Glucose Level Deviation Detection

The continuous glucose monitoring system addresses the challenge of interpreting raw glucose data by detecting deviations and providing user-friendly alerts, enhancing diabetes management through real-time insights.

JP2024540815APending Publication Date: 2024-11-06DEXCOM INC
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
JP2024519392
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2021-12-22
Filing Date
2022-10-26
Publication Date
2024-11-06

AI Technical Summary

Technical Problem

Conventional glucose monitoring applications provide raw data that is difficult for users to interpret, leading to frustration and reluctance in using these systems, especially on mobile devices with small screens, hindering effective glucose management.

Method used

A continuous glucose monitoring system that detects deviations in glucose levels by generating aggregate metrics from glucose measurements, comparing them to past trends, and providing user-friendly interfaces to alert users and healthcare providers about deviations.

Benefits of technology

Enables users to understand and respond to glucose level changes in real-time, improving diabetes management by providing actionable insights and reducing user frustration.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024540815000001_ABST
    Figure 2024540815000001_ABST
Patent Text Reader

Abstract

Glucose level measurements of a user are obtained over time, such as from a wearable glucose monitoring device worn by the user. These glucose level measurements may be generated substantially continuously, and thus the device may be configured to generate glucose level measurements at regular or irregular intervals, such as in response to establishing a communication coupling with a different device. These glucose level measurements are analyzed to detect deviations from previous glucose measurements (e.g., glucose measurements received earlier in the day, or glucose measurements received at a corresponding time in the past day or more). An indication of the detected deviations is provided to the user or communicated elsewhere, such as to a medical professional.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] (Related Applications) This application claims the benefit of U.S. Provisional Patent Application No. 63 / 292,942, filed on December 22, 2021, entitled "Glucose Level Deviation Detection," the entire disclosure of which is incorporated herein by reference, and also claims the benefit of U.S. Provisional Patent Application No. 63 / 263,188, filed on October 28, 2021, entitled "Ranking Feedback For Improving Diabetes Management," the entire disclosure of which is incorporated herein by reference. [Background technology]

[0002] Diabetes is a metabolic condition that affects hundreds of millions of people and is one of the leading causes of death worldwide. For people living with type I diabetes, access to treatment is essential for their survival, and it can reduce adverse outcomes among people with type II diabetes. With proper treatment, serious damage to the heart, blood vessels, eyes, kidneys, and nerves caused by diabetes can be avoided. Regardless of the type of diabetes (e.g., type I or type II), successfully managing diabetes involves monitoring and repeatedly adjusting food and activity to control a person's blood sugar, e.g., to reduce serious fluctuations in a person's glucose and / or to lower a person's glucose overall.

[0003] However, many conventional glucose monitoring applications use user interfaces that display raw glucose information in a manner that is difficult for users to interpret, especially those who have only recently begun monitoring their glucose. As a result, users are unable to change their behavior in a meaningful way to improve their glucose. Moreover, over time, these users often become overwhelmed and frustrated by the way these conventional glucose monitoring applications present information, and therefore discontinue use of these applications before improvements in glucose and overall health can be realized. Furthermore, as users increasingly utilize mobile devices (e.g., smart watches and smartphones) to access glucose monitoring information, the limitations imposed by the small screens of these mobile devices further exacerbate the inability of conventional systems to provide meaningful glucose information in a manner that users can understand and act upon. Summary of the Invention [Means for solving the problem]

[0004] To overcome these problems, techniques for glucose level deviation detection are discussed. In one or more implementations, in a continuous glucose level monitoring system, glucose measurements are obtained from a glucose sensor of the continuous glucose level monitoring system, the glucose sensor being inserted at an insertion site of a user. Glucose measurements are measured for the user for each of a plurality of time periods. A first aggregate metric of the user is generated during the time periods. For a first time period of the plurality of time periods, it is determined whether the first aggregate metric indicates a deviation by a first glucose measurement measured for the first time period from glucose measurements measured during a series of a plurality of time periods preceding the first time period. In response to determining that the first aggregate metric indicates a deviation, a user interface identifying the deviation is generated (optionally only if the deviation is selected for display), and the user interface identifying the deviation is displayed.

[0005] In one or more implementations, in a continuous glucose level monitoring system, glucose measurements are obtained from a glucose sensor of the continuous glucose level monitoring system, the glucose sensor being inserted at an insertion site of a user. Glucose measurements of the user are measured for a period of the current day. Aggregate metrics of the user for the period of the current day are generated based on the glucose measurements for the period. Furthermore, aggregate metrics of the user for corresponding periods of the past multiple days are generated based on the glucose measurements for each corresponding period of the past multiple days. It is determined whether the aggregate metrics for the current day period indicate a deviation by the glucose measurements measured for the period of the current day from the glucose measurements measured during the corresponding period of the past multiple days. In response to determining that the aggregate metrics for the current day period indicate a deviation, a user interface identifying the deviation is generated (optionally only if the deviation is selected for display), and the user interface identifying the deviation is displayed.

[0006] This Summary introduces a selection of concepts in a simplified form that are further described below in the Detailed Description. As such, this Summary is not intended to identify essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.

[0007] The detailed description is given with reference to the accompanying drawings. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram of an environment in an example implementation operable to perform glucose level deviation detection as described herein. [Diagram 2] 1 illustrates an example implementation of a wearable glucose monitoring device in more detail. [Diagram 3] FIG. 1 is a diagram of an exemplary architecture of a glucose level deviation detection system. [Figure 4] FIG. 1 illustrates an example implementation of a content-based deviation detection module. [Diagram 5] An example of generating deviation identification information will be described. [Figure 6] 1 shows a procedure in an example for performing glucose level deviation detection. [Figure 7] 13 shows a procedure in another example for performing glucose level deviation detection. [Figure 8] 1 illustrates an overview of example systems, including example computing devices that represent one or more computing systems and / or devices that may implement various techniques described herein. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] overview Techniques for glucose level deviation detection are discussed herein. Generally, blood glucose measurements of a user are obtained over time. These glucose level measurements may be obtained by a wearable glucose monitoring device worn by the user. These glucose level measurements may be generated substantially continuously, such that the device may be configured to generate glucose level measurements at regular or irregular time intervals (e.g., about every hour, about every 30 minutes, about every 5 minutes, etc.), such as in response to the establishment of a communication coupling with a different device (e.g., when a computing device establishes a wireless connection with the wearable glucose level monitoring device to retrieve one or more of the measurements). These glucose level measurements are analyzed to detect deviations from previous glucose measurements (e.g., glucose measurements received earlier in the day, or glucose measurements received at a corresponding time in the past day or more). An indication of the detected deviation is provided to the user or communicated elsewhere, such as to a medical professional.

[0010] In one or more implementations, a data stream of glucose measurements is received. Aggregate metrics (e.g., hyperglycemia risk value, hypoglycemia risk value, average glucose, average coefficient of variation, etc.) are generated for the collection of glucose measurements over a rolling time window (e.g., every 5 minutes, where the collection of glucose measurements includes glucose measurements from the last 30 or 60 minutes), fixed 30 minute intervals (e.g., every hour and half hour of the day), the last 60 minutes, etc. These aggregate metrics are compared to aggregate metrics generated for other time periods to identify deviations in glucose measurements between time periods.

[0011] For example, a risk value may be generated for a time period that includes glucose measurements received during a particular fixed time (e.g., approximately every half hour of the day). The aggregate metric for a given time period is compared to the aggregate metric over a number of immediately preceding time periods (e.g., 24) of the same day to determine whether the aggregate metric for the given time period deviates from the aggregate metric for the past time periods. If a deviation is detected, an indication is displayed or otherwise communicated that there is a deviation between the glucose measurements measured during the given time period and the glucose measurements measured during the past time periods. For example, a user interface may be displayed to the user stating, "Glucose is increasing to its highest level since this morning."

[0012] As another example, aggregate metrics may be generated for a period that includes glucose measurements received over a past hour (e.g., aggregate metrics are generated every 5 minutes based on glucose measurements received over the past 60 minutes). The aggregate metrics for a given period of the current day are compared to the aggregate metrics generated for each corresponding period of the past days to determine whether the aggregate metrics for the given period deviate from the aggregate metrics for the corresponding periods of the past days. If a deviation is detected (and, optionally, if the deviation is selected for display), an indication is displayed or otherwise communicated that there is a deviation between the glucose measurements measured during the given period of the current day and the glucose measurements measured during the past periods. For example, a user interface may be displayed to the user stating, "Glucose in the last hour is higher than this time for each day of the past few days."

[0013] The techniques discussed herein automatically detect deviations in a user's glucose level and provide a notification to the user that this is the case. This makes the user aware of deviations in real time as they occur and alerts the user that they may be doing something different that will significantly impact their glucose level. This provides a teachable moment for the user, helping the user to associate a real-time event or action with a change in glucose level and thus modify their current and future behavior to avoid such a change in glucose level (e.g., if the change is bad) or to maintain such a change in glucose level (e.g., if the change is good). Additionally, this allows alerts or updates to be communicated to health care providers so that they can help the user take corrective action, be alerted to the severity of the change, etc.

[0014] In the following description, an exemplary environment in which the techniques described herein can be used is first described. Then, details of example implementations and procedures that can be performed in the exemplary environment and other environments are described. The execution of the exemplary procedures is not limited to the exemplary environment, and the exemplary environment is not limited to the execution of the exemplary procedures.

[0015] Example Environment 1 is a diagram of an environment 100 in an example implementation operable to perform glucose level deviation detection as described herein. The illustrated environment 100 includes a person 102, who is depicted wearing a wearable glucose monitoring device 104. The illustrated environment 100 also includes a computing device 106, other users in a user population 108 who wear the glucose monitoring device 104, and a glucose monitoring platform 110. The wearable glucose monitoring device 104, the computing device 106, the user population 108, and the glucose monitoring platform 110 are communicatively coupled, such as via a network 112.

[0016] Alternatively or additionally, the wearable glucose monitoring device 104 and the computing device 106 may be communicatively coupled in other manners, such as using one or more wireless communication protocols or techniques. By way of example, the wearable glucose monitoring device 104 and the computing device 106 may communicate with each other using one or more of Bluetooth (e.g., a Bluetooth Low Energy link), near-field communication (NFC), 5G, etc.

