Depresyonda motor aktivitenin makine öğrenmesi ile değerlendirilmesi.

The clinical assessment of depression is based on observation and subjective patient complaints of almost all psychiatric disorders. Psychomotor retardation is one of the leading symptoms of depression, and as an indicator of this, physical activity is reduced in depressed patients. In this study, we aimed to develop a machine learning-based objective diagnostic support method for diagnosing depression using a dataset of daily physical activity data of individuals with and without depression as a reference. After detailed feature searches, we identified the four best features by Fisher Feature Selection. Using the Ensemble Bagged Tree method, we achieved a better classification result than the reference study, with an accuracy of 0.88. In addition, we found that the accuracy exceeded 0.90 when more than the four features we limited to compare with the reference study were selected. Thus, we could distinguish between individuals with and without depression with high accuracy with the machine learning-based method, which we developed using physical activity data. This study has shown promising results that activity data can be used as a diagnostic tool for depression. Our results show that different biomarkers, such as physical activity, when used with machine learning, can potentially overcome the lack of objective diagnostic support criteria in psychiatric evaluation. [ABSTRACT FROM AUTHOR]