Pattern recognition engine for blood glucose measurement

Abstract

The present specification relates to systems, methods and devices for identifying patterns in blood glucose measurements. According to a first aspect, the present specification discloses a computer-implemented blood glucose analysis method, comprising: receiving multiple blood glucose measurements associated with an individual taken over multiple time frames; identifying hypoglycemia and / or hyperglycemia blood glucose measurements in the multiple blood glucose measurements; identifying multiple subintervals of the time frame, in which there are a certain number of hypoglycemia and / or hyperglycemia blood glucose measurements that meet a threshold condition; inferring a temporal relationship between a blood glucose measurement in a first subinterval of the identified subinterval and a blood glucose measurement in a second subinterval of the identified subinterval; outputting one or more identified subintervals of the time frame; and outputting a suggested causal driver for the inferred temporal relationship.

Description

Technical Field

[0001] The present description relates to systems, methods, and apparatus for identifying patterns in blood glucose measurements. Background Art

[0002] Review of self-monitoring blood glucose data (SMBG) is a key tool for structured assessment of blood glucose, hypoglycemia, and hyperglycemia rates. It can play an important role in guiding treatment decisions.

[0003] Healthcare professionals (HCPs) struggle with time constraints and may not have the opportunity to systematically download and examine SMBG data. Additionally, some analyses and reports may not be fully useful or easy to understand, resulting in different HCPs interpreting the same data in fundamentally different ways. Summary of the invention

[0004] According to a first aspect, the present specification discloses a computer-implemented blood glucose analysis method, which includes: receiving multiple blood glucose measurements related to an individual obtained over multiple time frames; identifying hypoglycemia and / or hyperglycemia blood glucose measurements among the multiple blood glucose measurements; identifying multiple sub-intervals of the time frame, in which there are a certain number of hypoglycemia and / or hyperglycemia blood glucose measurements that meet a threshold condition; inferring the time relationship between the blood glucose measurement in a first sub-interval of the identified sub-interval and the blood glucose measurement in a second sub-interval of the identified sub-interval; outputting one or more identified sub-intervals of the time frame; and outputting suggested causal drivers for the inferred time relationship.

[0005] The multiple time frames may be consecutive.

[0006] The plurality of time frames may each have a duration of one day, and the sub-intervals may be periods of at most three hours. The plurality of time frames may each have a duration of one week, and the sub-intervals may be at most one day.

[0007] The method may further include plotting blood glucose measurements from each of the plurality of time frames to generate a blood glucose measurement graph. Outputting the identified one or more subintervals of the time frame may include outputting the blood glucose measurement graph, wherein the determined one or more subintervals of the modal time period are highlighted in the blood glucose measurement graph. Plotting blood glucose measurements from each of the plurality of time frames may include overlaying blood glucose measurements from each of the plurality of time frames to generate a modal time period.

[0008] The threshold condition may be the number and / or density of hypoglycemic and / or hyperglycemic blood glucose measurements within a subinterval.

[0009] Inferring the temporal relationship between the blood glucose measurements in the first subinterval and the blood glucose measurements in the second subinterval may include: determining a matching pair of blood glucose measurements, wherein the matching pair includes the blood glucose measurement in the first subinterval and the blood glucose measurement in the second subinterval; determining whether the total number of matching pairs exceeds a threshold condition; and in the event of a positive determination, inferring the temporal relationship between the determined trends including the identified pattern.

[0010] Determining a matching pair of blood glucose measurements may include comparing a timestamp associated with a blood glucose measurement in the first subinterval and a timestamp associated with a blood glucose measurement in the second subinterval; determining a matching pair if the timestamp associated with the blood glucose measurement in the first subinterval corresponds to the timestamp associated with the blood glucose measurement in the second subinterval.

[0011] The method may further include determining a time lag between the first subinterval and the second subinterval; and indicating that there is no temporal relationship between the first subinterval and the second subinterval if the time lag is greater than a threshold time period.

[0012] The method may further include: receiving additional data related to the individual taken over the plurality of time frames; and determining the suggested causal driver for the identified one or more subintervals of the time frames based at least in part on the additional data. The additional data may include one or more of: insulin dosage data; data related to exercise performed by the user; food intake data; and / or physiological measurements / data.

[0013] According to a second aspect, the present specification describes a device comprising: one or more processors; and a memory, wherein the memory comprises computer-readable instructions which, when executed by the one or more processors, cause the device to perform any one of the methods described herein.

[0014] According to a third aspect, the present specification describes a computer program product comprising computer readable code which, when executed by a computer, causes the computer to perform any of the methods described herein. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Example embodiments will now be described by way of non-limiting examples with reference to the accompanying drawings, in which:

[0016] FIG1 shows an example of a system for analyzing blood glucose measurements;

[0017] FIG2 shows a flow chart of an example of a blood glucose analysis method;

[0018] FIG3 shows an example of a modality day for blood glucose measurement;

[0019] FIG4 shows an example of a modality cycle for blood glucose measurement;

[0020] FIG5 shows an example of a historical trend graph of blood glucose measurements; and

[0021] FIG. 6 shows an example electronic circuit of a user device. DETAILED DESCRIPTION

[0022] Interpretation of self-monitoring blood glucose (SMBG) data patterns can elucidate the causes of poor glycemic control and suggest possible management strategies. It would be desirable to provide HCPs with tools to maximize the utility of SMBG data by quickly highlighting and interpreting patterns that might otherwise remain unidentified. This would also help maintain patient motivation to test their blood glucose (BG) levels regularly.

[0023] Usually, the average frequency of self-monitoring blood sugar measurement can be within the interval of 0.5 blood sugar measurement every day in patients who are not treated with insulin, and can be between 1 to 2 blood sugar measurements every day for patients treated with insulin. Pattern recognition method and system as described herein can be used to analyze this type of sparse data, thereby providing clinically useful information for users (such as, the health care professionals who monitor the blood sugar level in patients). In routine clinical practice, pattern recognition method and system as described herein are implemented to support treatment decision-making and patient education together with pattern reason prompts, so that the risk of hypoglycemia, hyperglycemia and excessive blood sugar fluctuations is minimized.

[0024] FIG. 1 illustrates an example of a system 100 for analyzing blood glucose measurements.

[0025] Described system comprises user computing device 102, and described user computing device is configured to receive the blood glucose measurement relevant with individual / patient.User device 102 is configured to analyze blood glucose measurement and identifies the clinically relevant blood glucose pattern in the blood glucose measurement in given time period.User device 102 can be configured to identify the time relationship between multiple groups of blood glucose measurement.In some embodiments, described time period can be modal time period.User device 102 is configured to provide the suggestion of the potential cause and effect driving factor of the blood glucose level of individual / patient based on the blood glucose measurement received.

[0026] The user device 102 is configured to perform any of the methods described herein (eg, as described with respect to FIG. 2 ). The methods may be performed by one or more applications running on the user device 102 .

[0027] The user device 102 may be, for example, any of the following: a mobile device, such as a mobile phone or tablet computer; a personal computer; a laptop computer; a personal digital assistant; a "smart" device; and / or a dedicated blood glucose monitoring device. Examples of such user devices 102 are described below with respect to FIG. 6 .

