Oscillometric Blood Pressure Correction Using Error-Learning Models

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing blood pressure measurement methods using the oscillometric method are prone to inaccuracies due to noise interminglement from body motion, cuff winding, and position, making it difficult to achieve accurate measurements with a small amount of training data.

Innovation Solution

A sphygmomanometer that utilizes a correction model constructed through machine learning, using cuff pressure waveform information and error as explanatory and objective variables, respectively, to correct blood pressure measurements and improve accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If machine learning is used to correct blood pressure measurement errors, then measurement accuracy is improved, but the amount of training data required increases

Engineering Contradiction:

Improveblood pressure measurement accuracyVSAvoidamount of training data

Core Design Contradiction:

Measurement precisionVSQuantity of substance

Solution Approach 1:

The patent transforms the objective variable from absolute blood pressure values (wide range: 80-200 mmHg) to measurement errors (narrow range: approximately ±10 mmHg). This parameter transformation reduces the variable range by about one-tenth, allowing the machine learning model to achieve high accuracy with significantly fewer training data points. The correction model learns to predict small error corrections rather than entire blood pressure values, improving data efficiency.

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If noise suppression techniques are applied to improve measurement accuracy, then measurement precision is improved, but device complexity increases

Engineering Contradiction:

Improveblood pressure measurement accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces a correction model as an intermediary component that processes the relationship between oscillometric measurements and actual blood pressure values. This mediator learns from training data to compensate for noise and measurement errors, effectively suppressing noise influence without requiring complex hardware modifications or multiple sensors. The correction model acts as a software-based intermediary that simplifies the overall system architecture while improving accuracy.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentEP4691355A1Sphygmomanometer, blood pressure measurement method, blood pressure measurement program, learning model construction method, and learning model construction program

Publication Date: 2026.02.11 OMRON CORP

Figure 1
Figure 2
Figure 3

AI summary

The sphygmomanometer includes: a cuff; a control unit that controls pressure applied to the arm by the cuff; a detection unit that detects cuff pressure; a measurement unit that measures blood pressure of the measurement subject by an oscillometric method by using a time-series change in the cuff pressure; a correction model, for multiple subjects, constructed by machine learning using information of a waveform related to the time-series change in the cuff pressure as an explanatory variable and using an error of blood pressure measured by the measurement unit with respect to blood pressure adopted as a true value as an objective variable; a correction unit that corrects the blood pressure based on an error output by the correction model by inputting the information of the waveform to the correction model; and an output unit that outputs the blood pressure corrected by the correction unit.