Respiratory Audio Analysis for Wheeze Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional respiratory analysis methods are costly, invasive, and lack accuracy in determining Ventilatory Threshold (VT) and Respiratory Compensation Threshold (RCT), and fail to analyze full breath cycles, making them cumbersome and unreliable for diagnosing lung pathologies like wheeze and crackle sounds.

Innovation Solution

A method and apparatus using a microphone to record breathing sounds, process them to generate audio respiratory signals, recognize breath cycles, extract metrics for breath intensity and rate, calculate master vectors with weighting coefficients, and detect thresholds, wheeze, and lung pathologies using auto-correlation functions and artificial neural networks.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional respiratory analysis methods are used, then diagnostic capability is provided, but device complexity and cost increase

Engineering Contradiction:

Improvediagnostic capabilityVSAvoidcomplexity of apparatus

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent uses audio recordings of breathing sounds as a simplified copy or representation of the actual respiratory physiological processes, replacing complex gas analysis equipment. The audio signal serves as a surrogate that captures essential respiratory information without requiring sophisticated metabolic analyzers

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent replaces mechanical and chemical measurement systems (gas analyzers, blood lactate tests) with an acoustic field-based system using microphones and audio processing. This substitutes complex mechanical/chemical instrumentation with simpler acoustic sensing and digital signal processing

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If conventional respiratory analysis methods are used, then VT and RCT can be determined, but ease of operation decreases

Engineering Contradiction:

Improveaccuracy of VT and RCT determinationVSAvoidease of use

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The system automatically processes breathing sounds to determine VT and RCT thresholds without requiring manual intervention or interpretation by trained personnel. The automated audio analysis and threshold detection algorithms enable the system to perform complex measurements independently, eliminating the need for specialized operators

Inventive Principle:

Principle #25Self-service

3Reliability

If conventional methods are used, then respiratory analysis is performed, but loss of information occurs due to not analyzing full breath cycles

Engineering Contradiction:

Improveaccuracy of respiratory analysisVSAvoidinformation loss from incomplete breath cycle analysis

Core Design Contradiction:

ReliabilityVSLoss of information

Solution Approach 1:

The patent segments the audio respiratory signal into distinct breath cycles and further divides each breath cycle into phases (inhalation, exhalation, transition periods). This segmentation allows comprehensive analysis of all breath phases to extract multiple respiratory parameters including VT, RCT, respiratory rate, and tidal volume without missing information from any phase

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS11529072B2Method and apparatus for performing dynamic respiratory classification and tracking of wheeze and crackle

Publication Date: 2022.12.20 STRYKER CORP

AI summary

A method for detecting wheeze from an audio respiratory signal comprises capturing the audio respiratory signal from a subject using a microphone. Further, the method comprises recognizing a plurality of breath cycles and a plurality of breath phases from the audio respiratory signal and detecting wheezing from the plurality of breath cycles and the plurality of breath phases. The detecting comprises analyzing a block of interest in the audio respiratory signal, wherein the block of interest comprises a plurality of frames. The detecting further comprises calculating an auto-correlation function (ACF) for each frame in the block and determining a maximum value of the ACF calculated for each frame in the block. Finally, the detecting comprises analyzing the maximum value to detect if wheezing is present in the block.