Respiratory Rate Extraction Using Quality-Weighted Modulations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for monitoring respiratory rate are unreliable, uncomfortable, and costly, particularly in hospital settings, and existing algorithms for extracting respiratory rate from ECG and PPG signals face challenges due to noise and patient-specific variations, making it difficult to accurately detect subtle modulations.
Innovation Solution
A method that involves obtaining time windows of physiological data, identifying reference features, extracting modulations, and calculating a quality parameter to select and weight the most reliable modulations for accurate frequency calculation, improving data quality and reducing processing power requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If respiratory rate is extracted from ECG and PPG signals using existing algorithms, then respiratory rate monitoring is achieved without special equipment, but the measurement reliability is low due to noise and patient-specific variations
Solution Approach 1:
The patent segments the respiratory rate extraction process into multiple modulation modes (amplitude modulation, frequency modulation, baseline modulation) and processes each mode separately through quality assessment and selective combination, thereby improving reliability while maintaining ease of implementation using existing ECG and PPG signals
Solution Approach 2:
The patent changes the approach from directly extracting respiratory rate to first extracting multiple modulation parameters (amplitude, frequency, baseline) and then combining them through quality-weighted processing, transforming the extraction process to achieve higher reliability from the same input signals
2Quantity of substance
If all extracted modulations are used for frequency calculation, then more data is available for analysis, but processing power requirements increase and accuracy decreases due to low-quality data
Solution Approach 1:
The patent applies local quality assessment by evaluating the quality of each extracted modulation individually through quality parameters, then selectively using only high-quality modulations or applying quality-based weightings, thereby maintaining measurement precision while efficiently processing the available data
Solution Approach 2:
The patent uses partial action by selecting only a subset of high-quality modulations for frequency calculation rather than processing all extracted modulations, reducing computational burden and improving accuracy by focusing on the most reliable data
3Measurement precision
If quality parameter filtering is applied to select modulations, then measurement accuracy improves, but device complexity increases
Solution Approach 1:
The patent applies preliminary action by performing quality parameter calculation and modulation selection before the final frequency calculation step, thereby improving respiratory rate accuracy through selective processing while managing device complexity by organizing the workflow in advance
Data Source
AI summary
Methods, devices and systems for determining the frequency of a periodic physiological process of a subject, particularly respiration rate or heart rate, are disclosed. In one arrangement plural time windows of physiological data are obtained. Reference features corresponding to modulation modes are identified. Modulations of the reference features are extracted. Quality parameters are obtained by processing the extracted modulations. The quality parameters represent how strongly the extracted modulation exhibits a waveform of the periodic physiological process. The extracted modulations are processed to calculate the frequency of the periodic physiological process of the subject. The frequency of the periodic physiological process may be calculated using only a subset of the extracted modulations, the subset being selected using the quality parameter, or using a combination of the extracted modulations wherein each extracted modulation has a weighting defined by the quality parameter of the extracted modulation.