System and method for providing alerts optimized for a user

• US 10,328,204 B2
• Filed: 04/28/2017
• Issued: 06/25/2019
• Est. Priority Date: 05/02/2016
• Status: Active Grant

• Current Assignee: DexCom Incorporated
• Original Assignee: DexCom Incorporated
• Inventors: Davis, Anna Leigh, Garcia, Arturo, Hall, Thomas, Hampapuram, Hari, Hannemann, Christopher Robert, Harley-Trochimczyk, Anna Claire, Heintzman, Nathaniel David, Jackson, Andrea J., Jepson, Lauren Hruby, Kamath, Apurv Ullas, Koehler, Katherine Yerre, Belliveau, Scott M., Mandapaka, Aditya Sagar, Marsh, Samuel Jere, Morris, Gary A., Pai, Subrai Girish, Pal, Andrew Attila, Polytaridis, Nicholas, Pupa, Philip Thomas, Reihman, Eli, Rindfleisch, Ashley Anne, Schunk, Sofie Wells, Bhavaraju, Naresh C., Simpson, Peter C., Smith, Daniel, Vanslyke, Stephen J., Vogel, Matthew T., Walker, Tomas C., West, Benjamin Elrod, Wiley, Atiim Joseph, Bowman, Leif N., Castillo, Rita M., Constantin, Alexandra Elena, Draeger, Rian, Dunn, Laura J., Gable, Gary Brian
• Primary Examiner(s): Odom, Curtis B
• Application Number:
  US15/582,057
• Publication Number:
  US 20170311903A1
• Time in Patent Office: 788 Days
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/024 Detecting, measuring or recording pulse rate or heart rate A61B5/0205, A61B5/021 take precedence
• CPC Class Codes: A61B 5/1112 Global tracking of patients, e.g. by using GPS
• CPC Class Codes: A61B 5/14517 for sweat
• CPC Class Codes: A61B 5/14532 for measuring glucose, e.g. by tissue impedance measurement
• CPC Class Codes: A61B 5/14546 for measuring analytes not otherwise provided for, e.g. ions, cytochromes
• CPC Class Codes: A61B 5/165 Evaluating the state of mind, e.g. depression, anxiety
• CPC Class Codes: A61B 5/4866 Evaluating metabolism A61B5/083 takes precedence
• CPC Class Codes: A61B 5/742 using visual displays A61B5/339 takes precedence
• CPC Class Codes: A61B 5/746 Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms alarms per se G08B
• CPC Class Codes: A61M 2205/18 with alarm
• 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 2205/52 with memories providing a history of measured variating parameters of apparatus or patient
• CPC Class Codes: A61M 2205/581 by audible feedback
• CPC Class Codes: A61M 2205/582 by tactile feedback
• CPC Class Codes: A61M 2205/8206 battery-operated
• 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 20/00 : Machine learning
• CPC Class Codes: G06N 5/043 : Distributed expert systems; Blackboards
• CPC Class Codes: G08B 21/0453 : worn on the body to detect health condition by physiological monitoring, e.g. electrocardiogram, temperature, breathing detecting, measuring or recording for diagnostic purposes A61B5/00
• CPC Class Codes: G16H 20/17 : delivered via infusion or injection
• CPC Class Codes: G16H 40/63 : for local operation
• 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: H04M 1/72412 : using two-way short-range wireless interfaces
• CPC Class Codes: Y02A 90/10 : Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Abstract

Systems and methods are disclosed that provide smart alerts to users, e.g., alerts to users about diabetic states that are only provided when it makes sense to do so, e.g., when the system can predict or estimate that the user is not already cognitively aware of their current condition, e.g., particularly where the current condition is a diabetic state warranting attention. In this way, the alert or alarm is personalized and made particularly effective for that user. Such systems and methods still alert the user when action is necessary, e.g., a bolus or temporary basal rate change, or provide a response to a missed bolus or a need for correction, but do not alert when action is unnecessary, e.g., if the user is already estimated or predicted to be cognitively aware of the diabetic state warranting attention, or if corrective action was already taken.

Claims

1. A non-transitory computer readable medium, comprising instructions for causing a computing environment to perform a method of dynamically adjusting or tuning user alerts based on a cognitive awareness determination, thereby providing data relevant to treatment of a diabetic state warranting attention, the method comprising steps of:

identifying a current or future diabetic state warranting attention, the identifying based at least partially on a glucose concentration value;

estimating or predicting a cognitive awareness of the user of the identified current or future diabetic state warranting attention; and

if the result of the estimating or predicting is that the user is cognitively unaware of the identified current or future diabetic state warranting attention, then alerting a user with a user prompt on a user interface of a monitoring device, the user prompt indicating the diabetic state warranting attention,

whereby the user is only alerted of the diabetic state warranting attention if and at a time that the user is unaware of the diabetic state warranting attention and that the notification is effective for the user.

2. The medium of claim 1, wherein the alerting is optimized for cognitive awareness of the patient such that fewer alarms occur than would otherwise be provided without consideration of user cognitive awareness.

3. The medium of claim 1, whereby over-prompting, repeat prompts, or nuisance prompts are minimized or avoided.

4. The medium of claim 1, whereby the user is enabled to build trust in the system, that the system will only alert on notifications optimized or effective for the user.

5. The medium of claim 1, wherein the estimating or predicting a cognitive awareness of the user includes determining if the identified current or future diabetic state warranting attention includes an atypical glucose trace.

6. The medium of claim 5, wherein the atypical glucose trace includes an atypical pattern or an atypical glucose response.