[0017] In accordance with the described techniques, the wearable glucose monitoring device 104 is configured to provide measurements of glucose of the person 102. Although a wearable glucose monitoring device is discussed herein, it should be understood that a user interface for glucose monitoring can be generated and presented in association with other devices capable of providing glucose measurements, e.g., non-wearable glucose devices such as blood glucose meters that require a fingerstick, patch, or the like. However, implementations that include a wearable glucose monitoring device 104 can be configured with, for example, a glucose sensor that continuously detects an analyte indicative of the glucose of the person 102 and enables the generation of glucose measurements. In the illustrated environment 100 and throughout the detailed description, these measurements are referred to as glucose measurements 114.

[0018] In one or more implementations, the wearable glucose monitoring device 104 is a continuous glucose monitoring (CGM) system. As used herein, the term "continuous" used in connection with glucose monitoring may refer to the ability of the device to generate measurements substantially continuously, such that the device may be configured to generate glucose measurements 114 in response to establishing a communication coupling with a different device (e.g., when a computing device establishes a wireless connection with the wearable glucose monitoring device 104 to retrieve one or more of the measurements), at regular or irregular time intervals (e.g., every hour, every 30 minutes, every 5 minutes, etc.). This functionality, along with further aspects of the configuration of the wearable glucose monitoring device 104, are described in more detail in connection with FIG. 2.

[0019] Additionally, the wearable glucose monitoring device 104 transmits glucose measurements 114 to the computing device 106, such as via a wireless connection. The wearable glucose monitoring device 104 can communicate these measurements in real time, for example, as they are generated using a glucose sensor. Alternatively or additionally, the wearable glucose monitoring device 104 can communicate the glucose measurements 114 to the computing device 106 at set time intervals. For example, the wearable glucose monitoring device 104 can be configured to communicate the glucose measurements 114 to the computing device 106 (as they are being generated) every five minutes.

[0020] Certainly, the time intervals at which glucose readings 114 are communicated may vary from the above examples without departing from the spirit or scope of the presently described techniques. The readings may be communicated by the wearable glucose monitoring device 104 to the computing device 106 according to other bases in accordance with the presently described techniques, such as upon request from the computing device 106. In any event, the computing device 106 may maintain the glucose readings 114 of the person 102 at least temporarily, for example, within a computer-readable storage medium of the computing device 106.

[0021] Although the computing device 106 is illustrated as a mobile device (e.g., a mobile phone), it may be configured in various ways without departing from the spirit or scope of the described techniques. By way of example and not limitation, the computing device 106 may be configured as different types of devices, such as a mobile device (e.g., a wearable device, tablet device, or laptop computer), a stationary device (e.g., a desktop computer), an automobile computer, etc. In one or more implementations, the computing device 106 may be configured as a dedicated device associated with the glucose monitoring platform 110, which has the functionality to, for example, obtain glucose readings 114 from the wearable glucose monitoring device 104, perform various calculations related to the glucose readings 114, display information related to the glucose readings 114 and the glucose monitoring platform 110, communicate the glucose readings 114 to the glucose monitoring platform 110, etc.

[0022] Furthermore, computing device 106 may represent more than one device in accordance with the described techniques. In one or more scenarios, for example, computing device 106 may correspond to both a wearable device (e.g., a smart watch) and a mobile phone. In such a scenario, both of these devices may be capable of performing at least some of the same operations, such as to retrieve glucose readings 114 from wearable glucose monitoring device 104, communicate those readings to glucose monitoring platform 110 via network 112, display information related to glucose readings 114, etc. Alternatively or additionally, different devices may have different capabilities that other devices do not have or are limited to designated devices through computational instructions.

[0023] In a scenario in which the computing device 106 corresponds to a separate smartwatch and a mobile phone, for example, the smartwatch may be configured with various sensors and capabilities for measuring various physiological markers (e.g., heart rate, heart rate variability, respiration, blood flow velocity, etc.) and activities (e.g., walking or other movement) of the person 102. In this scenario, the mobile phone may not be configured with these sensors and capabilities or may include a limited amount of the capabilities - although in other scenarios the mobile phone may be capable of providing the same functionality. Continuing with this particular scenario, the mobile phone may have capabilities that the smartwatch does not have, such as a camera for capturing images associated with glucose monitoring, and an amount of computing resources (e.g., battery and processing speed) that allows the mobile phone to more efficiently perform calculations related to the glucose measurements 114. Even in scenarios in which the smartwatch is capable of performing such calculations, the computing instructions may limit the execution of those calculations to the mobile phone to not burden both devices and efficiently utilize available resources. To this extent, computing device 106 may be configured in different ways and represent a different number of devices than described herein without departing from the spirit and scope of the described technology.

[0024] According to the discussed techniques, the computing device 106 is configured to perform glucose level deviation detection. In the environment 100, the computing device 106 includes a glucose monitoring application 116 and a storage device 118. Here, the glucose monitoring application 116 includes a glucose level deviation detection system 120. Although shown as being included in the computing device 106, additionally or alternatively, at least some functionality of the glucose level deviation detection system 120 is located elsewhere, such as in the glucose monitoring platform 110. Furthermore, the glucose readings 114 and the deviation identification library 122 are shown stored in the storage device 118. The storage device 118 may also represent one or more databases, as well as other types of storage devices capable of storing the glucose readings 114 and the deviation identification library 122. The deviation identification library 122 stores a number of deviation identification items (e.g., messages or message templates) that can be provided to the user 102 to, for example, inform the user 102 in real time of a current deviation of the user's glucose level relative to the user's glucose level at a corresponding time earlier in the day or in previous days.

[0025] In one or more implementations, the glucose measurements 114 and / or the deviation identification library 122 may be stored at least partially away from the computing device 106, for example, in a memory device of the glucose monitoring platform 110, and retrieved or otherwise accessed in connection with constructing and outputting (e.g., displaying) a user interface for presenting the deviation identification. By way of example, the glucose measurements 114 and / or the deviation identification library 122 may be stored in a memory device of the glucose monitoring platform 110 generally along with the glucose measurements 108 and / or the deviation identification library 122 of a user population, and portions of that data may be retrieved or otherwise accessed as needed to display a user interface for presenting the glucose level deviation identification.

[0026] Generally speaking, the glucose monitoring application 116 is configured to support interactions with a user such that deviations in the glucose level of the user 102 can be identified and presented to the user. This may include, for example, obtaining glucose measurements 114 for processing (e.g., to detect deviations), receiving information about the user (e.g., through an onboarding process and / or user feedback), communicating the information to a healthcare provider, communicating the information to the glucose monitoring platform 110, etc.

[0027] In one or more implementations, the glucose monitoring application 116 also leverages the resources of the glucose monitoring platform 110 in connection with glucose level deviation detection. As mentioned above, by way of example, the glucose monitoring platform 110 may be configured to store data, such as glucose measurements 114 associated with a user (e.g., person 102) and / or users of the user population 108, as well as a deviation identification library 122. The glucose monitoring platform 110 may also provide updates and / or additions to the glucose monitoring application 116. Additionally, the glucose monitoring platform 110 may train, maintain, and / or deploy algorithms (e.g., machine learning algorithms) to detect deviations and select which of a plurality of deviations to present to the user 102. One or more such algorithms may require an amount of computing resources that exceeds the resources of a typical personal computing device, such as a mobile phone, laptop, tablet device, and wearable, just to name a few. Nevertheless, the glucose monitoring platform 110 may include or otherwise have access to resources, such as cloud storage, server devices, virtualization resources, and the like, required to operate such algorithms. The glucose monitoring platform 110 may provide a variety of resources that the glucose monitoring application 116 utilizes in connection with enabling the identification and presentation of deviations via a user interface.

[0028] According to the described techniques, the glucose level deviation detection system 120 is configured to use the glucose measurement value 114 to identify deviations in the user's glucose level, retrieve one or more deviation identifications in a deviation identification library 122, and output one or more user interfaces presenting the deviation identifications. The glucose monitoring application 116 may cause the configured user interface 124 to be displayed via a display device of the computing device 106 or other display device.

[0029] As discussed above and below, in accordance with the described techniques, various glucose level deviation identifications (e.g., messages) may be selected or generated based on the user's glucose measurements 114. Consider the following description of FIG. 2 in the context of measuring glucose, for example, continuously, to obtain data describing such measurements.

[0030] 2 illustrates a more detailed example 200 of an implementation of the wearable glucose monitoring device 104 of FIG. 1. In particular, the illustrated example 200 includes a top view and a corresponding side view of the wearable glucose monitoring device 104. It should be understood from the following description that the wearable glucose monitoring device 104 may be modified in various ways in implementation without departing from the spirit or scope of the described techniques. As mentioned above, by way of example, a user interface that identifies a detected deviation in glucose level may be configured and displayed (or otherwise output) in association with other types of devices for glucose monitoring, such as non-wearable devices (e.g., blood glucose meters requiring a finger stick), patches, etc.

[0031] In this example 200, the wearable glucose monitoring device 104 is illustrated to include a sensor 202 and a sensor module 204. Here, the sensor 202 is shown in a side view inserted, for example, subcutaneously into the skin 206 of the person 102. The sensor module 204 is illustrated as a dashed rectangle in a top view. The wearable glucose monitoring device 104 also includes a transmitter 208 in the illustrated example 200. The use of a dashed rectangle for the sensor module 204 indicates that the sensor module may be contained or otherwise implemented within the housing of the transmitter 208. In this example 200, the wearable glucose monitoring device 104 further includes an adhesive pad 210 and an attachment mechanism 212.

