alterations, yet the development of reliable automated diagnostic models remains a challenge. In this study, we conduct a systematic benchmark of traditional machine learning (ML) and deep learning (DL) models for classifying PD using a publicly available oddball task dataset. Our aim is to lay the groundwork for developing an effective learning system and to determine which approach produces the best results. W e implement a unified seven-step prepro-cessing pipeline and apply consistent subject-wise cross-validation and evaluation criteria to ensure comparability across models. Our results demonstrate that while baseline deep learning architectures, particularly CNN-LSTM models, achieve the best performance compared to other deep learning architectures, underlining the importance of capturing long-range temporal dependencies, several traditional classifiers such as XGBoost also offer strong predictive accuracy and calibrated decision boundaries. By rigorously comparing these baselines, our work provides a solid reference framework for future studies aiming to develop and evaluate more complex or specialized architectures. Establishing a reliable set of baseline results is essential to contextualize improvements introduced by novel methods, ensuring scientific rigor and reproducibility in the evolving field of EEG-based neurodiagnostics.