Cuff-less Blood Pressure Estimation via Visibility Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional cuff-based blood pressure monitors are inconvenient and cannot provide continuous, non-invasive, and accurate blood pressure monitoring, which is crucial for managing hypertension and conditions like autonomic dysreflexia, where rapid BP changes can be life-threatening.
Innovation Solution
A computer-implemented method using a processor to convert photoplethysmography (PPG) signals into visibility graphs, which are then analyzed using pre-trained machine learning algorithms like AlexNet, VGG-19, or Inception v3 for cuff-less estimation of systolic and diastolic blood pressure, reducing computational requirements and enabling rapid BP change detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional cuff-based blood pressure monitors are used, then measurement accuracy can be maintained, but continuous monitoring capability and convenience deteriorate
Solution Approach 1:
The patent replaces the mechanical cuff-based measurement system with an optical PPG sensor system. The PPG sensor uses light absorption changes in blood vessels to detect blood pressure parameters, eliminating the need for mechanical cuffs while enabling continuous, non-invasive monitoring with maintained accuracy through machine learning algorithms.
Solution Approach 2:
The patent makes the PPG sensor system multi-functional by extracting multiple physiological parameters (blood pressure, heart rate, oxygen saturation) from a single optical signal source. This allows the device to perform continuous blood pressure monitoring alongside other vital signs measurement, improving convenience and comprehensive health tracking.
2Measurement precision
If conventional cuff-based monitors are used, then blood pressure can be measured, but rapid BP change detection capability deteriorates
Solution Approach 1:
The patent implements continuous blood pressure monitoring by continuously采集 PPG signals and processing them through the machine learning model. Unlike intermittent cuff-based measurements, the system maintains continuous data flow, enabling real-time detection of rapid blood pressure changes critical for conditions like autonomic dysreflexia.
Solution Approach 2:
The replacement of mechanical cuff inflation/deflation cycles with continuous optical sensing enables much faster response times. The PPG system can detect blood pressure changes at the speed of light propagation through tissue, allowing rapid detection of critical events without the time delays inherent in mechanical measurement systems.
3Measurement precision
If complex machine learning models are used for PPG analysis, then blood pressure estimation accuracy improves, but computational power requirements increase
Solution Approach 1:
The patent applies preliminary action by pre-training deep neural network models on large datasets and then using transfer learning to adapt these pre-trained models to blood pressure estimation. This allows the system to leverage previously computed knowledge, reducing the computational burden during actual blood pressure measurement while maintaining high accuracy through the pre-learned feature representations.
Solution Approach 2:
The patent optimizes the balance between model complexity and computational efficiency by adjusting model parameters, input signal characteristics, and processing architecture. This includes selecting appropriate PPG signal segments, optimizing neural network depth and width, and tuning hyperparameters to achieve accurate blood pressure estimation with minimal computational resource consumption suitable for wearable devices.
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 method allows for accurate, continuous, and cuff-less blood pressure monitoring, capturing rapid changes with low computational power, improving patient safety by enabling timely intervention in conditions like autonomic dysreflexia.
Implementation Method 1
cuff-less blood pressure estimation from photoplethysmography
Data Source
AI summary
A method includes receiving signal data from a sensor device; dynamically converting the signal data into a visibility point based on a time series vector associated with the signal data; generating an image to preserve the time series vector, wherein the a time series vector is a shape within the image; extracting a feature metric of a plurality of feature metrics from the image based on an analysis of a pre-trained machine learning algorithm; automatically determining, utilizing a transfer learning algorithm, a first position of a node in a plurality of nodes within the image based on a relationship between the feature metric and the time series vector associated with the time series data; predicting a second position of the node in the plurality of nodes based on the analysis of the pre-trained machine learning algorithm and the relation between the feature metric and the time series vector.