Capnography-Based Respiratory Obstruction Evaluation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for evaluating respiratory obstruction levels, such as spirometry, require subject cooperation and are not suitable for uncooperative populations or medical emergencies, and lack continuous monitoring capabilities.
Innovation Solution
The use of capnography to estimate respiratory obstruction levels through capnograph signal processing, including segmentation, feature extraction, and machine learning algorithms to provide continuous, real-time obstruction level measurements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If spirometry is used to estimate respiratory obstruction levels, then measurement precision is improved, but ease of operation deteriorates due to requiring subject cooperation and effort
Solution Approach 1:
The patent replaces the mechanical spirometry system requiring active subject participation with a capnography-based system that passively measures CO2 concentrations during normal breathing. The capnograph captures breath-by-breath CO2 data without requiring subject effort or cooperation beyond natural breathing, thereby resolving the contradiction between measurement precision and ease of operation.
Solution Approach 2:
The patent introduces CO2 concentration measurement as an intermediary parameter that indirectly reflects respiratory obstruction levels. Instead of directly measuring airflow volumes requiring subject cooperation (spirometry), the system uses CO2 concentration changes during normal breathing as a mediator to estimate obstruction levels, eliminating the need for active subject participation while maintaining measurement accuracy.
2Measurement precision
If spirometry is used for respiratory obstruction evaluation, then obstruction level estimation is achieved, but continuity of monitoring deteriorates due to discrete measurement nature
Solution Approach 1:
The patent implements continuous capnographic monitoring that captures CO2 concentrations breath-by-breath over extended periods, transforming the discrete nature of spirometry into a continuous monitoring system. The capnograph records multiple consecutive breaths, enabling real-time tracking of respiratory obstruction levels and detection of fluctuations that occur between discrete spirometry measurements.
3Ease of operation
If capnography is used instead of spirometry, then ease of operation is improved by requiring no subject effort, but measurement precision may deteriorate
Solution Approach 1:
The patent transforms capnographic CO2 concentration data into respiratory obstruction level estimates by applying signal processing techniques and machine learning algorithms. Multiple waveform features (area under curve, peak values, slopes, durations) are extracted and combined to compensate for the indirect measurement approach, ensuring that obstruction level estimation precision matches or exceeds traditional spirometry despite the passive nature of capnography.
Solution Approach 2:
The patent analyzes capnograph waveforms across multiple dimensions including temporal characteristics (breath duration, phase timing), amplitude characteristics (CO2 concentration levels), and derived features (slopes, areas, ratios). This multi-dimensional analysis of the capnographic signal compensates for the indirect measurement approach and achieves precision comparable to direct spirometry measurements.
4Duration of action of moving object
If continuous capnography monitoring is implemented, then monitoring continuity is improved, but device complexity increases due to signal processing requirements
Solution Approach 1:
The patent segments the continuous capnograph signal into individual breath cycles, each characterized by distinct phases (inspiration, expiration). This segmentation simplifies the analysis by allowing separate extraction of waveform features from each breath, making the continuous monitoring system more manageable and reducing computational complexity compared to analyzing the entire continuous signal as a whole.
Data Source
AI summary
Disclosed are computer-implemented methods and related systems for evaluating a respiratory obstruction-level in a subject with a respiratory condition, based on a capnograph signal of the subject. A first plurality of waveform features, derived from the capnograph signal, is used to discard invalid breath signals, thereby pre-processing the capnograph signal. A second plurality of waveform features, derived from the pre-processed signal, is fed into a machine learning algorithm to obtain a score quantifying the respiratory obstruction level of the subject.


