Noninvasive Blood Analyte Estimation Using Beer-Lambert Inversion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Noninvasive blood monitoring has been challenging due to the difficulty in modeling light-particle interactions, particularly for glucose measurement, leading to noisy data and unreliable estimation of blood analytes.
Innovation Solution
The use of Beer-Lambert Inversion techniques to develop models that estimate blood analyte concentrations through non-invasive electromagnetic radiation, incorporating methods to extract pulsatile and non-pulsatile signal components, and employing Beer-Lambert inversion models trained with features like JMLS to improve prediction accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If noninvasive electromagnetic radiation monitoring is used to measure blood analytes, then continuous monitoring capability is improved, but signal accuracy deteriorates due to noisy data and difficulty in modeling light-particle interactions
Solution Approach 1:
The patent segments the electromagnetic radiation signal into distinct components: DC offset component, pulsatile signal component, and non-pulsatile blood component. By separating these components, the system can process each one independently, removing the noisy DC offset while preserving the useful pulsatile and blood signal information, thereby improving measurement accuracy from noisy data.
Solution Approach 2:
The patent extracts and removes the DC offset component from the signal, recognizing that this component contains mostly noise and irrelevant information. By taking out this harmful element, the remaining signal components (pulsatile and non-pulsatile blood signals) can be processed more accurately to estimate blood analyte concentrations.
2Measurement precision
If Beer-Lambert inversion models are trained with multiple wavelength features, then estimation accuracy for blood analytes is improved, but model complexity increases
Solution Approach 1:
The patent develops a universal Beer-Lambert inversion model that can estimate multiple different blood analytes (glucose, hemoglobin, oxygen saturation, etc.) using the same multi-wavelength electromagnetic radiation measurement system. The model uses a set of features from multiple wavelengths that work across different analyte types, reducing the need for separate specialized models for each analyte.
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 allows for precise estimation of blood analytes such as glucose, hemoglobin, and other biomarkers by accurately separating and processing signal components, enhancing the reliability of non-invasive blood monitoring.
Implementation Method 1
emission of a plurality of distinct wavelengths of electromagnetic radiation in certain wavelength ranges and detection of such radiation reflected from various biological features
Implementation Method 2
deriving distributional estimates for photon scattering and absorption behavior
Implementation Method 3
use Beer-Lambert Inversion techniques to train models and/or work in conjunction with trained models to provide better predictions and/or estimates for various blood analyte conditions
Data Source
AI summary
Methods and systems for estimating blood analyte conditions. In some methods, signal data may be received from a non-invasive blood monitor. The signal data may be used to train a model, which model may use a feature comprising at least two distinct electromagnetic radiation wavelengths, such as a Beer-Lambert inversion model. Following model training, signal data may be received from a non-invasive blood monitor using the at least two distinct electromagnetic radiation wavelengths. The trained model may then be used to estimate a blood analyte condition associated with the blood analyte, such as a concentration of the blood analyte.