[0032] In operation, the sensor 202, adhesive pad 210, and attachment mechanism 212 may be assembled to form an application assembly, which is configured to be applied to the skin 206 such that the sensor 202 is inserted subcutaneously as depicted. In such a scenario, the transmitter 208 may be attached to the assembly after affixing to the skin 206 via the attachment mechanism 212. Alternatively, the transmitter 208 may be incorporated as part of an application assembly, such that the sensor 202, adhesive pad 210, attachment mechanism 212, and transmitter 208 (with sensor module 204) can be affixed to the skin 206 all at once. In one or more implementations, this application assembly is affixed to the skin 206 using a separate sensor applicator (not shown). Unlike the finger prick required by conventional blood glucose meters, user-initiated application of the wearable glucose monitoring device 104 is substantially painless and does not require the withdrawal of blood. Additionally, an automatic sensor applicator generally allows the person 102 to implant the sensor 202 subcutaneously in the skin 206 without the assistance of a clinician or healthcare provider.

[0033] The application assembly can also be removed by peeling the adhesive pad 210 from the skin 206. It should be understood that the wearable glucose monitoring device 104 and its various components as shown are simply one example form factor, and that the wearable glucose monitoring device 104 and its components can have different form factors without departing from the spirit or scope of the presently described techniques.

[0034] In operation, the sensor 202 is communicatively coupled to the sensor module 204 via at least one communication channel, which may be a wireless connection or a wired connection. Communications from the sensor 202 to the sensor module 204 or from the sensor module 204 to the sensor 202 may be performed actively or passively, and these communications may be continuous (e.g., analog) or discrete (e.g., digital).

[0035] The sensor 202 may be a device, molecule, and / or chemical that changes or causes a change in response to an event that is at least partially independent of the sensor 202. The sensor module 204 is implemented to receive an indication of a change to the sensor 202 or caused by the sensor 202. For example, the sensor 202 may include glucose oxidase that reacts with glucose and oxygen to form hydrogen peroxide that is electrochemically detectable by the sensor module 204, which may include electrodes. In this example, the sensor 202 may be configured as or include a glucose sensor configured to detect an analyte in blood or interstitial fluid that is indicative of a glucose level using one or more measurement techniques. In one or more implementations, the sensor 202 may also be configured to detect analytes in blood or interstitial fluid that are indicative of other markers, such as lactate levels, which may improve accuracy in detecting various glucose level deviations. Additionally or alternatively, the wearable glucose monitoring device 104 may include additional sensors to the sensor 202 for detecting those analytes indicative of other markers.

[0036] In another example, the sensor 202 (or additional, not shown, sensors of the wearable glucose monitoring device 104) can include first and second conductors, and the sensor module 204 can electrically detect a change in electrical potential across the first and second conductors of the sensor 202. In this example, the sensor module 204 and the sensor 202 are configured as a thermocouple, such that the change in electrical potential corresponds to a change in temperature. In some examples, the sensor module 204 and the sensor 202 are configured to detect a single analyte, e.g., glucose. In other examples, the sensor module 204 and the sensor 202 are configured to detect multiple analytes, e.g., sodium, potassium, carbon dioxide, and glucose. Alternatively or additionally, the wearable glucose monitoring device 104 includes multiple sensors for detecting not only one or more analytes (e.g., sodium, potassium, carbon dioxide, glucose, and insulin), but also one or more environmental conditions (e.g., temperature). Thus, the sensor module 204 and the sensor 202 (and any additional sensors) may detect the presence of one or more analytes, the absence of one or more analytes, and / or a change in one or more environmental conditions.

[0037] In one or more implementations, the sensor module 204 can include a processor and memory (not shown). The sensor module 204 can utilize the processor to generate glucose readings 114 based on communications with the sensor 202 exhibiting the changes described above. Based on these communications from the sensor 202, the sensor module 204 is further configured to generate communicable data packages that include the at least one glucose reading 114. In one or more implementations, the sensor module 204 can configure these packages to include additional data including, by way of example and not limitation, a sensor identifier, a state of the sensor, a temperature corresponding to the glucose reading 114, measurements of other analytes corresponding to the glucose reading 114, and the like. It should be understood that such packets can include a variety of data in addition to the at least one glucose reading 114 without departing from the spirit or scope of the described techniques.

[0038] In implementations in which the wearable glucose monitoring device 104 is configured for wireless transmission, the transmitter 208 can wirelessly transmit the glucose readings 114 as a data stream to the computing device. Alternatively or additionally, the sensor module 204 may buffer the glucose readings 114 (e.g., in a memory of the sensor module 204 and / or other physical computer-readable storage medium of the wearable glucose monitoring device 104) and later cause the transmitter 208 to transmit the buffered glucose readings 114 at various intervals, such as time intervals (every second, every 30 seconds, every minute, every 5 minutes, every hour, etc.), storage intervals (when the buffered glucose readings 114 reach a threshold amount of data or number of readings), etc.

[0039] Having considered example environments and example wearable glucose monitoring devices, a description of some example details of techniques for glucose level deviation detection is now considered.

[0040] System Architecture 3 is a diagram of an example architecture of the glucose level deviation detection system 120. The glucose level deviation detection system 120 includes a data collection module 302, a metric determination module 304, a content-based deviation detection module 306, a contextual deviation detection module 308, a deviation selection module 310, and a UI module 312. In general, the glucose level deviation detection system 120 analyzes the glucose measurements 114 of the user 102 and looks for deviations from the user's norm. These deviations from norm may be based on a variety of factors, such as metrics generated from the user's current or recent glucose level versus metrics generated from the user's glucose levels prior to that day, metrics generated from the user's current or recent glucose level versus metrics generated from the user's glucose levels at corresponding times in the past few days, etc. Upon detection of one or more deviations, the glucose level deviation detection system 120 takes a responsive action, such as presenting an identification of the deviation to the user, communicating an identification of the deviation to a medical professional, etc.

[0041] More specifically, the data collection module 302 receives glucose measurements 114 of the user 102. The glucose measurements 114 are received at specific intervals, such as approximately every minute or approximately every five minutes. The glucose measurements 114 are grouped into measurement sets. In one or more implementations, the measurement sets are set periods of time within 24 hours, such as glucose measurements 114 received during half-hourly periods (e.g., 1:00 PM to 1:30 PM, 1:30 PM to 2:00 PM, 2:00 PM to 2:30 PM, etc.). Additionally or alternatively, the measurement sets are rolling time windows, such as glucose measurements 114 received over the past 30 minutes or 60 minutes. For example, upon receiving a new glucose measurement 114 (e.g., approximately every 5 minutes), the data collection module 302 groups the glucose measurements 114 received over the past 30 minutes or hour into measurement sets. The data collection module 302 outputs the measurement sets as collected measurements 320.

[0042] The metric determination module 304 receives the collected measurements 320 and generates one or more aggregate metrics 322 (or single-value metrics) from the collected measurements 320. An aggregate metric (also simply called a metric) is a representation or summary of the data in the collected measurements 320. The metric determination module 304 can generate any of a variety of different metrics based on the collected measurements 320. In one or more implementations, the metric determination module 304 generates a risk value, which is a glycemic risk value indicative of a potential health risk to the user 102 due to the glucose level.

[0043] Additionally or alternatively, the metric determination module 304 may determine as aggregate metrics 322 the average glucose reading across the collected measurements 320, the average coefficient of variation across the glucose readings across the collected measurements 320 (the ratio of the standard deviation to the mean of the glucose readings across the collected measurements 320), the mean amplitude of glycemic excursion across the glucose readings across the collected measurements 320, the mean ... Any of a variety of statistics may be generated from the collected measurements 320, such as mean glucose excursion (MAGE), area under the glucose curve for the glucose measurements in the collected measurements 320, area on the glucose curve for the glucose measurements in the collected measurements 320, mean absolute rate of change of the glucose measurements in the collected measurements 320, standard deviation of the glucose measurements in the collected measurements 320, average time that the glucose measurements were below a particular glucose level (e.g., 250 mg / dL or 70 mg / dL) during collection of the collected measurements 320, average time that the glucose measurements were above a particular glucose level (e.g., 250 mg / dL) during collection of the collected measurements 320, maximum glucose reading for the collected measurements 320, etc.

[0044] Additionally or alternatively, the metric determination module 304 generates an aggregate metric 322 using different techniques to combine the glucose measurements in the collected measurements 320, such as median, interquartile range (IQR), XX rank, standard deviation, etc.

[0045] Additionally or alternatively, the metric determination module 304 generates single-valued metrics that are not aggregate metrics. For example, the metric determination module 304 can generate metrics that are the maximum glucose reading in the collected readings 320, the absolute rate of change of glucose readings in the collected readings 320, etc. The metric determination module 304 outputs these single-valued metrics for use by the content-based deviation detection module 306 and the contextual deviation detection module 308, as well as the aggregate metrics 322.

[0046] In one or more implementations, the aggregate metric 322 is a glycemic risk value that indicates the potential health risk to the user 102 due to the glucose level. In one or more embodiments, these risk values ​​include one or both of a hyperglycemic risk value and a hypoglycemic risk value. The hyperglycemic risk value and the hypoglycemic risk value may be determined in any of a variety of different ways.

[0047] In one or more embodiments, the hyperglycemia risk value is based on a hyperglycemic index (HBGI) value generated for a self-monitoring blood glucose (SMBG) measurement. The HBGI value (HBGI) is generated by generating a risk r(BG) as follows: r(BG)=10·(1.509·([log(BG)] 1.084 -5.381) 2 where BG refers to the collected measurement 320. The risk r(BG) balances the amplitudes of the hypoglycemic and hyperglycemic ranges (increasing the amplitude of the hypoglycemic range and decreasing the amplitude of the hyperglycemic range), makes the transformed data symmetrical around 0, and fits a normal distribution.

[0048] The HBGI value (HBGI) is generated as follows:

[0049]

number

[0050] In one or more embodiments, the hypoglycemia risk value is based on a hypoglycemic index (LBGI) value generated for the SMBG measurement. The LBGI value (LBGI) is generated as follows:

[0051]

number

[0052] The content-based deviation detection module 306 detects deviations from the user's typical glucose level trends in recent history by monitoring aggregate metrics 322. This is also referred to as content-based deviation detection because the detection is performed based on recent glucose measurements. The content-based deviation detection module 306 receives the aggregate metrics 322 and determines, based on the aggregate metrics 322, whether a recently collected measurement 320 indicates a deviation in the user's 102 glucose level relative to measurements 320 collected in the past (e.g., over the past 12 hours).

