Monitoring device for management of insulin delivery

• US 9,507,917 B2
• Filed: 01/21/2015
• Issued: 11/29/2016
• Est. Priority Date: 09/30/2009
• Status: Active Grant

• Current Assignee: Dreamed Diabetes Ltd.
• Original Assignee: Dreamed Diabetes Ltd.
• Inventors: Atlas, Eran, Nimri, Revital, Miller, Shahar, Grunberg, Eli Aviram, Phillip, Moshe
• Primary Examiner(s): Chaki, Kakali
• Assistant Examiner(s): Zidanic, Michael
• Application Number:
  US14/601,450
• Publication Number:
  US 20150134356A1
• Time in Patent Office: 678 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: A61B 5/14532 for measuring glucose, e.g. by tissue impedance measurement
• CPC Class Codes: A61M 2005/14208 with a programmable infusion control system, characterised by the infusion program
• 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 7/00 Computing arrangements based on specific mathematical models
• CPC Class Codes: G16H 20/17 delivered via infusion or injection
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

Monitoring system and method for use with diabetic treatment management. The system comprises: a communication interface configured to permit access to stored raw log data, obtained over a certain time, being indicative of glucose measurements, meals consumed and insulin delivery; and a control unit comprising an unsupervised learning controller configured to receive and process said raw log data and determine at least one global insulin pump setting of basal rate, correction factor, carbohydrate ratio and insulin activity curve parameters. The system may comprise a processing unit comprising a first processor for processing measured data indicative of blood glucose level and generating first processed data, a second processor comprising at least one fuzzy logic module which receives input parameters corresponding to the measured data, the first processed data and a reference data, and processes the data to produce a qualitative output parameter to determine whether any treatment parameter should be modified.

Claims

1. A monitoring system for use with disease treatment management, the monitoring system comprising:

a communication interface to permit input of raw log data, said raw log data being indicative of data obtained over a certain time and including time spaced data points of glucose measurements, meals consumed and insulin delivery;

a control unit configured for receiving and processing said raw log data, the control unit comprising;

a sectioning module configured to section the raw log data within at least one time window;

the sectioned time window being at least one of Basal data Section (BaS), Meals data Section (MS) and Bolus data Section (BS), each sectioned time window having a starting point and having an end point such that the BaS is selected outside an effect window of either a meal event or an insulin bolus, the MS is selected at a predetermined time ahead of a meal data point, and the starting point of the BS is selected as one of the following;

(a) the end point of the MS or the BaS, and (b) an insulin bolus data point which is outside the MS;

the end point of the BS being selected as one of the following, (i) the starting point of the MS or BaS and (ii) a predetermined time ahead of the insulin bolus data point without any intervening insulin bolus;

an unsupervised learning controller configured and operable to determine an informative data piece from a residual log data portion of said raw log data, analyze said informative data piece and select a sectioned time window for calculation of an individualized patient'"'"'s profile related data comprising at least one of drug injection setting of basal insulin treatment, correction factor (CF), carbohydrate ratio (CR) and activity curve parameters of said drug, wherein calculation of the basal insulin treatment is based on BaS, calculation of at least one of the drug activity curve parameters, correction factor (CF) and carbohydrate ratio (CR) is based on MS, and calculation of the correction factor (CF) or the drug activity curve parameters is based on BS; and

an output module for generating treatment data which is indicative of the individualized patient'"'"'s profile related data and is configured for at least one of the following;

for operating a drug injection device, and for presentation on user interface.

2. The system of claim 1, wherein said communication interface comprises user interface to permit user input of at least a part of the raw log data indicative at least of the insulin delivery over said certain time.

3. The system of claim 1, wherein said communication interface is configured to permit input of at least a part of the input raw log data from an external device.

4. The system of claim 3, wherein said external device comprises at least one of the following:

a measurement device, a storage device, and a drug injection device.

5. The system of claim 3, wherein said external device comprises a measurement device comprising a glucometer.

6. The system of claim 1, wherein said unsupervised learning controller is configured and operable to determine each of said parameters from a part of said informative data piece corresponding to a selected time window of said certain time.

