Pulse Oximeter Wavelet Transform Signal Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current pulse oximetry methods struggle to accurately analyze physiological signals in both time and frequency domains, leading to incomplete information for identifying physiological conditions, as they often result in globally averaged energy values without temporal component information.
Innovation Solution
The use of wavelet transforms to process physiological signals from pulse oximeters, enabling analysis of signal characteristics in multiple dimensions (frequency and amplitude with respect to time), and comparison with a library of wavelet signatures to identify specific physiological conditions, along with supervised learning techniques like neural networks for improved accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional frequency domain transformation is used to analyze physiological signals, then frequency characteristics can be identified, but temporal information is lost due to global averaging
Solution Approach 1:
The physiological signal is divided into multiple local segments or windows of time, and wavelet transform is applied to each segment independently. This segmentation allows frequency analysis to be performed locally in time, preserving temporal information while maintaining frequency analysis capabilities. Each local segment can be analyzed for its specific frequency characteristics without losing the temporal context of when those characteristics occurred.
Solution Approach 2:
The patent transitions from traditional one-dimensional frequency domain analysis to a two-dimensional time-frequency domain analysis using wavelet transform. This dimensional change allows simultaneous representation of both temporal and frequency characteristics, creating a scalogram that displays energy distribution across time and frequency axes, thereby preserving both types of information simultaneously.
2Reliability
If pulse oximetry measures blood oxygen saturation, then physiological information is obtained, but non-physiological noise interferes with accurate detection
Solution Approach 1:
The wavelet transform provides different resolution qualities at different scales and time locations. By analyzing the signal at multiple scales, the method can locally adapt to different signal characteristics, enhancing detection of physiological features while suppressing noise that appears at different scales or time locations. The local quality of analysis allows targeted enhancement of signal features while filtering out non-physiological interference.
Solution Approach 2:
The patent converts the presence of noise into a beneficial feature by analyzing the wavelet coefficients at multiple scales. Non-physiological noise typically manifests at specific scales or time locations, while physiological signals have characteristic patterns across scales. By examining the multi-scale wavelet decomposition, the method can identify and exploit the distinctive patterns of physiological signals versus noise, turning the complexity of the noisy signal into a means for discrimination and enhancement.
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 allows for more accurate estimation of physiological data by analyzing signal features in both time and frequency domains, enhancing the detection of physiological conditions and removing non-physiological noise, thereby improving the reliability of pulse oximeter readings.
Implementation Method 1
Pulse oximeters typically utilize a non-invasive sensor that transmits light through a patient's tissue and that photoelectrically detects the absorption of the transmitted light in such tissue
Data Source
AI summary
Methods and systems are provided for analyzing a physiological signal by applying a continuous wavelet transform on the signal and comparing the wavelet transformation to a library of wavelet signatures corresponding to one or more physiological conditions and/or patient conditions. A pulse oximeter system may relate the wavelet transformation with one or more of the wavelet signatures based on filters and/or thresholds, and may determine that the wavelet transformation indicates that the patient of the physiological signal has a physiological condition indicated by the related wavelet signature. In some embodiments, the pulse oximeter system may use previous analyses in a neural network to update the library. Further, non-physiological components of the wavelet transformation may also be identified and removed.