Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Sleeping state recognition classification method based on electrocardiogram data

A technology of sleep state and ECG data, applied in medical science, sensors, diagnostic recording/measurement, etc., can solve the problem of not including ECG, sleep-disordered breathing and cannot monitor respiratory events and sleep state information at the same time, and reduce the Effects of Physiological Load

Inactive Publication Date: 2019-08-23
SUN YAT SEN UNIV
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem that the method of using machine learning to monitor sleep-disordered breathing in the prior art cannot monitor respiratory events and sleep state information at the same time, and the eigenvalues ​​used do not contain all the information of ECG, the present invention provides a method based on ECG Sleep state recognition and classification method for data

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
  • Sleeping state recognition classification method based on electrocardiogram data
  • Sleeping state recognition classification method based on electrocardiogram data
  • Sleeping state recognition classification method based on electrocardiogram data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] Such as figure 1 As shown, a sleep state recognition and classification method based on ECG data, comprising the following steps:

[0042] Step S1: Export the ECG data of SAHS patients and healthy individuals from the polysomnography PSG, and calibrate the ECG data, respectively construct the breathing pattern and sleep state of SAHS patients, and the breathing pattern and sleep state of healthy individuals as Four types of ECG data sets;

[0043] Step S2: Divide each of the four types of data sets into a training set and a test set;

[0044] Step S3: Constructing a deep learning model using a deep neural network;

[0045] Step S4: Determine the key points of the ECG waveform in each of the four types of ECG data sets;

[0046] Step S5: Based on the key points of the four types of ECG waveforms, respectively extract ECG morphological features and HRV features, and construct a feature set;

[0047] Step S6: Evaluate and score the feature sets of the four types of data ...

Embodiment 2

[0063] Such as Figure 1-Figure 5 As shown, in this embodiment, the following steps are included:

[0064] (1) Construct a data set, and derive the ECG data of SAHS patients and healthy individuals from the polysomnography PSG, which is the first type of data set; for the patient's ECG data, calibrate different breathing patterns, including normal breathing and obstructive breathing events 5 types of respiratory events, hypopnea respiratory events, central respiratory events, and mixed respiratory events are the second type of data set; from the ECG data of patients, different sleep states are calibrated, including Weak period, REM period, N1 period, N2 period , N3 phase 5 categories, is the third category of data sets; from the ECG data of healthy individuals, different sleep states are calibrated, also including the above 5 categories, which is the fourth category of data sets; respiratory event classification and sleep state classification are as follows Figure 4 , 5 sho...

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 relates to a sleeping state recognition classification method based on electrocardiogram data. A dichotomous multilayer neural network is used for performing recognition and classification on SAHS patients and healthy individuals; then, a deep neural network and binary tree decision fusion method is used for decomposing a multi-classification problem into a plurality of dichotomous problems; for each dichotomous model, different optimum feature groups are respectively obtained through feature screening, so that the sleeping states of two groups and the sleeping modes of the SAHSpatients can be better recognized. The time domain of the electrocardiogram waveform and the heart rate variability information are used for performing SAHS screening, breathing mode and sleeping state recognition; the electrocardiogram signal waveform is stable; the physiological significance is clear; meanwhile, the measurement is convenient; the physiological load of patients is greatly reduced; the portable sleeping monitoring can be favorably realized; a wide application range is realized.

Description

technical field [0001] The present invention relates to the field of sleep state cascade recognition, and more particularly, to a sleep state recognition and classification method based on electrocardiographic data. Background technique [0002] Polysomnography (PSG) monitoring is the gold standard for sleep assessment, mainly used for the diagnosis of sleep-disordered breathing, including sleep apnea syndrome, snoring, upper airway resistance syndrome, and also for auxiliary diagnosis of other sleep disorders. Such as: narcolepsy, restless legs syndrome, insomnia classification, etc. The physiological signals detected by PSG include: EEG (analysis of sleep structure), oculoelectricity, jaw electromyography, mouth and nose airflow and respiratory movement, ECG, blood oxygen, snoring, limb movement, body position and other parameters. During the sleep monitoring process, professional technicians monitor and collect sleep data throughout the night, and the collected sleep dat...

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): A61B5/0402A61B5/0472A61B5/08A61B5/00A61B5/366
CPCA61B5/08A61B5/0826A61B5/4809A61B5/4812A61B5/4815A61B5/7267A61B5/366A61B5/318
Inventor 罗语溪吴欣曾令紫吴舒淇张仰婷
Owner SUN YAT SEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com