Method, apparatus, and computer program for managing diabetic patient using continuous glucose monitor

Abstract

The present invention relates to a method for managing a diabetic patient using a continuous glucose monitor, the method being characterized by comprising: a data reception step of receiving measurement data from a continuous glucose monitor; a data calculation step of calculating a sensor wearing time, a time within a specific glucose range, a time less than a first glucose value, a time greater than a second glucose value, EhyperE (whether a glucose level continuously exceeds 250 mg / dL for 2 hours or more), a time during which a glucose level is less than 54 mg / dL, and food intake time detection (FITD) by using the measurement data; and a data classification step of including a matrix part for classifying into one or more cases according to a time ratio, over a period of one week, of the sensor wearing time, the time within a specific glucose range, the time less than a first glucose value, the time greater than a second glucose value, EhyperE (whether a glucose level continuously exceeds 250 mg / dL for 2 hours or more), the time during which a glucose level is less than 54 mg / dL, and the food intake time detection, and an insulin and lifestyle correction part for classifying into one or more cases according to the number of times a predetermined glucose level occurs in a predetermined time period.

Description

Methods, devices, and computer programs for managing diabetic patients using continuous glucose monitoring devices

[0001] The present invention was made under the support of the Ministry of Health and Welfare under the task identification number 2460001311 and task number 00399025. The research management specialized organization of the task is "Korea Health Industry Development Institute", the research project name is "Patient-centered medical technology optimization research", the research project name is "Analysis of blood glucose pattern based on continuous glucose monitoring device use in Korean diabetics and study on optimization of target blood glucose index for type 1 diabetes", the main organization is Samsung Seoul Hospital, and the research period is from 2024.04.01. to 2025.12.31.

[0002] This invention claims priority to Republic of Korea Patent Application No. 10-2024-0119778, filed with the Korean Intellectual Property Office on September 4, 2024, the contents of which are incorporated herein by reference in their entirety.

[0003] The present invention relates to a method, device, and computer program for managing a diabetic patient using a continuous glucose monitoring device, and more particularly, to a method, device, and computer program for managing a diabetic patient using a continuous glucose monitoring device that provides summary blood glucose information, insulin control, and lifestyle correction information for a diabetic patient.

[0004] Diabetes is a type of metabolic disease in which insulin secretion is insufficient or its normal function is not performed. It is characterized by hyperglycemia, which is an increase in the concentration of glucose in the blood. Hyperglycemia causes various symptoms and signs and causes glucose to be excreted in the urine.

[0005] Continuous glucose monitoring (CGM) is a device that continuously monitors blood glucose levels to aid in blood sugar management. CGM can measure blood sugar levels without a separate blood draw. The recent decline in the price of CGM devices, the expansion of insurance coverage for them, and the widespread use of CGM devices are driving their popularity.

[0006] When summarizing blood glucose patterns for diabetic patients on insulin therapy using continuous glucose monitoring (CGM), the system relied on the existing report formats provided by diabetes management device companies. Interpreting these reports on days other than the initial clinical visit was left to the individual patient, resulting in patient-specific differences in therapeutic perspectives. Furthermore, when insulin doses needed to be adjusted based on blood glucose patterns on days other than the initial clinical visit, differences in patient knowledge of diabetes management emerged.

[0007] Accordingly, there is a need for a method, device, and computer program for managing diabetes patients using continuous glucose monitoring devices, which allows diabetic patients using continuous glucose monitoring devices to manage their diabetes and control their insulin on their own outside of the treatment schedule and to receive information on lifestyle modification.

[0008] The purpose of the present invention is to automatically generate a report based on blood sugar patterns that patients can understand on a weekly basis in addition to the date of treatment, to automatically interpret the contents of the report to patients based on their blood sugar patterns and suggest areas for improvement, and to provide patients with customized suggestions for insulin control, diet, and exercise based on their blood sugar patterns.

[0009] In order to achieve the above object, the present invention is characterized in that it includes a data receiving step of receiving measurement data from a continuous blood glucose monitoring device; a data generating step of calculating, using the measurement data, a sensor wearing time, a time within a specific blood glucose range, a time below a first blood glucose level, a time above a second blood glucose level, EhyperE (whether blood glucose continuously exceeds 250 mg / dL for 2 hours or more), a blood glucose level below 54 mg / dL, and a food intake time detection (FITD) ; and a data classification step including a matrix part that classifies into one or more cases according to the time ratio of the sensor wearing time, the time within a specific blood glucose range, the time below the first blood glucose level, the time above the second blood glucose level, EhyperE (whether blood glucose continuously exceeds 250 mg / dL for 2 hours or more), and the food intake time for a week, and an insulin and lifestyle correction part that classifies into one or more cases according to the number of times a certain blood glucose level occurs in a certain time interval.

