IP Library Granted Patent US 12,626,819
Granted Patent B2
US 12,626,819 · App. 17/163,186 · Granted May 12, 2026

Machine learning models for detecting outliers and erroneous sensor use conditions and correcting, blanking, or terminating glucose sensors

Inventors: Elaine Gee (Windsor, CA); Jeffrey Nishida (Chicago, IL); Peter Ajemba (Canyon Country, CA); Keith Nogueira (Mission Hills, CA); Andrea Varsavsky (Santa Monica, CA)
Assignee: MEDTRONIC MINIMED, INC.
G16H50/20G06N20/00G16H40/63
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,626,819
App. No.
17/163,186
Granted
May 12, 2026
Kind
B2
Abstract

Techniques for improving continuous glucose monitoring (“CGM”) are described herein. In some embodiments, the techniques involve obtaining sensor data; applying, to the sensor data, a machine learning model trained to identify sensor data error patterns; and detecting an erroneous sensor use condition based on output of the machine learning model indicating an error pattern identified in the sensor data.

Claims (60)

1 . A system comprising:

one or more processors; and

one or more processor-readable media storing instructions which, when executed by the one or more processors, cause performance of:

obtaining sensor data from a glucose sensor inserted into subcutaneous tissue of a user;

identifying a sensor data error pattern in real time;

identifying an erroneous sensor use condition from two or more different erroneous sensor use conditions that each could cause the sensor data error pattern using a machine learning model;

in response to identifying the erroneous sensor use condition, predicting, using the machine learning model, a resolution from a plurality of possible resolutions that is most effective for resolving the erroneous sensor use condition, wherein the machine learning model was trained with training data comprising pairs of erroneous sensor use conditions and corresponding resolutions, wherein predicting the resolution from the plurality of possible resolutions comprises identifying a possible resolution that is most effective for resolving the erroneous sensor use condition among the plurality of possible resolutions as the predicted resolution;

causing implementation of the resolution;

causing delivery of insulin to the user by an insulin delivery device based on the sensor data manipulated by the implementation of the resolution; and

updating a configuration of the machine learning model based on the predicted resolution, an assessment of the predicted resolution, and reference feedback information, wherein the updated configuration is used for future predictions.

2 . The system of claim 1 , wherein the one or more processor-readable media further store instructions which, when executed by the one or more processors, cause performance of:

blanking display of the sensor data in response to identifying the sensor data error pattern by the machine learning model.

3 . The system of claim 1 , wherein the one or more processor-readable media further store instructions which, when executed by the one or more processors, cause performance of:

generating an alert informing of the erroneous sensor use condition in response to identifying the erroneous sensor use condition using the machine learning model.

4 . The system of claim 1 , wherein the implementation of the resolution comprises:

implementing the resolution by manipulating the sensor data via a user interface of a sensor device.

5 . The system of claim 1 , wherein:

the sensor data includes impedance spectroscopy signals measured at a plurality of signal frequencies using the glucose sensor; and

applying the machine learning model comprises generating, from the sensor data that includes the impedance spectroscopy signals, a multi-dimensional feature input to the machine learning model.

6 . The system of claim 1 , wherein the one or more processor-readable media further store instructions which, when executed by the one or more processors, cause performance of:

obtaining input indicating context information relating to the sensor data; and

applying the machine learning model to the context information relating to the sensor data, wherein outputs of the machine learning model are further based on the context information relating to the sensor data.

7 . The system of claim 6 , wherein the context information relating to the sensor data includes historic information relating to the sensor data over a time period.

8 . The system of claim 1 , wherein the machine learning model is trained based on clinical data on the erroneous sensor use condition.

