Contactless Video-Audio Detection of Pediatric Sleep-Disordered Breathing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current diagnosis of sleep-disordered breathing (SDB) in children is cumbersome, expensive, and often limited to severe cases due to the high cost and limited facility spaces, leaving many children undiagnosed and at risk for severe medical complications.
Innovation Solution
A system using a camera and microphone to capture video and audio data, respectively, processes these signals with machine learning to detect SDB events like apnea and hypopnea without requiring sensors on the child, distinguishing between breathing sounds and background noise, and correlating visual and acoustic features for accurate diagnosis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sleep lab assessment with multiple sensors is used for SDB diagnosis, then diagnostic accuracy is improved, but cost and device complexity increase significantly
Solution Approach 1:
The patent extracts and focuses on two key diagnostic indicators (snoring sounds and respiratory motion) from the complex multi-sensor sleep lab assessment. By isolating these specific parameters, the system achieves adequate diagnostic accuracy without requiring the full complex sensor suite, thus reducing device complexity while maintaining measurement precision for the essential diagnostic function.
Solution Approach 2:
The patent employs a camera that serves multiple functions: capturing video for respiratory motion analysis, providing infrared illumination for thermal imaging, and enabling both visual and acoustic SDB detection. This multi-functionality replaces multiple specialized sensors, reducing overall device complexity while maintaining comprehensive diagnostic capability.
2Measurement precision
If sleep lab assessment is performed, then diagnostic accuracy is improved, but cost to families increases significantly
Solution Approach 1:
The patent uses a camera-based system with inexpensive components (camera, microphone, processor) compared to expensive sleep lab equipment. The system achieves sufficient diagnostic accuracy through computational analysis of video and audio data, providing a cost-effective alternative that reduces financial burden on families while maintaining adequate measurement precision for SDB detection.
Solution Approach 2:
The patent replaces expensive mechanical sensor systems with a camera and microphone-based computational system. Instead of using specialized physiological sensors, the system uses image processing and acoustic analysis algorithms to extract diagnostic information, significantly reducing hardware costs while maintaining diagnostic accuracy through software-based measurement.
3Measurement precision
If multiple sensors are used in sleep assessment, then measurement precision is improved, but ease of operation deteriorates due to sensor attachment requirements
Solution Approach 1:
The patent employs a non-contact measurement system where the camera and microphone automatically capture data without requiring sensor attachment to the child. The system self-deploys and automatically analyzes video and audio data, eliminating the complex sensor attachment process while maintaining measurement precision through computational analysis of natural behaviors.
Solution Approach 2:
The patent replaces mechanical sensor attachment systems with an optical and acoustic measurement system. The camera captures visual data and the microphone captures sound without physical contact, eliminating the complexity of sensor placement and attachment while maintaining adequate measurement precision through image and audio processing algorithms.
4Area of stationary object
If sleep lab assessment is limited to severe cases, then facility space requirements are reduced, but coverage of at-risk children decreases
Solution Approach 1:
The patent creates a portable copy of the sleep assessment capability that can be deployed in home environments. Instead of requiring children to travel to facility-based sleep labs, the system replicates the diagnostic function in the home setting, expanding coverage to all at-risk children regardless of facility location or capacity constraints.
Solution Approach 2:
The patent transitions the assessment from a facility-based centralized model to a distributed home-based model. By deploying the system across multiple home environments rather than concentrating capacity in single facilities, the system expands coverage to serve more at-risk children while maintaining adequate measurement precision through portable diagnostic capability.
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
Provides a cost-effective, home-based screening for SDB that offers comprehensive monitoring, improving diagnostic accuracy and reducing the need for expensive sleep lab assessments, enabling early detection and treatment.
Implementation Method 1
a camera captures a sequence of video images of a child in a bed
Implementation Method 2
a microphone placed in proximity to the child simultaneously captures acoustic signals
Data Source
AI summary
A method includes receiving a sequence of video images of a child (26) in a bed (24) captured by an image sensor (74), and a stream of audio data captured, simultaneously with the capturing of the sequence of video images, by a microphone (88) placed in proximity to the child (26). The method further includes extracting first features from the video images relating to motion of the child (26), extracting second features from the audio data relating to sounds produced by the child (26), and correlating the first and second features to generate an indication of sleep-disordered breathing by the child (26). Other embodiments are also described.