Paranoid Schizophrenia Diagnosis via Complex Network Analysis on EEG Data

Accurate and efficient diagnosis of schizophrenia remains a critical challenge in clinical neuroscience. This study presents a novel approach leveraging complex network analysis and Discrete Fourier Transform (DFT) applied to electroencephalogram (EEG) data for the diagnosis of schizophrenia. EEG, due to its high versatility and low cost, offers significant potential for widespread clinical application. Utilizing a rigorously validated dataset comprising 28 subjects—14 diagnosed with paranoid schizophrenia and 14 healthy controls—we achieved a classification accuracy of 93%. The methodology emphasizes computational efficiency, scalability, and flexibility, making it a promising tool for clinical applications. The findings demonstrate the potential of integrating advanced signal processing techniques with machine learning algorithms to advance psychiatric diagnostics.