Method for extracting features of neurosis based on graph theory and machine learning

Abstract

The invention discloses a method for extracting features of neurosis based on a graph theory and machine learning. The method comprises the steps: firstly, constructing a cerebral functional network of a body dimension and an emotion dimension in case of the neurosis based on EEG data, and separately selecting a phase lag index and a weighted phase lag index as measures of a network middle edge by taking 62 channels as network nodes; and extracting network topological attributes--global efficiency corresponding to the two indexes, carrying out fusing so as to obtain eigenvectors for identifying the body dimension and the emotion dimension, and carrying out classification by using a machine-learning classification model. Network abnormal link positions of two dimensions can be positioned by mapping the cerebral functional network corresponding to the features to a 3D brain model. According to the method, a marker can be further provided for identification on the neurosis, and targets for further researching diseases are provided.

Description

technical field [0001] Aiming at the physical dimension and emotional dimension under neurosis, the present invention proposes a neurosis feature extraction method based on graph theory construction of EEG brain function network and machine learning method. Background technique [0002] The morbidity, mortality and disability rate of chronic diseases remain high, and they tend to be younger. They are extremely hidden, and the early symptoms are not obvious. Various mental disorders such as anxiety, depression, neurasthenia, etc. Collectively referred to as neurosis, it is a kind of chronic disease, and seeking effective markers for diseases has become one of the problems to be solved urgently. The human brain itself is an extremely complex system, with intricate connections between neurons, based on graph theory [1] brain functional network [2] Analytical methods provide insight into the structure of the brain, how various functional areas work, and how they interact and c...

AI Technical Summary

Problems solved by technology

Traditional EEG feature extraction of independent channels or brain regions based on time domain, frequency domain or time-frequency domain, such as information entropy [6] ,power spectrum [7] etc. are still widely studied, but the disease is usually not the functional impairment of independent channels or brain regions, but the abnormal interaction and coordination of different functional brain regions, and these characteristics cannot effectively solve the common source problem

Images