[0010] Preferably, the data receiving step can receive the time at which blood sugar was measured and the blood sugar value using the measurement data.

[0011] Preferably, the data receiving step allows the user to directly download measurement data in a specific file format from the continuous blood glucose meter server.

[0012] Preferably, the data receiving step may include automatically submitting login information to a homepage managing a server to log in, then retrieving a list of patients to be managed from the homepage and automatically downloading the time of blood sugar measurement and blood sugar value stored in the server corresponding to the patient list.

[0013] Preferably, the automatic download may further include a step of extracting data including the time at which blood sugar was measured and the blood sugar value from the logged-in account, excluding unnecessary information, and converting the data into a format usable by a data analysis program.

[0014] Preferably, the data generation step may set the specific blood sugar range to 70 mg / dL to 180 mg / dL, the first blood sugar value to 70 mg / dL or 54 mg / dL, and the second blood sugar value to 180 mg / dL or 250 mg / dL.

[0015] Preferably, the data generation step can calculate the time corresponding to the minimum blood sugar level 2 hours prior to the time point (Glucose Rate Increase Detector, GRID) at which the blood sugar change rate increases by 95 mg / dL per hour for two consecutive values ​​or by 90 mg / dL or more per hour for three consecutive values, as the food intake time detection (FITD). In addition, the time point at which blood sugar level reaches a maximum after food intake corresponds to the maximum blood sugar level 3 hours after GRID.

[0016] Preferably, the matrix part classifies a case in which the time ratio within a specific blood sugar range is 70% or more, the time ratio of hyperglycemia exceeding 180 mg / dL is less than 25%, the time ratio of hyperglycemia exceeding 250 mg / dL is less than 5%, the time ratio of hypoglycemia below 70 mg / dL is less than 4%, the time ratio of hypoglycemia below 54 mg / dL is less than 1%, and the time ratio of sensor wearing is 70% or more as a first case, and a case in which the time ratio of sensor wearing is less than 70% is classified as a second case, and a case in which the time ratio of sensor wearing is 70% or more, the time ratio within a specific blood sugar range is 70% or more, but the time ratio of hyperglycemia above 180 mg / dL is less than 25%, the time ratio of hyperglycemia above 250 mg / dL is less than 5%, the time ratio of hypoglycemia below 70 mg / dL is less than 4%, and the time ratio of hypoglycemia below 54 mg / dL is less than 1% A case where at least one time ratio does not reach the corresponding value can be classified as a third case, and a case where the sensor wearing time ratio is 70% or more and the time ratio within a specific blood sugar range is less than 70% can be classified as a fourth case.

[0017] Preferably, the insulin and lifestyle correction part classifies the case in which the number of days in which hypoglycemia of less than 70 mg / dL occurred for 15 minutes or more between 00:00 and 06:00 is 2 or more times as the first case, the case in which the time ratio of hyperglycemia of more than 180 mg / dL between 00:00 and 06:00 is 25% or more and the time of food intake is 1 or less, and the lowest blood sugar of 100 mg / dL or more between 00:00 and 06:00 and the blood sugar of 150 mg / dL or more occurred for 3 or more consecutive days is classified as the second case, the case in which the number of days in which the time ratio of hypoglycemia of less than 70 mg / dL exceeded 4% between 08:00 and 06:00 is classified as the third case, and the number of days in which the time ratio of hyperglycemia of more than 250 mg / dL exceeded 10% between 08:00 and 06:00 is classified as the third case. Cases where this occurs 4 or more times are classified as case 4, and cases where the maximum blood sugar level is 220 mg / dL or higher after the meal intake time at a point where the blood sugar level is 70 mg / dL or higher between 8:00 and 24:00 are classified as case 5, and cases where the blood sugar level is 70 mg / dL or higher but 140 mg / dL or lower within 5 hours after the meal intake time (after the maximum blood sugar level after a meal) at a point where the blood sugar level is 70 mg / dL or higher between 8:00 and 24:00 are classified as case 5-1, and cases where the blood sugar level is 140 mg / dL or higher within 5 hours after the meal intake time (after the maximum blood sugar level after a meal) at a point where the blood sugar level is 70 mg / dL or higher between 8:00 and 24:00 are classified as case 5-2, and cases where the maximum blood sugar level between 00:00 and 03:00 starts from 250 mg / dL or higher and the difference from the lowest point within 4 hours is 100 mg / dL or higher on days. Cases where the number is 2 or more can be classified as case 6.

[0018] Preferably, the method may further include a message generation step for generating sentences for each of the matrix part and the insulin and lifestyle correction parts according to the cases classified in the data classification unit.

