Individualized Unit Spectra for Non-Invasive Blood Glucose Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Invasive methods for measuring blood glucose levels, such as finger pricking, cause pain and inconvenience and increase the risk of infections, while non-invasive methods face challenges in accurately estimating biological components due to interference from tissue heterogeneity and patient-to-patient variation.
Innovation Solution
An apparatus and method that obtains individualized unit spectra by processing first and second biological spectra using principal component analysis (PCA), independent component analysis (ICA), non-negative matrix factorization (NMF), and auto-encoding (AE), and selects candidate spectra based on similarity thresholds to estimate biological components like blood glucose, cholesterol, and skin components.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If invasive finger pricking method is used to measure blood glucose, then measurement reliability is improved, but patient comfort and safety deteriorate due to pain, inconvenience, and infection risk
Solution Approach 1:
The patent replaces the mechanical invasive finger pricking method with an optical spectroscopic system that uses light to measure blood glucose levels through tissue. The spectrometer captures spectral information from the tissue without physical penetration, eliminating pain and infection risk while maintaining measurement capability through optical absorption and scattering properties of blood components
2Object-affected harmful factors
If non-invasive spectroscopic method is used to measure blood glucose, then patient comfort is improved, but measurement precision deteriorates due to tissue heterogeneity and patient-to-patient variation
Solution Approach 1:
The patent transforms the complex biological spectrum into a simplified parameter space using dimensionality reduction techniques. By converting spectral data into principal components or auto-encoding representations, the system extracts key features that capture blood glucose information while filtering out variations due to tissue heterogeneity and individual differences, thereby improving measurement precision
Solution Approach 2:
The patent introduces intermediate processing steps including basis set correction and calibration models that act as mediators between the raw spectral data and the final blood glucose measurement. These intermediaries correct for tissue heterogeneity and patient-to-patient variations by comparing spectral features against reference databases and applying transformation algorithms that isolate glucose-specific signals
3Reliability
If basis set correction is applied to reduce tissue heterogeneity interference, then measurement reliability is improved, but device complexity increases due to multiple processing steps
Solution Approach 1:
The patent performs preliminary correction of tissue heterogeneity effects during the calibration phase by creating patient-specific basis sets from initial spectral measurements. These pre-computed correction factors are then applied automatically during subsequent measurements, improving reliability without requiring complex real-time processing during actual blood glucose monitoring
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, non-invasive estimation of biological components by reducing interference and personalizing the measurement to individual optical characteristics, improving measurement reliability and comfort.
Implementation Method 1
emits light onto skin and by receiving light reflected or scattered from the skin
Implementation Method 2
extracting at least one candidate spectrum from the first biological spectrum and the second biological spectrum based on principal component analysis
Implementation Method 3
research has been conducted on non-invasive measurements of blood glucose by using a spectrometer
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A apparatus for obtaining an individualized unit spectrum includes: a spectrum obtainer configured to obtain a first biological spectrum from a subject at a first measurement time, and obtain a second biological spectrum from the subject at a second measurement time; and a processor configured to extract the individualized unit spectrum from the first biological spectrum and the second biological spectrum, based on a predetermined unit spectrum of a target component.