Acoustic Respiratory Analysis for Wheeze Detection and Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional respiratory analysis methods are costly, invasive, and lack accuracy in determining ventilatory thresholds (VT) and respiratory compensation thresholds (RCT), and fail to effectively analyze full breath cycles and detect wheeze and crackle sounds for lung pathologies.
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, and detect thresholds and lung pathologies like wheeze using auto-correlation functions and spectrograms, with an artificial neural network for pathology determination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional gas or metabolic analyzers are used to determine VT and RCT, then measurement accuracy is improved, but device complexity and cost increase
Solution Approach 1:
The patent replaces complex mechanical gas analysis systems with an acoustic-based detection system using microphones and signal processing algorithms. The system captures breath sounds and processes them through auto-correlation functions and spectrogram analysis to determine respiratory thresholds, eliminating the need for expensive metabolic analyzers while maintaining diagnostic capability
Solution Approach 2:
The patent creates a simplified acoustic model that copies the essential information from complex gas exchange measurements. By analyzing breath sound patterns, timing, and intensity characteristics, the system reproduces the diagnostic value of metabolic analysis through a different physical modality (acoustics instead of gas exchange), providing comparable VT and RCT determination with simpler equipment
2Measurement precision
If blood lactate analysis is used to measure VT and RCT, then measurement accuracy is improved, but invasiveness increases
Solution Approach 1:
The patent substitutes invasive blood sampling with non-invasive acoustic sensing. By placing a microphone near the subject's airway, the system captures breath sounds that contain information about respiratory mechanics and metabolic state, eliminating needle punctures and blood draws while providing indirect measurement of physiological thresholds through sound analysis
3Ease of operation
If the Foster talk test is used to measure VT and RCT, then ease of operation is improved, but measurement precision deteriorates
Solution Approach 1:
The patent incorporates automated feedback through algorithmic analysis of breath sound patterns. The system continuously monitors acoustic signals, applies signal processing algorithms (auto-correlation, spectrogram analysis), and provides objective threshold determination based on detected patterns in breath timing and intensity, eliminating subjective interpretation while maintaining ease of operation
Solution Approach 2:
The system performs self-analysis by automatically processing captured breath sounds through embedded algorithms. The microphone captures signals, the processor analyzes patterns using auto-correlation functions and spectrograms, and the system autonomously determines VT and RCT thresholds without requiring external expert interpretation, making the test both simple to administer and objectively accurate
4Reliability
If conventional respiratory analysis methods are used, then diagnostic capability is improved, but ease of operation deteriorates due to cumbersome apparatus
Solution Approach 1:
The patent extracts the essential diagnostic function from complex conventional apparatus by isolating the breath sound capture and analysis process. Using a simple microphone positioned near the airway, the system extracts respiratory information from acoustic signals alone, separating the core diagnostic capability from the cumbersome equipment required by traditional methods
Solution Approach 2:
The patent creates a multi-functional system where a single acoustic sensing device performs multiple respiratory assessment functions. The same microphone and signal processing system can determine VT, RCT, detect wheeze, analyze breath patterns, and assess respiratory effort, replacing multiple specialized devices with one universal acoustic analysis platform that maintains comprehensive diagnostic capability
5Reliability
If conventional respiratory analysis is performed, then detection capability is improved, but ease of operation worsens due to lack of full breath cycle analysis
Solution Approach 1:
The patent segments the breath cycle into distinct phases (inspiration, transition, expiration, rest) and analyzes each phase separately using signal processing algorithms. By dividing the continuous breath signal into discrete temporal segments and applying auto-correlation and spectrogram analysis to each, the system comprehensively characterizes the entire breathing pattern, enabling detection of pathologies that may manifest in specific phases while maintaining automated ease of operation
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables non-invasive, accurate determination of VT and RCT, analysis of full breath cycles, and detection of wheeze and crackle sounds, providing a cost-effective and reliable tool for respiratory analysis and lung pathology diagnosis.
Implementation Method 1
recording breathing sounds of a subject using a microphone
Implementation Method 2
detecting wheeze from the plurality of breath cycles and the plurality of breath phases... calculating an auto-correlation function (ACF) for each frame in the block
Implementation Method 3
analyzing the maximum value to detect if wheezing is present in the block
Data Source
AI summary
A method for analyzing an audio respiratory signal comprises capturing the audio respiratory signal from a subject using a microphone and partitioning the audio respiratory signal into a plurality of overlapping frames. The method further comprises calculating a fourier transform for each frame and determining a magnitude spectrum using the fourier transform of the plurality of overlapping frames. Additionally, the method comprises extracting a spectrogram using the magnitude spectrum and analyzing the spectrogram to determine characteristics pertaining to wheeze sounds in the audio respiratory signal.