A Hybrid Framework for Early Prediction of Psychological Disorders by using AIML Techniques

Psychological stress affects one’s well-being significantly and is associated with psychiatric conditions which are often associated with bipolar disorder, schizophrenia, or obsessive compulsive disorder. Early diagnosis of disease is crucial for timely action and efficient planning of treatment. In the coming years promising trends for advanced devices are expected to enhance results in healthcare situations, especially early psychological disorders detection. In the present research work three machine learning algorithms are applied to predict obsessive compulsive disorder and bipolar disorder. Meanwhile, Agglomerative Clustering is used for unsupervised learning to unravel trends in clinical data and improve diagnostic accuracy, while random forest (R.F) along with support vector machine (S.V.M) are used for supervised learning to enable categorization and prediction. Medical professionals can treat individuals with a good amount of accuracy, detect anomalies and diagnose mental health disorders by the analysis of clinical data and patterns. The proposed research work’s objective is to help both patients and service providers identify psychological disorders so that treatment can be received in time. The proposed approach proves to be helpful in identification and treatment of several psychiatric disorders. The prediction of these conditions quite early helps in improving the standard of treatment.