[0028] In some embodiments, the user of user device 102 can be a healthcare professional (HCP). In other embodiments, the user can be an individual / patient from whom blood glucose measurements are obtained. Different information and / or suggestions can be provided based on whether the user is an HCP using the system to help optimize patient treatment or whether the user is a patient using the system to self-monitor their blood glucose measurements. For example, a simpler interface can be provided for patients using the system for self-monitoring, and the interface covers a shorter time period (e.g., one day) compared to the interface of the HCP, wherein the causal driving factors of the suggestion are limited to a narrow time frame, more situational and / or provided at a more general level (e.g., "I noticed that you have had several hypoglycemic symptoms this week, have you changed in your treatment / meal time / etc.? I may recommend XXX" or "I noticed that you injected your insulin about 30 minutes after your meal. In order to best control blood glucose, I may recommend injecting insulin at the beginning of the meal"). In contrast, historical trend data and / or data related to modal time periods (e.g., modal days or modal weeks) over a longer time period (e.g., weeks or months) can be provided for HCPs. The suggested causal drivers provided to the HCP may cover a wider range of potential causal drivers and be more detailed than those provided to the patient. Thus, the same, similar or different messages may be provided based on whether the user is a patient or an HCP.

[0029] The system may further include one or more blood glucose measuring devices 104. The blood glucose measuring device 104 is operable to test the patient's blood glucose level. The blood glucose level can be recorded by the blood glucose measuring device 104 and sent to the user device 102. This blood glucose measurement data can be transmitted to the user device 102 via a network 106. The network can be, for example, the Internet and / or a local area network. Alternatively or additionally, the blood glucose measurement can be manually input to the user device 102, for example, through a graphical user interface. In some embodiments, the blood glucose measurement can be transmitted directly from the blood glucose measuring device 104, for example, via a USB connection between the blood glucose device 104 and the user device. The blood glucose data can be transmitted to the user device 102 via a separate "hub" device.

[0030] The user device 102 may be further configured to receive additional data related to the patient. Examples of such additional data include: details of medications taken by the patient; insulin doses taken by the patient; data related to exercise performed by the patient, such as data collected by an activity tracker; food intake of the patient; and / or other physiological measurements related to the patient. The additional data may be used to refine the recommendations for potential causal drivers of the patient's blood glucose level. For example, hypoglycemic / hyperglycemic events may be associated with insulin doses, indicating that the patient's insulin dose is incorrect.

[0031] 2 shows a flow chart of an example of a blood glucose analysis method. The method may be implemented by a computing device / system comprising one or more processors and a memory containing computer readable instructions that, when executed by the one or more processors, cause the computing device / system to perform the method.

[0032] At operation 2.1, a plurality of blood glucose measurements associated with a patient taken over a plurality of time frames are received.

[0033] Blood glucose measurements may be received at the user device 102, for example, over a network from a blood glucose measuring device 104. Alternatively or additionally, blood glucose measurements may be manually input into the user device 102 by a user. Blood glucose measurements may be received continuously (i.e., as each measurement is taken). Alternatively, blood glucose measurements may be received as a batch of blood glucose measurements.

[0034] Each blood glucose measurement is associated with a timestamp indicating the date and time the blood glucose measurement was taken. Each blood glucose measurement is further associated with the respective patient for whom the measurement was taken.

[0035] The time frame includes a time interval each. The time frame can each have an equal duration. For example, the duration of the time frame can be one day, one week or one month. The time frame can be a continuous time interval, such as multiple days or multiple weeks of a continuous sequence. In some embodiments, the total time period covered by the multiple time frames is at most four weeks. This is usually the maximum time period that the patient can reliably recall the information associated with the blood glucose measurement (such as, the contextual information related to when, how and / or why the blood glucose measurement is performed). This can allow a healthcare professional to confirm a hypothesis about the patient based on the collected blood glucose measurements.

[0036] In some embodiments, additional data related to the patient taken over multiple time frames is received. Examples of such additional data include: insulin dosages taken by the patient; data related to exercise performed by the patient, e.g., data collected by an activity tracker or manually entered by the patient; the patient's food intake; and / or other physiological measurements related to the patient. The additional data can be used to refine recommendations for potential causal drivers of the patient's blood glucose level. For example, hypoglycemic / hyperglycemic events may be associated with insulin dosage, indicating that the patient's insulin dosage is incorrect.

[0037] At optional operation 2.2, blood glucose measurements from each of the plurality of time frames are plotted to generate a blood glucose measurement graph.

[0038] In some embodiments, plotting the blood glucose measurements from each of the plurality of time frames may include overlaying the blood glucose measurements from each of the plurality of time frames to generate a modal time period.

[0039] The modal time period includes all blood glucose measurements of a set of equal time periods (i.e., time frames) overlapped into a single copy of the equal time period. It can be considered as a stack of blood glucose measurements from the multiple time frames. For example, a modal time period may include a first set of blood glucose measurements taken during a first time frame / time interval, which is superimposed by a second set of blood glucose measurements taken during a second non-overlapping time frame / time interval having a duration equal to the first time frame / time interval. Additional blood glucose measurements from additional different time frames may be superimposed on the first and second sets of blood glucose measurements to create a modal time period.

[0040] For example, a set of blood glucose measurements including blood glucose measurements taken over multiple days is overlapped to form a modal day. An example of a modal day is described with respect to FIG. 3. In another example, a set of blood glucose measurements including blood glucose measurements taken over multiple weeks is overlapped to form a modal week. An example of a modal week is described with respect to FIG.

[0041] In some embodiments, plotting the blood glucose measurements from each of the plurality of time frames may include plotting the blood glucose measurements over consecutive time periods to generate a trend graph.

[0042] The historical trend chart includes a drawing of blood glucose measurements from a sequentially arranged time frame. It shows the history of the patient's blood glucose measurements. An example of a historical trend chart is shown in FIG5 . The historical trend chart shows a drawing of blood glucose measurements over a period of time. In the historical trend chart, the average value of the recurrence of high / low blood glucose events within a given time period (e.g., three months) can be calculated. Weeks with a higher number of recurrences can be highlighted, i.e., weeks in which the average number of low blood glucose events and high blood glucose events identified exceeds the weekly average.

[0043] At operation 2.3, hypoglycemic and / or hyperglycemic blood glucose measurements among the plurality of blood glucose measurements are identified.

[0044] Hypoglycemia blood sugar measurement includes blood sugar measurement that drops below the hypoglycemia threshold blood sugar value. The hypoglycemia threshold can be selected according to the patient whose blood sugar is being monitored. For example, the threshold can be a blood sugar value within the range of 60-90mg / dl. The example of the hypoglycemia threshold is 70mg / dl (3.9mmol / L). Other thresholds will be familiar to the technician. The blood sugar measurement in the modal time period is compared with the hypoglycemia threshold, and any blood sugar measurement with a value below the hypoglycemia threshold is identified as a hypoglycemia measurement.

