Early Detection of Schizophrenia Using Electroencephalogram (EEG) Signals with a Convolutional Neural Network (CNN) Model

Schizophrenia is a neurological disorder that affects thinking. It is important to have an early diagnosis. A new method for detecting Schizophrenia using Electroencephalogram (EEG) signals is presented in the study. The Convolutional Neural Network (CNN) model was tested with data from 28 participants, 14 healthy controls and 14 Schizophrenia patients. The model architecture is designed to extract features from EEG signals. Our method uses deep learning methods to overcome the limitations of traditional machine learning methods. The CNN model achieved 98. 07% classification accuracy in the off-subject test and 81. 26% in the subject-based test. This high accuracy shows the model's potential as a diagnostic tool and provides doctors with the best possible way to detect Schizophrenia at an early stage. CNN-based signal analysis can improve the accuracy of diagnosis and facilitate timely intervention strategies according to our results.