Anesthesia depth detection method based on machine learning

Abstract

The present invention relates to the field of data processing technology, and in particular to a method for detecting anesthesia depth based on machine learning, comprising: obtaining a plurality of EEG data sequences corresponding to a patient and an expected signal of the EEG data sequence, obtaining a three-dimensional graph of the power spectrum of the EEG data sequence, thereby obtaining the standard EMG signal frequency, EMG signal strength, standard EEG signal frequency and EEG signal strength at each moment, and then obtaining the degree of aliasing between the EMG signal and the EEG signal at each moment, thereby obtaining the learning rate of the EEG data sequence, and obtaining the patient's anesthesia depth detection result according to the learning rate and the expected signal of the EEG data sequence. The present invention uses an adaptive learning rate and an LMS filter to filter the EEG data to obtain an accurate and reliable filtered EEG data sequence, thereby improving the accuracy of the patient's anesthesia depth detection result.

Images