Blood glucose estimation using near infrared light emitting diodes
Inventors
Matichuk, Bruce • Moore, Mike E.
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12446781-B2
Publication Date
2025-10-21
Expiration Date
Abstract
Near Infrared Spectroscopy is employed to non-invasively detect blood glucose concentrations, in a multi-sensing detection device. A multi-layered artificial neural network is used to assess these relationships of non-linear interference from human tissue, as well as differences among individuals, and accurately estimate blood glucose levels. Diffuse reflectance spectrum from the palm at six different wavelengths analyzed with a neural network, results in a correlation coefficient as high as 0.9216 when compared to a standard electrochemical glucose analysis test.
Core Innovation
The invention relates to a continuous non-invasive sensor system having a multi-sensing detection device for employing spectral related skin response data to determine a light signature from which a concentration of glucose being present in a tissue of a body of a wearer may be determined. The system includes an attachment structure formed as a patch having an inner portion and an outer portion with an adhesive to hold the patch against the wearer's skin, and a multi-sensing detection device retained within the inner portion and positioned proximate the skin when the patch is adhered to the body of the wearer.
The multi-sensing detection device includes a housing encasing a glucose sensor unit and having a top cover and a bottom cover with an opening positioned therein. The glucose sensor unit detects a skin characteristic response of one or more tissues due to a presence of glucose within the tissue, and uses a printed circuit board having a first and a second sensor array coupled therewith, where each sensor array includes photoemitters and photoreceivers that illuminate tissue below the opening and collect reflected light to generate return signal.
The first sensor array includes six photoemitters in the form of light emitting diodes configured for emitting first through sixth wavelengths, and the first photoreceiver detects light reflected back from the six photoemitters. The second sensor array includes three or four photoemitters in the form of light emitting diodes configured for emitting seventh through ninth wavelengths, and a second photoreceiver detects light reflected back from the second sensor array photoemitters.
The printed circuit board includes an analog to digital converter converting the return signal into digital signal data and a communications module for transmitting the digital signal data. A server system receives the digital signal data and includes a first processing module having a first processor that analyzes the digital signal data to produce light signature data, and a second processor that analyzes the light signature data to determine the concentration of glucose present in the tissue. The analysis employs diffuse reflectance spectrum analysis and may include a non-linear relationship based on changes of reflectance across a range of different wavelengths to determine an absorption response, and may further employ an Artificial Intelligence module and/or a multi-layer neural network to model non-linear, individual-specific relationships between light signature results data and glucose concentration, and may determine a wearer health trajectory and predict a future health state.
Claims Coverage
The independent claims are clm-00001 and clm-00012. Across these independent claims, the inventive features focus on a continuous non-invasive wearable patch with a multi-sensing detection device, diffuse reflectance spectrum analysis using multiple photoemitters and photoreceivers arranged on a printed circuit board, transmitting digital return signal data to a server system for light signature generation and glucose/analyte concentration determination, and server-side processing that includes analyzing skin response and using AI/ANN/ML for mapping to concentration.
Continuous non-invasive patch with multi-sensing detection device
A continuous non-invasive sensor system comprising an attachment structure formed as a patch with an adhesive to hold the patch against the wearer's skin, and a multi-sensing detection device retained within an inner portion of the patch and configured to be positioned proximate the skin when adhered, including a glucose sensor unit for detecting glucose present within tissue.
Multi-wavelength sensor arrays for diffuse reflectance return signals
A printed circuit board having a first and a second sensor array coupled therewith, each sensor array including photoemitters and photoreceivers configured to illuminate tissue below an opening and receive reflected light to generate return signal, where the first sensor array includes six photoemitters of six light emitting diode wavelengths detected by a first photoreceiver and the second sensor array includes three or four photoemitters of additional wavelengths detected by a second photoreceiver.
Server analysis producing light signature data and determining concentration
An analog to digital converter converting return signal to digital signal data and a communications module transmitting the digital signal data to a server system, where a first processor analyzes digital signal data to produce light signature data and a second processor analyzes the light signature data to determine the concentration of glucose present in the tissue.
ANN/AI mapping between light signature results data and concentration or trajectory
A server system including an Artificial Intelligence module configured to analyze digital signal data to produce light signature results data, and an ANN to map light signature results data to the concentration of an analyte; additionally, an artificial neural network may be used to determine a wearer's health trajectory and predict a future health state.
The independent claims cover a continuous non-invasive wearable patch system that directs multiple wavelengths into tissue, collects diffuse reflectance return signals via photoemitters and photoreceivers, converts and transmits digital signal data to a server, and determines glucose/analyte concentration using light signature analysis; optional claim elements include AI/ANN/ML mapping for determining concentration and predicting health trajectory.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?