Graph Convolutional Network-based Approach for Parkinson’s Disease Classification using Euclidean Distance Graphs

Parkinson’s disease (PD) is a neurodegenerative disorder that affects millions of people worldwide. Early and accurate diagnosis of PD is crucial for effective treatment and management of the condition. However, the diagnosis of PD can be challenging due to the overlap of symptoms with other neurological disorders. In this paper, we propose a novel approach for Parkinson’s disease classification using Graph Convolutional Networks (GCNs) and Euclidean distance-based graph construction. Our method leverages the power of GCNs to learn meaningful representations from graph-structured data while utilizing Euclidean distances to capture the similarity between patient samples. We evaluate our approach on a publicly available Parkinson’s disease dataset and demonstrate its effectiveness in accurately classifying PD patients. The proposed GCN-based model achieves a high classification accuracy of 97.4% on the test set, outperforming traditional machine learning methods such as Support Vector Machines and Random Forests. Furthermore, we visualize the learned graph embeddings to gain insights into the clustering of PD and healthy samples. Our results highlight the potential of Graph Convolutional Networks and graph-based approaches for the diagnosis of Parkinson’s disease. The proposed methodology can assist healthcare professionals in the early detection and management of PD, ultimately improving patient outcomes. This study opens up new avenues for the application of graph-based deep learning techniques in the field of neurological disorder diagnosis.