Discrimination of psychiatric disorders by machine learning methods

Physicians follow a symptom-based approach in the diagnosis of psychiatric diseases. According to this approach, a process based on internationally valid diagnostic tools such as DSM or ICD, patient reports and the observation and experience of the physician is followed. As in other fields of medicine, the search for biomarkers that can be used in processes related to diseases continues in psychiatry and various studies are conducted in this field. Within the scope of this thesis, a data set containing electroencephalogram (EEG) measurements of individuals with different psychiatric diseases was analyzed by machine learning methods and the diseases were discriminated/classified with the obtined models. The models obtained allowed to distinguish between patient and healthy groups, and also enabled the discrimination of more than one psychiatric disease from each other.