Personalized event detection methods and related devices and systems

• US 10,463,297 B2
• Filed: 08/18/2016
• Issued: 11/05/2019
• Est. Priority Date: 08/21/2015
• Status: Active Grant

• Current Assignee: Medtronic Minimed Incorporated (Medtronic Plc)
• Original Assignee: Medtronic Minimed Incorporated (Medtronic Plc)
• Inventors: Abraham, Sinu Bessy, McMahon, Chantal M., Agrawal, Pratik, Jiang, Boyi, Zhong, Yuxiang, Stone, Michael P., Neemuchwala, Huzefa F.
• Primary Examiner(s): Gray, Phillip A
• Application Number:
  US15/240,711
• Publication Number:
  US 20170049386A1
• Time in Patent Office: 1,174 Days
• Field of Search: 604 66
• CPC Class Codes: A61B 5/14532 for measuring glucose, e.g. by tissue impedance measurement
• CPC Class Codes: A61B 5/4839 combined with drug delivery
• CPC Class Codes: A61B 5/7225 Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation A61B5/30, A61B5/316 take precedence; transformers for specific applications H01F38/00; amplifiers H03F
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: A61B 5/743 Displaying an image simultaneously with additional graphical information, e.g. symbols, charts, function plots
• CPC Class Codes: A61M 2205/3584 using modem, internet or bluetooth
• CPC Class Codes: A61M 2205/50 with microprocessors or computers
• CPC Class Codes: A61M 2205/502 User interfaces, e.g. screens or keyboards
• 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 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G16H 20/17 delivered via infusion or injection
• CPC Class Codes: G16H 20/60 relating to nutrition control, e.g. diets
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

Medical devices and related patient management systems and event detection methods are provided. An exemplary method of detecting events pertaining to operation of a medical device, such as an infusion device, involves obtaining measurements indicative of a condition in a body of a patient, determining statistics for an analysis interval based on the measurements, and determining an event probability associated with the analysis interval based on historical event data associated with the patient. An event detection model associated with the patient is obtained and applied to the statistics and the event probability to identify occurrence of the event using the event detection model, and in response, an indication of the event associated with the analysis interval is provided, for example, by tagging or marking data in a database, displaying graphical indicia of the event, or the like.

Claims

1. A method of detecting meals pertaining to operation of a medical device associated with a patient, the method comprising:

obtaining, by a computing device via a network, a plurality of glucose measurements indicative of a glucose level in a body of the patient during an analysis interval;

obtaining, by the computing device, a patient-specific meal detection model that identifies one or more glucose measurement statistics that are correlative to occurrence of a meal for the patient;

determining, by the computing device, values for the one or more glucose measurement statistics characterizing the glucose level in the body of the patient within the analysis interval based on the plurality of glucose measurements;

determining, by the computing device, a meal probability associated with the analysis interval based on historical event data associated with the patient;

determining, by the computing device, a meal consumption metric based on the values for the one or more glucose measurement statistics and the meal probability using respective correlation coefficient values from the patient-specific meal detection model;

autonomously detecting, by the computing device, an occurrence of a meal during the analysis interval based on the meal consumption metric; and

in response to detecting the occurrence of the meal, providing, by the computing device, an indication of the occurrence of the meal associated with the analysis interval.

2. The method of claim 1, further comprising generating the patient-specific meal detection model based on historical measurements indicative of the glucose level in the body of the patient and the historical event data.

3. The method of claim 2, wherein generating the patient-specific meal detection model comprises:

determining a plurality of glucose measurement statistics based on the historical measurements;

determining a predictive subset of the plurality of glucose measurement statistics for the patient based on a respective correlation between a respective glucose measurement statistic of the plurality of glucose measurement statistics and the historical event data; and

determining the respective correlation coefficients associated with respective ones of the predictive subset of glucose measurement statistics.

4. The method of claim 3, wherein:

the one or more glucose measurement statistics comprise the predictive subset of glucose measurement statistics for the analysis interval.

5. The method of claim 1, the historical event data comprising meal bolus data associated with the patient, wherein:

determining the meal probability comprises determining the meal probability for the analysis interval based on the meal bolus data associated with the patient; and

providing the indication comprises establishing an association between the occurrence of the meal and the analysis interval.

6. The method of claim 1, wherein providing the indication comprises updating the historical event data to indicate the occurrence of the meal associated with the analysis interval.

