System, method and article for controlling the dispensing of insulin

• US 9,056,168 B2
• Filed: 08/30/2013
• Issued: 06/16/2015
• Est. Priority Date: 06/19/2006
• Status: Active Grant

• Current Assignee: DexCom Incorporated
• Original Assignee: Dose Safety
• Inventors: Kircher, Robert C. Jr., Mauseth, Richard S., Bishop, Jason N., Matheson, Donald P., Bhatia, Suray, Bilmes, Jeff A.
• Primary Examiner(s): LaBalle, Clayton E
• Assistant Examiner(s): Chang, Fang-Chi
• Application Number:
  US14/014,711
• Publication Number:
  US 20140031786A1
• Time in Patent Office: 655 Days
• Field of Search: 600/316
• US Class Current: 1/1
• CPC Class Codes: A61B 5/14532 for measuring glucose, e.g. by tissue impedance measurement
• CPC Class Codes: A61M 2230/005 Parameter used as control input for the apparatus
• CPC Class Codes: A61M 2230/201 Glucose concentration
• CPC Class Codes: A61M 5/1723 using feedback of body parameters, e.g. blood-sugar, pressure measurement of body parameters A61B5/00
• CPC Class Codes: G06N 5/048 Fuzzy inferencing
• CPC Class Codes: G16H 20/10 relating to drugs or medications, e.g. for ensuring correct administration to patients
• CPC Class Codes: G16H 20/13 delivered from dispensers
• CPC Class Codes: G16H 20/17 delivered via infusion or injection
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders

Abstract

A system and method for automatically adjusting parameters for predicting blood glucose levels and/or controlling the dispensing of insulin. In one embodiment, the system is a stand-alone system. In one embodiment, the system is part of a system for controlling the dispensing of insulin.

Claims

1. A computer-implemented method, comprising:

receiving blood glucose-related data;

retrieving stored blood glucose-related data;

adjusting fuzzy-logic control parameters based on the received and the retrieved blood glucose-related data; and

generating a control signal to control dispensing of insulin based on the received blood glucose-related data and fuzzy-logic control parameters, wherein the receiving, the retrieving, the adjusting and the generating are performed by one or more configured computing systems.

2. The computer-implemented method of claim 1, comprising predicting blood glucose levels based on the received blood glucose-related data.

3. The computer-implemented method of claim 2, comprising predicting blood glucose levels based on the retrieved blood glucose-related data.

4. The method of claim 2 wherein the predicting blood glucose levels comprises predicting a subsequent blood glucose level based on a previously predicted blood glucose level.

5. The method of claim 2 wherein the predicting blood glucose levels comprises maintaining a fuzzy-logic rules matrix.

6. The computer-implemented method of claim 1, comprising dispensing insulin based on the control signal.

7. The computer-implemented method of claim 1, comprising sensing blood glucose levels.

8. The computer-implemented method of claim 1, comprising selectively transitioning between using a post-meal correction protocol and a fasting protocol.

9. The computer-implemented method of claim 1, comprising transitioning from a post-meal correction protocol to a fasting protocol when a fasting criteria is satisfied.

10. The computer-implemented method of claim 1, comprising transitioning from a fasting protocol to a post-meal correction protocol when a prandial event is detected.

11. The computer-implemented method of claim 1, comprising transitioning from a fasting protocol to a user-input protocol when a prandial event is detected.

12. The computer-implemented method of claim 1 wherein the fuzzy-logic control parameters comprise fuzzy-logic multipliers.

13. The computer-implemented method of claim 12 wherein adjusting the fuzzy-logic control parameters comprises selectively adjusting a fuzzy logic rules matrix.

14. The method of claim 13 wherein the selectively adjusting the fuzzy logic rules matrix comprises applying a dosing matrix coherency policy.

15. The method of claim 1 wherein the adjusting fuzzy-logic control parameters comprises using at least one of a neural network and a dynamic Bayesian network.

16. The method of claim 1 wherein the adjusting fuzzy-logic control parameters occurs in real-time.

17. A method, comprising:

receiving blood glucose-related data;

predicting blood glucose levels based on the received data; and

generating, using fuzzy logic, a control signal to control the dispensing of insulin based on the received data and the predicted blood glucose levels, the predicting and the generating being performed by one or more configured computing systems.

18. The method of claim 17, comprising controlling an insulin dispenser based on the control signal.

19. The method of claim 17, comprising:

predicting blood glucose levels based on parameters of a statistical model; and

adjusting the parameters of the statistical model.

20. The method of claim 19 wherein the adjusting the parameters of the statistical model occurs in real-time as blood glucose related data is received.

21. The method of claim 17, comprising:

generating the control signal based on control parameters; and

adjusting the control parameters.

22. The method of claim 21, comprising

adjusting the control parameters based on a comparison of the predicted blood glucose levels to the received data.

23. The method of claim 17, comprising:

storing historical blood glucose-related data; and

predicting blood glucose levels based on stored historical blood glucose-related data.

24. The method of claim 17, comprising:

generating the control signal using at least one of a neural network and a dynamic Bayesian network.

25. The method of claim 17, comprising:

predicting blood glucose levels using at least one of a neural network and a dynamic Bayesian network.

26. A method, comprising:

receiving sensed indications of blood glucose levels;

selectively adjusting fuzzy logic parameters based on the sensed indications of blood glucose levels; and

generating a control signal to control dispensing of insulin based on the sensed indications of blood glucose levels and the fuzzy logic parameters, the receiving, the adjusting and the generating being performed by one or more configured processing devices.

27. The method of claim 26, comprising controlling an insulin dispenser based on the control signal.

28. The method of claim 27, comprising selectively adjusting a fuzzy logic rules matrix.

29. The method of claim 28, comprising selectively adjusting the fuzzy logic rules matrix according to a dosing matrix coherency policy.

30. The method of claim 29, comprising predicting blood glucose levels based on the fuzzy-logic rules matrix and generating the control signal based on the predicted blood glucose levels.

31. The method of claim 27, comprising sensing the sensed indication with a sensor.

32. The method of claim 27, comprising using at least one of a neural network and a dynamic Bayesian network to generate the control signal.

33. The method of claim 27, comprising using at least one of a neural network and a dynamic Bayesian network to adjust the fuzzy logic parameters.