Child delirium prediction method based on electroencephalogram signals and system thereof

A prediction method and technology of EEG signals, which are used in diagnostic recording/measurement, medical science, sensors, etc., can solve the problems of unpredictable delirium and low detection accuracy, and achieve the effect of excellent prediction performance.

Active Publication Date: 2021-07-09
ZHONGSHAN OPHTHALMIC CENT SUN YAT SEN UNIV
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing research on delirium detection based on EEG signals has the following problems: the subjects focus on elderly delir

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Child delirium prediction method based on electroencephalogram signals and system thereof
  • Child delirium prediction method based on electroencephalogram signals and system thereof
  • Child delirium prediction method based on electroencephalogram signals and system thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] Such as figure 1 As shown, a method for predicting delirium in children based on EEG signals, the specific processing steps are as follows:

[0052] Step 1: Collect multi-channel EEG data of children who are awake after anesthesia surgery;

[0053] Step 2: Preprocessing the collected multi-channel EEG data;

[0054] Step 3: Extracting multi-domain features of the preprocessed multi-channel EEG data;

[0055] Step 4: Input the multi-domain features into the SVM classifier to obtain the delirium prediction result, that is, whether or not there is delirium.

[0056] The preprocessing in the step 2 specifically includes the following steps:

[0057] Step 21: Downsampling the multi-channel EEG data to 1000 Hz;

[0058] Step 22: Eliminate the interference data in the multi-channel EEG data obtained in Step 21 through 0.5-45 Hz band-pass filtering to improve the signal-to-noise ratio;

[0059] Step 23: Correct the abnormal multi-channel EEG data after interference elimina...

Embodiment 2

[0065] This embodiment is a child delirium prediction system based on EEG signals, including:

[0066] The EEG data acquisition module is used to collect multi-channel EEG data of children in the awakening period after anesthesia surgery;

[0067] The preprocessing module is used to preprocess the EEG data obtained by the EEG data acquisition module;

[0068] The feature extraction module is used to extract the multi-domain features of the preprocessed EEG data;

[0069] The classification module is used to input the extracted multi-domain features into the SVM classifier to obtain prediction results.

[0070] The preprocessing module specifically includes:

[0071] A downsampling module, configured to downsample the multi-channel EEG data to 1000Hz;

[0072] Filtering module, for eliminating the interference data in the multi-channel EEG data obtained in step 21 through 0.5~45Hz bandpass filtering, and improving the signal-to-noise ratio;

[0073] The correction module is...

Embodiment 3

[0077] This embodiment provides the selection method of multi-domain features and kernel functions.

[0078] Step 1: Collect 64-channel EEG data of subjects during the postoperative recovery period in the anesthesia recovery room, with a sampling rate of 2048Hz; after the subject wakes up, two professional medical staff judge whether the subject has delirium or not according to the PAED scale. The label was recorded as 1, and the non-delirium label was recorded as 0; finally, 21 subjects were included, including 11 delirium subjects and 10 non-delirium subjects.

[0079] Step 2: Preprocessing the EEG data: down-sampling the EEG data to 1000 Hz; eliminating interference through 0.5-45 Hz band-pass filtering and improving the signal-to-noise ratio; correcting abnormal EEG data by interpolation Electrical channels, specifically, use the average value of adjacent channels to replace abnormal EEG channels; segment EEG signal segments based on a sliding window with a fixed window le...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a children delirium prediction method and system based on electroencephalogram signals. The method comprises the following specific processing steps: 1, collecting multi-channel electroencephalogram data of children in a waking period after an anesthesia operation; 2, preprocessing the acquired multichannel electroencephalogram data; 3, extracting multi-domain features of the preprocessed multi-channel electroencephalogram data; and 4, inputting the multi-domain features into an SVM classifier to obtain a delirium prediction result. The system comprises an electroencephalogram data acquisition module, a preprocessing module, a feature extraction module and a classification module. The invention provides the children delirium prediction method and the system thereof, and the method and system are objective, are high in accuracy, and are beneficial to early warning and timely treatment of clinical children delirium.

Description

technical field [0001] The invention relates to the fields of pediatrics and anesthesia detection, in particular to a method and system for predicting children's delirium based on electroencephalogram signals. Background technique [0002] Postoperative delirium is an acute, reversible syndrome of brain dysfunction manifested by nonspecific, acute, fluctuating disturbances of consciousness and cognitive function. Studies have shown that children are highly susceptible to delirium, with an incidence rate of 4% to 47%. Delirium in children may lead to many problems, such as not conducive to the recovery of the primary disease, increasing the hospitalization time and treatment costs of children, increasing the 6-month mortality rate in the hospital, and leading to adverse events such as unplanned extubation and falling from the bed , Interference with delusions and hallucinations after discharge. Therefore, accurate and effective detection of delirium in children is particula...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): A61B5/369A61B5/374
CPCA61B5/4088
Inventor 袁进马可肖鹏顾莉甘小亮
Owner ZHONGSHAN OPHTHALMIC CENT SUN YAT SEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap