Depression state detection system based on lateral brain habenular nucleus signals

Abstract

The invention discloses a depression state detection system based on lateral brain habenula nucleus signals. The system comprises a computer memory, a computer processor and a computer program which is stored in the computer memory and can be executed on the computer processor, and a trained depression state detection model is stored in the computer memory. The depression state detection model is constructed by using a plurality of groups of different types of weak classifiers, and each weak classifier selects part of feature values from sub-feature spaces constructed in a training set and a test set for training. When the computer processor executes the computer program, the following steps are realized: acquiring a lateral brain habenular nucleus signal, inputting the lateral brain habenular nucleus signal into a trained detection model, extracting a high-dimensional feature vector of each time slice, counting depression and non-depression labels deduced by each weak classifier, and generating a prediction label corresponding to each time slice by adopting a majority voting system. The method can improve the detection precision, and is of great significance to clinical diagnosis, evaluation and treatment of depression.

Description

technical field [0001] The invention relates to the field of EEG signal processing, in particular to a depression state detection system based on signals of the lateral habenula of the brain. Background technique [0002] Currently, there are more and more people suffering from depression, and 10%-30% of them develop into treatment-resistant depression due to ineffective or ineffective traditional treatment methods. Brain closed-loop control technology based on brain-computer interface is expected to bring new treatment methods for patients with treatment-resistant depression. An important part of this technology is the detection of depression status based on brain signals. When the occurrence of depression status is detected, it triggers therapeutic electrical stimulation of brain regulation to achieve depression relief and therapeutic effect. [0003] The Chinese patent document with the publication number CN110960233A discloses a method and system for detecting depressio...

AI Technical Summary

Problems solved by technology

However, this device uses an EEG cap to collect scalp EEG, which is a non-invasive signal acquisition method. The signal source positioning is not accurate, and there are many artifacts. The signal quality is not as good as the invasive signal acquisition method, which makes it difficult to Remove the influence of noise and artifacts, which directly affects the classification accuracy; and in the process of model training, multiple classifiers are used to train separately, and the one with the best test effect is selected as the final classifier. A single model cannot effectively capture multi-channel brain. The internal connection of electrical features cannot effectively improve the classification accuracy

Images