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

Stethoscope audio data processing method based on deep learning

A technology of audio data and processing method, applied in the medical field, can solve the problem that the accuracy depends on human experience, etc., and achieve the effect of scientific processing method and accurate measurement result

Active Publication Date: 2020-01-17
CHENGDU UNIV OF INFORMATION TECH
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing manual auscultation method needs human auscultation to judge whether the sound belongs to Korotkoff sound, and its accuracy depends on human experience, so misjudgment is inevitable

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
  • Stethoscope audio data processing method based on deep learning
  • Stethoscope audio data processing method based on deep learning
  • Stethoscope audio data processing method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The technical solutions of the present invention will be described in detail below with reference to the drawings and specific embodiments. It is worth noting that the implementation of the present invention is not limited to the following specific embodiments.

[0026] The principle of measuring blood pressure with a cuff (mercury) sphygmomanometer: when measuring blood pressure, the "click, click" sound heard with a stethoscope is not the sound of heart beating, but the sound of blood vessels. There is no sound when blood flows through blood vessels, but it can make sound when blood flows through narrow blood vessels to form a vortex.

[0027] When measuring blood pressure, the cuff is inflated and pressurized first, and the pressure acts on the brachial artery. When the pressure is higher than the systolic pressure, the blood is blocked. After deflation, the pressure in the cuff drops accordingly. When the pressure in the cuff is equal to or slightly lower than the systol...

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 stethoscope audio data processing method based on deep learning, comprising: firstly, collecting audio data, and performing segmentation processing on the audio data, and dividing the audio data into frames through segmentation; secondly, adopting a deep learning method to process the voice data Carry out classification, and then reorganize the classification results according to the sequence of segmentation processing; finally, perform blood pressure value mapping to convert the classification results into blood pressure values. The method proposed in this patent simplifies the measurement of blood pressure values ​​into a classification problem, and uses the most widely used deep learning method to classify the collected stethoscope audio data, that is, to judge whether the signal in the stethoscope data is a Kostig sound or not Signal. The stethoscope audio data processing method provided by the invention is more scientific, and the measurement result is more accurate and reliable.

Description

Technical field [0001] The invention relates to the field of medical technology, in particular to a stethoscope audio data processing method based on deep learning. Background technique [0002] Using a cuff sphygmomanometer to measure blood pressure is the most commonly used method of measuring blood pressure in clinical practice. It was invented by the Russian physician Korotkoff in the 19th century. The measurement principle is to inflate and pressurize the cuff to completely occlude the artery, and then gradually deflate the cuff and gradually decrease the pressure. When the pressure in the artery just exceeds the pressure exerted by the cuff, it will open the occluded artery to allow blood to pass through. The highest pressure that can be used to open the cuff is defined as the systolic pressure, and the lowest pressure that can be used to open the cuff is defined as the diastolic pressure. In the field of blood pressure testing, the manual auscultation method is currently ...

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 Patents(China)
IPC IPC(8): A61B5/022
CPCA61B5/02141A61B5/02208A61B5/7264
Inventor 潘帆刘澄玉郑定昌黄珂
Owner CHENGDU UNIV OF INFORMATION TECH
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