CN-122004861-A - Method and system for evaluating dyskinesia of children based on brain electrical pattern recognition

CN122004861ACN 122004861 ACN122004861 ACN 122004861ACN-122004861-A

Abstract

The invention relates to the technical field of obstacle evaluation, in particular to a method and a system for evaluating dyskinesia of children based on brain electricity pattern recognition. The method comprises the steps of obtaining multichannel electroencephalogram information and basic information of children when a reading task is carried out, carrying out crest detection processing on the multichannel electroencephalogram information to determine all potential candidate crests, extracting potential distribution information according to the basic information of the children, carrying out matching degree assessment on each potential distribution information by using a preset reference model to obtain a matching degree assessment value, determining potential assessment crests according to the matching degree assessment value and all potential candidate crests, and assessing reading disorder of the children by using the potential assessment crests to obtain a reading disorder assessment result of the children. The invention aims to solve the problem that the existing evaluation method is easy to be interfered by individual differences and physiological interference signals of children in the process of evaluating the dyskinesia of the children, so that misjudgment occurs in an evaluation result.

Inventors

ZHANG QINFEN
WANG CHAOQUN
JI SHIYAN
WANG RUI
WANG YUHAO
LIN YUANXIN
ZHU YU

Assignees

常州市儿童医院(常州市第六人民医院)

Dates

Publication Date: 20260512
Application Date: 20260325

Claims (10)

1. The method for evaluating the dyskinesia of the child based on the brain electricity pattern recognition is characterized by comprising the following steps of: Acquiring multichannel brain electrical information and child basic information when a child performs a reading task; performing peak detection processing on the multichannel electroencephalogram information to determine all potential candidate peaks; According to the basic child information, extracting potential distribution information of each potential candidate wave crest on all electrode channels; Carrying out matching degree evaluation on each potential distribution information by using a preset reference model to obtain a matching degree evaluation value; Determining potential evaluation wave peaks according to the matching degree evaluation value and all potential candidate wave peaks; and evaluating the reading disorder of the children by utilizing the potential evaluation peak to obtain a reading disorder evaluation result of the children.
2. The method for evaluating dyskinesia in children based on electroencephalogram pattern recognition according to claim 1, wherein the step of evaluating the degree of matching for each piece of potential distribution information by using a preset reference model to obtain a degree of matching evaluation value comprises the steps of: Extracting each potential change rate between two adjacent potential distribution information within a preset time window; Comparing each potential change rate with a preset change rate threshold value to obtain a change rate comparison average value; And comparing the average value according to a preset reference model and the change rate, and carrying out matching degree evaluation on each potential distribution information to obtain a matching degree evaluation value.
3. The method for evaluating dyskinesia in children based on electroencephalogram pattern recognition according to claim 2, wherein the step of evaluating the matching degree of each potential distribution information according to a preset reference model and a change rate comparison average value to obtain a matching degree evaluation value comprises the following steps: Correcting the preset reference model by utilizing the change rate comparison average value to obtain a corrected preset reference model; And carrying out matching degree evaluation on each potential distribution information by using the corrected preset reference model to obtain a matching degree evaluation value.
4. The method for assessing the dyskinesia of a child based on electroencephalogram pattern recognition according to claim 1, wherein the step of extracting potential distribution information of each potential candidate peak on all electrode channels according to the child basic information comprises: According to the basic child information, carrying out quality evaluation analysis on each potential candidate wave crest to obtain a quality evaluation coefficient; Performing coefficient verification on the quality evaluation coefficient to obtain a quality evaluation coefficient after verification is qualified; and extracting potential distribution information of each potential candidate wave crest on all electrode channels according to the quality evaluation coefficient after the verification is qualified.
5. The method for assessing the dyskinesia of a child based on electroencephalogram pattern recognition according to claim 4, wherein the step of performing quality assessment analysis on each potential candidate peak according to the basic child information to obtain a quality assessment coefficient comprises the steps of: Determining child age information and cognitive peak types according to the child basic information; determining the development stage of the child according to the child age information; determining a quality evaluation parameter library according to the development stage to which the child belongs and the cognitive peak type; and carrying out quality evaluation analysis on each potential candidate wave crest by using the quality evaluation parameter library to obtain a quality evaluation coefficient.
6. The method for assessing a dyskinesia in a child based on electroencephalogram pattern recognition according to claim 5, wherein the step of determining a quality assessment parameter library according to the developmental stage to which the child belongs and the cognitive peak type comprises: determining the fatigue degree and the attention physiological index of the child according to the development stage to which the child belongs and the cognitive peak type; carrying out fusion processing on the child fatigue and the attention physiological index to obtain a state evaluation signal; and adjusting a preset evaluation basic parameter set according to the state evaluation signal to obtain a quality evaluation parameter library.
7. The method for evaluating dyskinesia in children based on electroencephalogram pattern recognition according to claim 1, wherein the step of performing peak detection processing on the multichannel electroencephalogram information to determine all potential candidate peaks comprises: performing peak detection processing on the multichannel brain electric information to obtain all potential detection peaks; Screening all potential detection peaks by utilizing a peak change threshold value to obtain each potential screening peak; and identifying each potential screening wave crest to obtain all potential candidate wave crests.
8. The method for assessing a dyskinesia in a child based on electroencephalogram pattern recognition according to claim 1, wherein the step of determining a potential assessment peak from the matching degree assessment value and all potential candidate peaks comprises: Determining the peak time and amplitude information of each potential candidate peak according to all the potential candidate peaks; judging the peak time and amplitude information of each potential candidate peak to obtain a peak characteristic parameter of each potential candidate peak; and screening the peak characteristic parameters of each potential candidate peak by using the matching degree evaluation value to obtain potential evaluation peaks.
9. The method for assessing the dyskinesia of a child based on electroencephalogram pattern recognition according to claim 1, wherein the step of acquiring multichannel electroencephalogram information of the child when the child performs a reading task comprises: acquiring multichannel brain electricity original signals of children when the children perform reading tasks; Preprocessing the multichannel electroencephalogram original signal to obtain a preprocessed multichannel electroencephalogram original signal; and performing signal verification on the preprocessed multichannel electroencephalogram original signals to obtain multichannel electroencephalogram information.
10. A child dyskinesia assessment system based on brain electrical pattern recognition, the system comprising: The information acquisition module is used for acquiring multichannel electroencephalogram information and basic information of the child when the child performs a reading task; The peak detection module is used for carrying out peak detection processing on the multichannel brain electric information and determining all potential candidate peaks; The information extraction module is used for extracting potential distribution information of each potential candidate wave crest on all electrode channels according to the child basic information; the information matching module is used for carrying out matching degree evaluation on each potential distribution information by using a preset reference model to obtain a matching degree evaluation value; the peak determining module is used for determining potential evaluation peaks according to the matching degree evaluation value and all potential candidate peaks; And the obstacle evaluation module is used for evaluating the reading obstacle of the child by utilizing the potential evaluation peak to obtain a reading obstacle evaluation result of the child.