[0019] Preferably, the message generation step may further include a message re-generation step of re-generating a sentence having the same meaning as the sentence of the message generated in the message generation step but composed of different words.

[0020] Preferably, the method may further include a step of generating a graph of blood sugar levels by time zone, an average blood sugar pattern for each time zone, and a percentage change in one or more key matrices based on measurement data received over a week.

[0021] In addition, the present invention provides a device for managing a diabetic patient using a continuous glucose monitoring device, comprising: a processor including one or more cores; and a memory; wherein the processor receives measurement data from the continuous glucose monitoring device, and calculates, using the measurement data, a sensor wearing time, a time within a specific blood glucose range, a time below a first blood glucose value, a time above a second blood glucose value, EhyperE (whether blood glucose continuously exceeds 250 mg / dL for more than 2 hours), whether blood glucose is below 54 mg / dL, and a food intake time (food intake time detection (FITD), and classifies the device into one or more cases according to a time ratio of the sensor wearing time, the time within a specific blood glucose range, the time below the first blood glucose value, the time above the second blood glucose value, EhyperE (whether blood glucose continuously exceeds 250 mg / dL for more than 2 hours), whether blood glucose is below 54 mg / dL, and a food intake time, and classifies the device into one or more cases according to a time ratio of the sensor wearing time, the time within a specific blood glucose range, the time below the first blood glucose value, the time above the second blood glucose value, EhyperE (whether blood glucose continuously exceeds 250 mg / dL for more than 2 hours), the occurrence of blood glucose is below 54 mg / dL, and the food intake time, and classifies the device into one or more cases according to the number of times a certain blood glucose level occurs in a certain time interval.

[0022] In addition, the present invention is a computer program including commands stored in a computer-readable storage medium and causing a computer to perform the following operations, wherein the operations include: a data receiving operation for receiving measurement data from a continuous blood glucose meter; a data generating operation for calculating, using the measurement data, a sensor wearing time, a time within a specific blood glucose range, a time below a first blood glucose value, a time above a second blood glucose value, EhyperE (whether blood glucose continuously exceeds 250 mg / dL for 2 hours or more), an occurrence of a blood glucose below 54 mg / dL, and a food intake time detection (FITD); And another feature is that it includes a data classification operation including a matrix part that classifies into one or more cases according to the sensor wearing time, time within a specific blood sugar range, time below the first blood sugar value, time above the second blood sugar value, EhyperE (whether blood sugar continuously exceeds 250 mg / dL for more than 2 hours), occurrence of blood sugar below 54 mg / dL, and time ratio of food intake time, and an insulin and lifestyle correction part that classifies into one or more cases according to the number of times a certain blood sugar level occurs in a certain time interval.

[0023] The present invention has the advantage of reducing the burden on medical staff and helping patients manage their blood sugar levels by automatically generating reports based on blood sugar patterns on a weekly basis in addition to the date of treatment so that patients can understand them, automatically interpreting the contents of the reports to patients based on their blood sugar levels and suggesting areas for improvement, and providing patients with customized suggestions for insulin control, diet, and exercise based on their blood sugar levels.

[0024] Figure 1 shows a flowchart of a method for managing a diabetic patient using a continuous blood glucose monitoring device according to an embodiment of the present invention.

[0025] Figure 2 is a schematic diagram of a method for managing a diabetic patient using a continuous blood glucose monitoring device according to an embodiment of the present invention.

[0026] Figure 3 shows a configuration diagram of a device for managing a diabetic patient using a continuous blood glucose meter according to an embodiment of the present invention.

[0027] A method for managing a diabetic patient using a continuous glucose monitoring device, comprising: a data receiving step for receiving measurement data from the continuous glucose monitoring device; a data generating step for calculating, using the measurement data, a sensor wearing time, a time within a specific blood glucose range, a time below a first blood glucose level, a time above a second blood glucose level, EhyperE (whether blood glucose continuously exceeds 250 mg / dL for 2 hours or more), a blood glucose level below 54 mg / dL, and a food intake time detection (FITD) ; and a data classification step including a matrix part for classifying into one or more cases according to the time ratio of the sensor wearing time, the time within a specific blood glucose range, the time below the first blood glucose level, the time above a second blood glucose level, EhyperE (whether blood glucose continuously exceeds 250 mg / dL for 2 hours or more), and the food intake time for a week, and an insulin and lifestyle modification part for classifying into one or more cases according to the number of times a certain blood glucose level occurs in a certain time interval.

[0028]

[0029] Hereinafter, the present invention will be described in detail with reference to the contents described in the attached drawings. However, the present invention is not limited or restricted by the exemplary embodiments. The same reference numerals in each drawing indicate components that perform substantially the same functions.