7. The medium of claim 1, wherein the estimating or predicting a cognitive awareness of the user includes determining if the user has previously treated a like identified diabetic state warranting attention by taking an action without a user prompt.

8. The medium of claim 1, wherein the estimating or predicting a cognitive awareness of the user includes:

determining if the user has entered meal or bolus data or has requested a bolus calculation, analyzing historic data of glucose values of the user versus time, receiving data from an application or website through an appropriate API, or determining if user behavior is consistent with cognitive awareness.

9. The medium of claim 1, wherein the estimating or predicting a cognitive awareness of the user includes receiving user input and basing the estimating or predicting at least in part on the received input.

10. The medium of claim 1, wherein the steps of identifying and estimating or predicting are repeated until such a time as the user is estimated or predicted to be cognitively unaware of the identified diabetic state warranting attention, and then performing a step of alerting the user with the user prompt.

11. The medium of claim 1, wherein the estimating or predicting a cognitive awareness of the user is based at least partially on one or more of the following:

population data, data associated with behavioral or contextual information, data associated with a life goal of the user, data associated with a user privacy setting, or a combination of these.

12. The medium of claim 1, wherein the estimating or predicting a cognitive awareness of the user is based at least partially on real-time data, and wherein the real-time data includes one or more of the following:

data associated with a GPS application in the monitoring device, data associated with an accelerometer in the monitoring device, data associated with behavioral or contextual information, data associated with a location of a follower of the user, data associated with a metabolic rate of the user, data associated with a glycemic urgency index of the user, heart rate data, sweat content data, data associated with a wearable sensor of the user, insulin data, or a combination of these.

13. The medium of claim 1, wherein the method further comprises indicating a confidence level associated with the user prompt.

14. The medium of claim 1, wherein if the result of the estimating or predicting is that the user is not cognitively aware of the diabetic state that warrants attention, then alerting the user with the user prompt after a time delay, a duration of the time delay based on at least the identified diabetic state warranting attention and the glucose concentration value and/or a glucose concentration value rate of change.

15. The medium of claim 1, wherein the user prompt includes a query for a user to enter data.

16. The medium of claim 15, wherein the query requests data for the user to enter about dosing, meals or exercise.

17. The medium of claim 1, wherein if the user ignores the user prompt as determined by data from the user interface or data from an accelerometer associated with the monitoring device, and if the user prompt does not correspond to a danger condition, then storing information about the user ignoring the user prompt under prior conditions and using the stored information as part of a subsequent estimating or predicting step.

18. The medium of claim 1, wherein the identifying a current or future diabetic state warranting attention includes determining a clinical value of a glucose concentration and/or a glucose rate of change and/or a glycemic urgency index value, or measuring a glucose signal signature and comparing the measured signature with a plurality of binned signatures and classifying the diabetic state warranting attention into one of a plurality of bins based on the comparison, or determining one or more time-based trends in the glucose concentration value, and basing the identified state on the determined trend.

19. The medium of claim 18, wherein the trend corresponds to whether the glucose concentration value is hovering within a range or is rising or falling, wherein hovering constitutes staying within a predetermined range for a period of greater than 5 or 10 or 15 or 30 minutes.

20. The medium of claim 1, wherein, if the result of the estimating or predicting is that the user is not cognitively aware of the diabetic state warranting attention, then determining when to alert the user with the user prompt.

21. The medium of claim 1, wherein the user prompt, if displayed, includes a color or arrow instead of or in addition to a glucose concentration value, or includes a prediction of a glucose concentration value, or includes an audible indicator, and wherein the volume of the audible indicator is automatically adjusted for ambient noise as measured by the monitoring device or by a device in signal communication with the monitoring device, wherein the adjusting for ambient noise includes raising the volume of the audible indicator relative to the ambient noise until a threshold level of signal to noise ratio is achieved.

22. The medium of claim 1, wherein the user prompt is related to a diabetic state warranting attention occurring during a period when the user has a glycemic urgency index that is low.

23. The medium of claim 1, wherein if the result of the estimating or predicting is that the user is not cognitively aware of the diabetic state warranting attention, then alerting the user with the user prompt after a delay based not on a time duration but on the identified diabetic state warranting attention and on the glucose concentration value and/or a glucose concentration value rate of change, or alerting the user with the user prompt after a delay based not on a time duration but on an individualized pattern learned by the monitoring device, or alerting the user with the user prompt immediately regardless of indications to not alert the user with a user prompt received from other monitoring device applications, or alerting the user with the user prompt immediately regardless of indications to not alert the user with a user prompt based on other user-entered data or settings.

24. The medium of claim 1, wherein the identified diabetic state warranting attention corresponds to an atypical glucose response or an atypical pattern, and wherein the atypical response or atypical pattern is learned by a monitoring device and not by user entry.

25. The medium of claim 1, wherein the user prompt is displayed with dynamic timing on a predesigned user interface and not on an adaptive user interface.

26. The medium of claim 1, wherein the estimating or predicting if the user is cognitively aware of the diabetic state warranting attention is based at least in part on real-time data and not entirely on retrospective data.

27. The medium of claim 1, wherein the alerting a user with a user prompt on a user interface of a monitoring device includes rendering an ultrasonic pulse.

28. A system for providing smart alerts corresponding to diabetic states warranting user attention, comprising:

a CGM application running on a mobile device, the CGM application configured to receive data from a sensor on an at least periodic or occasional basis and to calibrate and display glucose concentration data in clinical units; and

a smart alerts application running as a subroutine within the CGM application or running as a parallel process with the CGM application on the mobile device and receiving data from the CGM application, the smart alerts application configured to perform the method contained on the medium of claim 1.