Intelligent Therapy Recommendation Algorithm and Method of Using the Same

• US 20080097289A1
• Filed: 09/06/2006
• Published: 04/24/2008
• Est. Priority Date: 09/06/2006
• Status: Active Grant

• Current Assignee: Medtronic Minimed Incorporated (Medtronic Plc)
• Original Assignee: Medtronic Minimed Incorporated (Medtronic Plc)
• Inventors: Panteleon, Antonios, Steil, Garry M.
• Granted Patent: US 9,056,165 B2
• Time in Patent Office: Days
• US Class Current: 604/67
• CPC Class Codes: A61M 2205/18 with alarm
• CPC Class Codes: A61M 2205/502 User interfaces, e.g. screens or keyboards
• CPC Class Codes: A61M 2205/52 with memories providing a history of measured variating parameters of apparatus or patient
• CPC Class Codes: A61M 2230/201 Glucose concentration
• CPC Class Codes: A61M 5/14244 adapted to be carried by the patient, e.g. portable on the body
• CPC Class Codes: A61M 5/1723 using feedback of body parameters, e.g. blood-sugar, pressure measurement of body parameters A61B5/00

Abstract

An algorithm and method of making intelligent therapy recommendations for insulin pump parameters is described. The pump parameters include basal rates, carbohydrate-to-insulin ratios (CIR), and insulin sensitivity factors (ISF). A determination of whether a therapy recommendation should be made is based on comparing an updated recommended change with a threshold. The updated recommended change to the pump parameter is made based on a previous recommended change to the pump parameter and the difference between a current blood glucose value and a targeted blood glucose level. The algorithm and method confirms the therapy recommendation is within safety parameters before displaying the therapy recommendation.

Claims

1. A method of automatically making a therapy recommendation to an insulin pump parameter, the method comprising the steps of:

obtaining a blood glucose value;

updating a recommended change to the pump parameter based on a previous recommended change to the pump parameter and the difference between the blood glucose value and a target blood glucose level;

comparing the updated recommended change to a threshold;

deriving the therapy recommendation if the updated recommended change exceeds the threshold;

confirming the therapy recommendation is within safety parameters; and

displaying the therapy recommendation;

2. The method of claim 1, wherein the blood glucose value is obtained by a continuous glucose monitor.

3. The method of claim 1, wherein the pump parameter is a basal rate.

4. The method of claim 1, wherein the pump parameter is a carbohydrate-to-insulin ratio (CIR).

5. The method of claim 1, wherein the pump parameter is an insulin sensitivity factor (ISF).

6. The method of claim 1, wherein the step of confirming the therapy recommendation is within safety parameters comprises:

reviewing recent blood glucose history; and

using a moving standard deviation analysis on the recent blood glucose history to confirm the blood glucose value is relatively consistent with the blood glucose history.

7. The method of claim 6, wherein the moving standard deviation analysis is only performed on a therapy recommendation that will lead to an increase in insulin.

8. The method of claim 1, wherein the step of confirming the therapy recommendation is within safety parameters further comprises:

limiting the therapy recommendation to a particular maximum value.

9. The method of claim 1, wherein the step of confirming the therapy recommendation is within safety parameters comprises:

limiting the pump parameter to an absolute maximum or absolute minimum.

10. The method of claim 4, wherein the step of updating a recommended change further comprises:

updating the recommended change for the CIR from a first postprandial blood glucose value;

updating the recommended change using a second postprandial blood glucose value if a second postprandial blood glucose value exists; and

repeating the updating step for any additional postprandial blood glucose values if they exist.

11. The method of claim 10, wherein the first, second or any additional postprandial blood glucose value is skipped if an intervening event occurs during the postprandial period.

12. The method of claim 5, wherein the step of updating a recommended change further comprises:

updating the recommended change for the ISF from a first post correction bolus blood glucose value;

updating the recommended change using a second postprandial blood glucose value if a second post correction bolus blood glucose value exists; and

repeating the updating step for any additional post correction bolus blood glucose values if they exist.

13. The method of claim 12, wherein the first, second, or any additional post correction bolus blood glucose value is skipped if an intervening event occurs within a predetermined window of time after the correction bolus.

14. The method of claim 1, further comprising:

resetting the recommended change when the recommended change exceeds the threshold.

15. A method of automatically making a therapy recommendation for a basal rate on an insulin pump, the method comprising the steps of:

obtaining a blood glucose value at the end of a time interval;

updating a recommended change to the basal rate based on a previous day recommended change to the basal rate during that interval and the difference between the blood glucose value and a target blood glucose level;

comparing the updated recommended change to a threshold;

deriving the therapy recommendation if the updated recommended change exceeds the threshold;

confirming the therapy recommendation is within safety parameters; and

displaying the therapy recommendation;

16. The method of claim 15, wherein the basal rate is an overnight basal rate.

17. The method of claim 15, wherein the blood glucose value is skipped if there was a meal or correction bolus during the time interval before the blood glucose value was obtained.

18. The method of claim 15, wherein the step of confirming the therapy recommendation is within safety parameters comprises:

reviewing recent blood glucose history; and

using a moving standard deviation analysis on the recent blood glucose history to confirm the blood glucose value is relatively consistent with the blood glucose history.