[0053] The content-based deviation detection module 306 determines whether there is a deviation in the glucose level of the user 102 at regular or irregular intervals based on a past period of time. In one or more implementations, the metric determination module 304 generates an aggregate metric 322 approximately every 30 minutes, and the content-based deviation detection module 306 determines whether there is a deviation in the glucose level of the user 102 approximately every 30 minutes, in response to receiving a new aggregate metric 322 from the metric determination module 304, by comparing the most recently received aggregate metric 322 with the 24 previously received aggregate metrics 322 (e.g., the aggregate metrics 322 received over the past 12 hours). The aggregate metrics 322 are stored, for example, in an aggregate metric store 324, so that previously received aggregate metrics 322 are readily available to the content-based deviation detection module 306. The aggregate metric store 324 can be any of various types of storage devices (e.g., random access memory, flash memory, magnetic disk, etc.).

[0054] Additionally or alternatively, other intervals or time periods can be used. For example, the metric determination module 304 may generate one or more aggregate metrics 322 approximately every 15 minutes, and the content-based deviation detection module 306, in response to receiving a new aggregate metric 322 from the metric determination module 304, determines whether there is a deviation in the glucose level of the user 102 approximately every 15 minutes by comparing the most recently received aggregate metric 322 with the aggregate metrics 322 received over the past 10 hours. As another example, the metric determination module 304 may generate one or more aggregate metrics 322 approximately every 5 minutes (using a rolling time window of the past 30 minutes), and the content-based deviation detection module 306, in response to receiving a new aggregate metric 322 from the metric determination module 304, determines whether there is a deviation in the glucose level of the user 102 approximately every 5 minutes by comparing the most recently received aggregate metric 322 with the aggregate metrics 322 received over the past 12 hours.

[0055] In one or more embodiments, the content-based deviation detection module 306 receives the most recently generated aggregate metrics 322 (e.g., the hypoglycemia risk values ​​and hyperglycemia risk values ​​most recently generated by the metric determination module 304) and generates predicted aggregate metrics (e.g., predicted hypoglycemia risk values ​​and predicted hyperglycemia risk values) based on the previously received aggregate metrics 322. The content-based deviation detection module 306 compares the predicted aggregate metrics to the received aggregate metrics and determines that a deviation exists in the glucose level of the user 102 relative to the previously collected measurements 320 if the predicted aggregate metrics and the received aggregate metrics differ by more than a specified amount (e.g., more than a threshold amount such as 5.5). The content-based deviation detection module 306 outputs an indication of the detected deviation based on the aggregate metrics 322.

[0056] 4 is a diagram of an example implementation of the content-based deviation detection module 306. In the example of FIG. 4, the aggregate metric 322 includes a hypoglycemia risk value and a hyperglycemia risk value. It should be noted that although described with reference to a hypoglycemia risk value and a hyperglycemia risk value, the content-based deviation detection module 306 may similarly use any other aggregate metric in addition to or in place of the hypoglycemia risk value and the hyperglycemia risk value.

[0057] In the example of FIG. 4, the content-based deviation detection module 306 includes a hypoglycemia risk value prediction module 402, a hyperglycemia risk value prediction module 404, and a deviation identification module 406. Hypoglycemia risk values ​​408 and 410 and hyperglycemia risk values ​​412 and 414 are generated by the metric determination module 304 from the collected measurements 320, as described above. As shown, hypoglycemia risk values ​​and hyperglycemia risk values ​​are generated for each set of measurements 320. The hypoglycemia risk value 408 is provided to the hypoglycemia risk value prediction module 402. The hypoglycemia risk value prediction module 402 generates a predicted risk value 416 for the most recently received hypoglycemia risk value (actual hypoglycemia risk value 410 in the example of FIG. 4) based on the past hypoglycemia risk values ​​408. Similarly, the hyperglycemia risk value 412 is provided to the hyperglycemia risk value prediction module 404. The hyperglycemia risk value prediction module 404 generates a predicted risk value 418 for the most recently received hyperglycemia risk value (actual hyperglycemia risk value 414 in the example of FIG. 4) based on the past hyperglycemia risk values ​​412.

[0058] In one or more implementations, the hypoglycemia risk prediction module 402 uses a machine learning system to generate the predicted risk value 416, and the hyperglycemia risk value prediction module 404 uses a machine learning system to generate the predicted risk value 418. A machine learning system refers to a computer representation that can be tuned (e.g., trained) based on inputs to approximate an unknown function. In particular, a machine learning system can include a system that utilizes algorithms that learn from and make predictions on known data by analyzing known data to learn to generate outputs that reflect patterns and attributes of the known data. For example, machine learning systems can include decision trees, support vector machines, linear regression, logistic regression, Bayesian networks, random forest learning, dimensionality reduction algorithms, boosting algorithms, artificial neural networks, deep learning, and the like.

[0059] The machine learning system of the hypoglycemia risk value prediction module 402 is trained by using training data, e.g., a set of multiple risk values. Each set of multiple (X) risk values ​​includes hypoglycemia risk values ​​(values ​​1, ..., X-1) for multiple sets of measurements. The machine learning system generates predicted hypoglycemia risk values ​​based on the training data values ​​(1, ..., X-1), and the machine learning system is trained by updating weights or values ​​of layers within the machine learning system to minimize the loss between the predicted hypoglycemia risk values ​​416 and the actual hypoglycemia risk values ​​(value X). A variety of different loss functions can be used in training the machine learning system, such as cross-entropy loss, mean squared error loss, etc.

[0060] Similarly, the machine learning system of the hyperglycemia risk value prediction module 404 is trained by using training data, which may be, for example, a set of multiple risk values. This training data may be the same training data used to train the machine learning system of the hypoglycemia risk value prediction module 402. Each set of multiple (X) risk values ​​includes hyperglycemia risk values ​​(values ​​1, ..., X-1) for multiple sets of measurements. The machine learning system generates predicted hyperglycemia risk values ​​based on the training data values ​​(1, ..., X-1), and the machine learning system is trained by updating the weights or values ​​of layers within the machine learning system to minimize the loss between the predicted hyperglycemia risk values ​​418 and the actual hyperglycemia risk values ​​(values ​​X). A variety of different loss functions may be used in training the machine learning system, such as cross-entropy loss, mean squared error loss, etc.

[0061] In one or more embodiments, users are divided into different populations having one or more similar characteristics. User 102 is part of one of these different populations, and the machine learning systems of the hypoglycemia risk value prediction module 402 and the hyperglycemia risk value prediction module 404 are trained using training data obtained from other users who belong to the same population as user 102 (e.g., excluding all data obtained from users who do not belong to the same population as user 102). The populations may be defined in any of a variety of different ways. In one or more embodiments, the populations are defined by a diabetes diagnosis (e.g., the user is not diabetic, the user has type 1 diabetes, or the user has type 2 non-insulin dependent diabetes). Additionally or alternatively, the populations are defined in different ways, such as age-based populations. For example, the populations are based on whether the user is an adult or a child (e.g., over 18 years old or under 18 years old), the age group the user belongs to (e.g., 0-5 years old, 5-10 years old, 10-20 years old, 20-30 years old, etc.), etc. As another example, a population may be defined based on additional medical conditions the user may have, such as hypertension, obesity, cardiovascular disease, neuropathy, nephropathy, retinopathy, Alzheimer's disease, depression, etc. As another example, a population may be defined based on the habits or activities of the user, such as exercise or other physical activity, sleep patterns, work hours versus leisure time, etc. As another example, a population may be defined based on the manner in which the glucose readings 114 are obtained or the equipment used to obtain the glucose readings 114, e.g., whether the glucose readings 114 are obtained via CGM, the brand of the wearable glucose monitoring device 104, the frequency with which the glucose readings 114 are obtained, etc.

[0062] As another example, the population may be defined based on the users' past glucose measurements 114, such as by grouping users by clustering based on the past glucose measurements 114. Examples of such clusters include users with high glycemic variability, users with frequent hypoglycemia, users with frequent hyperglycemia, etc. As another example, users may be grouped by clustering by using the users' past activity data (e.g., steps, energy expenditure, exercise minutes, sleep hours, etc. obtained from an activity tracker worn by the users). Examples of such clusters include users with a high average number of steps per day, users with a low average energy expenditure per day, users with a low average number of sleep hours, etc.

[0063] Dividing users into different populations allows the glucose level deviation detection system 120 to be customized to a particular user 102, such as by training a machine learning system based on data from other users with similar characteristics. This improves the accuracy of the machine learning systems of the hypoglycemia risk value prediction module 402 and the hyperglycemia risk value prediction module 404, since data from users different from the particular user 102 does not need to be considered.

[0064] Although separate hypoglycemia risk value prediction modules 402 and hyperglycemia risk value prediction modules 404 are discussed, additionally or alternatively, the content-based deviation detection module 306 includes a single risk value prediction module that generates both the predicted risk value 416 and the predicted risk value 418 (and optionally additional aggregate metrics). For example, a single machine learning system can be trained to generate both the predicted risk value 416 and the predicted risk value 418 (and optionally other predictive aggregate metrics). Additionally or alternatively, the content-based deviation detection module 306 may include a prediction module that generates predictive aggregate metrics of other aggregate metrics (e.g., average glucose, average coefficient of variation, average time in range, etc.).

[0065] The deviation identification module 406 determines whether a hypoglycemic deviation exists in the glucose level of the user 102 based on the predicted risk value 416 and the actual risk value 410. The deviation identification module 406 may make this determination in any of a variety of different ways. In one or more embodiments, the deviation identification module 406 determines that a deviation exists in the glucose level of the user 102 in response to the predicted risk value 416 and the actual risk value 410 differing by at least a threshold amount. This threshold amount may be a fixed value (e.g., 5.5) or a variable value (e.g., 10% of the predicted risk value 416 or the actual risk value 410).

[0066] Similarly, the deviation identification module 406 determines whether a hyperglycemic deviation exists in the glucose level of the user 102 based on the predicted risk value 418 and the actual risk value 414. The deviation identification module 406 may make this determination in any of a variety of different ways. In one or more embodiments, the deviation identification module 406 determines that a deviation exists in the glucose level of the user 102 in response to the predicted risk value 418 and the actual risk value 414 differing by at least a threshold amount. This threshold amount may be a fixed value (e.g., 5.5) or a variable value (e.g., 10% of the predicted risk value 418 or the actual risk value 414).

