Advanced Data Mining to Explore the Effects of Brain Due to Schizophrenia

The paper investigates changes in microstate dynamics across various schizophrenia stages. Changes in microstate dynamics across schizophrenia stages can be detected through K-means clustering of EEG data. Machine learning models for classifying different stages of schizophrenia include random forest, gradient boosting, and XGBoost. Results show that there are significant changes in microstate dynamics during schizophrenia phases and this shows changes in brain processing. Furthermore, it can be noted from the use of machine learning models that their accuracy levels are quite impressive when it came to distinguishing different phases of schizophrenia through patterns generated by activities taking place inside our brains which are obtained from electroencephalography analysis. Evidently, such a statement reflects how a combination between machine learning capabilities with electroencephalography research has been used so far for this purpose which may imply a better understanding regarding its neurological underpinnings or else creation of early diagnostic devices before treatment commences.