NEAR REAL TIME BLOOD GLUCOSE LEVEL FORECASTING

• US 20140149329A1
• Filed: 04/19/2013
• Published: 05/29/2014
• Est. Priority Date: 04/19/2012
• Status: Abandoned Application

• Current Assignee: Stephen Shaw
• Original Assignee: Stephen Shaw
• Inventors: Shaw, Stephen
• Application Number:
  US13/866,612
• Publication Number:
  US 20140149329A1
• Time in Patent Office: Days
• US Class Current: 706/46
• CPC Class Codes: G16H 20/17 delivered via infusion or injection
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

A method of forecasting optimal insulin dosage levels calculates a near real time blood glucose forecast based on frequently updated data representative of blood glucose levels and displays a near real time blood glucose forecast to a user.

Claims

1. A method of forecasting optimal insulin dosage levels comprising the steps of:

calculating a near real time blood glucose forecast based on frequently updated data representative of blood glucose levels; and

displaying the near real time blood glucose forecast, thereby allowing a user to determine an appropriate dosage based on said near real time blood glucose forecast.

2. The method of claim 1, wherein said step of calculating a near real time blood glucose forecast based on frequently updated data representative of blood glucose levels further comprises:

initiating a forecasting process in response to a forecast request;

accessing a plurality of historic event values and corresponding attributes from a master event record;

generating the near real time blood glucose forecast based on the historic event values and corresponding attributes using a predictive time series model.

3. The method of claim 2, wherein said predictive time series model selected from the list of time series time series modeling, state space modeling, Bayes theorem modeling, quantitative trend spotting and dynamic factor analysis.

4. The method of claim 3, wherein said time series time series modeling is a vector autoregression.

5. The method of claim 3, wherein said near real time blood glucose forecast calculation includes at least one indicator variable, wherein said at least one indicator variable is selected from a group of seasonal factors, environmental factors, and lifestyle factors.

6. The method of claim 5, wherein said group of seasonal factors, environmental factors, and lifestyle factors includes a time of day, a day of the week, a month of the year, a current weather condition, a change in routine, a menstrual cycle status, a body weight change, a value representative of a current stress level, and a value representative of a current mood.

7. The method of claim 2, further comprising the step of continuously generating a personal patient history comprising a master event database and a master electronic calendar, wherein said master event database includes entries corresponding to at least a regular blood glucose reading and insulin intake quantity readings, and wherein each of said entries includes a date and time stamp.

8. The method of claim 7, wherein each of said entries further includes at least one associated valued from a master electronic calendar, and wherein said master electronic calendar stores periodic standard attributes and non-periotic personal patient attributes.

9. The method of claim 7, wherein said personal patient history includes an underlying general patient history derived from multiple individuals and an overlying personal patient history derived from a specific patient to perform the calculation of the single near real time blood glucose forecast, wherein said general patient history is derived from four or more patients.

10. A method of monitoring a near real time blood glucose forecast comprising the steps of:

determining a near real time blood glucose forecast; and

transmitting an alert based on said near real time blood glucose forecast, wherein said alert indicates an expected future high or low blood glucose level.

11. The method of claim 10, wherein said alert triggers a notifying event, and said notifying event is one of a group of notifying events including a telephone call, an electronic message, an audible cue, a vibration and the display of a symbol.

12. The method of claim 10, wherein said alert includes at least one recommended action for maintaining optimum blood glucose levels.

13. The method of claim 12, wherein said recommendation includes a recommended dosage of insulin and timing of said dosage of insulin.

14. The method of claim 10, wherein said step of determining a near real time blood glucose forecast is performed by a computerized device local to a user, wherein said computerized device is one of a medical device, a portable phone, a personal computer, and a portable tablet.

15. The method of claim 14, further comprising the additional step of displaying a determined near real time blood glucose forecast on a display screen of said computerized device.

16. The method of claim 10, wherein said step of determining a near real time blood glucose forecast is performed on a remote computerized device remote from a user in near-real time.

17. The method of claim 16, further comprising the step of transmitting a determined near real time blood glucose forecast from said remote computerized device to a local computerized device in close physical proximity to a user.

18. The method of claim 10, further comprising the step of allowing remote access to the near real time blood glucose forecast such that an authorized third party can access the determined a near real time blood glucose forecast.

19. The method of claim 10, further comprising the step of using the near real time blood glucose forecast data to determine the dosage of insulin to administer at any moment in time via an automated medical device.

20. A blood glucose forecasting system including a near real time blood glucose forecast comprising:

a processor;

a computer readable memory storing instructions for causing the processor to perform the steps of calculating a near real time blood glucose forecast based on frequently updated data representative of blood glucose levels and displaying the near real time blood glucose forecast, thereby allowing a user to determine an appropriate dosage based on said near real time blood glucose forecast;

a data input operable to at least receive periodic data representative of blood glucose levels;

an output medium comprising at least one of the list of a portable device screen, an electronic message transmission, and an audible output component.

21. The blood glucose forecasting system of claim 20, wherein said blood glucose meter further comprises a wireless transmitter/receiver operable to allow said blood glucose meter to receive wireless inputs and transmit wireless reports.