Utilizing neuroimaging and machine learning (ML) to differentiate schizophrenia (SZ) patients from normal controls (NCs) and\nfor detecting abnormal brain regions in schizophrenia has several benefits and can provide a reference for the clinical diagnosis of\nschizophrenia. In this study, structural magnetic resonance images (sMRIs) from SZ patients and NCs were used for discriminative\nanalysis. This study proposed an ML framework based on coarse-to-fine feature selection. The proposed framework\nused two-sample t-tests to extract the differences between groups first, then further eliminated the nonrelevant and redundant\nfeatures with recursive feature elimination (RFE), and finally utilized the support vector machine (SVM) to learn the decision\nmodels with selected gray matter (GM) and white matter (WM) features. Previous studies have tended to report differences at the\ngroup level instead of at the individual level and cannot be widely applied. The method proposed in this study extends the\ndiagnosis to the individual level and has a higher recognition rate than previous methods. The experimental results of this study\ndemonstrate that the proposed framework distinguishes SZ patients from NCs, with the highest classification accuracy reaching\nover 85%. The identified biomarkers are also consistent with previous literature findings. As a universal method, the proposed\nframework can be extended to diagnose other diseases.
Loading....