Snore Sound Analysis for Obstructive Sleep Apnea Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for diagnosing obstructive sleep apnea (OSA) are invasive, expensive, and time-consuming, requiring overnight polysomnography studies, whereas a non-invasive and cost-effective method is needed to accurately detect and classify the severity of OSA.
Innovation Solution
A non-invasive method using a device called ADITESTER, which employs a microphone to record snoring sounds during sleep and a computer system to process these sounds, determining an apnea diagnosing index (ADI) based on features like mel-cepstability, variance in energy of snore groups, and silent periods, correlating with the apnea-hypopnea index (AHI) to classify OSA severity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If polysomnography (PSG) is used to diagnose OSA, then diagnostic accuracy is improved, but device complexity and cost increase
Solution Approach 1:
The patent extracts the essential diagnostic function from complex PSG by isolating snoring sound analysis as the key indicator of OSA. The system removes unnecessary sensors and procedures, keeping only the microphone and signal processing components needed to detect apnea events through snoring pattern recognition.
Solution Approach 2:
The patent creates a simplified acoustic model that copies the diagnostic information from complex PSG studies. By analyzing snoring sound characteristics (frequency, intensity, patterns) and comparing them against established OSA criteria, the system reproduces diagnostic accuracy without requiring full polysomnography equipment.
2Measurement precision
If polysomnography (PSG) is used to diagnose OSA, then diagnostic accuracy is improved, but cost increases
Solution Approach 1:
The patent replaces expensive, reusable PSG equipment with inexpensive, disposable-like acoustic sensors (microphones). The system uses low-cost audio recording devices that can be easily replaced or reused, eliminating the need for expensive medical-grade polysomnography equipment while maintaining diagnostic capability.
Solution Approach 2:
The patent substitutes complex mechanical and electronic PSG systems with a simplified acoustic analysis system. Instead of using multiple sensors, amplifiers, and complex signal processing hardware, the system relies on standard microphones and software-based snoring pattern recognition algorithms to achieve accurate OSA diagnosis.
3Measurement precision
If polysomnography (PSG) is used to diagnose OSA, then diagnostic accuracy is improved, but waiting time increases
Solution Approach 1:
The patent enables preliminary self-diagnosis by allowing patients to record their own snoring sounds at home before scheduling a formal medical appointment. The system processes the audio recordings immediately, providing preliminary diagnostic results that can guide patients in seeking appropriate medical care, thereby eliminating the multi-week waiting period for PSG scheduling.
Solution Approach 2:
The patent implements a self-service diagnostic system where patients independently record and analyze their own snoring patterns without requiring scheduled appointments with sleep specialists. The automated analysis provides immediate results, empowering patients to take control of their health screening and reducing the burden on medical facilities.
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
This method allows for convenient, cost-effective diagnosis of OSA in a home environment, providing accurate classification of OSA severity, correlating well with traditional polysomnography results, and reducing the waiting period for diagnosis.
Implementation Method 1
a microphone that registers sounds generated by a person and the person's environment during sleep
Data Source
AI summary
An embodiment of the invention provides a method of diagnosing obstructive sleep apnea, the method comprising: acquiring a sleep sound signal comprising sounds made by a person during sleep; detecting a plurality of snore sounds in the sleep sound signal; determining a set of mel-frequency cepstral coefficients for each of the snore sounds; determining a characterizing feature for the sleep sound signal responsive to a sum of the variances of the cepstral coefficients; and using the characterizing feature to diagnose obstructive sleep apnea in the person.