Using PCA Machine Learning Approach Based on Psychological Questionnaires and Spectral Characteristics of the EEG to Separate the Healthy Participants and Participants with Major Depressive Disorder

Statistical method Principal Component Analysis (PCA) based on psychological questionnaires and EEG spectral characteristics was used to reduce the complex data by finding the most important variables to separate the healthy participants and participants with major depressive disorder from clinie of the State Researeh Institute of Neuroseienees and Medieine. The basic idea of PCA is to identify data patterns that are difficult to see otherwise. In this article it was used PCA for disease classification. We applied PCA to reduce the data dimensionality, for uncovering hidden patterns or relationships between the features. Finally, we trained the classification model on the reduced data to distinguish between healthy participants and participants with major depressive disorder. The study aimed to investigate the relationship between psychological factors and EEG spectral characteristics in participants with major depressive disorder. The study found that there was a significant correlation between the severity of depression and the EEG spectral characteristics. These findings suggest that the combination of psychological questionnaires and EEG spectral characteristics could be a useful tool for the diagnosis and classification of major depressive disorder.