US 12,433,511 B2
Systems, methods, and devices for biophysical modeling and response prediction
Parin Bhadrik Dalal, Palo Alto, CA (US); Salar Rahili, Menlo Park, CA (US); Solmaz Shariat Torbaghan, Burlingame, CA (US); Saransh Agarwal, Pittsburgh, PA (US); and Mehrdad Yazdani, Santa Clara, CA (US)
Assigned to JANUARY, INC., Menlo Park, CA (US)
Filed by January, Inc., Menlo Park, CA (US)
Filed on Feb. 7, 2020, as Appl. No. 16/785,436.
Application 16/785,436 is a continuation of application No. PCT/US2019/063788, filed on Nov. 27, 2019.
Claims priority of provisional application 62/773,117, filed on Nov. 29, 2018.
Claims priority of provisional application 62/773,134, filed on Nov. 29, 2018.
Claims priority of provisional application 62/773,125, filed on Nov. 29, 2018.
Prior Publication US 2020/0245913 A1, Aug. 6, 2020
Int. Cl. G16H 40/67 (2018.01); A61B 5/00 (2006.01); A61B 5/024 (2006.01); A61B 5/145 (2006.01); G06F 40/205 (2020.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01); G06N 3/088 (2023.01); G16H 10/60 (2018.01); G16H 20/60 (2018.01); G16H 50/20 (2018.01); G16H 50/50 (2018.01); G16H 50/70 (2018.01)
CPC A61B 5/14532 (2013.01) [A61B 5/0022 (2013.01); A61B 5/0024 (2013.01); A61B 5/024 (2013.01); A61B 5/6801 (2013.01); A61B 5/7275 (2013.01); G06F 40/205 (2020.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06N 3/088 (2013.01); G16H 10/60 (2018.01); G16H 20/60 (2018.01); G16H 40/67 (2018.01); G16H 50/20 (2018.01); G16H 50/50 (2018.01); G16H 50/70 (2018.01)] 16 Claims
OG exemplary drawing
 
1. A personalized glucose monitoring device for a test subject, comprising:
a heart rate monitor configured to obtain time-series heart rate data of the test subject over a period of time;
a continuous glucose monitor configured to obtain time-series blood glucose levels of the test subject over the period of time;
computer memory configured to store a set of training data comprising food source data for a set of training subjects and glucose levels responsive to the food source data; and
one or more computer processors operatively coupled to the computer memory, wherein the one or more computer processors are individually or collectively programmed to:
(i) train a starting glucose prediction model with the set of training data to predict blood glucose levels in response at least in part to food source data, the starting glucose regulation model comprising population-based insulin resistance parameters, wherein the starting glucose regulation model comprises an artificial neural network configured to analyze time-series input data, wherein the artificial neural network comprises (i) an input layer configured to receive a sequence of the time-series input data and (ii) and one or more hidden layers that are trained to maintain a state across time increments and capture dependencies in the sequence of the time-series input data;
(ii) obtain personalized glycemic response data of the test subject, wherein obtaining the personalized glycemic response data comprises obtaining the time-series heart rate data of the test subject from the heart rate monitor, and obtaining the time-series blood glucose levels of the test subject from the continuous glucose monitor;
(iii) update the starting glucose regulation model with the personalized glycemic response data of the test subject, wherein the updating comprises adjusting the population-based insulin resistance parameters, until convergence is achieved between a predicted glycemic response of the test subject and an actual glycemic response of the test subject, thereby producing a personalized glucose regulation model for the test subject;
(iv) generate a predicted blood glucose level for the test subject, using the personalized glucose regulation model for the test subject;
(v) automatically generate a message containing the predicted blood glucose level for the test subject whenever an updated predicted blood glucose level has been generated; and
(vi) transmit the message to all users of the personalized glucose monitoring device over a computer network in real time, so that each user has real-time access to up-to-date predicted blood glucose information for the test subject.