Computer-Aided Disease Diagnosis Prediction Using Scalogram Images Obtained From Graded Scales Applied To Adolescents With Psychiatric Illness

Adolescence is a difficult period for both adolescents and their families. Adolescents are sad and pessimistic. Adolescents may also experience outbursts of anger from time to time. Adolescents need above all to feel understood and valued. Otherwise, adolescents need another environment to satisfy these feelings. Adolescence is a difficult period of life and a psychologically challenging time for the individual and the family. If psychiatric illnesses during adolescence are left untreated, adolescents may suffer from permanent mental disorders. These disorders may continue by increasing the psychological disturbance of the person. Youth is an important factor in the development of a country in every field. For this reason, adolescence should be managed appropriately and a rapid diagnosis/treatment process should be applied when a psychiatric illness occurs. Diagnosis of mental illnesses is also based on expert observation and requires good expertise. Of course, these systems are decision support systems and the final decision is left to the experts. In this study, we use machine learning to investigate the automatic treatment of mental illnesses in the challenging life stages of adolescence. Random Forest and Support Vector Machines algorithms, which are frequently used in the literature, are used. In these algorithms, higher classification success was obtained in scalogram images compared to the unprocessed data set. Random Forest: 91%, Support Vector Machines: 88%.