US 11,723,560 B2
System and method for decision support
Alexandra Elena Constantin, San Jose, CA (US); Scott M. Belliveau, San Diego, CA (US); Naresh C. Bhavaraju, San Diego, CA (US); Jennifer Blackwell, San Diego, CA (US); Eric Cohen, San Diego, CA (US); Basab Dattaray, San Diego, CA (US); Anna Leigh Davis, Cardiff by the Sea, CA (US); Rian Draeger, San Francisco, CA (US); Arturo Garcia, Chula Vista, CA (US); John Michael Gray, San Diego, CA (US); Hari Hampapuram, Portland, OR (US); Nathaniel David Heintzman, San Diego, CA (US); Lauren Hruby Jepson, San Diego, CA (US); Matthew Lawrence Johnson, Solana Beach, CA (US); Apurv Ullas Kamath, San Diego, CA (US); Katherine Yerre Koehler, Solana Beach, CA (US); Phil Mayou, San Diego, CA (US); Patrick Wile McBride, San Diego, CA (US); Michael Robert Mensinger, San Diego, CA (US); Sumitaka Mikami, San Diego, CA (US); Andrew Attila Pal, San Diego, CA (US); Nicholas Polytaridis, San Diego, CA (US); Philip Thomas Pupa, San Diego, CA (US); Eli Reihman, San Diego, CA (US); Peter C. Simpson, Cardiff, CA (US); Tomas C. Walker, Henderson, NV (US); and Daniel Justin Wiedeback, Portland, OR (US)
Assigned to Dexcom, Inc., San Diego, CA (US)
Filed by DexCom, Inc., San Diego, CA (US)
Filed on Feb. 6, 2019, as Appl. No. 16/269,533.
Application 16/269,533 is a continuation of application No. 16/269,480, filed on Feb. 6, 2019.
Claims priority of provisional application 62/628,895, filed on Feb. 9, 2018.
Prior Publication US 2019/0252079 A1, Aug. 15, 2019
Int. Cl. A61B 5/145 (2006.01); G16H 70/20 (2018.01); A61B 5/00 (2006.01); G06N 20/00 (2019.01); G06N 5/045 (2023.01); A61B 5/11 (2006.01); A61B 5/01 (2006.01); A61B 5/0205 (2006.01); G16H 50/20 (2018.01); A61B 5/024 (2006.01); A61B 5/08 (2006.01)
CPC A61B 5/14532 (2013.01) [A61B 5/0022 (2013.01); A61B 5/01 (2013.01); A61B 5/02055 (2013.01); A61B 5/1118 (2013.01); A61B 5/486 (2013.01); A61B 5/4839 (2013.01); A61B 5/4866 (2013.01); A61B 5/7221 (2013.01); A61B 5/7275 (2013.01); A61B 5/7282 (2013.01); A61B 5/746 (2013.01); A61B 5/7475 (2013.01); G06N 5/045 (2013.01); G06N 20/00 (2019.01); G16H 70/20 (2018.01); A61B 5/024 (2013.01); A61B 5/0816 (2013.01); G16H 50/20 (2018.01)] 16 Claims
OG exemplary drawing
 
1. A system comprising:
a glucose concentration sensor configured to detect a host glucose concentration;
a communication circuit configured to receive the host glucose concentration from the glucose concentration sensor; and
a processor configured to:
receive host glucose concentration measurements from the communication circuit;
predict, using a machine learning model, a future occurrence of a host entering a second host state from a first host state, wherein the first host state is associated with a first glucose concentration profile and the second host state is associated with a second glucose concentration profile, wherein the machine learning model is trained using a training dataset including behavioral and physiological data associated with the host, wherein the behavioral and physiological data includes at least one of (i) heart rate data received from a heart rate sensor, (ii) respiration data received from a respiration sensor (iii) the host glucose concentration from the glucose concentration sensor, (iv) host motion data from a motion sensor, (v) posture data from a posture sensor, or (vi) acoustic data from an acoustic sensor, and wherein each of the first and second glucose concentration profiles corresponds to glucose levels and/or a glucose rate of change of the host over time in connection with a behavioral state or a physiological state of the host, wherein the first host state is a pre-sleep or a pre-exercise state, and wherein the second host state is a sleep or exercise state;
determine, during the pre-sleep or pre-exercise state, a guidance message based at least in part on the prediction of the future occurrence of the host entering the sleep or exercise state from the pre-sleep or pre-exercise state, respectively, the second glucose concentration profile associated with the sleep or exercise state, the behavioral and physiological data, and the physiological data including the host glucose concentration measurements; and
deliver, during the pre-sleep or pre-exercise state, the guidance message through a user interface.