[0045] Hyperglycemia blood sugar measurement includes blood sugar measurement higher than the hyperglycemia threshold blood sugar value.The hyperglycemia threshold can be selected according to the patient whose blood sugar is being monitored.For example, the threshold can be a blood sugar value within the range of 160-220mg / dl.The example of the hyperglycemia threshold is 180mg / dl (10mmol / L).Other thresholds will be familiar to the technician.The blood sugar measurement in the modal time period is compared with the hyperglycemia threshold, and any blood sugar measurement with a value higher than the hyperglycemia threshold is identified as a hyperglycemia measurement.

[0046] At operation 2.4, one or more subintervals of the time frame are determined in which there are a certain number of hypoglycemic and / or hyperglycemic blood glucose measurements that satisfy a threshold condition.

[0047] In the embodiment using the modal time period, the method uses the concept of recurrence to identify the trend in the blood glucose measurement. Repeating hyperglycemia and / or hypoglycemia blood glucose measurements in one or more subintervals of the modal time period can be used to indicate the trend / pattern in the blood glucose measurement. The subinterval of the modal day that meets the threshold condition is referred to as the "relevant subinterval" of the modal time period here. The modal time period assumes that there is a certain "repeatability" in the patient's behavior on the modal time period. This is why the similar time identification pattern is used on one day / multiple days of the week.

[0048] Historical trend charts are intended to identify specific sub-intervals (e.g., weeks / periods) in recent weeks / months of a patient's blood glucose history where patterns may exist. These are not relied upon to imply "repeatability," but rather an opportunity for the healthcare provider to work with the patient to identify causal drivers and address them together - in terms of fit with Rx or behavior change.

[0049] Subintervals can be fixed time periods. For example, a modal day can use subintervals of up to three hours. In general, a modal time period can use subintervals of any relevant length. Fixed subintervals can be used as a rolling window to identify relevant subintervals, i.e., subintervals that meet a threshold condition.

[0050] In another example, a modal week can view days of the week with a rolling time period. The rolling time period can be, for example, a 3-hour window. For example, if the modal time period is a day, the time period can be three hours, and the rolling window is one minute.

[0051] Patterns in blood glucose measurements are identified by identifying modal time periods or sub-time intervals in historical blood glucose measurements (i.e., relevant sub-intervals) that satisfy a threshold condition. The threshold condition may be a threshold number of hypoglycemic and / or hyperglycemic blood glucose measurements within a sub-interval of a given length.

[0052] For example, when at least two low blood glucose blood sugar measurements are identified within a period of time in a modal time period of up to three hours, a relevant sub-interval may be identified. Alternatively or additionally, when at least three high blood glucose blood sugar measurements are identified within a period of time in a modal time period of up to three hours, a relevant sub-interval may be identified.

[0053] The threshold condition may alternatively or additionally include a density threshold. If the density of hypoglycemia and / or hyperglycemia blood glucose measurements in a subinterval is higher than a threshold density, the subinterval may be identified as a relevant subinterval. The threshold density may be based on the average density of hypoglycemia and / or hyperglycemia blood glucose measurements in the modality day. For example, when the density of hypoglycemia and / or hyperglycemia blood glucose measurements is significantly higher than the sum of the blood glucose values ​​in the same period, a relevant subinterval may be detected. The threshold density may be set based on the average density of the time period. The threshold density may be the average density multiplied by a number greater than one, for example, 150% of the average density. This may be calculated by moving the window forward one observation at a time.

[0054] As an illustrative example, the method may identify three subintervals within a time frame that have more than two hypoglycemic values, e.g., subinterval 1: 5 hypoglycemic values ​​(2.5 hours long); subinterval 2: 2 values ​​(3 hours long); and subinterval 3: 4 hypoglycemic values ​​(3 hours long). The density of these values ​​is compared to the average hypoglycemic density for the day. For example, if the total number of hypoglycemic values ​​for the day is 20 (i.e., 11 are in the subinterval and 9 are not). A density of 20 / 24 hypoglycemic events per hour will be determined. These are compared to the density in the subintervals.

[0055] In this example, the densities in the three subintervals would be: 2, 0.67, and 1.33, respectively. Based on a threshold density (which can be set by the user / HCP), the system can highlight subintervals 1 and 3 as patterns, and ignore subinterval 2 because its density (0.67 events / hour) is below the daily density.

[0056] A factor can be applied to the average density that a subinterval density must be above the average daily density (e.g., 130%, 140%, 150%, etc.) to be considered a subinterval a-mode; this can be in addition to the absolute number of events in a subinterval meeting a threshold number (e.g., 2 hypoglycemic events or 3 hyperglycemic events).

[0057] Repeated measurements obtained within a short time period of each other using a time frame can reduce the reliability of the trend of using recurrence marks and the relevant sub-intervals of the modal day. In some embodiments, for the purpose of determining the sub-interval of a certain number of hypoglycemia and / or hyperglycemia blood glucose measurements that meet the threshold conditions in the modal time period, the measurements obtained in real time within the threshold time period of each other in the same time interval are considered as single events. For example, two or more blood glucose measurements obtained within half an hour of each other can be considered as single events / measurements.

[0058] In some embodiments, both a threshold number and a threshold density of blood glucose measurements need to be met in order to identify relevant subintervals.

[0059] Further analysis may be performed on the blood glucose measurements in the modal time period / time frame to identify patterns. For example, temporal relationships between identified sub-intervals may be identified. These may be used to infer causal relationships between patterns of hypoglycemia and / or hyperglycemia blood glucose measurements and suggest possible causal drivers.

[0060] At operation 2.5, the determined one or more subintervals of the modal time period are output. The identified relevant subintervals can be output in a graph of the modal time period, where the relevant subintervals are highlighted. Examples of such output are provided in Figures 3 to 5. The relevant patterns of hypoglycemia and / or hyperglycemia are based on the absolute and relative frequencies of these events and can be superimposed on a report that a healthcare professional has used to analyze blood glucose measurements.

[0061] At operation 2.6, suggested causal drivers for the identified one or more subintervals of the time frame and / or the identified pattern are output.

[0062] Suggestions are provided to the HCP / patient regarding what the causal drivers of the identified one or more sub-intervals of the time frame and / or the identified patterns may be. These may include areas focused on discussing the patient, for example, potential causes that may lead to these blood glucose patterns. Messages related to the identified one or more patterns and potential suggestions based on the identified patterns may be provided to the patient. For example, suggestions may be provided to the patient on how to adjust their daily routine based on the identified patterns. The messages provided to the patient may relate to individual events, data patterns at certain time frames within a day, for example, spanning days or weeks.

[0063] The recommendations may be provided through an interactive graph of blood glucose measurements (e.g., a graph of modal time periods or a historical trend chart). For example, the HCP may select an identified mode on the graph via an interactive user interface of the user device 102. A pop-up window may appear providing the HCP with selectable options related to the patient's treatment. For example, the HCP may select basal only, oral dosing, basal with meals, etc.

