Sniff Detection via EMG and Accelerometer Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for distinguishing sniff activity from artifacts in electromyography (EMG) signals are inadequate, leading to inaccurate assessments of respiratory muscle effort, particularly in patients with chronic obstructive pulmonary disease (COPD), as signal artifacts from non-respiratory activities resemble sniff efforts, and existing invasive devices are cumbersome.
Innovation Solution
A system utilizing EMG electrodes and accelerometers to measure respiratory muscle activity and thoracic acceleration, preprocessing signals to isolate regular breathing and sniff activity, and employing machine learning models to classify candidate sniffs as either respiratory efforts or artifacts based on feature analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If EMG signals are used to measure respiratory muscle activity, then non-invasive measurement of breathing effort is achieved, but accurate distinction between sniff activity and signal artifacts becomes difficult
Solution Approach 1:
The patent combines EMG signals with accelerometer signals to create a multi-parameter monitoring system. The accelerometer measures thoracic acceleration during breathing, while the EMG measures respiratory muscle activity. By merging these two signal types, the system can distinguish between true sniff activity (which produces both EMG and acceleration changes) and artifact (which produces only EMG changes), thereby resolving the reliability issue while maintaining non-invasive measurement capability
Solution Approach 2:
The accelerometer acts as an intermediary device that provides additional information about thoracic movement. During sniff activity, the accelerometer detects specific acceleration patterns that correlate with the EMG signal, whereas during artifact events, the accelerometer shows different patterns. This intermediary measurement helps disambiguate the EMG signal interpretation without requiring invasive procedures
2Reliability
If invasive devices such as nasal cannulas or esophageal electrodes are used to distinguish sniffs from artifacts, then accurate sniff detection is achieved, but patient comfort and ease of measurement deteriorates
Solution Approach 1:
The patent replaces invasive mechanical devices (nasal cannulas, esophageal electrodes) with a non-invasive surface EMG and accelerometer system. The surface EMG electrodes placed on the skin and the accelerometer attached to the thorax provide sufficient data to accurately detect sniffs without penetrating the body or requiring uncomfortable intrathoracic placement, thus maintaining reliability while dramatically improving ease of operation and patient comfort
3Reliability
If multiple signal processing steps are applied to EMG data, then sniff artifact distinction improves, but system complexity and processing time increase
Solution Approach 1:
The patent segments the signal processing into distinct modules: EMG signal processing, accelerometer signal processing, and integrated analysis. Each module handles specific tasks (EMG filtering, acceleration thresholding, pattern recognition) independently, making the overall system more manageable and easier to implement. This segmentation reduces the complexity burden on any single processing step while maintaining high reliability in sniff-artifact distinction
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 approach enables accurate, non-invasive quantification of respiratory muscle effort by effectively differentiating sniff activity from artifacts, improving the assessment of respiratory status without the discomfort of invasive devices.
Implementation Method 1
measuring acceleration in a plurality of planes of the patient's thorax concurrently with respiratory activity with an accelerometer
Implementation Method 2
measuring respiratory muscle activity of the patient with a number of EMG electrodes
Data Source
AI summary
Non-invasive systems and methods for quantifying respiratory muscle effort (RME) (or breathing effort, work-of-breathing) are provided. The systems and methods utilize simultaneously measured EMG and accelerometer signals. The measured EMG signal is preprocessed to produce both a signal accentuating regular breathing activity and a signal accentuating sniff activity (deep, sharp inhalations). Time intervals of candidate sniffs are determined from the preprocessed EMG signals. The measured accelerometer signal is preprocessed to produce multiple signals accentuating either upper or lower frequency band activity. Features of the preprocessed EMG and accelerometer signals corresponding to the time intervals of candidate sniffs are analyzed to determine if the candidate sniffs constitute actual sniffs or artifacts. Subsequently, after maximum sniff effort has been identified, RME is quantified by the ratio of the mean of the maxima of regular breathing activity to the value of the maximum sniff effort.