[0067] The deviation identification module 406 outputs a deviation indication 326 that indicates whether a deviation in glucose level (hyperglycemia or hypoglycemia) exists for the user 102 .

[0068] It can thus be seen that the deviation identification module 406 focuses on errors in predictions by the hypoglycemia risk value prediction module 402 and the hyperglycemia risk value prediction module 404. Large prediction errors indicate that the glucose measurements in the collected measurements 320 are changing in an unpredictable manner and thus potentially deviating from the predicted measurements.

[0069] Returning to FIG. 3, the context deviation detection module 308 detects real-time deviations from recurring, typical glucose level trends found in the extended history of the user's glucose levels. This is also referred to as context-based outlier detection, as the detection is based on the current glucose level in the context of the user's extended history of glucose levels (e.g., the past 3 days, the past 2 weeks, etc.). The context deviation detection module 308 receives an aggregate metric 322 and determines, based on the aggregate metric 322, whether a recently collected measurement 320 (e.g., received over the past hour) indicates a deviation in the user's 102 glucose level relative to a previously collected measurement 320 (e.g., over a corresponding time period of the past 3-14 days).

[0070] The context deviation detection module 308 determines whether there is a deviation in the glucose level of the user 102 based on the recent time period and corresponding time periods in each of the past days. The context deviation detection module 308 receives one or more aggregate metrics 322 from the metric determination module 304. Although shown as the same aggregate metric, the content-based deviation detection module 306 and the context deviation detection module 308, optionally, receive different aggregate metrics. For example, the content-based deviation detection module 306 and the context deviation detection module 308 may receive aggregate metrics 322 at different time intervals based on measurements 320 collected over different time periods or past minutes, may receive aggregate metrics for different metrics (e.g., the content-based deviation detection module 306 may receive hypoglycemia risk values ​​and hyperglycemia risk values, the context deviation detection module 308 may receive average glucose and average amplitude for the blood glucose excursion metric), etc.

[0071] In one or more implementations, the metric determination module 304 generates an aggregate metric 322 approximately every 5 minutes (using a rolling window of a particular time period, such as the past 60 minutes), and the context deviation detection module 308, in response to receiving a new aggregate metric 322 from the metric determination module 304, determines whether there is a deviation in the glucose level of the user 102 approximately every 5 minutes by comparing the aggregate metric 322 received for the particular time period with the aggregate metric 322 received for each corresponding time period of the past multiple days. The data collection module 302 can generate a set of measurements 320, and the metric determination module 304 can generate one or more aggregate metrics 322 in response to receiving the glucose measurements 114.

[0072] The context deviation detection module 308 can compare the most recently generated aggregate metrics 322 (e.g., the hypoglycemia risk values ​​and hyperglycemia risk values ​​most recently generated by the metric determination module 304) with the aggregate metrics for each corresponding period of the past several days in any of a variety of different ways to determine whether a deviation exists in the glucose level of the user 102.

[0073] In one or more embodiments, the context deviation detection module 308 generates a value representing or combining the aggregate metric for a corresponding period of each of the past days. For example, this value may be any of a variety of statistical values, such as an average of the risk values ​​for each of the past days (or for a subgroup of the past days), an average of the risk values ​​for each of the past days (or for a subgroup of the past days), etc. The context deviation detection module 308 determines that a deviation in the glucose level of the user 102 exists in response to a difference between the value representing the aggregate metric for the corresponding period of each of the past days and the most recently generated aggregate metric 322 being at least a threshold amount. This threshold amount may be a fixed value (e.g., 7) or a variable value (e.g., 10% of the most recently received aggregate metric 322 or 10% of the value representing the aggregate metric for the corresponding period of each of the past days).

[0074] The context deviation detection module 308 may use any of a variety of rules or criteria to determine the number of previous days (or days) to compare with the most recently generated aggregate metric. For example, the context deviation detection module 308 may compare the most recently generated aggregate metric with each of the aggregate metrics of the previous days for a predefined number of days, such as 14 days. The number of days may be predefined in a variety of ways, such as by a developer or designer of the context deviation detection module 308, by user input from the user 102, by input from a healthcare provider, etc. As another example, the context deviation detection module 308 may compare the most recently generated aggregate metric with aggregate metrics of at least a certain number of days, and then increment that number (e.g., aggregate metrics for the last 3 days, then aggregate metrics for the last 4 days, then aggregate metrics for the last 5 days, etc.).

[0075] The context deviation detection module 308 determines whether a deviation exists in the glucose level of the user 102 based on the aggregate metric generated by the metric determination module 304. The context deviation detection module 308 outputs a deviation indication 328 that indicates whether a deviation exists in the glucose level of the user 102 (e.g., and an indication of the aggregate metric that provides an identification of the deviation in the glucose level).

[0076] Figure 5 illustrates an example 500 of generating a deviation indication 328. In the example of Figure 5, the aggregate metric 322 includes a hypoglycemia risk value. It should be noted that although described with reference to a hypoglycemia risk value, the context deviation detection module 308 may similarly use any other aggregate metric in addition to or instead of the hypoglycemia risk value.

[0077] In the example of Figure 5, example 500 shows a graph 502 of glucose measurements and risk values ​​over multiple days (December 27th - January 1st). Graph 502 shows glucose measurements on the right ranging from 0 to 300 and hyperglycemia risk values ​​on the left ranging from 0 to 30. A solid line 504 plots the glucose measurements and a dashed line 506 plots the precursor to the hyperglycemia risk value. Multiple risk values ​​508 are generated over a one hour period.

[0078] In the illustrated example, the metric determination module 304 generates a hyperglycemia risk value 508 approximately every 5 minutes (using a rolling window of 60 minute periods). In response to receiving a new hyperglycemia risk value 510 from the metric determination module 304, the context deviation detection module 308 determines whether there is a deviation between the glucose level of the user 102 for the previous 60 minutes of the current day and the hyperglycemia risk value 512 for a corresponding period on each of the past days. In the illustrated example, the context deviation detection module 308 receives the risk value 510 on January 1, 2022 at approximately 3:40 PM and compares the risk value 510 to risk values ​​512 corresponding to the same previous 60 minutes (2:40 PM to 3:40 PM) from each of December 27, 2021 to December 31, 2021.

[0079] In the illustrated example, the context deviation detection module 308 determines that a deviation exists in the glucose level of the user 102 in response to a difference between the most recently generated hyperglycemia risk value and a value representative of the hyperglycemia risk value for the previous three days being at least a threshold amount. The hyperglycemia risk value for each day is represented by a circle in the graph 502, and the hyperglycemia risk value for the previous three days is represented by a solid circle with cross-hatching.

[0080] Returning to FIG. 3, the content-based deviation detection module 306 and the context deviation detection module 308 each enable detection of glucose level deviations that the other modules cannot detect. For example, glucose levels over a period of time may be relatively consistent within a small range for the previous 12 hours, but significantly different from the corresponding period of the past few days. Thus, the content-based deviation detection module 306 does not detect the deviation, but the context deviation detection module 308 does. As another example, glucose levels over a period of time may be relatively consistent for the corresponding period of the past few days, but significantly different from the previous 12 hours. Thus, the context deviation detection module 308 does not detect the deviation, but the content-based deviation detection module 306 does.

[0081] The deviation selection module 310 receives deviation indications 326 and 328 from the content-based deviation detection module 306 and the contextual deviation detection module 308, respectively. The deviation selection module 310 selects one or more of the deviation indications 326 and 328 and retrieves a corresponding deviation identification 330 from the deviation identification library 122. The retrieved deviation identification 330 is a message or communication that may be displayed or communicated to another device, a user, a medical professional, etc. that identifies or describes the corresponding deviation indication 326 or deviation indication 328. The deviation selection module 310 provides the retrieved corresponding deviation identification 330 to the UI module 312.

[0082] The deviation selection module 310 determines the deviation identification 330 that corresponds to the deviation indication 326 or the deviation indication 328 in any of a variety of different ways. In one or more implementations, the deviation selection module 310 maintains a mapping of deviation identifications 330 to deviation indications. Additionally or alternatively, the deviation selection module 310 can determine the deviation identification 330 that corresponds to the deviation indication 326 or the deviation indication 328 using any of a variety of other rules or criteria.

[0083] In one or more embodiments, the deviation selection module 310 selects a deviation identification 330 for each deviation identified in the deviation indications 326 and 328. This causes the deviation selection module 310 to select multiple deviation identifications 330 to be displayed or otherwise presented by the UI module 312.

[0084] Additionally or alternatively, in situations where multiple deviation identification information is received, the deviation selection module 310 selects a subset (e.g., one) of the deviations. The deviation selection module 310 may select one of the multiple deviations in various ways, such as randomly or pseudo-randomly selecting one of the multiple deviations. Additionally or alternatively, the deviation selection module 310 may prioritize the multiple deviations and select one of the multiple deviations having the highest priority. For example, the deviation having the highest priority is selected.

[0085] The deviation selection module 310 optionally uses various criteria to determine which deviation to select from among the multiple deviations. These criteria may be based on various factors such as how long ago the deviation occurred, the rank or priority of the deviation or metric, the category of the deviation or metric, the number of consecutive days the deviation or metric occurred, etc. For example, a less recent, previously occurring deviation is selected in preference to a more recently occurring deviation. For example, this may allow a different deviation to be selected, to prevent the same deviation from being displayed repeatedly too frequently.

[0086] As another example, the deviation selection module 310 can select deviations from one of the content-based deviation detection module 306 and the contextual deviation detection module 308 in preference to the other. For example, the deviation selection module 310 may select deviations identified by the content-based deviation detection module 306 in preference to deviations identified by the contextual deviation detection module 308. Or, the deviation selection module 310 may select deviations from one of the content-based deviation detection module 306 and the contextual deviation detection module 308 that have not been identified for the longest period of time.

