Optimization of Schizophrenia Diagnosis Prediction using Machine Learning Techniques

The objective of this paper is to automatically diagnose the mental state disorder named schizophrenia by using multimodal features which are extracted from Magnetic Resonance Imaging (MRI) brain scans. The aim is to achieve highest possible classification (binary) accuracy to achieve best possible prediction of the schizophrenia diagnosis. The importance of feature selection in combination with fine-tuning the parameters of Machine Learning classifiers to solve this problem is explained. Various supervised Machine Learning classifiers were employed and compared with themselves and then with existing systems. The proposed solution achieved AUC score of 0.9473 and an accuracy of 0.9412 as opposed to till date best existing system’s AUC score of 0.928.