Retrospective sensor systems, devices, and methods

Patent metadata

Field	Value
Publication number	US-2023360799-A1
Application number	US-202318324820-A
Country	US
Kind code	A1
Filing date	May 26, 2023
Priority date	Dec 28, 2015
Publication date	Nov 9, 2023
Grant date	—

Abstract

A method for retrospective calibration of a glucose sensor uses stored values of measured working electrode current (Isig) to calculate a final sensor glucose (SG) value retrospectively. The Isig values may be preprocessed, discrete wavelet decomposition applied. At least one machine learning model, such as, e.g., Genetic Programing (GP) and Regression Decision Tree (DT), may be used to calculate SG values based on the Isig values and the discrete wavelet decomposition. Other inputs may include, e.g., counter electrode voltage (Vcntr) and Electrochemical Impedance Spectroscopy (EIS) data. A plurality of machine learning models may be used to generate respective SG values, which are then fused to generate a fused SG. Fused SG values may be filtered to smooth the data, and blanked if necessary.

First claim

What is claimed is:

1 . A method for retrospective calibration of a glucose sensor for measuring a level of glucose in a body of a user, the glucose sensor including physical sensor electronics, a microcontroller, a recorder, and a working electrode, the method comprising:
measuring, by the physical sensor electronics, an electrode current (Isig) for the working electrode; storing a plurality of Isig values for the working electrode in the recorder; retrieving the plurality of Isig values from the recorder; preprocessing the retrieved plurality of Isig values by the microcontroller; decomposing the preprocessed plurality of Isig values using discrete wavelet decomposition; and using at least one machine learning model to calculate, by the microcontroller, a final sensor glucose (SG) value based on the plurality of Isig values and the discrete wavelet decomposition.

2 . The method of claim 1 , wherein the at least one machine learning model is one of genetic programming and regression decision tree.

3 . The method of claim 1 , wherein the at least one machine learning model is a neural network.

4 . The method of claim 1 , wherein a first sensor glucose value is calculated by using genetic programming, and a second sensor glucose value is calculated by using regression decision tree.

5 . The method of claim 4 , further including fusing said first and second sensor glucose values to obtain a fused SG value, wherein the final SG value is determined based on the fused SG value.

6 . The method of claim 5 , further including performing an electrochemical impedance spectroscopy (EIS) procedure for the working electrode to obtain a plurality of values of an EIS-based parameter for the working electrode, wherein the fused SG is further calculated based on the plurality of values of the EIS-based parameter.

7 . The method of claim 6 , wherein the EIS-based parameter is imaginary impedance.

8 . The method of claim 6 , wherein the EIS-based parameter is real impedance.

9 . The method of claim 6 , further including smoothing the plurality of values of the EIS-based parameter prior to calculating the fused SG value.

10 . The method of claim 6 , wherein calculation of the fused SG value is repeated periodically to generate a plurality of fused SG values over time.

11 . The method of claim 6 , wherein calculation of the fused SG value is repeated continuously to generate a stream of fused SG values over time.

12 . The method of claim 11 , further including smoothing one or more segments of the stream of fused SG values.

13 . The method of claim 12 , wherein the one or more segments are smoothed with a low-pass filter.

14 . The method of claim 11 , further including blanking one or more portions of the stream of fused SG values.

15 . The method of claim 14 , wherein the blanking is based on a level of noise in the stream of fused SG values.

16 . The method of claim 14 , wherein the blanking is based on respective values of at least one of Isig, a counter electrode voltage (Vcntr), or the EIS-based parameter.

17 . The method of claim 11 , wherein the fused SG value and the final SG value are calculated in real time.

18 . The method of claim 1 , further including smoothing the preprocessed plurality of Isig values.

19 . The method of claim 18 , wherein the preprocessed plurality of Isig values are smoothed by using a polynomial model for local regression with weighted linear least squares.

20 . The method of claim 19 , further including calculating signal noise for the smoothed plurality of Isig values.

Assignees

• Medtronic Minimed Inc

Inventors

• Nogueira Keith
• Engel Taly G
• Grosman Benyamin
• Li Xiaolong
• Liang Bradley C
• Shah Rajiv
• Liu Mike C
• Tsai Andy Y
• Varsavsky Andrea
• Nishida Jeffrey

Classifications

• G16H50/20 Primary

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title

• A61B5/14532

  for measuring glucose, e.g. by tissue impedance measurement · CPC title

• A61B5/14735

  comprising an immobilised reagent · CPC title

• A61B5/1495

  Calibrating or testing of in-vivo probes · CPC title

• G06N3/126

  Evolutionary algorithms, e.g. genetic algorithms or genetic programming · CPC title