Feature Extraction and Analysis of Multilayer Higher-Order Brain Functional Networks in Patients with Schizophrenia

Objectives: A schizophrenia patient model based on Persistent homology and multilayer brain networks combines full-frequency band information to mine and categorize key brain regions, providing a decision-making basis for patient treatment. Methods: Using the information of 198 subjects from Huilongguan Hospital in Beijing who met the requirements of this study, the network features based on the constructed multilayer brain network were mined by Persistent homophony and traditional methods of mining multi-frequency band information of subjects, and finally analyzed by using a deep learning model. Results: After the lesion, the brain area changes were mainly in the frontal central cortex and left parietal lobe, leading to the alteration of the patient's perceptual and cognitive abilities, and the classification training using a deep learning model resulted in a classification accuracy of 92.3%. Conclusion: By constructing a multilayer brain network model and using a persistent homology approach, cross-frequency band information can be effectively utilized, and higher-order information can be exploited to improve disease diagnosis.