OSAHS diagnostic method based on probability integrated regression model

A regression model and probabilistic integration technology, applied in the directions of diagnosis, diagnostic recording/measurement, medical science, etc., can solve problems such as instability of a single device, and achieve the effect of reducing pressure

Active Publication Date: 2020-09-22
XIAN UNIV OF TECH
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a OSAHS diagnosis method based on the combination of snoring and blood oxygen saturation, which solves the influence of unstable factors of a single device and improves the accuracy of OSAHS diagnosis

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
  • OSAHS diagnostic method based on probability integrated regression model
  • OSAHS diagnostic method based on probability integrated regression model
  • OSAHS diagnostic method based on probability integrated regression model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] Implementation steps of OSAHS diagnosis method based on probability integrated regression model

[0043] Step 1: read the blood oxygen saturation signal, the present invention reads the blood oxygen saturation signal from the European data format (edf) synchronized with the snoring audio signal read by the polysomnography equipment.

[0044] Step 2: Remove zero, remove the value of the blood oxygen saturation signal that is not collected due to equipment or external reasons.

[0045] Step 3: Denoising, median filter to denoise blood oxygen saturation, replace the value of a point in the digital sequence with the median value of each point in a neighborhood of the point, so that the surrounding pixel values ​​are close to the true value , thereby eliminating isolated noise points.

[0046] Step 4: Derivation, which is to perform a differential operation on the blood oxygen saturation: Δf(x k ) = f(x k )-f(x k-1 )

[0047] Step 5: feature extraction, blood oxygen sat...

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 an OSAHS diagnostic method based on a probability integrated regression model. The method comprises the steps that blood oxygen saturation is collected and subjected to preprocessing, and a snore signal is found according to the time corresponding to a descending segment of the blood oxygen saturation; feature extraction is conducted by using the Mel-frequency cepstrum coefficient, the features are input into a convolutional neural network, the audio signals of the descending section are classified into snore, breath and noise by combining a logistic regression model, and feature extraction is conducted on the processed snore and blood oxygen saturation; and finally, the probability integrated regression model is used for automatically predicting the sleep apnea hypopnea index of a patient to diagnose the OSAHS. Thus the patient can preliminarily detect the sleep state at home, the problem that the OSAHS patient queues in a hospital for PSG monitoring is solved,and meanwhile the pressure of doctors is relieved.

Description

technical field [0001] The invention belongs to the technical fields of sleep medicine, signal processing and machine learning, and specifically relates to an OSAHS diagnosis method based on snoring and blood oxygen saturation analysis, which uses a probability integrated regression model to predict apnea-hypopnea index and diagnose OSAHS. Background technique [0002] The Mel cepstral coefficient is mainly used in the feature processing algorithm of automatic speech and speaker recognition. It is a filter constructed according to the mechanism of the human ear: a filter with more low-frequency regions and fewer high-frequency regions. The Mel cepstrum coefficient is a linear transformation of the logarithmic energy spectrum based on the nonlinear Mel scale of the sound frequency, and is the coefficient that makes up the Mel frequency cepstrum. According to the human hearing experiment to analyze the spectrum of the snoring audio, better snoring audio features are obtained a...

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): A61B5/145A61B5/08A61B5/00
CPCA61B5/14542A61B5/0826A61B5/725A61B5/7203A61B5/4809A61B5/4812A61B5/4815A61B5/4818A61B5/7267
Inventor 黑新宏朱小贝罗靖陈浩任晓勇刘海琴赖厚涛张俊杰
Owner XIAN UNIV OF TECH
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