Objective:To analyze brain topological property data through machine learning methods and explore changes in brain network topological properties in patients with schizophrenia.Methods:From January 2022 to August 2023, functional magnetic resonance imaging data of 60 patients with schizophrenia and 56 healthy controls were collected , and the data were preprocessed to construct brain functional networks and extract global and nodal topological properties. All subjects were divided into a training group and a testing group.The data of training group were fitted based on support vector machine, and the predictive performance was evaluated through cross-validation.The model was optimized by recursive feature elimination algorithm, then the indicators that contributed the most to predictive performance were extrated.The classification performance of the testing group was calculated based on the trained model with optimal predictive performance.SPSS 20.0 software was used for data analysis, the independent t-test and χ2 test were used for comparing the differences between the two groups. Results:The support vector machine achieved an accuracy of 75.00% in predicting the test group of schizophrenia patients based on all indicators. After removing redundant features and combining with the recursive feature elimination algorithm, the accuracy of the SVM model in predicting the test group increased to 90.00%. The nodal global efficiency(Ne)of the left superior temporal gyrus, right dorsal agranular insula, bilateral dorsal granular insula, bilateral caudal cingulate gyrus, and left lateral orbitofrontal cortex in the model contributed the most to classification.Compared to the control group, patients with schizophrenia had abnormal Ne values in these brain regions.Conclusion:There are multiple brain regions with abnormal Ne values in patients with schizophrenia, indicating that the abnormalities in information integration and transmission functions may be related to the imbalance in the dynamic equilibrium of the patients' brain networks.

Objective:To investigate the changes of abnormal spontaneous brain activity and whole-brain effector connectivity in patients with obsessive-compulsive disorder (OCD) by combining low frequency amplitude (ALFF) and Granger causality analysis (GCA), and explore their relations with clinical symptoms.Methods:Forty-nine patients with OCD admitted to Department of Psychiatry, Second Affiliated Hospital of Xinxiang Medical College from January 2020 to September 2023 were selected as OCD group; 50 healthy volunteers matched with gender, age and years of education were enrolled as healthy control (HC) group. Obsessive-compulsive symptoms and severities in the OCD group were assessed by Yale Brown obsessive-compulsive scale (Y-BOCS). All subjects underwent whole-brain resting-state functional magnetic resonance imaging scanning (rs-fMRI). ALFF differences between the 2 groups were compared. Brain regions with ALFF differences were used as seed points, and effector connectivity changes in seed points were compared with those in whole-brain by GCA. Correlations of ALFF and effector connectivity in brain regions with ALFF differences with total scores, obsession scores and compulsion scores of Y-BOCS were analyzed by partial correlation analysis.Results:(1) Compared with that in the HC group, ALFF was significantly enhanced in the right supplementary motor area, right hippocampus, left caudate nucleus, and right fusiform gyrus, and statistically attenuated in the left suboccipital gyrus in the OCD group ( P<0.05). (2) Compared with that in the HC group, effector connectivity from the right dorsolateral superior frontal gyrus to right supplementary motor area was significantly attenuated, and effector connectivity from the left superior occipital gyrus to right supplementary motor area was significantly enhanced in the OCD group ( P<0.05); compared with that in the HC group, effector connectivity from the right fusiform gyrus to right precentral gyrus was significantly attenuated, and effector connectivity from the right hippocampus to left mesial temporal gyrus was significantly enhanced in the OCD group ( P<0.05). (3) In OCD patients, altered ALFF in the left caudate nucleus was positively correlated with obsession scores ( r=0.357, P=0.027), and altered effector connectivity from the right dorsolateral superior frontal gyrus to right supplementary motor area was negatively correlated with obsession scores ( r=-0.312, P=0.029). Conclusion:Abnormalities in sensorimotor network function are closely related to clinical symptoms in patients with OCD.