Dual-Axis Cervical Accelerometry for Swallowing Impairment Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting swallowing impairments, particularly dysphagia, are invasive, unreliable, and often fail to identify silent aspiration and swallowing inefficiency, leading to high false-positive rates and inadequate management of aspiration risk in high-risk populations like stroke patients.
Innovation Solution
A device and method using dual-axis cervical accelerometry to classify vibrational data from swallowing events, extracting features to distinguish between normal and impaired swallowing, providing a non-invasive tool for detecting aspiration and inefficiency with high sensitivity and specificity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If invasive techniques such as videofluoroscopic swallowing examinations are used, then measurement precision of aspiration detection is improved, but device complexity and ease of operation deteriorate
Solution Approach 1:
The patent replaces the mechanical/optical videofluoroscopic system with an acoustic sensing system using microphones and signal processing to detect aspiration events, eliminating the need for complex imaging equipment while maintaining detection capability
Solution Approach 2:
The system enables automated detection and classification of aspiration events through algorithmic analysis of acoustic signals, reducing the need for trained clinicians to perform complex manual assessments
2Reliability
If invasive procedures are used for swallow screening, then reliability of aspiration identification is improved, but ease of operation deteriorates
Solution Approach 1:
The patent substitutes invasive mechanical procedures with non-invasive acoustic monitoring that automatically detects aspiration events through voice and respiratory signal analysis, making the procedure easier to perform while maintaining reliability
Solution Approach 2:
The system uses acoustic signals as an intermediary to detect aspiration events indirectly through changes in voice and respiratory patterns, avoiding direct observation requirements while maintaining detection reliability
3Ease of operation
If clinical screening protocols are used, then ease of operation is improved, but measurement precision deteriorates due to silent aspiration
Solution Approach 1:
The patent uses acoustic signals as an intermediary to detect aspiration events that occur without overt clinical signs, enabling detection of silent aspiration through analysis of voice and respiratory pattern changes
Solution Approach 2:
The system provides automated feedback through algorithmic analysis of acoustic signals, objectively identifying aspiration events without relying on clinician interpretation of subtle clinical signs, thereby improving detection precision
4Reliability
If extensive training is provided for screening staff, then reliability of detection is improved, but device complexity and time consumption increase
Solution Approach 1:
The system performs automated detection and classification through embedded algorithms that analyze acoustic signals, eliminating the need for extensive training of screening staff while maintaining high detection reliability
Solution Approach 2:
The patent replaces the need for trained human assessors with an automated computational system that processes acoustic signals and classifies aspiration events, removing the training time requirement while preserving detection reliability
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
The solution effectively identifies impaired swallowing safety and efficiency with 90% sensitivity and 77% specificity, reducing the need for invasive procedures and extensive training, and improves early detection and management of aspiration risk.
Implementation Method 1
A device and method using dual-axis cervical accelerometry to classify vibrational data from swallowing events
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
Disclosed herein is a method and apparatus for swallowing impairment detection, whereby a candidate executes one or more swallowing events and dual axis accelerometry data is acquired representative thereof. Upon feature extraction and classification, vibrational data acquired in respect of each swallowing event is classified as indicative of one of normal or possibly impaired swallowing. Computer-readable media comprising statements and instructions for implementation by a processing device are also described in facilitating swallowing impairment detection respective to candidate swallowing events.