7. The method of claim 1, wherein providing the indication comprises storing an indicator of the occurrence of the meal in association with the one or more glucose measurements.

8. The method of claim 1, further comprising determining a timestamp for the occurrence of the meal based on the one or more glucose measurements, wherein providing the indication comprises storing meal indicator having the timestamp associated therewith.

9. The method of claim 1, wherein providing the indication comprises providing a pattern guidance display for an event pattern that is influenced by the occurrence of the meal associated with the analysis interval.

10. A computer-readable medium having instructions stored thereon that are executable by a processing system of the computing device to perform the method of claim 1.

20. The method of claim 1, wherein the one or more glucose measurement statistics include at least one of a mean sensor glucose measurement value over the analysis interval, a standard deviation of the plurality of glucose measurement values during the analysis interval, a mean rate of change of the plurality of glucose measurement values on a sample-to-sample basis during the analysis interval, a standard deviation associated with the mean rate of change of the plurality of glucose measurement values, an absolute amplitude of the plurality of glucose measurement values during the analysis interval, and an amplitude difference between first and last glucose measurement values of the plurality of glucose measurement values during the analysis interval.

11. A method of detecting meals during to operation of an insulin infusion device associated with a patient, the method comprising:

obtaining sensor glucose measurements for the patient;

obtaining a bolus history for the patient;

obtaining a meal detection model associated with the patient, the meal detection model identifying a predictive subset of glucose measurement statistics correlative to meals by the patient;

calculating the predictive subset of glucose measurement statistics characterizing a glucose level of the patient for an analysis interval of the sensor glucose measurements;

determining a meal probability associated with the analysis interval based on the bolus history;

determining a meal consumption metric based on the calculated predictive subset of glucose measurement statistics for the analysis interval of the sensor glucose measurements and the meal probability associated with the analysis interval using respective correlation coefficient values from the meal detection model;

autonomously detecting occurrence of a meal during the analysis interval based on the meal consumption metric; and

in response to autonomously detecting occurrence of the meal, providing an indication of the occurrence of the meal associated with the analysis interval.

12. The method of claim 11, wherein providing the indication comprises updating the bolus history to indicate the occurrence of the meal associated with the analysis interval.

13. The method of claim 12, wherein providing the indication comprises classifying the analysis interval of the sensor glucose measurements as a meal segment.

14. The method of claim 11, further comprising determining the meal detection model associated with the patient based on historical sensor glucose measurements for the patient corresponding to the bolus history.

15. The method of claim 14, wherein determining the meal detection model comprises:

classifying the historical sensor glucose measurements into meal and non-meal segments; and

determining a predictive glucose measurement statistic of the predictive subset based on a correlation between the meal segments and values of the predictive glucose measurement statistic for portions of the historical sensor glucose measurements corresponding to the meal segments.

16. The method of claim 11, further comprising providing a pattern guidance display corresponding to an event pattern influenced by the occurrence of the meal and including a graphical indication of the occurrence of the meal associated with a time of day corresponding to the analysis interval.

17. A system comprising:

a sensing arrangement to obtain glucose measurement values for a glucose level in a body of a patient;

a database to store historical event data and a meal detection model associated with the patient; and

a computing device communicatively coupled to the database and a network to;

obtain the glucose measurement values;

determine values for one or more glucose measurement statistics characterizing the glucose level in the body of the patient that are correlative to occurrence of a meal for the patient for an analysis interval based on the glucose measurement values;

determine a meal probability associated with the analysis interval based on the historical event data associated with the patient;

apply the meal detection model to the one or more glucose measurement statistics and the meal probability to determine a meal consumption metric based on the values for the one or more glucose measurement statistics and the meal probability using respective correlation coefficient values from the meal detection model and autonomously detect occurrence of a meal during the analysis interval based on the meal consumption metric; and

provide an indication of the occurrence of the meal associated with the analysis interval.

18. The system of claim 17, further comprising an infusion device coupled to the sensing arrangement and the network, wherein the infusion device is operable to deliver fluid to the body of the patient based on the glucose measurement values and upload the glucose measurement values to the computing device.

19. The system of claim 17, wherein the computing device generates a graphical user interface display on a client device coupled to the computing device over the network, wherein the indication comprises a graphical indication of the occurrence of the meal associated with the analysis interval on the graphical user interface display.