Intelligent data mining and machine learning for mental health diagnosis using genetic algorithm

Inappropriate diagnosis of mental health illnesses leads to wrong treatment and causes irreversible deterioration in the client's mental health status including hospitalization and/or premature death. About 12 million patients are misdiagnosed annually in US. In this paper, a novel study introduces a semi-automated system that aids in preliminary diagnosis of the psychological disorder patient. This is accomplished based on matching description of a patient's mental health status with the mental illnesses illustrated in DSM-IV-TR, Fourth Edition Text Revision. The study constructs the semi-automated system based on an integration of the technology of genetic algorithm, classification data mining and machine learning. The goal is not to fully automate the classification process of mentally ill individuals, but to ensure that a classifier is aware of all possible mental health illnesses could match patient's symptoms. The classifier/psychological analyst will be able to make an informed, intelligent and appropriate assessment that will lead to an accurate prognosis. The analyst will be the ultimate selector of the diagnosis and treatment plan.