[0064] Based on the identified pattern / identified subinterval (and the information entered by the HCP), the system displays a list of potential causes that may have caused the pattern. For example, the HCP may be provided with a message through the user interface of the user device 102. For example, the message may be "During or shortly before the [4 week] period, were any of the following:

[0065] - Changes or irregularities in treatment, e.g., new prescription, higher basal insulin dose, changed injection schedule

[0066] -Lifestyle changes or irregularities, e.g., more exercise / walking, skipping meals (especially dinner)

[0067] - Others, e.g. shift work"

[0068] To the patient, for example, the recommendation would be provided as a contextual message such as, "I noticed that you inject your insulin approximately 30 minutes after your meals. For best blood sugar control, I may recommend injecting insulin at the beginning of a meal." The contextual message may be based on additional information provided about the patient, such as meal times, exercise times and durations, and / or insulin dose times and values.

[0069] Suggested causal drivers may be provided based on the type of temporal relationship identified in the blood glucose measurement. A database of potential temporal relationships and associated causal drivers may be provided. The database may be used to match the identified temporal relationship with one or more causal drivers. Alternatively or additionally, a default set of causal drivers may be provided. In some embodiments, if no matching temporal relationship is found in the database, the default set may be restored.

[0070] The suggested causal drivers may be provided based at least in part on any additional data provided. For example, patterns in the additional data may be identified based on timestamps of the additional data and / or matched to corresponding blood glucose measurements. Based on the type of additional data and its value, causal drivers for blood glucose measurements may be suggested. Such causal drivers may include, for example: incorrect insulin dosage; dietary factors; meal timing; overeating / undereating; excessive / lack of exercise; and / or underlying physiological conditions.

[0071] As mentioned above with respect to operation 2.4, further analysis may be performed on the blood glucose measurements in the modal time period to identify patterns. For example, temporal relationships between patterns and trends may be identified. These may be used to infer causal relationships between patterns of hypoglycemia and / or hyperglycemia blood glucose measurements.

[0072] For example, based on the identified relevant subintervals, patterns of hypoglycemia-hyperglycemia, hyperglycemia-hypoglycemia, hypoglycemia-hypoglycemia, and / or hyperglycemia-hyperglycemia blood glucose measurements can be identified within the modal time period. These patterns include a first pattern of hypoglycemia or hyperglycemia events in a first relevant subinterval, followed by a second pattern of hypoglycemia or hyperglycemia events in a second relevant subinterval.

[0073] In order to identify a pattern between two related subintervals, multiple hypoglycemia or hyperglycemia blood glucose measurements in a first subinterval of a time frame can be identified. Multiple hypoglycemia or hyperglycemia blood glucose measurements in a second subinterval of the time frame can then be identified. The timestamps associated with the blood glucose measurements in the first subinterval and the timestamps associated with the blood glucose measurements in the second subinterval are compared. If the timestamps of any pair of blood glucose measurements (one from the first subinterval and one from the second subinterval) correspond (e.g., they are taken on the same day), the two measurements match. If the total number of matches is above a threshold, a pattern is identified. The threshold can, for example, be a fraction (e.g., 50%) of the total number of blood glucose measurements in the first subinterval or the second subinterval.

[0074] For example, on a modal day, the system may identify a first relevant subinterval with 4 low blood glucose values ​​in the period 8-10am. Then identify a second relevant subinterval with 5 high blood glucose values ​​in the period 11-1pm. The system then looks to see how many of these values ​​in the first subinterval have a corresponding "match" in the second subinterval. If this number meets a threshold condition, there is a correlation between the low blood glucose pattern and the high blood glucose pattern; and the system may infer that it is likely that the low blood glucose pattern caused the high blood glucose pattern.

[0075] In other words, the correlated subintervals identified in the blood glucose measurements can be processed to determine whether the composition of the pattern is causally related, i.e., whether there is a causal relationship between a first subinterval and a second subinterval. For example, looking first at the modal time periods, the patterns may appear to be correlated, but in reality, the blood glucose measurements may be part of different time frames.

[0076] The identified pattern is checked to see if the first relevant subinterval and the second relevant subinterval correspond in time. If the blood glucose measurement in the first relevant subinterval originates from the same time frame as the blood glucose measurement in the second relevant subinterval, a causal / temporal relationship can be established between the two subintervals.

[0077] For example, the method may include attempting to pair a blood glucose measurement in a first subinterval with a blood glucose measurement in a second subinterval based on whether the blood glucose measurement in the second subinterval is taken from the same time frame as the measurement in the first subinterval. If a threshold number of pairs is formed, the temporal / causal relationship between the two subintervals is identified. The threshold number may, for example, be a fixed number, or may be a fraction of the number of blood glucose measurements in the first subinterval or the second subinterval.

[0078] Once the temporal relationship has been identified, it can be highlighted in a representation of the modal time period. For example, an outline can be provided on a graph of the modal day.

[0079] Determining the temporal relationship between two or more patterns may further include: determining a time lag between two of the subintervals; and indicating that there is no temporal relationship between the two subintervals if the time lag is greater than a threshold time period. For example, if a first subinterval spans a first time and a second subinterval spans a second time, the time lag may be calculated based on the difference between the time at the end of the first subinterval and the time at the beginning of the second subinterval, or vice versa, depending on the temporal ordering of the subintervals.

[0080] FIG3 shows an example of a modal day of blood glucose measurement. The modal day is represented as a graph 300. Time is represented along an x-axis 302, and blood glucose measurements are represented along a y-axis 304. Graph 300 includes a plurality of blood glucose measurements taken from a set of time frames. Each time frame is a day in duration. The time frames have been superimposed to generate a modal day.

[0081] The hypoglycemia blood glucose threshold 306 is indicated by the lower dashed line. Blood glucose measurements below this line are identified as hypoglycemia blood glucose measurements.

[0082] The hyperglycemic blood glucose threshold 308 is indicated by an upper dashed line. Blood glucose measurements above this line are identified as hyperglycemic blood glucose measurements.

[0083] The associated high-glucose sub-interval is indicated by the shaded area 310 around the high-glucose blood glucose measurement cluster. The associated low-glucose sub-interval is indicated by the shaded area 312 around the low-glucose blood glucose measurement cluster.

[0084] These patterns highlight the time of day when the patient has more frequent hypoglycemic (e.g. <70 mg / dl) or hyperglycemic (e.g. >180 mg / dl) episodes, which may be associated with the patient's daily routine. Occurrences are calculated over periods of up to 4 weeks. A pattern is detected when at least 2 hypoglycemic or 3 hyperglycemic blood glucose measurements and / or a density of hypoglycemic or hyperglycemic blood glucose measurements is identified in a period of up to 3 hours and is above average.

[0085] A median blood glucose measurement line 314 is shown, as well as a 75th percentile line 316 and a 25th percentile line 318 .

[0086] 4 shows an example of a modality week of blood glucose measurements. The modality week is represented as a graph 400. The times of the days of the week (e.g., Sunday to Saturday) are represented along the x-axis 402, and the blood glucose measurements are represented along the y-axis 404.