7. The system of claim 1, wherein the information indicative of the glucose measurements, insulin delivery and meals consumed is a file obtained from a remote controller independently accumulating said information.

8. The system of claim 7, wherein the file is downloaded from a network and stored in a memory module.

9. The system of claim 1, wherein said treatment data is configured for transmission to a remote device.

10. The system of claim 9, wherein said remote device comprises at least one of the drug injection device or measurement device.

11. The system of claim 1, wherein said treatment data comprises operational settings of the drug injection device.

12. The system of claim 1, wherein said treatment data comprises treatment recommendation for user enabling the user to choose whether to apply the treatment recommendation or not.

13. The system of claim 1, wherein said control unit is operable to update and/or calibrate said individualized patient'"'"'s profile related data during treatment or during monitoring procedure.

14. The system of claim 1, wherein said unsupervised learning controller is adapted for receiving and analyzing individualized patient'"'"'s treatment history related data comprising patient'"'"'s insulin delivery regimen given to the patient at different hours of the day.

15. A method for use in monitoring operation of an insulin injection device, the method comprising:

performing unsupervised learning of settings of the drug injection device, said unsupervised learning comprising;

a) obtaining raw log data input accumulated on one or more glucose monitoring units recording glucose levels of a single treated patient along a certain time;

b) sectioning the raw log data to predetermined data sections;

each of the predetermined data sections being at least one of Basal data Section (BaS), Meals data Section (MS) and Bolus data Section (BS), each section having a starting point and having an end point such that the BaS being selected outside an effect window of either a meal event or an insulin bolus, the MS being selected at a predetermined time ahead of a meal data point, and the starting point of the BS being selected as one of the following;

(a) the end point of the MS or the BaS, and (b) an insulin bolus data point which is outside the MS;

the end point of the BS being selected as one of the following, (i) the starting point of the MS or BaS and (ii) a predetermined time ahead of the insulin bolus data point without any intervening insulin bolus;

c) determining informative data piece from the raw log data input being sectioned to data sections, the informative data piece being determined from said data section; and

d) calculating the settings of the insulin injection device from the informative data piece, wherein said settings include at least one parameter of basal insulin treatment, Carbohydrate Ratio (CR), Correction Factor (CF) or Active Insulin Function (AIF) wherein the BaS enables calculation of the basal insulin treatment, the MS enables calculation of at least one of insulin activity curve parameters, correction factor (CF) and carbohydrate ratio (CR), and the BS enables calculation of the correction factor (CF) or insulin activity curve parameters; and

e) analyzing the settings of the insulin injection device and generating treatment data configured for at least one of the following;

for operating the insulin injection device, and for presentation on user interface.

16. The method of claim 15 further comprising aligning plurality of data portions of said raw log data input along a shared time axis.

17. The method of claim 16, comprising determining a representative data point comprising both a value of aggregated blood glucose levels and a time stamp;

the representative data point is paired to a selected basal insulin treatment period;

the representative data point indicates a basal insulin treatment determination for the selected basal insulin treatment period.

18. The method of claim 15, wherein the raw log data input of said Basal Section (Bas) includes a series of basal insulin treatments as a function of time;

the method comprising;

determining a time delay characterizing the treated patient at said Basal Section (Bas), said time delay being between a basal insulin treatment and changes in the glucose level;

obtaining a plurality of selected basal insulin treatments at a delivery time, a respective paired glucose level being at the time delay measured from the delivery time;

determining a resultant basal insulin treatment from the plurality of selected basal insulin treatments which minimizes a change in the glucose level.

19. The method of claim 15, comprising determining the AIF by carrying out the following method:

(i) obtaining a set of glucose measurements and paired time stamps for the raw log data in the time section;

(ii) normalizing each glucose measurement of the set thereby obtaining a series of normalized glucose measurements and paired time stamp;

(iii) processing said normalized glucose measurements and paired time stamp into a substantially monotonic non-increasing series;

thereby obtaining the AIF.

20. A control unit for use in disease treatment management, the control unit comprising:

a data processor utility configured and operable as an unsupervised learning controller preprogrammed for carrying out the method of claim 15.