Depression biomarker identification method based on non-invasive electroencephalogram signal

Abstract

The invention provides a depression biomarker identification method based on a non-invasive electroencephalogram signal. The method comprises the following steps: acquiring tested depression marker identification data according to a preset data acquisition rule, wherein the data includes an HDRS-17 score and/or an IMS score, and EEG signals corresponding to the HDRS-17 score and/or the IMS score;designing k rounds of cross inspection, and in each round of cross inspection, dividing depression marker identification data into a training set and a test set; establishing a low-dimensional EEG-HDRS-17 model and/or a low-dimensional EEG-IMS model and a high-dimensional EEG-low-dimensional EEG model according to the training sets; converting the high-dimensional EEG feature vector of the test sets into a low-dimensional EEG feature vector by using the high-dimensional EEG-low-dimensional EEG model, and predicting an HDRS-17 score and/or an IMS score of the test set by using the low-dimensional EEG-HDRS-17 model and/or low-dimensional EEG-IMS model; and comparing the predicted HDRS-17 score with an actually measured HDRS-17 score, and/or comparing the predicted IMS score with an actuallymeasured IMS score, and judging whether the depression biomarker to be tested is identified or not according to a comparison result.

Description

technical field [0001] The invention relates to the technical field of EEG signal analysis, in particular to a method for identifying a biomarker of depression based on a non-invasive EEG signal. Background technique [0002] Depression (Major Depressive Disorder, MDD) is one of the most serious mental diseases in the world. The incidence of depression in China is as high as 8-9%, and it is increasing year by year, of which about 30% are treatment-resistant depression. -resistant depression, TRD). Standard drug therapy is rarely effective in patients with treatment-resistant depression. Therefore, existing cutting-edge research on the treatment of treatment-resistant depression focuses on developing novel treatment modalities, such as neurofeedback therapy, to replace or supplement standard drug therapy. [0003] A key issue in the development of novel depression treatments is the identification and identification of effective depression biomarkers. Studies have shown tha...

AI Technical Summary

Problems solved by technology

However, due to the following reasons, the current technology (for example, Palmiero.M.and Piccardi.L.Frontal EEGAsymmetry of Mood:A Mini-Review[J].Frontiers in Behavioral Neuroscience.2017.11:224) cannot yet identify effective non-invasive based Depression biomarkers of EEG signals: (1) The existing technology cannot effectively remove the noise of the EEG and extract sub-signals that are truly related to the degree of depression; (2) The existing technology cannot identify the unique depression of each patient Biomarkers; (3) the existing technology does not collect the patient's depression degree changes over time while collecting EEG; (4) the existing technology does not collect the patient's real-time mood swings over time while collecting EEG , real-time mood swings are closely related to depression status but different from the degree of depression, because the degree of depression measures the patient's mental state over a long period of time rather than real-time mood swings; (5) The existing technology cannot use EEG to predict depression in patients with depression The degree of depression changes over time, and the mood swings of patients with depression cannot be predicted over time; (6) prior art does not carry out strict cross-check

Images