Wearable Blood Pressure Sensing With Multi-Wavelength PPG Ratios
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing single-site PPG-based blood pressure estimation algorithms suffer from high feature overlap and correlation, leading to overfitting and inaccurate predictions due to the capricious nature of PPG signals, especially in real-world scenarios with varying signal quality and patient-specific physiology.
Innovation Solution
A wearable device using multi-wavelength PPG sensors processes photoplethysmography signals at different wavelengths, employs a Signal Quality Indicator to filter high-quality signals, and utilizes a cluster-based Random Forest model with personalized fine-tuning for accurate blood pressure estimation, incorporating demographic and vital sign data to adapt to individual physiology.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If single-wavelength PPG signals with time- and frequency domain features are used for blood pressure estimation, then the device complexity is reduced and single-site measurement is achieved, but the measurement precision deteriorates due to high feature overlap and correlation causing overfitting
Solution Approach 1:
The patent introduces a novel wavelength ratio parameter (ratio of PPG signals at different wavelengths) that transforms the feature space. Instead of using traditional time- and frequency-domain features from single-wavelength PPG that suffer from high correlation, the invention creates new parameters by comparing PPG signals at multiple wavelengths, thereby reducing feature overlap and improving measurement precision while maintaining single-site measurement capability
Solution Approach 2:
The patent adds a spectral dimension to the PPG analysis by incorporating multiple wavelengths. This transforms the problem from analyzing temporal variations in a single wavelength signal to analyzing both temporal and spectral characteristics across multiple wavelengths, creating additional discriminative features that reduce overfitting and improve blood pressure estimation accuracy
2Measurement precision
If multi-wavelength PPG signals are used for blood pressure measurement, then the measurement precision is improved by reducing feature overlap, but the device complexity and signal processing requirements increase
Solution Approach 1:
The patent extracts and isolates the wavelength ratio as a specific feature from the multi-wavelength PPG signals. By focusing on the ratio between wavelengths rather than processing all possible spectral-temporal combinations, the invention reduces the complexity of signal processing while retaining the precision benefits of multi-wavelength measurement
Solution Approach 2:
The patent transforms complex multi-wavelength PPG data into simplified wavelength ratio parameters. This parameter transformation reduces the dimensionality of the problem and simplifies subsequent processing steps while maintaining the discriminative power needed for accurate blood pressure estimation
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
The solution provides enhanced accuracy and reliability in blood pressure measurement by filtering high-quality signals, reducing overfitting, and continuously adapting to individual physiological changes, ensuring precise systolic and diastolic pressure predictions.
Implementation Method 1
Photoplethysmography (PPG) is a non-invasive optical technique that measures blood volume changes in the microvascular bed of tissue. It works by shining a light source, typically an LED, onto the skin and detecting the amount of light that is transmitted or reflected back to a photodetector.
Implementation Method 2
different wavelengths of light are absorbed differently by different chromophores, such as oxygenated and deoxygenated hemoglobin, which can provide insights into tissue oxygenation and metabolism
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present invention relates to a wearable device for non-invasively measuring blood pressure using multi-wavelength photoplethysmography (PPG) signals obtained from peripheral blood vessels. The wearable device is calibrated using PPG signals measured distal to the wearable device and analyzed in order to create a cardiovascular profile of a wearer. After calibration, windows of PPG signals are analyzed to provide a blood pressure estimation, based on the created profile. The current invention utilizes single-site measured PPG signals in order to make a prediction of the wearer's blood pressure. By using a combination of multi-wavelength PPG waveform features and a range of vital signs calculated by the wearable device, the current invention is able to provide a more accurate and robust prediction of blood pressure compared to existing methods. This has important implications for clinical settings where frequent and remote monitoring of blood pressure is necessary for managing a range of health conditions.