9 . A processor-implemented method comprising:

obtaining sensor data from a glucose sensor inserted into subcutaneous tissue of a user;

identifying a sensor data error pattern in real time;

identifying an erroneous sensor use condition from two or more different erroneous sensor use conditions that each could cause the sensor data error pattern using a machine learning model;

in response to identifying the erroneous sensor use condition, predicting, using the machine learning model, a resolution from a plurality of possible resolutions that is most effective for resolving the erroneous sensor use condition, wherein the machine learning model was trained with training data comprising pairs of erroneous sensor use conditions and corresponding resolutions, wherein predicting the resolution from the plurality of possible resolutions comprises identifying a possible resolution that is most effective for resolving the erroneous sensor use condition among the plurality of possible resolutions as the predicted resolution;

causing implementation of the resolution;

causing delivery of insulin to the user by an insulin delivery device based on the sensor data manipulated by the implementation of the resolution; and

updating a configuration of the machine learning model based on the predicted resolution, an assessment of the predicted resolution, and reference feedback information, wherein the updated configuration is used for future predictions.

10 . The processor-implemented method of claim 9 , wherein the resolution comprises at least one of:

adjusting a signal of the sensor data;

adding a filter to a signal of the sensor data,

adjusting a filter of a signal of the sensor data,

replacing a signal of the sensor data;

removing a signal from the sensor data; or

replacing the glucose sensor with a replacement glucose sensor.

11 . The processor-implemented method of claim 9 , further comprising generating an alert informing of the erroneous sensor use condition in response to identifying the erroneous sensor use condition using the machine learning model.

12 . The processor-implemented method of claim 9 , wherein the implementation of the resolution comprises implementing the resolution by manipulating the sensor data via a user interface of a sensor device.

13 . The processor-implemented method of claim 9 , wherein:

the sensor data includes impedance spectroscopy signals measured at a plurality of signal frequencies using the glucose sensor; and

applying the machine learning model comprises generating, from the sensor data that includes the impedance spectroscopy signals, a multi-dimensional feature input to the machine learning model.

14 . The processor-implemented method of claim 9 , further comprising:

obtaining input indicating context information relating to the sensor data; and

applying the machine learning model to the context information relating to the sensor data, wherein outputs of the machine learning model are further based on the context information relating to the sensor data.

15 . The processor-implemented method of claim 14 , wherein the context information relating to the sensor data includes historic information relating to the sensor data over a time period.

16 . The processor-implemented method of claim 9 , wherein the machine learning model is trained based on clinical data on the erroneous sensor use condition.

17 . A processor-implemented method comprising:

obtaining sensor data from a glucose sensor inserted into subcutaneous tissue of a user, wherein the glucose sensor includes a single working electrode;

identifying a sensor data error pattern in real time;

identifying an erroneous sensor use condition from two or more different erroneous sensor use conditions that each could cause the sensor data error pattern using a machine learning model;

in response to identifying the erroneous sensor use condition, predicting, using the machine learning model, a resolution from a plurality of possible resolutions that is most effective for resolving the erroneous sensor use condition, wherein the machine learning model was trained with training data comprising pairs of erroneous sensor use conditions and corresponding resolutions, wherein predicting the resolution from the plurality of possible resolutions comprises identifying a possible resolution that is most effective for resolving the erroneous sensor use condition among the plurality of possible resolutions as the predicted resolution;

causing implementation of the resolution;

causing delivery of insulin to the user by an insulin delivery device based on the sensor data manipulated by the implementation of the resolution; and

updating a configuration of the machine learning model based on the predicted resolution, an assessment of the predicted resolution, and reference feedback information, wherein the updated configuration is used for future predictions.

18 . The processor-implemented method of claim 17 , further comprising:

obtaining input indicating context information relating to the sensor data,

wherein the sensor data error pattern comprises a low signal error pattern, and wherein the context information comprises historic sensor data over a time period that is used to disambiguate between the two or more different erroneous sensor use conditions comprising temporary signal loss and sensitivity loss.

