Blood Pressure Estimation Using Threshold-Based Feature Combination
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current non-invasive blood pressure estimation methods face challenges in accurately measuring blood pressure outside clinical settings due to limitations in bio-signal analysis and feature extraction, particularly in mobile healthcare scenarios where noise and external factors affect sensor accuracy.
Innovation Solution
A method and apparatus that extract reference and candidate features from bio-signals, such as heart rate and amplitude ratios, using thresholds to combine features for blood pressure estimation, incorporating a processor to analyze and estimate blood pressure through cardiac output and total peripheral resistance-associated features.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If simple bio-signal analysis is used for blood pressure estimation, then device complexity is reduced, but measurement precision deteriorates due to noise and external factors in mobile healthcare settings
Solution Approach 1:
The patent segments the blood pressure estimation process into multiple independent stages: extracting reference features (heart rate, pulse wave velocity), extracting candidate features (amplitude ratios, waveform characteristics), and combining them through threshold-based selection. This segmentation allows each stage to focus on specific aspects of bio-signal analysis, improving overall precision while maintaining manageable complexity through modular processing
Solution Approach 2:
The patent performs preliminary feature extraction and threshold determination before final blood pressure estimation. Reference features are extracted and stored in advance, and threshold values are pre-calculated based on calibration data. This preliminary action enables rapid, accurate estimation during actual measurement without requiring complex real-time calculations, thus improving measurement precision while keeping device complexity manageable
2Measurement precision
If multiple candidate features are combined for blood pressure estimation, then measurement precision is improved, but device complexity increases due to additional feature extraction and combination processing
Solution Approach 1:
The patent implements dynamic feature selection based on threshold conditions. The system adapts which candidate features to use by comparing reference features against pre-determined thresholds. When reference features fall within certain ranges, specific candidate features are selected and combined; when outside ranges, different features are used. This dynamic adaptation improves measurement precision by selecting optimal features for each physiological state while managing complexity through rule-based decision logic rather than complex machine learning models
Solution Approach 2:
The patent changes the parameters of feature extraction and combination based on reference feature values. Different candidate features are extracted and combined using different weighting factors or selection criteria depending on the magnitude of reference features such as heart rate or pulse wave characteristics. This parameter adjustment allows the system to optimize measurement precision for different physiological conditions without requiring a completely complex feature processing architecture
3Device complexity
If feature extraction is performed without threshold-based selection, then device complexity is reduced, but measurement precision deteriorates due to noise-related degradation in mobile healthcare scenarios
Solution Approach 1:
The patent incorporates feedback through threshold-based validation of extracted features. Reference features are continuously compared against threshold values, and candidate features are selectively combined based on whether reference features meet specific criteria. This feedback mechanism filters out noise-related errors by only using features that pass validation thresholds, thereby improving measurement precision while maintaining relatively simple extraction logic through clear decision boundaries
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 and reliable non-invasive blood pressure estimation by progressively comparing reference features with thresholds, combining candidate features to improve estimation accuracy and reduce noise-related degradation, suitable for mobile healthcare applications.
Implementation Method 1
a PPG signal is based on a superposition of a propagation wave starting from the heart toward the body distal ends and reflection waves returning from the body distal ends
Data Source
AI summary
A method of obtaining a feature for blood pressure estimation is provided. The method includes extracting a reference feature from a bio-signal; obtaining a feature for blood pressure estimation by: obtaining, as the feature for blood pressure estimation, a first candidate feature based on the reference feature being less than a first threshold; obtaining, as the feature for blood pressure estimation, a second candidate feature based on the reference feature being greater than or equal to a second threshold that is greater than the first threshold; or obtaining, as the feature for blood pressure estimation, a combination of the first candidate feature and the second candidate feature based on the reference feature being less than the second threshold; and estimating a blood pressure by using the obtained feature.