Parkinson’s disease (PD) is a slowly progressing neurological disorder with symptoms that overlap with those of other conditions, making early detection and accurate diagnosis vital for effective treatment and a patient’s quality of life. Symptoms such as tremors, stiffness, slow movements, and balance issues, along with psychiatric manifestations, are typical of PD. This study introduces a groundbreaking approach to PD diagnosis, utilizing a multimodal machine learning framework that integrates Electroencephalography (EEG) and Magnetic Resonance Imaging (MRI) data. Focusing on the early detection and accurate classification of PD, the proposed research leverages the distinct yet complementary nature of EEG and MRI datasets to enhance diagnostic precision. We employed a robust algorithmic strategy, including LightGBM and machine learning techniques, to analyze the complex patterns inherent in neurological data. The key steps of the proposed research are preprocessing and feature extraction from both EEG and MRI modalities, followed by their fusion using Principal Component Analysis (PCA) for dimensionality reduction. The fused dataset was then analyzed using a LightGBM model and validated through a 10-fold cross-validation process to ensure reliability and stability. The model’s efficacy was further tested on independent datasets, demonstrating its robustness across diverse patient demographics. The obtained results showcased an accuracy of 97.17%, sensitivity of 96.58%, and specificity of 96.82% in PD classification, outperforming traditional multimodal as well as single-modality diagnostic methods. The integration of EEG and MRI data provided a more comprehensive view of the neurophysiological and neuroanatomical changes associated with PD. Additionally, the use of advanced machine learning algorithms allowed for a nuanced analysis, capturing subtle patterns indicative of early PD stages.

Background/Objectives: Parkinson’s disease (PD) is a progressive neurodegenerative disorder characterized by motor dysfunction, cognitive decline, and a diminished quality of life. Early and accurate diagnosis is essential for effective disease management. However, traditional diagnostic approaches, which rely on clinical observations and subjective assessments, often lead to delays and inaccuracies. This research aims to address these limitations by proposing FCN-PD, an advanced deep learning framework for accurate PD diagnosis using MRI data. Methods: The FCN-PD framework incorporates a hybrid feature extraction phase that combines EfficientNet to capture local spatial details and attention mechanisms to extract global contextual information. These features are then processed by a Fully Connected Network (FCN) for final classification. This architecture enables the model to effectively represent hierarchical features and handle high-dimensional MRI data while mitigating issues such as overfitting and feature redundancy. Results: The performance of FCN-PD was evaluated on three publicly available MRI datasets. On the PPMI dataset, it achieved an accuracy of 97.2%, outperforming traditional CNN-based models by 5.3%. On the OASIS dataset, the model achieved 95.6% accuracy, and on the MIRIAD dataset, it reached 96.8% accuracy. These results establish FCN-PD as a superior alternative to existing PD diagnostic methods. Conclusions: FCN-PD demonstrates significant improvements in diagnostic accuracy and efficiency for Parkinson’s disease using MRI data. Its robust architecture effectively captures both local and global features, making it a promising tool for clinical integration and early PD detection, ultimately contributing to better patient outcomes.