IP Library Granted Patent US 12,478,331
Granted Patent B2
US 12,478,331 · App. 17/464,456 · Granted Nov 25, 2025

Glucose alert prediction horizon modification

Inventors: Lauren Hruby Jepson (San Diego, CA); Sarah Kate Pickus (Henderson, NV); Joost van der Linden (San Diego, CA)
Assignee: Dexcom, Inc.
A61B5/7275A61B5/14532A61B5/7267A61B5/746G16H40/67G16H50/30A61B5/6833A61B2560/0487
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 12,478,331
App. No.
17/464,456
Granted
Nov 25, 2025
Kind
B2
Abstract

Data describing glucose measurements is received from a continuous glucose monitoring (CGM) system worn by a user and predicted glucose values during a future time period are generated for the user based on the data. A determination is made that at least one of the predicted glucose values satisfies a threshold value for an alert, which is associated with a prediction horizon that defines an amount of time prior to satisfaction of the threshold value for communicating the alert to the user. Output of the alert is caused responsive to determining that the at least one predicted glucose value satisfies the threshold value for the alert within the prediction horizon, relative to a current time. The prediction horizon is modified based on a user response to the alert. Output of a subsequent instance of the alert is caused based on the modified prediction horizon.

Claims (50)

1 . A method comprising:

determining that a first at least one glucose value predicted by a continuous glucose monitoring (CGM) system satisfies a threshold value for an alert, wherein the determining is performed according to a prediction horizon setting of the CGM system, the prediction horizon setting defining how far into a future time period predicted glucose values are considered relative to the threshold value;

causing output of the alert in a user interface of a computing device responsive to the determining that the first at least one glucose value satisfies the threshold value for the alert,

receiving feedback data including (1) an indication from a user that the user performed an intervening action in response to the output alert, and (2) an indication that a current glucose measurement for the user satisfied the threshold value for the alert before the intervening action was performed;

extending the prediction horizon setting of the CGM system based on the feedback data;

determining that a second at least one glucose value predicted by the CGM system satisfies the threshold value for the alert within the extended prediction horizon setting; and

causing output of a subsequent instance of the alert in the user interface responsive to the determining that the second at least one glucose value satisfies the threshold value for the alert within the extended prediction horizon setting.

2 . The method as described in claim 1 , further comprising causing output of a feedback prompt in the user interface requesting feedback regarding whether the alert was helpful to the user, wherein the indication from the user includes an interaction with the feedback prompt.

3 . The method as described in claim 1 , wherein the feedback data comprises a user indication of an adequacy of an advance warning time for the output of the alert.

4 . The method as described in claim 1 , further comprising withholding output of an additional subsequent instance of the alert based on a determination that the subsequent instance of the alert is a nuisance alert.

5 . The method as described in claim 1 , wherein:

the causing output of the alert is performed according to a threshold level of confidence that is compared to a confidence level for glucose values predicted by the CGM system to determine whether to generate the alert;

the method further comprises modifying the threshold level of confidence based on the feedback data; and

the causing output of the subsequent instance of the alert is performed according to the modified threshold level of confidence.

6 . A system comprising:

one or more processors; and

a computer-readable storage medium storing instructions that are executable by the one or more processors to perform operations comprising:

determining that a first at least one glucose value predicted by a continuous glucose monitoring (CGM) system satisfies a threshold value for an alert, wherein the determining is performed according to a prediction horizon setting of the CGM system, the prediction horizon setting defining how far into a future time period predicted glucose values are considered relative to the threshold value;

causing output of the alert in a user interface of a computing device responsive to the determining that the first at least one glucose value satisfies the threshold value for the alert,

receiving feedback data including (1) an indication from a user that the user performed an intervening action in response to the output alert, and (2) an indication that a current glucose measurement for the user satisfied the threshold value for the alert before the intervening action was performed;

extending the prediction horizon setting of the CGM system based on the feedback data;

determining that a second at least one glucose value predicted by the CGM system satisfies the threshold value for the alert within the extended prediction horizon setting; and

causing output of a subsequent instance of the alert in the user interface responsive to the determining that the second at least one glucose value satisfies the threshold value for the alert within the extended prediction horizon setting.

