Lung Sound Analysis Using Pause-Phase Noise Exclusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing lung sound analysis systems struggle to accurately diagnose heart failure in non-specialist settings due to the inclusion of noise during the pause phase of breathing, which can erroneously detect abnormalities in lung sounds.
Innovation Solution
A lung sound analysis system that identifies the pause phase in breathing cycles and separates the time-series acoustic signals to exclude noise, allowing for accurate detection of abnormalities in lung sounds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If lung sounds are analyzed by dividing breathing into two periods (first-half inspiration and latter-half expiration), then abnormality detection can be performed, but noise during the pause phase is erroneously detected as abnormality
Solution Approach 1:
The patent segments the breathing cycle into three distinct phases: inspiration period, pause phase, and expiration period. This finer segmentation allows the system to identify and exclude the pause phase where noise is most likely to occur, thereby improving detection accuracy while maintaining automated analysis
Solution Approach 2:
The patent extracts and removes the pause phase from the analysis period. By identifying the pause phase as a separate entity and excluding it from abnormality detection, the system eliminates the source of erroneous noise detection while preserving the automated detection capability for actual lung abnormalities
2Ease of operation
If lung sound analysis is performed to enable diagnosis by non-specialists, then ease of operation improves, but detection accuracy deteriorates due to noise during pause phase
Solution Approach 1:
By segmenting the breathing cycle into three phases and automatically identifying the pause phase, the system provides accurate abnormality detection without requiring specialist knowledge. The automated phase identification ensures consistent accuracy across all users, making the tool accessible to non-specialists while maintaining high detection precision
Solution Approach 2:
The system extracts and excludes the pause phase from analysis, eliminating the primary source of noise-induced false positives. This extraction approach enables non-specialists to perform accurate lung sound analysis without needing to manually filter noise, thereby improving both ease of operation and maintaining detection accuracy
Data Source
AI summary
A lung sound analysis system includes an acquisition means for acquiring time-series acoustic signals including lung sounds of a subject who is a heart failure patient, a determination means for determining a pause phase of breathing of the subject, a dividing means for dividing the time-series acoustic signals into those in a period of the pause phase of breathing of the subject and those in a period other than the pause phase, according to a result of the determination, and a detection means for detecting abnormality in the lung sounds from the time-series acoustic signals in the period other than the pause phase after the division. The system supports medical decision making for healthcare professionals monitoring heart failure patients.