Spectral Analyte Testing Model for Non-Invasive Glucose Accuracy

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing non-invasive blood glucose testing methods using spectral data from blood vessels are inaccurate due to interference from skin and subcutaneous tissue spectral data, leading to unreliable results.

Innovation Solution

A method and system utilizing a convolutional neural network model that processes spectral data from distinct areas of the skin, such as those with and without blood vessels, to improve accuracy by excluding non-analyte interference, employing infrared and ultraviolet light for imaging and fluorescence spectroscopy to obtain precise analyte concentration.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If spectral data from blood vessel area is collected for non-invasive glucose testing, then non-invasive testing is achieved, but accuracy deteriorates due to interference from skin and subcutaneous tissue spectral data

Engineering Contradiction:
Improvenon-invasive testingVSAvoidtesting accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent divides the imaging area into multiple regions including blood vessel areas and non-blood vessel areas. By segmenting the spectral data collection into distinct regions, the system can separately analyze spectral characteristics of blood vessels while excluding interference from surrounding skin and subcutaneous tissues, thereby maintaining non-invasive testing while improving accuracy.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent extracts and isolates spectral data specifically from blood vessel areas by identifying and separating these regions from the overall imaging area. This extraction process removes interfering spectral data from skin and subcutaneous tissues, allowing the testing model to focus solely on relevant analyte signals while preserving the non-invasive nature of the test.

Inventive Principle:
Principle #2Taking out (Extraction)

2Quantity of substance

If traditional spectral analysis collects data from the entire imaging area, then comprehensive data is obtained, but interference from non-analyte components increases

Engineering Contradiction:
Improvespectral data volumeVSAvoidinterference from skin and subcutaneous tissue
Core Design Contradiction:
Quantity of substanceVSObject-generated harmful factors

Solution Approach 1:

The patent extracts only the relevant spectral data from blood vessel areas while discarding interfering data from skin and subcutaneous tissues. This selective extraction maintains sufficient spectral data volume for accurate analysis while eliminating harmful interference from non-analyte components.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent applies different data processing qualities to different regions: spectral data from blood vessel areas is collected and analyzed with high detail, while spectral data from skin and subcutaneous tissue areas is excluded or minimized. This local quality approach ensures comprehensive data coverage where needed while reducing interference from problematic regions.

Inventive Principle:
Principle #3Local quality

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 method achieves accurate, non-invasive glucose testing by distinguishing between skin and blood vessel spectral data, reducing interference and enhancing the model's output accuracy, enabling real-time, low-cost, and miniaturized testing.

Implementation Method 1

spectral data indicating an uneven distribution of a reflection signal or an excitation signal generated by the analyte when irradiated by light

Methodology Applied
Scientific EffectReflection: Reflection

Implementation Method 2

employing infrared and ultraviolet light for imaging and fluorescence spectroscopy to obtain precise analyte concentration

Methodology Applied
Scientific EffectFluorescence: Fluorescence

Data Source

PatentEP4681601A1Method and system for testing analyte based on testing model, medium, and device
Publication Date: 2026.01.21 SENSURA PTE LTD
  • EP4681601A1 patent drawingFigure 1~2
  • EP4681601A1 patent drawingFigure 3~4
  • EP4681601A1 patent drawingFigure 5~6

AI summary

The present invention relates to the field of optical analysis, and provides a method and a system for testing an analyte based on a testing model, a medium, and a device. The method includes: model input: obtaining an analyte testing model and providing an input amount to the analyte testing model; and model output: collecting an output amount of the analyte testing model, where the input amount includes: spectral data that indicate uneven distribution of a reflection signal or an excitation signal generated by the analyte when irradiated by light; and the output amount includes: a test result of the analyte, and the test result of the analyte includes information of the analyte correlated to the spectral data. In the present invention, the testing model is used to process input spectral data with interference to obtain an accurate output result, thereby improving the output accuracy of the model.