[0087] The daily average 410 of the blood glucose measurements for the modal week is plotted for each day, and a bar 412 representing the range in which 50% of the blood glucose measurements for that day in the modal week fall within the average. Lines extending up and down from the bar indicate the 10-90% range of blood glucose measurements. The modal week also shows a median line 414.

[0088] The relevant subintervals 406, 408 are highlighted to show days of the week when the patient has more frequent hypoglycemic or hyperglycemic episodes that may be associated with the patient's weekly routine. The pattern requires that the occurrence of hypoglycemic or hyperglycemic episodes is consistent on the same weekdays over several weeks and that the same weekdays are significantly higher when compared to the weekly average.

[0089] FIG5 shows an example of a historical trend chart of blood glucose measurements. The historical trend chart is represented as a graph 500. Time is represented along the x-axis 502, and blood glucose measurements are represented along the y-axis 504. It shows the history of blood glucose measurements for a patient. During a selected time period, it shows the weeks in which the average number of hypoglycemic events and hyperglycemic events exceeded the weekly average.

[0090] The time axis spans continuous time periods, such as one or more months or a number of weeks. Blood glucose measurements are shown as dots in the graph, with high and low blood glucose values ​​highlighted. Relevant sub-intervals 506, 508 of time are highlighted.

[0091] FIG6 shows an example electronic circuit of a user device 102. An electronic system 600 of the user device 102 includes a processor component 202. The processor component 602 and other hardware components may be connected via a system bus (not shown). Each hardware component may be connected to the system bus directly or via an interface. A power supply 604 is arranged to provide power to the electronic system.

[0092] Processor component 602 controls the operation of other hardware components of electronic system 600. Processor component 602 can be any type of integrated circuit. Processor component 602 can be, for example, a general-purpose processor. It can be a single-core device or a multi-core device. Processor component 602 can be a central processing unit (CPU) or a general-purpose processing unit (GPU). Alternatively, it can be a more specialized unit, such as a RISC processor or programmable hardware with embedded firmware. Multiple processors may be included. Processor component 602 can be referred to as a processing device.

[0093] The electronic system 600 includes a working or volatile memory 606. The processor component 602 can access the volatile memory 606 to process data and can control the storage of data in the memory. The volatile memory 606 can be any type of RAM, for example, static RAM (SRAM), dynamic RAM (DRAM), or it can be flash memory. Multiple volatile memories can be included, but are omitted in the figure.

[0094] The electronic system includes a non-volatile memory 608. The non-volatile memory 608 stores a set of operating instructions 610 for controlling the normal operation of the processor component. The non-volatile memory 608 can be any type of memory, such as read-only memory (ROM), flash memory, or magnetic drive memory. Other non-volatile memories may be included, but are omitted in the figure.

[0095] The processor component 602 operates under the control of the operating instructions 610. The operating instructions 610 may include code related to the hardware components of the electronic system 600 (i.e., drivers), as well as code related to the basic operation of the user device. The operating instructions 610 may also cause the activation of one or more software modules stored in the non-volatile memory 608. In general, the processor component 602 executes one or more instructions in the operating instructions 610 that are permanently or semi-permanently stored in the non-volatile memory 608, using the volatile memory 606 to temporarily store data generated during the execution of the operating instructions. The operating instructions may include computer-readable instructions that, when executed by the processor component 602, cause the user device to perform any of the methods described herein.

[0096] Processor component 602, volatile memory 606 and non-volatile memory 608 may be provided as separate integrated circuit chips connected by an off-chip bus, or they may be provided on a single integrated circuit chip. Processor component 602, volatile memory 606 and non-volatile memory 608 may be provided as a microcontroller.

[0097] The electronic system 600 includes a clock 612. The clock 612 can be a clock crystal, such as a quartz crystal oscillator. The clock 612 can be a component separate from the processor component 602 that is configured to provide a clock signal to the processor component 602. The processor component 602 can be configured to provide a real-time clock based on a signal from the clock 612. Alternatively, the clock 612 can be a clock crystal that is provided on a single integrated circuit chip with the processor component 602.

[0098] The electronic system 600 includes one or more network interfaces 614. The network interface 614 facilitates the connection of the user device 102 to one or more computer networks and the two-way exchange of information between the user device 102 and other members of the network. These networks may include the Internet, a local area network, or any other network required for the user device to communicate with a data center and / or a contact center. The network interface 614 includes a network interface controller, such as an Ethernet adapter, a Wi-Fi adapter, and / or a Bluetooth adapter. The network interface 614 is associated with one or more network addresses for identifying the user device on the network. The one or more network addresses may be in the form of an IP address, a MAC address, and / or an IPX address. Other members of the network may include a blood glucose measuring device 104.

[0099] In some embodiments, the processor component 602 in the user may not be powerful enough to perform one or more functions in the functions described herein. On the contrary, the processing component 602 is configured to communicate with an additional computer system via a network interface, and the additional computer system has more computing power available to it. The processor component 602 can transfer data from the user device to the additional computer system, wherein the additional computing power of the additional computer system can be used to process data. The additional computer system can return the result of this processing to the processor component for further processing. The additional computing system can be, for example, a part for a remote computer system, a distributed computer system, or a data center.

[0100] The electronic system 600 further includes a display 616. The display 616 can be operated by the processing component 602 via a display driver to provide a graphical user interface to the user. The display 616 can be in the form of an LCD screen. The display 216 can alternatively be in the form of an LED screen. The display 616 provides the user with status information related to the user device 102. Examples of such status information include the mode in which the user device is located, the battery status, the memory status, the network connection status, and / or whether an external power source is connected. The display 616 can provide the results of the method of Figure 2, for example in the form of the diagrams in Figures 3 to 5.

[0101] The electronic system 600 may include a speaker 618. The speaker 618 is an example of an audio transducer. The speaker 618 may be operated to provide an audio output in the form of spoken words, or more generally any sound. The speaker 618 may provide audible feedback to the user regarding the use of the user device 102 and / or the blood glucose measuring device 104. Such an example may be an audible indication that the blood glucose testing material of the blood glucose measuring device 104 is insufficient. In some embodiments, the speaker 618 may provide an audible reminder to the user. For example, the speaker 618 may remind the user to take a predetermined dose of a medication or to record a blood glucose measurement.

[0102] The electronic system 600 further includes one or more input interfaces 620. The input interface 620 allows a user to input data into the user device 102. Examples of input interfaces include a touch screen, a keyboard, a numeric keypad, one or more dedicated buttons, and / or a voice recognition engine.

[0103] Implementations of the methods described herein may be implemented in digital electronic circuitry, integrated circuits, specially designed ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These may include computer program products (such as software stored on, for example, a disk, an optical disk, a memory, a programmable logic device), the computer program product comprising computer readable instructions that, when executed by a computer (such as described with respect to FIG. 6 ), cause the computer to perform one or more of the methods described herein.

[0104] The terms "drug" or "medicament" are used synonymously herein and describe a pharmaceutical preparation containing one or more active pharmaceutical ingredients or a pharmaceutically acceptable salt or solvate thereof and optionally a pharmaceutically acceptable carrier. In the broadest sense, an active pharmaceutical ingredient ("API") is a chemical structure that has a biological effect on humans or animals. In pharmacology, a drug or medicament is used to treat, cure, prevent, or diagnose disease or to otherwise enhance physical or mental health. A drug or medicament may be used for a limited duration, or periodically for a chronic disorder.

