Wearable HbA1c Sensing Using Multi-Wavelength PPG and ML
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for measuring glycated hemoglobin (HbA1c) are invasive, costly, and not suitable for continuous monitoring, with challenges including signal interference from skin reflection and overlapping absorption spectra of different hemoglobin types, leading to inaccurate and inconvenient measurements.
Innovation Solution
A wearable device using multiple radiation sources and detectors at varying wavelengths, combined with a pre-trained machine learning model, to accurately measure glycated hemoglobin levels by filtering artifacts and normalizing data at isobestic points, enabling non-invasive and continuous monitoring.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional spectrometers are used for HbA1c measurement, then measurement accuracy is improved, but device bulkiness and cost increase
Solution Approach 1:
The patent segments the spectral measurement task into multiple discrete wavelength channels (at least three different wavelengths) that can be measured sequentially rather than simultaneously. This allows using simpler, smaller detectors for each wavelength band rather than requiring a full conventional spectrometer, thereby reducing device bulkiness while maintaining measurement capability through multi-wavelength discrimination of hemoglobin species.
Solution Approach 2:
The patent employs periodic action by sequentially switching between different wavelength measurement channels during a measurement cycle. Instead of using all wavelengths simultaneously as in conventional spectrometers, the system periodically activates different wavelength pairs (e.g., green and red channels) to collect spectral data over time, enabling accurate HbA1c measurement with simpler hardware.
2Measurement precision
If multi-wavelength measurement is implemented, then HbA1c measurement accuracy is improved, but signal interference from skin reflection and overlapping absorption spectra worsens
Solution Approach 1:
The patent introduces an intermediary processing step involving a trained machine learning model that acts as a mediator between the raw multi-wavelength optical signals and the final HbA1c concentration value. This model processes the complex signals containing skin reflection and overlapping absorption artifacts, separating the relevant hemoglobin absorption information from interfering signals through pattern recognition trained on reference datasets.
Solution Approach 2:
The patent utilizes parameter changes by measuring at multiple discrete wavelength points across the visible spectrum and using these spectral parameter variations to differentiate between oxyhemoglobin, deoxyhemoglobin, and glycated hemoglobin. The system analyzes how absorption characteristics change with wavelength to resolve overlapping spectra and extract accurate HbA1c information despite interference.
3Measurement precision
If invasive electrochemical sensors are used, then glucose level measurement is achieved, but user convenience and continuous monitoring capability deteriorate
Solution Approach 1:
The patent replaces the mechanical/invasive approach of electrochemical sensors requiring skin penetration with an optical measurement system that uses non-invasive light absorption through the skin. By substituting mechanical contact with optical fields, the system achieves glucose and HbA1c measurement without breaking the skin, dramatically improving user convenience and enabling continuous monitoring.
Solution Approach 2:
The patent implements universality by designing a single optical device capable of measuring multiple parameters including glucose concentration and glycated hemoglobin levels using the same hardware platform. The multi-wavelength optical system can simultaneously or sequentially extract information about different blood components, providing versatile health monitoring functionality without requiring multiple separate devices or invasive procedures.
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 device provides rapid, easy-to-use, and accurate glycated hemoglobin measurements suitable for non-professional use, suitable for continuous monitoring and reducing the need for laboratory equipment.
Implementation Method 1
at least three radiation sources configured to irradiate biological tissues of a user with radiation of at least three different wavelengths
Implementation Method 2
the visible, infrared (IR) and near IR spectroscopy is the most promising technique
Implementation Method 3
form, from the detected PPG signals, a dataset including a time series of values of the PPG signals relative to the at least three different wavelengths and relative to lengths of the measurement channels, and which defines an absorption of the PPG signals by the biological tissues of the user
Implementation Method 4
at least two radiation detectors, each of the at least two radiation detectors being configured to detect photoplethysmographic (PPG) signals representing the radiation of the at least three different wavelengths backscattered by the biological tissues
Data Source
AI summary
A wearable device for determining glycated hemoglobin level, includes at least three radiation sources; at least two radiation detectors configured to detect photoplethysmographic (PPG) signals of the at least three different wavelengths backscattered by the biological tissues; and a processor configured to: activate the radiation sources and the radiation detectors in pairs of measurement channels for the PPG signals; sequentially detect the PPG signals through each of the measurement channels; form, from the detected PPG signals, a dataset representing a time series of absorption of the PPG signals by the biological tissues of the user; generate a pre-processed dataset by carrying out a pre-processing of the dataset; and determine a glycated hemoglobin level based on the pre-processed dataset by a pre-trained machine learning model.


