Blood Pressure Estimation Using PPG Convolution

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for estimating blood pressure using photoplethysmography (PPG) traces face challenges in accurately fitting cardiologically significant parameters due to the broad range of patients and varying PPG signals, resulting in high mean absolute error.

Innovation Solution

The method involves obtaining calibration traces that yield a fit between selected reference traces and corresponding parameter reference values, and then determining a convolution of the PPG trace with these calibration traces to estimate blood pressure, treating all PPG trace points uniformly and using a discrete convolution approach.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If correlation models use a limited number of cardiologically significant parameters to estimate blood pressure, then the model complexity is reduced, but the measurement precision deteriorates due to high mean absolute error

Engineering Contradiction:

Improvemodel complexityVSAvoidblood pressure estimation accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent transforms the blood pressure estimation problem from using a limited set of extracted cardiologically significant parameters to utilizing all PPG trace points through convolution. This parameter transformation maintains low computational complexity while improving measurement precision by maximizing data utilization.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The calibration trace serves multiple functions: it acts as a filter, a reference signal, and a weighting mechanism simultaneously. This universal approach allows the same convolution operation to handle both systolic and diastolic blood pressure estimation without requiring separate complex processing pipelines.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Loss of information

If all PPG trace points are used uniformly in convolution, then data utilization is maximized, but the computational load increases for battery-powered devices

Engineering Contradiction:

Improvedata utilizationVSAvoidcomputational energy consumption

Core Design Contradiction:

Loss of informationVSUse of energy by moving object

Solution Approach 1:

The patent replaces complex mechanical processing (multiple parameter extraction and correlation calculations) with a simpler convolution operation. This substitution maintains full data utilization while reducing computational energy consumption through a more efficient mathematical operation.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

By changing from correlation-based processing to convolution-based processing, the patent achieves the same information extraction goal with reduced computational complexity, making it suitable for battery-powered wearable devices.

Inventive Principle:

Principle #35Parameter changes

3Adaptability or versatility

If calibration traces are constructed to fit broad patient populations, then adaptability is improved, but measurement precision worsens due to signal variability

Engineering Contradiction:

Improvepatient population coverageVSAvoidblood pressure estimation accuracy

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The calibration traces are pre-computed offline to capture the relationship between PPG signals and blood pressure across diverse patient populations. This preliminary action allows the system to adapt to different patients without requiring complex real-time adjustments, maintaining both adaptability and precision.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The calibration trace acts as an intermediary that bridges the gap between raw PPG signals and blood pressure estimates. It encapsulates the variability across different patient populations, allowing the convolution operation to produce accurate results without directly processing each patient's unique signal characteristics.

Inventive Principle:

Principle #24Intermediary (Mediator)

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 accurate blood pressure estimation with reduced mean absolute error, maximizing data utilization and enabling operation within the constraints of battery-powered wearable devices.

Implementation Method 1

a photodetector 602 positioned to detect light 650 passing through the finger 640. The photodetector 602 generates a photoplethysmography (“PPG”) signal in response to the absorbed light.

Methodology Applied

Scientific EffectPhotoplethysmography: Absorption (EM radiation)

Data Source

PatentUS20250049331A1Estimating Blood Pressure Using PPG Traces

Publication Date: 2025.02.13 ARTILUX INC

AI summary

Methods and systems for estimating a blood pressure of a user of a computing device are disclosed herein. The method can include obtaining at least one calibration trace, the at least one calibration trace being constructed to yield a fit between one or more selected reference traces and a corresponding parameter reference value for each of the one or more selected reference traces and obtaining a photoplethysmography (PPG) trace associated with a heartbeat cycle. The method can also include determining a convolution of the PPG trace with the at least one calibration trace, determining a blood pressure estimate for the user based on the convolution of the PPG trace with the at least one calibration trace, and providing data representing the blood pressure estimate.