Depression classification model training method and device, terminal and medium

Abstract

The invention discloses a depression classification model training method and device, a terminal and a medium. The method comprises the following steps: acquiring electroencephalogram signals respectively corresponding to a plurality of users so as to determine frequency domain characteristics respectively corresponding to the plurality of users; determining attention features and depression features respectively corresponding to the plurality of users; performing fusion processing on the frequency domain features, the attention features and the depression features respectively corresponding to the plurality of users to obtain fusion feature sets respectively corresponding to the plurality of users; determining classification identifiers of the fused feature sets corresponding to the plurality of users respectively; and training a preset neural network model according to the fused feature sets and the classification identifiers corresponding to the plurality of users. According to the method and the device, various characteristics of depression patients of different degrees are fused, so that the purpose of improving the classification precision of the depression classification model after training is completed is achieved, and the problems of long analysis time and poor precision caused by depression recognition depending on manpower are avoided.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a training method, device, terminal and medium for a depression classification model. Background technique [0002] Depression, also known as depressive disorder, is an affective disorder with a high incidence rate. People with depression often have the classic symptoms of low mood, loss of interest and enjoyment, and low energy or fatigue. The diagnosis of depression should be mainly based on medical history, clinical symptoms, course of disease, physical examination and laboratory tests. Therefore, this diagnostic method is easily affected by subjective factors, which may easily lead to misdiagnosis and missed diagnosis. The study found that the EEG signals of patients with depression and healthy controls have different variations in parameters such as band, power, and amplitude. Therefore, in order to overcome the problem that the diagnosis of depression is easi...

AI Technical Summary

Problems solved by technology

However, this method of diagnosing depression through EEG signals has the problems of long analysis time and low efficiency; at the same time, this method of analysis and diagnosis also has the disadvantage of relying on a single EEG factor, resulting in poor classification accuracy for depression. question

Images