Non-Gaussianity Index for Snore Sound Sleep Apnea Screening
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for diagnosing obstructive sleep apnea (OSA) are costly, time-consuming, and often require supervised overnight polysomnography, leading to long waiting lists and a high percentage of undiagnosed cases due to the need for extensive medical technologist involvement and inadequate sensitivity/specificity in home monitoring systems.
Innovation Solution
A method and apparatus that process digitized audio signals from snoring sounds using electronic processors to estimate parameters such as non-Gaussianity index, pitch, higher-order spectrum, and cepstral coefficients, applying these to a diagnostic model to indicate the presence of obstructive sleep apnea, allowing for automated diagnosis without the need for on-site medical professionals.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If supervised overnight polysomnography is used for diagnosis, then diagnostic accuracy is improved, but cost and time consumption increase significantly
Solution Approach 1:
The patent extracts only the audio signal component from the full polysomnography system, isolating the snoring sound analysis as a separate diagnostic method. This allows diagnosis without requiring the complete PSG system with multiple sensors and manual analysis, thereby reducing time and cost while maintaining diagnostic capability through automated audio processing
Solution Approach 2:
The patent replaces the mechanical/manual analysis system of polysomnography with an automated electronic signal processing system. Instead of manual examination of multiple physiological signals by medical technologists, the system uses digital audio signal processing algorithms to automatically detect and classify snoring patterns, eliminating the need for on-site medical professionals and reducing diagnostic time
2Ease of manufacture
If home monitoring systems are used, then cost is reduced, but sensitivity and specificity are insufficient
Solution Approach 1:
The patent employs multiple signal processing parameters including non-Gaussianity index, higher-order spectrum analysis, cepstral coefficients, and pitch parameters to enhance the diagnostic capability of home monitoring systems. By transforming and analyzing the audio signal through these sophisticated parameter changes, the system achieves improved sensitivity and specificity for detecting sleep apnea while maintaining cost-effectiveness
Solution Approach 2:
The system incorporates automated feedback mechanisms where the processed audio signals are continuously evaluated against diagnostic criteria, and results are automatically interpreted to provide diagnostic feedback. This automated feedback loop eliminates the need for on-site medical technologist interpretation, improving both reliability and cost-efficiency by enabling remote diagnostic decision-making
3Productivity
If automated audio signal processing is implemented, then cost and time are reduced, but diagnostic complexity increases
Solution Approach 1:
The patent segments the complex diagnostic task into distinct processing stages: audio signal acquisition, segmentation into epochs, feature extraction (non-Gaussianity index, higher-order spectrum, cepstral coefficients, pitch parameters), and diagnostic classification. This segmentation allows complex processing to be broken down into manageable steps that can be implemented through standardized algorithms, reducing the barrier to adoption while maintaining high diagnostic efficiency
Data Source
AI summary
A parameter quantifying deviation from Gaussianity distribution of a patient's sounds, in the form of a non-Gaussianity distribution index, may be used to assist in diagnosis of sleep dysfunction such as OSAHS. A method for diagnosing a sleeping disorder of a subject includes processing a digitized audio signal from the subject with at least one electronic processor. The processing includes estimating a parameter quantifying deviation from Gaussianity distribution of the audio signal. in the form of a non-Gaussianity Index (NGI). The NGI value is then applied to a diagnostic model. The presence of a sleeping disorder is then indicated based on the output of the diagnostic model.