Vein-Segmented Spectral Training for Accurate Analyte Testing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current non-invasive analyte testing methods, particularly for blood glucose, suffer from inaccuracies due to the significant impact of non-analyte components in spectral data, leading to discomfort and inefficiencies in traditional optical testing.

Innovation Solution

A method and system utilizing a convolutional neural network model trained with spectral data from distinct areas of the skin, such as veins and non-veins, to differentiate and exclude non-analyte influences, combined with fluorescence spectroscopy for accurate analyte concentration measurement.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If traditional optical testing methods are used for non-invasive analyte testing, then testing can be performed without invasion, but measurement precision deteriorates due to significant impact of non-analyte components in spectral data

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

Solution Approach 1:

The patent divides the spectral data acquisition process into multiple distinct areas (vein area and non-vein area) and collects spectral data from each area separately. This segmentation allows the system to differentiate between signals from the analyte (in veins) and non-analyte components (in non-vein areas), thereby improving measurement precision while maintaining non-invasive operation.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent extracts and removes the influence of non-analyte components from the spectral data by comparing and subtracting the spectral characteristics obtained from non-vein areas from those obtained from vein areas. This extraction process eliminates interfering signals from non-analyte components, significantly improving the accuracy of analyte concentration measurement.

Inventive Principle:
Principle #2Taking out (Extraction)

2Measurement precision

If spectral data from multiple areas is collected and processed, then non-analyte interference is reduced, but device complexity increases

Engineering Contradiction:
Improvetesting accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent employs a single spectral acquisition device that performs multiple functions: collecting spectral data from both vein and non-vein areas, processing the data to eliminate non-analyte interference, and providing accurate analyte concentration measurements. This multi-functional approach improves testing accuracy without proportionally increasing device complexity.

Inventive Principle:
Principle #6Universality (Multi-functionality)

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 enhances testing accuracy by reducing non-analyte interference, enabling non-invasive, real-time, and cost-effective analyte testing with improved comfort and precision.

Implementation Method 1

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

Methodology Applied
Scientific EffectReflection: Reflection

Implementation Method 2

obtaining spectral data that indicate uneven distribution of a reflection signal or an excitation signal generated by an analyte when irradiated by light

Methodology Applied
Scientific EffectFluorescence: Fluorescence

Data Source

PatentEP4682845A1Model training method and system for analyte testing, medium, and device
Publication Date: 2026.01.21 SENSURA PTE LTD
  • EP4682845A1 patent drawingFigure 1~2
  • EP4682845A1 patent drawingFigure 3~4
  • EP4682845A1 patent drawingFigure 5~6

AI summary

The present invention provides a model training method and system for analyte testing, a medium, and a device which relate to the field of optical analysis. The method includes: data obtaining: obtaining spectral data that indicate uneven distribution of a reflection signal or an excitation signal generated by an analyte when irradiated by light, and obtaining a true test result of the analyte in a same time period; and model training: using the obtained spectral data as an input of the testing model, using the true test result as an output of the testing model, and training the testing model. According to this application, the obtained spectral data can be prevented from being affected by the influence of a non-analyte, improving the accuracy of the testing model.