Assignments (2)
SECURITY INTEREST Recorded Jan 16, 2026
From: MEDTRONIC MINIMED, INC.; COMPANION MEDICAL, INC.
To: CITIBANK, N.A.
Reel/Frame 074394/0237 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 29, 2021
From: GEE, ELAINE; NISHIDA, JEFFREY; AJEMBA, PETER; NOGUEIRA, KEITH; VARSAVSKY, ANDREA
To: MEDTRONIC MINIMED, INC.
Reel/Frame 055086/0312 →
Continuity (2)
Continuation 17121624 · Dec 14, 2020
Related Publication 20220189631A1 · Jun 16, 2022
References Cited (105)
US 4562751A · Nason et al. · 1986 [cited by applicant]
US 4573994A · Fischell et al. · 1986 [cited by applicant]
US 4678408A · Nason et al. · 1987 [cited by applicant]
US 4685903A · Cable et al. · 1987 [cited by applicant]
US 4755173A · Konopka et al. · 1988 [cited by applicant]
US 5391250A · Cheney, II et al. · 1995 [cited by applicant]
US 5482473A · Lord et al. · 1996 [cited by applicant]
US 5485408A · Blomquist · 1996 [cited by applicant]
US 5522803A · Teissen-Simony · 1996 [cited by applicant]
US 5665065A · Colman et al. · 1997 [cited by applicant]
US 5800420A · Gross et al. · 1998 [cited by applicant]
US 5807375A · Gross et al. · 1998 [cited by applicant]
US 5925021A · Castellano et al. · 1999 [cited by applicant]
US 5954643A · Van Antwerp et al. · 1999 [cited by applicant]
US 6017328A · Fischell et al. · 2000 [cited by applicant]
US 6186982B1 · Gross et al. · 2001 [cited by applicant]
US 6246992B1 · Brown · 2001 [cited by applicant]
US 6248067B1 · Causey, III et al. · 2001 [cited by applicant]
US 6248093B1 · Moberg · 2001 [cited by applicant]
US 6355021B1 · Nielsen et al. · 2002 [cited by applicant]
US 6379301B1 · Worthington et al. · 2002 [cited by applicant]
US 6544212B2 · Galley et al. · 2003 [cited by applicant]
US 6558351B1 · Steil et al. · 2003 [cited by applicant]
US 6591876B2 · Safabash · 2003 [cited by applicant]
US 6641533B2 · Causey, III et al. · 2003 [cited by applicant]
US 6736797B1 · Larsen et al. · 2004 [cited by applicant]
US 6749587B2 · Flaherty · 2004 [cited by applicant]
US 6766183B2 · Walsh et al. · 2004 [cited by applicant]
US 6801420B2 · Talbot et al. · 2004 [cited by applicant]
US 6804544B2 · Van Antwerp et al. · 2004 [cited by applicant]
US 7003336B2 · Holker et al. · 2006 [cited by applicant]
US 7029444B2 · Shin et al. · 2006 [cited by applicant]
US 7066909B1 · Peter et al. · 2006 [cited by applicant]
US 7137964B2 · Flaherty · 2006 [cited by applicant]
US 7303549B2 · Flaherty et al. · 2007 [cited by applicant]
US 7399277B2 · Saidara et al. · 2008 [cited by applicant]
US 7442186B2 · Blomquist · 2008 [cited by applicant]
US 7602310B2 · Mann et al. · 2009 [cited by applicant]
US 7647237B2 · Malave et al. · 2010 [cited by applicant]
US 7699807B2 · Faust et al. · 2010 [cited by applicant]
US 7727148B2 · Talbot et al. · 2010 [cited by applicant]
US 7785313B2 · Mastrototaro · 2010 [cited by applicant]
US 7806886B2 · Kanderian, Jr. et al. · 2010 [cited by applicant]
US 7819843B2 · Mann et al. · 2010 [cited by applicant]
US 7828764B2 · Moberg et al. · 2010 [cited by applicant]
US 7879010B2 · Hunn et al. · 2011 [cited by applicant]
US 7890295B2 · Shin et al. · 2011 [cited by applicant]
US 7892206B2 · Moberg et al. · 2011 [cited by applicant]
US 7892748B2 · Norrild et al. · 2011 [cited by applicant]
US 7901394B2 · Ireland et al. · 2011 [cited by applicant]
US 7942844B2 · Moberg et al. · 2011 [cited by applicant]
US 7946985B2 · Mastrototaro et al. · 2011 [cited by applicant]
US 7955305B2 · Moberg et al. · 2011 [cited by applicant]