[0087] As another example, deviations designated (e.g., by a developer or designer of the deviation selection module 310) as being more critical or safety relevant may be selected in preference to deviations that are less critical or safety relevant. For example, this may allow deviations corresponding to critical or safety relevant characteristics (e.g., not staying within range or not exceeding a threshold glucose level) to be selected in preference to other non-critical or non-safety relevant characteristics to display or otherwise present more important diabetes management information to the user.

[0088] As another example, deviations designated (e.g., by the user 102) to be of higher priority may be selected in preference to deviations designated (e.g., by the user 102) to be of lower priority. For example, this may allow deviations of greater interest to the user to be displayed or otherwise presented rather than deviations of less interest to the user.

[0089] As another example, the deviation selection module 310 may select a deviation only if the deviation has not been selected for at least a threshold time. For example, the deviation selection module 310 may select a deviation only if the deviation has not been selected for at least 30 minutes or two days, the deviation selection module 310 may select a particular deviation only if at least a threshold number (e.g., 3 or 5) other deviations have been selected since the particular deviation was last selected, etc.

[0090] As another example, the deviation selection module 310 may select deviations based on a population of which the user 102 is a part. The population may be defined or described in various ways, as described above. By way of example, a particular deviation may be selected over other deviations based on whether the user has type 1 or type 2 diabetes, based on the age of the user, based on other medical conditions the user has, etc.

[0091] As another example, the deviation selection module 310 may select deviations based on other factors or input from various medical sources. By way of example, certain deviations may be selected in preference to other deviations based on input from subject matter experts (e.g., experts in the field of diabetes management), clinical guidelines, professional literature, etc.

[0092] The UI module 312 receives the one or more deviation identifications 330 and causes (e.g., at the computing device 106) to be displayed or otherwise presented the deviation identifications 330. This display or other presentation may take a variety of forms, such as a static text display, a graphic or video display, an audio presentation, combinations thereof, etc. Additionally or alternatively, the one or more deviation identifications 330 may be communicated or otherwise presented to a clinician, pharmacist, other healthcare provider, etc.

[0093] The particular content or message of the deviation identification 330 presented by the UI module 312 may vary. The content or message in the deviation identification 330 may be any suitable text or other content based on the selected deviation. Examples of such content or messages include "Glucose is a little higher than normal," "Glucose is a little lower than normal," "Glucose is a little higher than it has been in the past few afternoons," "Glucose has risen significantly since this morning," "Glucose has increased to its highest level since this morning," "Glucose is higher than it has been at this time each day for the past few days," etc.

[0094] Thus, the content or message in deviation identification 330 may be a positive response, such as a positive or self-serving praise response for deviations trending away from normal behavior. Additionally or alternatively, the content or message in deviation identification 330 may be a preemptive warning, such as acknowledging deviations trending negatively, to forestall a worsening pattern.

[0095] The UI module 312 can communicate, display, or otherwise present the deviation identification 330 at any of a variety of different times. In one or more embodiments, the UI module 312 communicates, displays, or otherwise presents the deviation identification 330 in response to receiving the deviation identification 330 from the deviation selection module 310 (e.g., approximately simultaneously with the deviation being detected by the content-based deviation detection module 306 or the contextual deviation detection module 308). Additionally or alternatively, the UI module 312 communicates, displays, or otherwise presents the deviation identification 330 at other times, such as upon completion of a meal, at regular or irregular intervals (e.g., approximately every 5 minutes, with the deviation selection module 310 optionally selecting a different one of the plurality of deviation identifications 330 every 5 minutes), in response to a user input requesting a current deviation identification 330, etc.

[0096] The glucose level deviation detection system 120 optionally takes additional actions based on the detected deviation (or lack thereof). In one or more implementations, these actions include informing the glucose monitoring application 116 or the wearable glucose monitoring device 104 that it may increase or decrease the frequency of generating glucose readings 114. For example, if the glucose level deviation detection system 120 identifies a period (e.g., multiple days) during which no deviations are detected, the glucose level deviation detection system 120 informs the glucose monitoring application 116 or the wearable glucose monitoring device 104 that it may reduce the frequency of generating glucose readings 114 during that period (e.g., from every 5 minutes to every 10 minutes) to reduce the power consumed in generating the glucose readings 114. As another example, if the glucose level deviation detection system 120 identifies a deviation for a period of time, the glucose level deviation detection system 120 notifies the glucose monitoring application 116 or the wearable glucose monitoring device 104 that the frequency of generating glucose readings 114 may be increased (e.g., from every 5 minutes to every 2 minutes) during that period of the following days or for subsequent periods of the day to increase the accuracy of the risk value generated due to the increased number of glucose readings 114.

[0097] Although described as using aggregate metrics 322, additionally or alternatively, the collected measurements 320 are provided to one or both of the content-based deviation detection module 306 and the contextual deviation detection module 308. In such a situation, the content-based deviation detection module 306 or the contextual deviation detection module 308 would be similar to that described above, but would use the collected measurements 320 rather than the aggregate metrics 322 to identify deviations.

[0098] Further, the glucose level deviation detection system 120 is described as including both a content-based deviation detection module 306 and a contextual deviation detection module 308, which can operate simultaneously to generate deviation indications. Additionally or alternatively, the glucose level deviation detection system 120 includes only one of the content-based deviation detection module 306 and the contextual deviation detection module 308.

[0099] Having discussed exemplary details of techniques relating to user interfaces that present glucose insights, we now consider some example procedures to illustrate additional aspects of these techniques.

[0100] Exemplary Procedure This section describes example procedures for performing glucose level deviation detection. Aspects of the procedures may be implemented in hardware, firmware, software, or combinations thereof. The procedures are illustrated as a set of blocks that specify operations to be performed by one or more devices, and are not necessarily limited to the order shown for performing the operations by each block.

[0101] 6 illustrates an example procedure 600 for performing glucose level deviation detection. The procedure 600 is performed by a glucose level deviation detection system, such as the glucose level deviation detection system 120.

[0102] Glucose measurements of the user are obtained for each of a number of time periods (block 602). These glucose measurements are obtained, for example, from a glucose sensor of a continuous glucose level monitoring system, where the glucose sensor is inserted at an insertion site of the user. These time periods are, for example, 30 minutes.

[0103] During each of the multiple time periods, one or more aggregate metrics are generated for the user (block 604). These one or more aggregate metrics may include, for example, hyperglycemic and hypoglycemic risk values ​​(e.g., hyperglycemic and hypoglycemic indices), average glucose, average coefficient of variation, average time in range, etc.

[0104] The aggregate metric indicates deviation from glucose measurements taken during a series of previous time periods (block 606). For example, a determination may be made as to whether a most recently generated aggregate metric indicates deviation from glucose measurements taken during the previous 12 hours.

[0105] A user interface is generated that identifies the deviations (block 608). In some situations, multiple deviations may be shown in block 606, in which case one or more of the identified deviations are selected for inclusion in the user interface in block 608.

[0106] A user interface including the identified deviations is displayed (block 610) or otherwise presented. Additionally or alternatively, the identified or selected deviations may be communicated or otherwise presented to a clinician, pharmacist, or other healthcare provider.

[0107] 7 illustrates another example procedure 700 for performing glucose level deviation detection. The procedure 700 is performed by a glucose level deviation detection system, such as the glucose level deviation detection system 120.

[0108] Glucose measurements of the user are obtained for a period of time during the day (block 702). These glucose measurements are obtained, for example, from a glucose sensor of a continuous glucose level monitoring system, where the glucose sensor is inserted at an insertion site of the user. The period of time is, for example, 30 minutes.

[0109] One or more aggregate metrics are generated for the user during that period of the day (block 704). These one or more aggregate metrics may include, for example, hyperglycemic and hypoglycemic risk values ​​(e.g., hyperglycemic and hypoglycemic indices), average glucose, average coefficient of variation, average time in range, etc.

[0110] An aggregate metric is generated for the user during a corresponding time period for each of the past days (block 706). For example, the corresponding time periods are the same 30 minute period as the current day. The aggregate metric is the same as at least one of the aggregate metrics generated in block 704. A determination is made as to whether the aggregate metric for the current day period indicates a deviation from glucose measurements taken during the corresponding time period for the past days (block 708).

[0111] A user interface is generated that identifies the deviations (block 710). In some situations, multiple deviations may be shown in block 708, in which case one or more of the identified deviations are selected for inclusion in the user interface in block 710.

[0112] A user interface including the identified deviations is displayed (block 712) or otherwise presented. Additionally or alternatively, the identified or selected deviations may be communicated or otherwise presented to a clinician, pharmacist, or other healthcare provider.

[0113] Exemplary Systems and Devices 8 illustrates at 800 an overview of an example system that includes an example computing device 802 that represents one or more computing systems and / or devices capable of implementing the various techniques described herein. This is illustrated through the inclusion of glucose level deviation detection system 120. Computing device 802 may be, for example, a service provider's server, a device associated with a client (e.g., a client device), an on-chip system, and / or any other suitable computing device or computing system.

[0114] The exemplary computing device 802 as shown includes a processing system 804, one or more computer-readable media 806, and one or more I / O interfaces 808 communicatively coupled to each other. Although not shown, the computing device 802 may further include a system bus or other data and command transfer system coupling the various components together. The system bus may include any one or combination of different bus structures, such as a memory bus or memory controller, a peripheral bus, a universal serial bus, and / or a processor or local bus utilizing any of a variety of bus architectures. Various other examples, such as control and data lines, are also contemplated.

[0115] The processing system 804 represents functionality for performing one or more operations using hardware. Thus, the processing system 804 is illustrated as including hardware elements 810, which may be configured as a processor, functional blocks, etc. This may include implementation in hardware as an application specific integrated circuit or other logic device formed using one or more semiconductors. The hardware elements 810 are not limited by the material from which they are formed, or the processing mechanisms employed therein. For example, a processor may be comprised of semiconductors and / or transistors (e.g., electronic integrated circuits (ICs)). In this context, processor-executable instructions may be electronically executable instructions.

