PPG Blood Pressure Estimation via Parameter Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing blood pressure measurement technologies using photoplethysmography signals are inconvenient for wearable devices as they require simultaneous electrocardiogram and photoplethysmography signals, and conventional calibration methods are cumbersome, reducing the usability of wearable blood pressure measurement apparatuses.
Innovation Solution
A blood pressure measurement apparatus that detects photoplethysmography signals, calculates time information, and applies a blood pressure estimation equation using parameter information, with a parameter learning unit that updates parameters through statistical processing to estimate systolic and diastolic blood pressure, eliminating the need for simultaneous ECG and PPG signals and simplifying calibration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a method using electrocardiogram and photoplethysmography signals in combination is employed to measure blood pressure, then measurement precision is improved, but device complexity and ease of operation deteriorate due to requiring simultaneous detection of multiple signals
Solution Approach 1:
The invention extracts and utilizes only the photoplethysmography signal component for blood pressure measurement, eliminating the requirement for electrocardiogram signal detection. This is achieved by focusing on specific time parameters (systolic upstroke time and diastolic time) from the PPG signal alone, thereby simplifying the detection system while maintaining measurement capability
Solution Approach 2:
The photoplethysmography sensor performs multiple functions: it detects pulse rate and provides blood pressure measurement information through time parameter analysis. By making the PPG sensor universal for both heart rate and blood pressure measurements, the invention eliminates the need for separate ECG detection hardware
2Measurement precision
If conventional calibration methods are used to update blood pressure estimation parameters, then measurement precision is improved, but ease of operation and productivity deteriorate due to cumbersome calibration procedures
Solution Approach 1:
The system performs self-calibration by automatically updating parameters using statistical processing of collected PPG signal time data. The parameter learning unit autonomously adjusts the blood pressure estimation equation parameters based on accumulated measurement data, eliminating the need for manual calibration procedures requiring external equipment or professional intervention
Solution Approach 2:
The system collects and processes time parameter data in advance to build accurate parameter information for the blood pressure estimation equation. By performing preliminary data collection and statistical processing, the system prepares optimized parameters that improve subsequent measurement accuracy without requiring calibration at the time of use
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
Enables accurate and convenient blood pressure measurement in a wearable form factor by continuously updating parameters, reducing the need for external calibration and allowing real-time estimation of blood pressure using photoplethysmography signals alone.
Implementation Method 1
a photoplethysmography sensor, which detects a pulse wave of a subject
Data Source
AI summary
A blood pressure measurement apparatus includes circuitry configured to: detect a pulse of a subject, and obtain a photoplethysmography signal; and obtain estimated blood pressure of the subject based on the photoplethysmography signal. The circuitry receives parameter information, generates time information based on the photoplethysmography signal, applies a blood pressure estimation equation to the time information and the parameter information to calculate the estimated blood pressure, receives basic blood pressure information for the subject and the time information, and performs learning processing of applying a learning operational equation to statistical time information, which is obtained by performing statistical processing on the time information, and the basic blood pressure information to update the parameter information.