Predicting Individuals Mental Health Status in Kenya using Machine Learning Methods

Mental Health diseases affect prominent individuals worldwide. According to WHO, 264 million people globally are affected by one mental health disease, depression. The lack of resources about the disease causes the difficulty of diagnosis and producing an efficient treatment, which eventually increases the number of cases. Depression affects several countries with a lack of knowledge about the disease and lack of resources, such as psychiatrists, psychiatric nurses, mental psychologists. In Kenya, almost 50% of its population suffers from many depression cases. This paper aims to find a robust reliable supervised Machine Learning classifier that gives the best performance evaluation for predicting if an individual is likely suffering from depression or not. The study is based on a data survey made by Busara Center in Kenya. We evaluate different machine learning methods, SVM, Random Forest, Ada Boosting, and Voting-Ensemble models scored the highest f1-score and accuracy with 0.78 and 85%, respectively.