[0105] As described below, a drug or medicament may include at least one API or a combination thereof in various types of formulations for treating one or more diseases. Examples of APIs may include small molecules (having a molecular weight of 500 Da or less); polypeptides, peptides, and proteins (e.g., hormones, growth factors, antibodies, antibody fragments, and enzymes); carbohydrates and polysaccharides; and nucleic acids, double-stranded or single-stranded DNA (including naked and cDNA), RNA, antisense nucleic acids such as antisense DNA and RNA, small interfering RNA (siRNA), ribozymes, genes, and oligonucleotides. Nucleic acids may be incorporated into molecular delivery systems (such as vectors, plasmids, or liposomes). Mixtures of one or more drugs are also contemplated.

[0106] The drug or medicament can be contained in a primary package or "drug container" suitable for a drug delivery device. The drug container can be, for example, a cartridge, a syringe, a reservoir or other solid or flexible vessel, which is configured to provide a suitable chamber for storing (e.g., short-term or long-term storage) one or more drugs. For example, in some cases, the chamber can be designed to store the drug for at least one day (e.g., 1 day to at least 30 days). In some cases, the chamber can be designed to store the drug for about 1 month to about 2 years. It can be stored at room temperature (e.g., about 20 ° C) or refrigerated temperature (e.g., from about -4 ° C to about 4 ° C). In some cases, the drug container can be or may include a dual-chamber cartridge, which is configured to store two or more components (e.g., API and diluent, or two different drugs) of the pharmaceutical preparation to be applied separately, one of which is stored in each chamber. In this case, the two chambers of the dual-chamber cartridge can be configured to allow mixing between two or more components before and / or during distribution to the human or animal body. For example, the two chambers can be configured so that they are in fluid communication with each other (e.g., through a conduit between the two chambers), and allow the user to mix the two components if necessary before dispensing. Alternatively or additionally, the two chambers can be configured to allow mixing when dispensing the components into the human or animal body.

[0107] The medicine or medicament contained in the drug delivery device described herein can be used for treating and / or preventing many different types of medical diseases. The example of obstacle includes, for example, diabetes or complications related to diabetes (such as diabetic retinopathy), thromboembolic obstacles (such as deep vein or pulmonary thromboembolism). Another example of obstacle is acute coronary syndrome (ACS), angina pectoris, myocardial infarction, cancer, macular degeneration, inflammation, hay fever, atherosclerosis and / or rheumatoid arthritis. The example of API and medicine is those as described in the following manual: such as Rote Liste 2014 (for example, but not limited to, main group (main group) 12 (antidiabetic drugs) or 86 (tumor drugs)) and Merck Index, the 15th edition.

[0108] Examples of APIs for treating and / or preventing type 1 or type 2 diabetes or complications associated with type 1 or type 2 diabetes include insulin (e.g., human insulin, or human insulin analogs or derivatives); glucagon-like peptide (GLP-1), GLP-1 analogs or GLP-1 receptor agonists, or analogs or derivatives thereof; dipeptidyl peptidase-4 (DPP4) inhibitors, or pharmaceutically acceptable salts or solvates thereof; or any mixture thereof. As used herein, the terms "analogs" and "derivatives" refer to polypeptides having a molecular structure that can be formally derived from the structure of a naturally occurring peptide (e.g., the structure of human insulin) by deleting and / or exchanging at least one amino acid residue present in a naturally occurring peptide and / or by adding at least one amino acid residue. The added and / or exchanged amino acid residues can be codable amino acid residues or other natural residues or purely synthetic amino acid residues. Insulin analogs are also referred to as "insulin receptor ligands." In particular, the term "derivative" refers to a polypeptide having a molecular structure that is formally derived from the structure of a naturally occurring peptide (e.g., the structure of human insulin), wherein one or more organic substituents (e.g., fatty acids) are bound to one or more amino acids. Optionally, one or more amino acids present in the naturally occurring peptide may have been deleted and / or replaced by other amino acids (including non-encodable amino acids), or amino acids (including non-encodable amino acids) have been added to the naturally occurring peptide.

[0109] Examples of insulin analogs are Gly(A21), Arg(B31), Arg(B32) human insulin (insulin glargine); Lys(B3), Glu(B29) human insulin (insulin glulisine); Lys(B28), Pro(B29) human insulin (insulin lispro); Asp(B28) human insulin (insulin aspart); human insulin in which the proline at position B28 is replaced by Asp, Lys, Leu, Val or Ala and in which the Lys at position B29 may be replaced by Pro; Ala(B26) human insulin; Des(B28-B30) human insulin; Des(B27) human insulin and Des(B30) human insulin.

[0110] Examples of insulin derivatives are, for example, B29-N-myristoyl-des(B30) human insulin, Lys(B29)(N-tetradecanoyl)-des(B30) human insulin (insulin detemir, ); B29-N-palmitoyl-des(B30) human insulin; B29-N-myristoyl human insulin; B29-N-palmitoyl human insulin; B28-N-myristoylLysB28ProB29 human insulin; B28-N-palmitoyl-LysB28ProB29 human insulin; B30-N-myristoyl-ThrB29LysB30 human insulin; B30-N-palmitoyl-ThrB29LysB30 human insulin; B29-N-(N-palmitoyl-γ-glutamyl)-des(B30) human insulin, B29-N-ω-carboxypentadecanoyl-γ-L-glutamyl-des(B30) human insulin (insulindegludec, ); B29-N-(N-lithocholyl-γ-glutamyl)-des(B30) human insulin; B29-N-(ω-carboxyheptadecanoyl)-des(B30) human insulin and B29-N-(ω-carboxyheptadecanoyl) human insulin.

[0111] Examples of GLP-1, GLP-1 analogs and GLP-1 receptor agonists are e.g. lixisenatide Exendin-4 Liraglutide (a 39-amino acid peptide produced by the salivary glands of the Gila monster) Semaglutide, Taspoglutide, Albiglutide Dulaglutide rExendin-4, CJC-1134-PC, PB-1023, TTP-054, Langlenatide / HM-11260C, CM-3, GLP-1Eligen, ORMD-0901, NN-9924, NN-9926, NN-9927, Nodexen, Viador-GLP-1, CVX-096, ZY OG-1, ZYD-1, GSK-2374697, DA-3091, MAR-701, MAR709, ZP-2929, ZP-3022, TT-401, BHM-03 4. MOD-6030, CAM-2036, DA-15864, ARI-2651, ARI-2255, Exenatide-XTEN and Glucagon-Xten.

[0112] Examples of oligonucleotides are e.g. Mipomersen sodium It is a cholesterol-reducing antisense therapeutic used to treat familial hypercholesterolemia.

[0113] Examples of DPP4 inhibitors are Vildagliptin, Sitagliptin, Denagliptin, Saxagliptin, Berberine.

