Prediction Model for Common Mental Disorder and Depression in Users of Psychoactive Drugs

Mental disorders are among the most prevalent diseases in the world. Many studies have observed the relationship between the use of psychoactive substances and mental diseases, such as Common Mental Disorder (CMD) or depression. The present paper aims to test the effectiveness of ML techniques as auxiliary tools in the pre-diagnosis of CMD and depression, through the classification of users of psychoactive substances. The main objective is to obtain a model for predicting the risk of depression and CMD, as well as to determine which factors contribute most to the risk of these mental diseases. The databases used in this work are composed of 605 samples from people from eight cities in the state of Ceará, Brazil, collected from January to July 2019. The results showed that the tested ML techniques reached an accuracy of 82.81% and 81.98% in the prediction of CMD and depression respectively, with the Support Vector Machine (SVM) and Sequential Backward Selection (SBS) methods. The results also showed that the use of tobacco derivatives, alcohol and cocaine/crack are the most significant factors for predicting these CMD and depression.