Description

Method and system for evaluating dyskinesia of children based on brain electrical pattern recognition Technical Field The invention relates to the technical field of obstacle evaluation, in particular to a method and a system for evaluating dyskinesia of children based on brain electricity pattern recognition. Background In clinical assessment of dysreading in children, existing methods seek specific peaks of brain electrical components by presetting a fixed time frame, for example, seek FN400 peaks between 300 and 500 milliseconds after presentation of the stimulus. However, children tend to be distracted during testing, thereby creating frequent non-brain-derived physiological electrical signal disturbances, and children may involuntarily blink frequently, turn eyes or bite into the jaw or shake their head slightly due to tension during testing. The minute physical activity generates bioelectric signals such as Electrooculography (EOG) and myoelectricity (EMG), and the intensity of non-brain-derived interference signals is much greater than the target brain electrical component and is captured by electrodes on the scalp. Since the child brain is in a rapid developmental stage, when the interfering signal falls within a broad search range, the abrupt eye rotation produces a very sharp and steep peak with a magnitude several times that of the true FN400 component. Meanwhile, by recording the latency and amplitude of the artifact peak as evaluation basis, the analysis report shows FN400 with extremely short latency and extremely large amplitude, and an error conclusion that the brain language processing function of the child is seriously abnormal is obtained. The erroneous conclusions not only deviate completely from the true situation of the child, but are more misleading than the conclusions of undetected signals made by the traditional fixed time frame method. Moreover, the individual difference of each child is remarkable, so that a truly effective signal is missed, and the evaluation result is deviated, and even misjudgment occurs. Disclosure of Invention The invention aims to provide a method and a system for evaluating a children dyskinesia based on brain electricity pattern recognition, which are used for solving the problem that the existing evaluation method is easily interfered by individual differences and physiological interference signals of children in the process of evaluating the children dyskinesia, so that misjudgment occurs in an evaluation result. In order to achieve the aim, the invention adopts the following technical scheme that the method for evaluating the dyskinesia of the children based on the brain electricity pattern recognition comprises the following steps: Acquiring multichannel brain electrical information and child basic information when a child performs a reading task; performing peak detection processing on the multichannel electroencephalogram information to determine all potential candidate peaks; According to the basic child information, extracting potential distribution information of each potential candidate wave crest on all electrode channels; Carrying out matching degree evaluation on each potential distribution information by using a preset reference model to obtain a matching degree evaluation value; Determining potential evaluation wave peaks according to the matching degree evaluation value and all potential candidate wave peaks; and evaluating the reading disorder of the children by utilizing the potential evaluation peak to obtain a reading disorder evaluation result of the children. Preferably, the step of obtaining the matching degree evaluation value by using a preset reference model to evaluate the matching degree of each potential distribution information includes: Extracting each potential change rate between two adjacent potential distribution information within a preset time window; Comparing each potential change rate with a preset change rate threshold value to obtain a change rate comparison average value; And comparing the average value according to a preset reference model and the change rate, and carrying out matching degree evaluation on each potential distribution information to obtain a matching degree evaluation value. Preferably, the step of evaluating the matching degree of each potential distribution information according to a preset reference model and a change rate comparison average value to obtain a matching degree evaluation value includes: Correcting the preset reference model by utilizing the change rate comparison average value to obtain a corrected preset reference model; And carrying out matching degree evaluation on each potential distribution information by using the corrected preset reference model to obtain a matching degree evaluation value. Preferably, the step of extracting potential distribution information of each potential candidate peak on all electrode channels according to the child basic information comprises the