7 . The system as described in claim 6 , the operations further comprising causing output of a feedback prompt in the user interface requesting feedback regarding whether the alert was helpful to the user, wherein the indication from the user includes an interaction with the feedback prompt.

8 . The system as described in claim 6 , wherein the feedback data comprises a user indication of an adequacy of an advance warning time for the output of the alert.

9 . The system as described in claim 6 , the operations further comprising withholding output of an additional subsequent instance of the alert based on a determination that the subsequent instance of the alert is a nuisance alert.

10 . The system as described in claim 6 , wherein:

the causing output of the alert is performed according to a threshold level of confidence that is compared to a confidence level for glucose values predicted by the CGM system to determine whether to generate the alert;

the operations further comprise modifying the threshold level of confidence based on the feedback data; and

the causing output of the subsequent instance of the alert is performed according to the modified threshold level of confidence.

11 . One or more computer-readable storage media storing instructions that are executable by a computing device to perform operations comprising:

determining that a first at least one glucose value predicted by a continuous glucose monitoring (CGM) system satisfies a threshold value for an alert, wherein the determining is performed according to a prediction horizon setting of the CGM system, the prediction horizon setting defining how far into a future time period predicted glucose values are considered relative to the threshold value;

causing output of the alert in a user interface of a computing device responsive to the determining that the first at least one glucose value satisfies the threshold value for the alert,

receiving feedback data including (1) an indication from a user that the user performed an intervening action in response to the output alert, and (2) an indication that a current glucose measurement for the user satisfied the threshold value for the alert before the intervening action was performed;

extending the prediction horizon setting of the CGM system based on the feedback data;

determining that a second at least one glucose value predicted by the CGM system satisfies the threshold value for the alert within the extended prediction horizon setting; and

causing output of a subsequent instance of the alert in the user interface responsive to the determining that the second at least one glucose value satisfies the threshold value for the alert within the extended prediction horizon setting.

12 . The one or more computer-readable storage media as described in claim 11 , the operations further comprising causing output of a feedback prompt in the user interface requesting feedback regarding whether the alert was helpful to the user, wherein the indication from the user includes an interaction with the feedback prompt.

13 . The one or more computer-readable storage media as described in claim 11 , wherein the feedback data comprises a user indication of an adequacy of an advance warning time for the output of the alert.

14 . The one or more computer-readable storage media as described in claim 11 , wherein:

the causing output of the alert is performed according to a threshold level of confidence that is compared to a confidence level for glucose values predicted by the CGM system to determine whether to generate the alert;

the operations further comprise modifying the threshold level of confidence based on the feedback data; and

the causing output of the subsequent instance of the alert is performed according to the modified threshold level of confidence.

15 . An apparatus comprising:

determining means for determining that a first at least one glucose value predicted by a continuous glucose monitoring (CGM) system satisfies a threshold value for an alert, wherein the determining is performed according to a prediction horizon setting of the CGM system, the prediction horizon setting defining how far into a future time period predicted glucose values are considered relative to the threshold value;

alert means for causing output of the alert in a user interface of a computing device responsive to the determining that the first at least one glucose value satisfies the threshold value for the alert;

receiving means for receiving feedback data including (1) an indication from a user that the user performed an intervening action in response to the output alert, and (2) an indication that a current glucose measurement for the user satisfied the threshold value for the alert before the intervening action was performed;

modifying means for extending the prediction horizon setting of the CGM system based on the feedback data;

the determining means being further configured to determine that a second at least one glucose value predicted by the CGM system satisfies the threshold value for the alert within the extended prediction horizon setting; and

