Blood Pressure Estimation Using Dynamic TPR Feature Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies face challenges in accurately estimating blood pressure using pulse wave signals, particularly in determining the appropriate total peripheral resistance (TPR) feature for reliable blood pressure estimation.
Innovation Solution
The proposed solution involves an apparatus and method that extract cardiac output (CO) and two candidate TPR features from a bio-signal. By analyzing the direction of change in the CO feature and the candidate TPR features between a blood pressure measurement time and a calibration time, the apparatus determines the most suitable TPR feature for blood pressure estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple candidate TPR features are extracted and selected based on direction of change analysis, then blood pressure estimation accuracy is improved, but device complexity increases
Solution Approach 1:
The patent segments the TPR feature extraction process into multiple candidate features (first candidate TPR feature and second candidate TPR feature), each derived from different aspects of the pulse wave signal. This segmentation allows the system to analyze different characteristics separately and select the most appropriate one based on directional consistency with CO feature changes, thereby improving accuracy while maintaining manageable complexity through structured division of the analysis process.
Solution Approach 2:
The patent employs parameter changes by dynamically selecting between different TPR feature representations based on the directional relationship between CO feature and TPR feature changes. The system transforms the static feature selection problem into a dynamic parameter selection process where the choice of TPR feature representation depends on the observed directional consistency, allowing optimal adaptation to different physiological states without requiring a fixed complex structure.
2Reliability
If direction of change analysis is performed between blood pressure measurement time and calibration time, then reliability of TPR feature selection is improved, but loss of time increases
Solution Approach 1:
The patent applies preliminary action by performing calibration measurements in advance to establish baseline CO and TPR feature values. During actual blood pressure measurement, the system only needs to compute directional changes from these pre-established calibration values, rather than performing full feature extraction and analysis from scratch. This preliminary calibration step significantly reduces the computational time required during routine measurements while maintaining reliable feature selection through the directional consistency check.
3Measurement precision
If CO feature and TPR feature are combined for blood pressure estimation, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent merges two distinct physiological parameters - Cardiac Output (CO) feature and Total Peripheral Resistance (TPR) feature - to estimate blood pressure. By combining these features based on their physiological relationship (blood pressure = CO × TPR), the system achieves improved measurement precision. The merging is performed through a integrated estimation algorithm that processes both features together, leveraging their complementary information to produce more accurate blood pressure estimates than either feature could provide alone.
Data Source
AI summary
An apparatus for estimating blood pressure may include: a memory storing one or more instructions; and a processor configured to execute the one or more instructions to: extract a cardiac output (CO) feature, a first candidate total peripheral resistance (TPR) feature, and a second candidate TPR feature from a bio-signal; determine one of the first candidate TPR feature and the second candidate TPR feature as a TPR feature based on a direction of change in the CO feature and a direction of change in the first candidate TPR feature between a blood pressure measurement time and a calibration time; and estimate the blood pressure based on the TPR feature and the CO feature.