US 7963954B2 · Kavazov · 2011 [cited by applicant]
US 7977112B2 · Burke et al. · 2011 [cited by applicant]
US 7979259B2 · Brown · 2011 [cited by applicant]
US 7985330B2 · Wang et al. · 2011 [cited by applicant]
US 8024201B2 · Brown · 2011 [cited by applicant]
US 8100852B2 · Moberg et al. · 2012 [cited by applicant]
US 8114268B2 · Wang et al. · 2012 [cited by applicant]
US 8114269B2 · Cooper et al. · 2012 [cited by applicant]
US 8137314B2 · Mounce et al. · 2012 [cited by applicant]
US 8181849B2 · Bazargan et al. · 2012 [cited by applicant]
US 8182462B2 · Istoc et al. · 2012 [cited by applicant]
US 8192395B2 · Estes et al. · 2012 [cited by applicant]
US 8195265B2 · Goode, Jr. et al. · 2012 [cited by applicant]
US 8202250B2 · Stutz, Jr. · 2012 [cited by applicant]
US 8207859B2 · Enegren et al. · 2012 [cited by applicant]
US 8226615B2 · Bikovsky · 2012 [cited by applicant]
US 8257259B2 · Brauker et al. · 2012 [cited by applicant]
US 8267921B2 · Yodfat et al. · 2012 [cited by applicant]
US 8275437B2 · Brauker et al. · 2012 [cited by applicant]
US 8277415B2 · Mounce et al. · 2012 [cited by applicant]
US 8292849B2 · Bobroff et al. · 2012 [cited by applicant]
US 8298172B2 · Nielsen et al. · 2012 [cited by applicant]
US 8303572B2 · Adair et al. · 2012 [cited by applicant]
US 8305580B2 · Aasmul · 2012 [cited by applicant]
US 8308679B2 · Hanson et al. · 2012 [cited by applicant]
US 8313433B2 · Cohen et al. · 2012 [cited by applicant]
US 8318443B2 · Norrild et al. · 2012 [cited by applicant]
US 8323250B2 · Chong et al. · 2012 [cited by applicant]
US 8343092B2 · Rush et al. · 2013 [cited by applicant]
US 8352011B2 · Van Antwerp et al. · 2013 [cited by applicant]
US 8353829B2 · Say et al. · 2013 [cited by applicant]
US 20070123819A1 · Memoe et al. · 2007 [cited by applicant]
US 20090168832A1 · Bauerle · 2009 [cited by applicant]
US 20100160861A1 · Causey, III et al. · 2010 [cited by applicant]
US 20150351673A1 · Vanslyke · 2015 [cited by examiner]
US 20170185733A1 · Nogueira · 2017 [cited by examiner]
US 20170311897A1 · Faccioli · 2017 [cited by examiner]
US 20180185733A1 · King · 2018 [cited by applicant]
US 20190076066A1 · Ajemba et al. · 2019 [cited by applicant]
US 20210110313A1 · Jones · 2021 [cited by applicant]
US 20220189630A1 · Gee et al. · 2022 [cited by applicant]
US 20220254492A1 · Armitage · 2022 [cited by examiner]
CN 105403705A · 2016 [cited by applicant]
CN 108937954A · 2018 [cited by applicant]
CN 110448306A · 2019 [cited by applicant]
CN 110785816A · 2020 [cited by applicant]
Code of Federal Regulations: A point in time eCFR system, Title 21, Chapter I, Subchapter H, Part 862, Subpart B (21 CFR 862.1355), pp. 1-3. URL: https://www.ecfr.gov/current/title-21/chapter-I/subchapter-H/part-862/sub… [cited by applicant]
Freckmann, G. et al., “Measures of Accuracy for Continuous Glucose Monitoring and Blood Glucose Monitoring Devices”, Journal of Diabetes Science and Technology, May 2019, vol. 13, No. 3, 575-583. DOI: 10.1177/1932296818… [cited by applicant]
Extended European Search Report issued in corresponding application EP 21212472.1 dated May 23, 2022 (8 pages). [cited by applicant]
U.S. Non-Final Office Action dated Apr. 3, 2024 in U.S. Appl. No. 17/121,624. [cited by applicant]
U.S. Final Office Action dated Oct. 22, 2024 in U.S. Appl. No. 17/121,624. [cited by applicant]
CN Office Action dated Nov. 12, 2025 in CN Application No. 202111520115.X, with English Translation. [cited by applicant]