Unlock instant, AI-driven research and patent intelligence for your innovation.

Establishment method of stroke severity classification prediction model based on electroencephalogram signals

A technology of EEG signal and severity, applied in diagnostic recording/measurement, medical science, sensors, etc., can solve the problems affecting the treatment effect of patients, and achieve the effect of effective differentiation

Pending Publication Date: 2022-03-15
HANGZHOU DIANZI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Mild stroke is misjudged as severe stroke, and as many as 30% of severe stroke patients are missed by pre-hospital examination, which seriously affects the treatment effect of patients

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
  • Establishment method of stroke severity classification prediction model based on electroencephalogram signals
  • Establishment method of stroke severity classification prediction model based on electroencephalogram signals
  • Establishment method of stroke severity classification prediction model based on electroencephalogram signals

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] Such as figure 1 As shown, this embodiment includes the following steps:

[0064] Step 1: Data collection. Collect subjects' EEG data. Data collection is divided into two parts: the experimental recording part and the rest part. The recording part of the experiment lasted 15 seconds from the clenched fist state to the open hand state. The rest is 15 seconds from open hand to clenched fist. At the beginning of the experiment, the subjects were asked to stare at the white cross on the black screen of the notebook for 30 seconds in a static state. When the subject heard "make a fist", the subject clenched his fist, and the medical staff recorded the data and tagged it. When the subject heard "let go", the subject opened his hand, and the medical staff ended the data recording and made a label. Three consecutive recordings constituted one experiment, and each subject performed 3 experiments. The experiment required the subjects to take sedative drugs before the exper...

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 discloses a method for establishing a stroke severity classification prediction model based on electroencephalogram signals. Firstly, electroencephalogram signals of a subject are recorded in the experiment process. And preprocessing the electroencephalogram signals. Then, characteristic values in delta frequency band relative power, theta frequency band relative power, alpha frequency band relative power, beta frequency band relative power, the ratio of the delta frequency band relative power to the alpha frequency band relative power, the ratio of slow frequency relative power to fast frequency relative power and brain symmetry indexes are screened through variance analysis; and finally, constructing a model by using machine learning to distinguish the severity of the stroke. The invention provides a method for screening characteristic values on the basis of variance analysis, and constructing a stroke severity classification method by matching with a method for outputting correct rate by machine learning. According to the model provided by the invention, the severity of the stroke can be more effectively distinguished according to the feature values extracted from the electroencephalograms of normal people and patients with different severity of the stroke.

Description

technical field [0001] The invention belongs to the field of bioelectrical signal processing, and relates to a method for establishing a stroke severity classification prediction model based on electroencephalogram signals. Background technique [0002] Stroke is the leading cause of adult disability worldwide, and EEG is one of the most important techniques for diagnosing stroke and is considered a standard tool for assessing changes in brain activity with millisecond temporal resolution. The severity of the stroke and the speed with which it was found and treated had a large impact on disability and mortality. However, despite the existence of demographic, clinical, and imaging factors associated with stroke prognosis, early prediction of short-term and long-term stroke outcomes remains challenging due to large individual variability. Therefore, it is extremely important to find biosignatures that can distinguish different stroke severities from controls as feature values...

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
Patent Type & Authority Applications(China)
IPC IPC(8): A61B5/369A61B5/374A61B5/00
CPCA61B5/369A61B5/374A61B5/4064A61B5/7203A61B5/725A61B5/7267A61B5/7235A61B5/7275
Inventor 席旭刚戴金霄汪婷叶飞高云园李训根马玉良
Owner HANGZHOU DIANZI UNIV