[0116] The computer readable medium 806 is illustrated as including a memory / storage component 812. The memory / storage component 812 represents memory / storage capacity associated with one or more computer readable media. The memory / storage component 812 may include volatile media (such as random access memory (RAM)) and / or non-volatile media (such as read only memory (ROM), flash memory, optical disks, magnetic disks, etc.). The memory / storage component 812 may include fixed media (e.g., RAM, ROM, fixed hard drives, etc.) as well as removable media (e.g., flash memory, removable hard drives, optical disks, etc.). The computer readable medium 806 may be configured in a variety of other ways, as further described below.

[0117] Input / output interface 808 represents functionality that allows a user to input commands and information into computing device 802 and that allows information to be presented to a user and / or other components or devices using various input / output devices. Examples of input devices include keyboards, cursor control devices (e.g., a mouse), microphones, scanners, touch capabilities (e.g., capacitive or other sensors configured to detect physical contact), cameras (e.g., employing visible wavelengths or non-visible wavelengths such as infrared frequencies to recognize movements as non-touch gestures), and the like. Examples of output devices include display devices (e.g., a monitor or projector), speakers, printers, network cards, haptic response devices, and the like. Thus, computing device 802 can be configured in a variety of ways to support user interaction, as described further below.

[0118] Various techniques may be described herein in the general context of software, hardware elements, or program modules. Generally, such modules include routines, programs, objects, elements, components, data structures, etc. that perform particular tasks or implement particular abstract data types. As used herein, the terms "module," "function," and "component" generally refer to software, firmware, hardware, or combinations thereof. Aspects of the techniques described herein are platform-independent, meaning that the techniques may be implemented on a variety of commercial computing platforms having a variety of processors.

[0119] An implementation of the described modules and techniques may be stored on or transmitted across some form of computer-readable media. Computer-readable media may include a variety of media that may be accessed by computing device 802. By way of example, computer-readable media may include "computer-readable storage media" and "computer-readable signal media."

[0120] A "computer-readable storage medium" may refer to a medium and / or device that allows for persistent and / or non-transient storage of information thereon, as opposed to merely a signal transmission, carrier wave, or signal itself. Thus, a computer-readable storage medium refers to a non-signal-bearing medium. A computer-readable storage medium includes hardware, such as volatile and non-volatile, removable and non-removable media, and / or storage devices implemented in a manner or technology suitable for storage of information, such as computer-readable instructions, data structures, program modules, logic elements / circuits, or other data. Examples of computer-readable storage media may include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical storage, hard disk, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device, or other storage device, tangible media, or any article suitable for storing the desired information and that can be accessed by a computer.

[0121] A "computer-readable signal medium" may refer to a signal-bearing medium configured to transmit instructions to the hardware of the computing device 802, such as via a network. Signal media may typically embody computer-readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave, data signal, or other transport mechanism. Signal media also includes any information delivery media. The term "modulated data signal" means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. By way of example, communication media includes wired media, such as a wired network or direct-wired connection, and wireless media, such as acoustic, RF, infrared, and other wireless media.

[0122] As previously described, the hardware elements 810 and computer-readable media 806 represent modules, programmable device logic, and / or fixed device logic implemented in hardware form that may be employed in some embodiments to implement at least some aspects of the techniques described herein, such as to execute one or more instructions. The hardware may include integrated circuits or components of on-chip systems, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), complex programmable logic devices (CPLDs), and other implementations in silicon or other hardware. In this context, the hardware may operate as a processing device that executes program tasks defined by instructions and / or logic embodied by the hardware, as well as hardware utilized to store instructions for execution, such as computer-readable storage media previously described.

[0123] Combinations of the foregoing may be used to implement the various techniques described herein. Thus, software, hardware, or executable modules may be implemented as one or more instructions and / or logic embodied on some form of computer-readable storage medium and / or by one or more hardware elements 810. Computing device 802 may be configured to implement specific instructions and / or functions corresponding to software and / or hardware modules. Thus, implementation of modules executable as software by computing device 802 may be achieved at least partially in hardware, for example, through use of computer-readable storage medium and / or hardware elements 810 of processing system 804. The instructions and / or functions may be executable / operable by one or more articles of manufacture (e.g., one or more computing devices 802 and / or processing system 804) to implement the techniques, modules, and examples described herein.

[0124] The techniques described herein may be supported by various configurations of computing device 802 and are not limited to the specific examples of the techniques described herein. This functionality may also be implemented in whole or in part through the use of a distributed system, such as on a "cloud" 814 via platform 816, as described below.

[0125] Cloud 814 includes and / or represents a platform 816 for resources 818. Platform 816 abstracts the underlying functionality of the hardware (e.g., servers) and software resources of cloud 814. Resources 818 may include applications and / or data available while computer processing is running on a server remote from computing device 802. Resources 818 may also include services provided over the Internet and / or over a subscriber network, such as a cellular network or a Wi-Fi network.

[0126] The platform 816 can abstract resources and functionality for connecting the computing device 802 with other computing devices. The platform 816 can also serve to abstract the scaling of resources to provide a level of scale corresponding to the demand faced by the resources 818 implemented via the platform 816. Thus, in an embodiment of interconnected devices, implementations of the functionality described herein can be distributed throughout the system 800. For example, the functionality can be performed in part on the computing device 802 as well as via the platform 816 that abstracts the functionality of the cloud 814.

[0127] In some aspects, techniques described herein relate to a method implemented in a continuous glucose level monitoring system, the method including obtaining, for each of a plurality of time periods, glucose measurements measured for a user for the time period from a glucose sensor of the continuous glucose level monitoring system, the glucose sensor being inserted at an insertion site of the user; generating a first aggregate metric for the user for the time period based on the glucose measurements for each of the plurality of time periods; determining, for a first time period of the plurality of time periods, whether the first aggregate metric indicates a deviation by a first glucose measurement measured for the first time period from glucose measurements measured during a series of a plurality of time periods preceding the first time period; and, in response to determining that the first aggregate metric indicates a deviation, generating a user interface identifying the deviation; and displaying the user interface identifying the deviation.

[0128] In some aspects, the techniques described herein relate to a method, where the determining includes predicting an aggregate metric for a first time period based on aggregate metrics for a series of multiple time periods preceding the first time period, determining a difference between the predicted aggregate metric for the first time period and the first aggregate metric, and determining that the first aggregate metric exhibits a deviation in response to the difference exceeding a threshold amount.

[0129] In some aspects, the techniques described herein further include generating an aggregate metric for the user for the period based on the glucose measurements for each of the multiple periods; determining, for a first period of the multiple periods, whether the aggregate metric for the first period indicates a further deviation by a first glucose measurement measured for the first period from glucose measurements measured during a series of multiple periods preceding the first period; and, in response to determining that the aggregate metric for the first period indicates a further deviation, generating a user interface identifying the further deviation; and displaying the user interface identifying the further deviation.

[0130] In some aspects, the techniques described herein relate to a method, wherein the aggregate metric includes a hyperglycemic index value.

[0131] In some aspects, the techniques described herein relate to a method, wherein the aggregate metric includes a hypoglycemic index value.

[0132] In some aspects, techniques described herein relate to a method, where the determining includes determining whether the aggregate metrics for the first time period exhibit a deviation using a machine learning system trained with a set of multiple aggregate metrics as training data and trained to minimize a loss between the predicted aggregate metrics and the actual aggregate metrics.

[0133] In some aspects, the techniques described herein relate to a method, wherein each of the plurality of periods comprises 30 minutes, and the plurality of periods comprises 24 periods.

[0134] In some aspects, the techniques described herein further include obtaining glucose measurements measured for the user for the period from a glucose sensor for a period of the current day, generating a second aggregate metric for the user for the period of the current day based on the glucose measurements for the period, generating an aggregate metric for the user for the corresponding period of the past days based on the glucose measurements for each corresponding period of the past days, determining whether the second aggregate metric indicates a deviation by a first glucose measurement measured for a first period of the current day from glucose measurements measured during the corresponding period of the past days, and in response to determining that the second aggregate metric indicates a deviation, generating a user interface identifying the deviation, and displaying the user interface identifying the deviation.

[0135] In some aspects, the techniques described herein relate to a method, where the deviation is one of a plurality of deviations, the method further including identifying a population of which the user is a part, and selecting one of the plurality of deviations based on the population, where the population is one of a plurality of different populations of the user, and where generating includes generating a user interface that identifies the selected deviation.

[0136] In some aspects, the techniques described herein relate to a method, where identifying a population of which the user is a part includes identifying a population of which the user is a part based on the user's age or the user's diagnosis of diabetes.

[0137] In some aspects, the techniques described herein relate to a computing device including a processor; a display device; and a computer-readable storage medium storing a plurality of instructions of an application that, responsive to execution by the processor, causes the processor to: obtain, for each of a plurality of time periods, glucose measurements measured for a user during the time period from a glucose sensor of a continuous glucose level monitoring system, where the glucose sensor is inserted at an insertion site of the user; generate an aggregate metric for the user for the time period based on the glucose measurements for each of the plurality of time periods; determine, for a first time period of the plurality of time periods, whether the aggregate metric for the first time period indicates a deviation by a first glucose measurement measured for the first time period from glucose measurements measured during a series of a plurality of time periods preceding the first time period; and, responsive to determining that the aggregate metric for the first time period indicates a deviation, generate a user interface identifying the deviation; and cause the display device to display the user interface identifying the deviation.

[0138] In some aspects, the techniques described herein relate to a computing device, where the deviation is one of a plurality of deviations, and the instructions further cause the processor to identify a population of which the user is a part and select one of the plurality of deviations based on the population, where the population is one of a plurality of different populations of users, and where generating the user interface is generating a user interface that identifies the selected deviation.

[0139] In some aspects, the techniques described herein relate to a computing device, where the instructions further cause the processor to generate an aggregate metric for the user for the period based on the glucose measurements for each of the multiple time periods; determine, for a first period of the multiple time periods, whether the aggregate metric for the first period indicates a further deviation by a first glucose measurement measured for the first period from glucose measurements measured during a series of multiple time periods preceding the first period; in response to determining that the aggregate metric for the first period indicates a further deviation, generate a user interface identifying the further deviation; and display on a display device the user interface identifying the further deviation.

[0140] In some aspects, the techniques described herein relate to a computing device, where the aggregate metric includes a hyperglycemic index value.

