Classification of Schizophrenia and Bipolar Disorder by Using Machine Learning Algorithms

Data mining based investigations of disease mediating factors and related potential diagnostic biomarkers using genomic information obtained from gene expression analysis tools become very informative and useful. In the present study, public Gene Expression Omnibus (GEO) genome wide expression dataset (ID: GSE12654) consisting of schizophrenia, bipolar disorders patients besides normal groups were analyzed by using different classification algorithms including kNN, naive bayes and decision tree. A set of most differentially expressed genetic features (p