[0114] Examples of hormones include pituitary hormones or hypothalamic hormones or regulatory activity peptides and their antagonists, such as gonadotropins (follicle-stimulating hormone, luteinizing hormone, chorionic gonadotropin, tocopherol), somatropine (growth hormone), desmopressin, terlipressin, gonadorelin, triptorelin, leuprorelin, buserelin, nafarelin and goserelin.

[0115] Examples of polysaccharides include glucosaminoglycanes, hyaluronic acid, heparin, low molecular weight heparin or ultra low molecular weight heparin or derivatives thereof, or sulfated polysaccharides (e.g., polysulfated forms of the above polysaccharides), and / or pharmaceutically acceptable salts thereof. An example of a pharmaceutically acceptable salt of polysulfated low molecular weight heparin is enoxaparin sodium. An example of a hyaluronic acid derivative is Hylan G-F20 It is a sodium hyaluronate.

[0116] As used herein, the term "antibody" refers to an immunoglobulin molecule or an antigen binding portion thereof. Examples of antigen binding portions of immunoglobulin molecules include F (ab) and F (ab') 2 fragments, which retain the ability to bind antigens. The antibody can be a polyclonal antibody, a monoclonal antibody, a recombinant antibody, a chimeric antibody, a deimmunized or humanized antibody, a fully human antibody, a non-human (e.g., mouse) antibody, or a single-chain antibody. In some embodiments, the antibody has effector functions and can fix complement. In some embodiments, the antibody has reduced or no ability to bind to Fc receptors. For example, the antibody can be an isotype or subtype, an antibody fragment or a mutant, which does not support binding to Fc receptors, for example, it has a mutagenic or missing Fc receptor binding region. The term antibody also includes antigen binding molecules based on tetravalent bispecific tandem immunoglobulins (TBTI) and / or dual variable region antibody-like binding proteins with cross-binding region orientation (CODV).

[0117] The term "fragment" or "antibody fragment" refers to a polypeptide derived from an antibody polypeptide molecule (e.g., an antibody heavy chain and / or light chain polypeptide), which does not include a full-length antibody polypeptide, but still includes at least a portion of a full-length antibody polypeptide capable of binding to an antigen. Antibody fragments may include cleavage portions of full-length antibody polypeptides, although the term is not limited to such cleavage fragments. Antibody fragments that can be used in the present invention include, for example, Fab fragments, F(ab')2 fragments, scFv (single-chain Fv) fragments, linear antibodies, monospecific or multispecific antibody fragments (such as bispecific, trispecific, tetraspecific and multispecific antibodies (e.g., double-chain antibodies, three-chain antibodies, four-chain antibodies)), monovalent or multivalent antibody fragments (such as bivalent, trivalent, tetravalent and multivalent antibodies), mini antibodies, chelated recombinant antibodies, three antibodies or double antibodies, intracellular antibodies, nano antibodies, small modular immunopharmaceuticals (SMIP), binding domain immunoglobulin fusion proteins, camelized antibodies and antibodies containing VHH. Other examples of antigen-binding antibody fragments are known in the art.

[0118] The term "complementarity determining region" or "CDR" refers to short polypeptide sequences within the variable region of both heavy and light chain polypeptides that are primarily responsible for mediating specific antigen recognition. The term "framework region" refers to amino acid sequences within the variable region of both heavy and light chain polypeptides that are not CDR sequences and are primarily responsible for maintaining the correct positioning of the CDR sequences to allow antigen binding. Although the framework region itself is generally not directly involved in antigen binding, as known in the art, certain residues within the framework region of certain antibodies may be directly involved in antigen binding or may affect the ability of one or more amino acids in the CDR to interact with the antigen.

[0119] Examples of antibodies are anti-PCSK-9 mAb (eg, Alirocumab), anti-IL-6 mAb (eg, Sarilumab), and anti-IL-4 mAb (eg, Dupilumab).

[0120] Pharmaceutically acceptable salts of any API described herein are also contemplated for use as drugs or medicaments in drug delivery devices. Pharmaceutically acceptable salts are, for example, acid addition salts and basic salts.

[0121] Any system features described herein may also be provided as method features, and vice versa. As used herein, means-plus-function features may be represented alternatively according to their corresponding structures. Specifically, method aspects may be applied to system aspects, and vice versa.

[0122] Those skilled in the art will appreciate that various components of the API, formulations, devices, methods, systems, and embodiments described herein may be modified (added and / or removed) without departing from the overall scope and spirit of the invention, and that the invention encompasses such modifications and any and all equivalents thereof.

[0123] This manual also includes the following:

[0124] 1. A computer-implemented blood glucose analysis method, comprising:

[0125] receiving a plurality of blood glucose measurements associated with a patient taken over a plurality of time frames;

[0126] identifying hypoglycemic and / or hyperglycemic blood glucose measurements among the plurality of blood glucose measurements;

[0127] identifying one or more subintervals of the time frame in which there are a certain number of hypoglycemic and / or hyperglycemic blood glucose measurements that satisfy a threshold condition; and

[0128] outputting the identified one or more subintervals of the time frame; and

[0129] Suggested causal drivers are output for the identified one or more sub-intervals of the time frame.

[0130] 2. A method according to claim 1, wherein the multiple time frames are consecutive.

[0131] 3. A method according to clause 2, wherein the plurality of time frames each have a duration of one day, and wherein the sub-intervals are periods of at most three hours.

[0132] 4. A method according to clause 2, wherein the plurality of time frames each have a duration of one week, and wherein the sub-interval is at most one day.

[0133] 5. A method according to clause 1, wherein the method further comprises plotting blood glucose measurements from each of the plurality of time frames to generate a blood glucose measurement graph.

[0134] 6. A method according to item 5, wherein outputting the identified one or more sub-intervals of the time frame includes outputting the blood glucose measurement graph, wherein the determined one or more sub-intervals of the modal time period are highlighted in the blood glucose measurement graph.

[0135] 7. The method of clause 5, wherein plotting the blood glucose measurements from each of the plurality of time frames comprises superimposing the blood glucose measurements from each of the plurality of time frames to generate a modal time period.

[0136] 8. A method according to item 1, wherein the threshold condition is the number and / or density of hypoglycemic and / or hyperglycemic blood glucose measurements within a sub-interval.

[0137] 9. The method according to claim 1, further comprising:

[0138] identifying a plurality of hypoglycemic or hyperglycemic blood glucose measurements in a first subinterval of the time frame;

[0139] identifying a plurality of hypoglycemic or hyperglycemic blood glucose measurements in a second subinterval of the time frame; and

[0140] A temporal relationship between the blood glucose measurement in the first sub-interval and the blood glucose measurement in the second sub-interval is inferred.

[0141] 10. The method of clause 9, wherein inferring a temporal relationship between the blood glucose measurement in the first subinterval and the blood glucose measurement in the second subinterval comprises:

[0142] determining a matching pair of blood glucose measurements, wherein the matching pair includes a blood glucose measurement in the first subinterval and a blood glucose measurement in the second subinterval;

[0143] determining whether the total number of matching pairs exceeds a threshold condition; and

[0144] In the event of a positive determination, a temporal relationship between the determined trends comprising the identified pattern is inferred.