[0141] In some aspects, the techniques described herein relate to a computing device, where the aggregate metric includes a hypoglycemic index value.

[0142] In some aspects, techniques described herein relate to a computing device, wherein determining whether an aggregate metric for a first time period exhibits a deviation is determining whether an aggregate metric for a first time period exhibits a deviation using a machine learning system trained with a set of multiple aggregate metrics as training data and trained to minimize a loss between the predicted risk aggregate metric and the actual aggregate metric.

[0143] In some aspects, the techniques described herein relate to a computing device, where the user is part of a population of multiple distinct populations of users, and where using the machine learning system includes using a machine learning system trained with training data for the one population.

[0144] In some aspects, techniques described herein relate to a method implemented in a continuous glucose level monitoring system, the method including obtaining glucose measurements measured for a user for a daily period from a glucose sensor of the continuous glucose level monitoring system, the glucose sensor being inserted at an insertion site for the user; generating aggregate metrics for the user for the daily period based on the glucose measurements for the period; generating aggregate metrics for the user for corresponding periods of a past number of days based on the glucose measurements for each corresponding period of a past number of days; determining whether the aggregate metrics for the daily period indicate a deviation by the glucose measurements measured for the daily period from the glucose measurements measured during the corresponding period of the past number of days; and, in response to determining that the aggregate metrics for the daily period indicate a deviation, generating a user interface identifying the deviation; and causing a display device to display the user interface identifying the deviation.

[0145] In some aspects, techniques described herein relate to a method, the method further including generating a value representative of the user's aggregate metric during a corresponding period of the past multiple days, and determining includes determining that in response to a difference between the value representative of the user's aggregate metric during the corresponding period of the past multiple days and the user's aggregate metric during the current day period that exceeds a threshold amount, the aggregate metric for the current day period indicates a deviation by glucose measurements measured for the current day period from glucose measurements measured during the corresponding period of the past multiple days.

[0146] In some aspects, the techniques described herein relate to a method, wherein a value representative of the user's aggregate metric for a corresponding period of the past multiple days includes an average of the user's aggregate metric for the corresponding period of the past multiple days.

[0147] In some aspects, the techniques described herein relate to a method, where the deviation is one of a plurality of deviations, the method further including identifying a population of which the user is a part, and selecting one of the plurality of deviations based on the population, where the population is one of a plurality of different populations of the user, and where generating includes generating a user interface that identifies the selected deviation.

[0148] In some aspects, the techniques described herein relate to a method, where identifying a population of which the user is a part includes identifying a population of which the user is a part based on the user's age or the user's diagnosis of diabetes.

[0149] In some aspects, techniques described herein relate to a device including a continuous glucose level monitoring system, the device including: a display device; a data collection module implemented at least partially in hardware for obtaining glucose measurements measured for a user for a period of the day from a glucose sensor, the glucose sensor being inserted at an insertion site of the user; a deviation detection module implemented at least partially in hardware for generating aggregate metrics for the user for the period of the day based on the glucose measurements for the period, and for generating aggregate metrics for the user for corresponding periods of a plurality of past days based on the glucose measurements for each corresponding period of the plurality of past days; and a deviation selection module implemented at least partially in hardware for determining whether the aggregate metrics for the period of the day indicate a deviation by glucose measurements measured for the period of the day from glucose measurements measured during corresponding periods of the plurality of past days, for generating a user interface identifying the deviation in response to determining that the aggregate metrics for the period of the day indicate a deviation, and for displaying the user interface identifying the deviation.

[0150] In some aspects, the techniques described herein relate to a device, the device being at least partially implemented in hardware, further including a metric determination module for generating a value representative of an aggregate metric of the user during a corresponding period of a plurality of past days, the deviation selection module being further for determining, in response to a difference between the value representative of the aggregate metric of the user during the corresponding period of the plurality of past days and the aggregate metric of the user during the current day period that exceeds a threshold amount, that the aggregate metric of the current day period indicates a deviation by glucose measurements measured for the current day period from glucose measurements measured during the corresponding period of the plurality of past days.

[0151] In some aspects, the techniques described herein relate to a device where the value representative of the user's aggregate metric for a corresponding period of the past days includes an average of the user's aggregate metric for the corresponding period of the past days.

[0152] conclusion Although the systems and techniques have been described in language specific to structural features and / or methodological acts, it should be understood that the systems and techniques defined in the appended claims are not necessarily limited to the particular features or acts described. Rather, the particular features and acts are disclosed as exemplary forms for implementing the claimed subject matter. [Explanation of symbols]

[0153] 100 Environment 102 users 104 Wearable glucose monitoring devices 106 Computing Devices 108 User Population 110 Glucose Monitoring Platform 112 Network 114 Glucose Measurements 116 Glucose Monitoring Applications 118 Storage Devices 120 Glucose Level Deviation Detection System 122 Deviation Identification Information Library 124 User Interface 202 Sensor 204 Sensor Module 206 Skin 208 Transmitter 210 Adhesive Pad 212 Mechanism 302 Data Collection Module 304 Metric Decision Module 306 Content-Based Deviation Detection Module 308 Context Deviation Detection Module 310 Deviation Selection Module 312 UI Module 320 measurements 322 Aggregated Metrics 324 Aggregated Metrics Store 326 Deviation Indication 328 Deviation Indication 330 Deviation Identification Information 402 Hypoglycemia Risk Value Prediction Module 404 Hyperglycemia Risk Value Prediction Module 406 Deviation Identification Module 408 Hypoglycemia Risk Value 410 Hypoglycemia risk level 412 Hyperglycemia risk level 414 Hyperglycemia risk value 416 Predicted hypoglycemia risk value 418 Predicted hyperglycemia risk value 502 Graph 504 Solid Line 506 Dashed Line 508 Hyperglycemia risk value 510 Hyperglycemia risk level 512 Hyperglycemia risk value 800 Systems 802 Computing Devices 804 Processing System 806 Computer Readable Medium 808 I / O Interface 810 Hardware Elements 812 Storage Component 814 Cloud 816 Platform 818 resources

Claims

1. 1. A method implemented in a continuous glucose level monitoring system, the method comprising: obtaining (602) a glucose measurement measured for a user during each of a plurality of time periods from a glucose sensor of the continuous glucose level monitoring system, the glucose sensor being inserted at an insertion site for the user; generating (604) a first aggregate metric for the user during each of the time periods based on the glucose measurements for each of the time periods; determining (606) for a first period of the plurality of periods whether the first aggregate metric indicates a deviation by the first glucose measurement measured for the first period from glucose measurements measured during a series of a plurality of periods preceding the first period; In response to determining that the first aggregate metric indicates the deviation, generating (608) a user interface that identifies the deviation; and displaying (610) the user interface identifying the deviation.

2. The determining step comprises: predicting an aggregate metric for the first time period based on the aggregate metric for the series of time periods preceding the first time period; determining a difference between the predicted aggregate metric and the first aggregate metric for the first time period; and determining that the first aggregate metric indicates a deviation in response to the difference exceeding a threshold amount.

3. generating an aggregate metric for the user during each of the multiple time periods based on the glucose measurements for the time periods; determining, for the first time period of the plurality of time periods, whether the aggregate metric for the first time period indicates a further deviation by the first glucose measurement measured for the first time period from glucose measurements measured during a series of a plurality of time periods preceding the first time period; in response to determining that the aggregate metrics for the first time period indicate the further deviation, generating a user interface that identifies the further deviation; The method of claim 1 or claim 2, further comprising: displaying the user interface identifying the further deviations.

4. The method of any one of claims 1 to 3, wherein the aggregate metric comprises a hyperglycemic index value.

5. The method of any one of claims 1 to 4, wherein the aggregate metric comprises a hypoglycemic index value.

6. 6. The method of claim 1, wherein the determining step comprises determining whether the aggregate metrics for the first time period exhibit a deviation using a machine learning system trained with a set of a plurality of aggregate metrics as training data and trained to minimize a loss between a predicted aggregate metric and an actual aggregate metric.

7. The deviation is one of a plurality of deviations, and the method further comprises: identifying a population of which the user is a part; 7. The method of claim 1, further comprising: selecting one of the plurality of deviations based on the population, the population being one of a plurality of different populations of users, and wherein the generating comprises generating the user interface identifying the selected deviation.

8. A device (106) comprising a continuous glucose level monitoring system, the device comprising: A display device; a data collection module (302) implemented at least partially in hardware for obtaining glucose measurements measured for a user for a period of the day from a glucose sensor, the glucose sensor being inserted at an insertion site for the user; a deviation detection module (308) implemented at least partially in hardware for generating aggregate metrics for the user during the time period of the current day based on the glucose measurements for the time period, and for generating aggregate metrics for the user during the corresponding time period of the past days based on the glucose measurements for each corresponding time period of the past days; a deviation selection module (310) implemented at least partially in hardware for determining whether the aggregate metrics for the period of the current day indicate a deviation by the glucose measurements measured for the period of the current day from glucose measurements measured during the corresponding period of the past days, for generating a user interface identifying the deviation in response to determining that the aggregate metrics for the period of the current day indicate the deviation, and for displaying the user interface identifying the deviation.

9. 10. The device of claim 8, further comprising a metric determination module implemented at least partially in hardware for generating a value representative of the aggregate metric for the user during the corresponding period of the past days, the deviation selection module being further for determining that the aggregate metric for the period of the present day indicates a deviation by the glucose measurements measured for the period of the present day from the glucose measurements measured during the corresponding period of the past days.

10. The device of claim 9 , wherein the value representative of the aggregate metric for the user during the corresponding time period of the past days comprises an average of the aggregate metric for the user during the corresponding time period of the past days.

Citation Information

Patent Citations

  • Glycemic urgency assessment and warning interface

    JP2017515520A

  • SYSTEM AND METHOD FOR PROVIDING OPTIMIZED ALERTS FOR A USER - Patent application

    JP2019525276A

  • System and method for data analytics and visualization

    US20160098848A1

  • Computer-implemented method and system for determining a relative risk for lack of glycemic control for a plurality of patients, and computer program product

    WO2020201077A1