the alert means being further configured to cause output of a subsequent instance of the alert in the user interface responsive to the determining that the second at least one glucose value satisfies the threshold value for the alert within the extended prediction horizon setting.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 23, 2021
From: JEPSON, LAUREN HRUBY; PICKUS, SARAH KATE; VAN DER LINDEN, JOOST
To: DEXCOM, INC.
Reel/Frame 058199/0854 →
Continuity (2)
Provisional Application 63074391 · Sep 3, 2020
Related Publication 20220061775A1 · Mar 3, 2022
References Cited (39)
US 11969267B2 · Jepson et al. · 2024 [cited by applicant]
US 20030208113A1 · Mault et al. · 2003 [cited by applicant]
US 20100298765A1 · Budiman et al. · 2010 [cited by applicant]
US 20110106011A1 · Cinar et al. · 2011 [cited by applicant]
US 20110124992A1 · Brauker et al. · 2011 [cited by applicant]
US 20110225112A1 · Cameron et al. · 2011 [cited by applicant]
US 20130085679A1 · Budiman · 2013 [cited by examiner]
US 20140012511A1 · Mensinger · 2014 [cited by examiner]
US 20140073892A1 · Randloev et al. · 2014 [cited by applicant]
US 20140118166A1 · Hampapuram et al. · 2014 [cited by applicant]
US 20140121488A1 · Budiman · 2014 [cited by examiner]
US 20150120317A1 · Mayou et al. · 2015 [cited by applicant]
US 20160361028A1 · Sparacino et al. · 2016 [cited by applicant]
US 20170049386A1 · Abraham et al. · 2017 [cited by applicant]
US 20170053552A1 · Zhong · 2017 [cited by examiner]
US 20170311904A1 · Davis et al. · 2017 [cited by applicant]
US 20180256095A1 · Arnold · 2018 [cited by examiner]
US 20180277246A1 · Zhong · 2018 [cited by examiner]
US 20180279911A1 · Lucisano · 2018 [cited by examiner]
US 20180353112A1 · Dassau · 2018 [cited by examiner]
US 20190066831A1 · Mairs · 2019 [cited by examiner]
US 20190252079A1 · Constantin · 2019 [cited by examiner]
US 20200197606A1 · Doron et al. · 2020 [cited by applicant]
US 20200375549A1 · Wexler · 2020 [cited by examiner]
US 20210050085A1 · Hayter · 2021 [cited by examiner]
US 20220061774A1 · Jepson et al. · 2022 [cited by applicant]
EP 4208078A1 · 2023 [cited by applicant]
JP 2016502420A · 2016 [cited by applicant]
JP 2019525276A · 2019 [cited by applicant]
JP 2020527085A · 2020 [cited by applicant]
WO 2007116226A2 · 2007 [cited by applicant]
WO 2014070456A1 · 2014 [cited by applicant]
WO 2022051411A1 · 2022 [cited by applicant]
International Search Report and Written Opinion for Application No.PCT/US2021/048733, mailed Dec. 7, 2021, 27 pages. [cited by applicant]
Palerm C.C et al., “Hypoglycemia Detection and Prediction Using Continuous Glucose Monitoring—A Study on Hypoglycemic Clamp Data,” Journal of Diabetes Sciences and Technology, Sep. 2007, vol. 1(5), pp. 624-629. [cited by applicant]
Li K., et al., “GluNet: A Deep Learning Framework for Accurate Glucose Forecasting,” IEEE Journal of Biomedical and Health Informatics, Jul. 27, 2019 [Retrieved on Feb. 4, 2020], vol. 24, No. 02, XP011770212, ISSN: 2168… [cited by applicant]
Li N., et al., “Chaotic Time Series Analysis Approach for Prediction Blood Glucose Concentration Based on Echo State Networks,” 2018 Chinese Control and Decision Conference (CCDC), Jun. 9, 2018 [Retrieved on Jul. 6, 201… [cited by applicant]
Medtronic Minimed, “Guardian REAL-Time Continuous Glucose Monitoring System User Guide,” Medtronic, Dec. 31, 2006, 184 pages. [cited by applicant]
Palerm C.C., et al., “Issues on Hypoglycemia Prediction and Deduction,” IEEE 30th Annual Northeast Bioengineering Conference, 2004. Proceedings of the, Apr. 17, 2004, XP010706879, DOI: 10.1109/NEBC.2004.1300003, ISBN: 9… [cited by applicant]