[0145] 11. The method of clause 10, wherein determining matching pairs of blood glucose measurements comprises:

[0146] comparing a timestamp associated with a blood glucose measurement in the first subinterval and a timestamp associated with a blood glucose measurement in the second subinterval;

[0147] A matching pair is determined if the timestamp associated with the blood glucose measurement in the first sub-interval corresponds to the timestamp associated with the blood glucose measurement in the second sub-interval.

[0148] 12. The method according to claim 9, further comprising:

[0149] determining a time lag between the first subinterval and the second subinterval; and

[0150] If the time lag is greater than a threshold time period, it indicates that there is no temporal relationship between the first sub-interval and the second sub-interval.

[0151] 13. The method according to claim 1, further comprising:

[0152] receiving additional data related to the patient acquired over the plurality of time frames; and

[0153] The suggested causal driver is determined for the identified one or more subintervals of the time frame based at least in part on the additional data.

[0154] 14. A method according to item 13, wherein the additional data comprises one or more of: insulin dosage data; data related to exercises performed by the patient; food intake data; and / or physiological measurements / data.

[0155] 15. An apparatus comprising:

[0156] one or more processors; and

[0157] a memory, wherein the memory comprises computer-readable instructions that, when executed by the one or more processors, cause the apparatus to perform a method comprising:

[0158] receiving a plurality of blood glucose measurements associated with a patient taken over a plurality of time frames;

[0159] identifying hypoglycemic and / or hyperglycemic blood glucose measurements among the plurality of blood glucose measurements;

[0160] identifying one or more subintervals of the time frame in which there are a certain number of hypoglycemic and / or hyperglycemic blood glucose measurements that satisfy a threshold condition; and

[0161] outputting the identified one or more subintervals of the time frame; and

[0162] Suggested causal drivers are output for the identified one or more sub-intervals of the time frame.

[0163] 16. A non-transitory computer readable medium comprising computer readable code, which when executed by a computer causes the computer to perform a method comprising:

[0164] receiving a plurality of blood glucose measurements associated with a patient taken over a plurality of time frames;

[0165] identifying hypoglycemic and / or hyperglycemic blood glucose measurements among the plurality of blood glucose measurements;

[0166] identifying one or more subintervals of the time frame in which there are a certain number of hypoglycemic and / or hyperglycemic blood glucose measurements that satisfy a threshold condition; and

[0167] outputting the identified one or more subintervals of the time frame; and

[0168] Suggested causal drivers are output for the identified one or more sub-intervals of the time frame.

[0169] 17. A system comprising:

[0170] Blood glucose measuring devices;

[0171] A computing device configured to receive blood glucose measurements from the blood glucose measuring device via a network, the computing device comprising a memory and one or more processors, wherein the memory comprises computer readable instructions which, when executed by the one or more processors, cause the computing device to perform a method comprising:

[0172] receiving a plurality of blood glucose measurements associated with a patient taken over a plurality of time frames;

[0173] identifying hypoglycemic and / or hyperglycemic blood glucose measurements among the plurality of blood glucose measurements;

[0174] identifying one or more subintervals of the time frame in which there are a certain number of hypoglycemic and / or hyperglycemic blood glucose measurements that satisfy a threshold condition; and

[0175] outputting the identified one or more subintervals of the time frame; and

[0176] Suggested causal drivers are output for the identified one or more sub-intervals of the time frame.

Claims

1. A computer-implemented blood glucose analysis method, comprising: receiving a plurality of blood glucose measurements associated with the individual taken over a plurality of time frames; receiving additional data related to the individual taken over the plurality of time frames, wherein the additional data comprises one or more of: insulin dosage data; data related to exercise performed by the user; food intake data; and / or physiological measurements / data; identifying hypoglycemic and / or hyperglycemic blood glucose measurements among the plurality of blood glucose measurements; identifying a plurality of subintervals of the time frame in which there are a certain number of hypoglycemic and / or hyperglycemic blood glucose measurements that satisfy a threshold condition; Inferring a temporal relationship between a blood glucose measurement in a first subinterval of the identified subintervals and a blood glucose measurement in a second subinterval of the identified subintervals, wherein inferring the temporal relationship comprises: determining a matching pair of blood glucose measurements, wherein the matching pair includes a blood glucose measurement in the first subinterval and a blood glucose measurement in the second subinterval, and wherein determining the matching pair of blood glucose measurements includes: comparing a timestamp associated with a blood glucose measurement in the first subinterval and a timestamp associated with a blood glucose measurement in the second subinterval; and determining a matching pair if the timestamp associated with the blood glucose measurement in the first subinterval corresponds to the timestamp associated with the blood glucose measurement in the second subinterval; determining whether the total number of matching pairs exceeds a threshold condition; and in the event of a positive determination, inferring a temporal relationship between the first subinterval and the second subinterval; determining a suggested causal driver for the inferred temporal relationship, comprising matching the inferred temporal relationship to potential temporal relationships stored in a database of potential temporal relationships and associated causal drivers, the one or more causal drivers comprising one or more of: incorrect insulin dosage; dietary factors; meal timing; overeating / undereating; excessive / lack of exercise; and / or an underlying physiological condition, wherein the suggested causal driver for the identified one or more subintervals of the time frame is determined based at least in part on the additional data; outputting the identified one or more subintervals of the time frame; and The suggested causal drivers are output for the inferred temporal relationship. The method of claim 1 , wherein the plurality of time frames are consecutive.

3. A method according to any one of claims 1 or 2, wherein the plurality of time frames each have a duration of one day, and wherein the sub-intervals are periods of at most three hours.

4. The method of claim 1 or 2, wherein the plurality of time frames each have a duration of one week, and wherein the sub-interval is at most one day.

5. The method of claim 1 or 2, wherein the method further comprises plotting blood glucose measurements from each of the plurality of time frames to generate a blood glucose measurement graph.

6. The method of claim 5, wherein outputting the identified one or more subintervals of the time frame comprises outputting the blood glucose measurement graph, wherein the determined one or more subintervals of the modal time period are highlighted in the blood glucose measurement graph. 7 . The method of claim 5 , wherein plotting the blood glucose measurements from each of the plurality of time frames comprises overlaying the blood glucose measurements from each of the plurality of time frames to generate a modal time period.

8. The method according to claim 1 or 2, wherein the threshold condition is the number and / or density of hypoglycemic and / or hyperglycemic blood glucose measurements within a subinterval.

9. The method according to claim 1 or 2, further comprising: determining a time lag between the first subinterval and the second subinterval; as well as If the time lag is greater than a threshold time period, it indicates that there is no temporal relationship between the first sub-interval and the second sub-interval.

10. A device comprising: one or more processors; as well as A memory, wherein the memory comprises computer readable instructions which, when executed by the one or more processors, cause the apparatus to perform a method according to any one of claims 1 to 9.

11. A computer program product comprising computer readable code which, when executed by a computer, causes the computer to perform the method according to any one of claims 1 to 9.

Images