[0030] The purpose and effects of the present invention can be naturally understood or made clearer by the following description, and the purpose and effects of the present invention are not limited solely by the following description. Furthermore, in describing the present invention, if a detailed description of known technologies related to the present invention is deemed to unnecessarily obscure the gist of the present invention, such detailed description will be omitted.

[0031] The terminology used herein is merely used to describe specific embodiments and is not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly indicates otherwise. In this application, it should be understood that the terms "comprise" or "have" indicate the presence of a feature, number, step, operation, component, part, or combination thereof described in the description of the invention, but do not preclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0032] While terms like "first" and "second" may be used to describe various components, these components should not be limited by these terms. These terms are used solely to distinguish one component from another. For example, without departing from the scope of the present invention, a first component could be referred to as a "second component," and similarly, a second component could also be referred to as a "first component."

[0033] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and shall not be interpreted in an idealized or overly formal sense unless explicitly defined herein.

[0034] When interpreting components, even if there is no explicit description, it is interpreted as including the margin of error. When describing temporal relationships, for example, when temporal continuity is described with phrases such as "after," "following," "next to," or "before," this also includes cases where the relationship is not continuous, unless "immediately" or "directly" is used.

[0035] Hereinafter, the technical configuration of the present invention will be described in detail with reference to the attached drawings.

[0036] Fig. 1 is a flowchart illustrating a method for managing a diabetic patient using a continuous glucose monitoring device according to an embodiment of the present invention, and Fig. 2 is a schematic diagram illustrating a method for managing a diabetic patient using a continuous glucose monitoring device according to an embodiment of the present invention. Referring to Figs. 1 and 2, the method for managing a diabetic patient using a continuous glucose monitoring device may include a data receiving step (S100), a data generating step (S200), a data classification step (S300), a message generating step (S400), a message re-calculating step (S500), a picture generating step (S600), and a message sending step (S700).

[0037] A method for managing diabetic patients using continuous glucose monitoring (CGM) can automatically calculate and provide to patients a summary of their CGM results, suggestions for insulin control and lifestyle modifications tailored to their individual blood glucose patterns over the past week, using algorithmic programming code.

[0038] A method of managing diabetic patients using a continuous glucose monitoring device is to automatically generate a report based on blood glucose patterns on a weekly basis so that patients can understand it without having to visit a doctor on a day of treatment to hear information about blood glucose patterns, insulin control, and lifestyle modifications. The report is automatically interpreted by the patient based on the blood glucose pattern to suggest areas for improvement, and suggestions for insulin control, diet, and exercise are provided to the patient according to the blood glucose pattern, tailored to the individual.

[0039] The data receiving step (S100) can receive measurement data from a continuous glucose monitoring device. The data receiving step (S100) can receive raw data from the continuous glucose monitoring device and process the raw data so that the measurement data can be utilized in the data generation step (S200), etc. The data receiving step (S100) can allow a user to directly download measurement data in a specific file format from the continuous glucose monitoring device server. The data receiving step (S100) can automatically proceed with the steps of creating a list of patients to be managed, logging in, and downloading, or can be performed manually by the user, and the user can adjust the details of each step when directly performing the steps.

[0040] The data reception step (S100) may include automatically submitting login information to a website managing a server, logging in, then retrieving a list of patients to be managed from the website and automatically downloading the blood sugar measurement times and blood sugar values ​​stored in the server corresponding to the patient list. Here, the list of patients to be managed may be a list containing at least one of a patient list organized in Excel format and required data (a list of data to be downloaded).

[0041] As an example, the homepage that manages the server in the data receiving step (S100) may be, but is not limited to, Dexcom and CareSense.

[0042] In one embodiment, the algorithm of the data reception step (S100) uses code written based on Python code to automatically submit login information to the website managing the server, log in, retrieve a list of patients to be managed from the website, and automatically download data based on the list. This operation can be performed using code in a language other than Python, and the downloaded data can additionally reflect or exclude other data contained in the server, in addition to the time and value of blood glucose measurement.

[0043] The automatic download may further include a step of extracting data including the time and blood sugar level when blood sugar was measured from a logged-in account, excluding unnecessary information, and converting it into a format usable by a data analysis program. The data reception step (S100) may receive the time and blood sugar level when blood sugar was measured as measurement data. The data reception step (S100) may download the raw data in the form of a CSV file that can be downloaded from the Dexcom, FreeStyle Libre, CareSense, or Guardian Connect homepage. The data reception step (S100) may process the raw data into a dataset consisting of two columns and corresponding rows each consisting of the time and blood sugar level when blood sugar was measured by excluding unnecessary information, and may convert it into a format usable by an R language program.

[0044] In one embodiment, the data reception step (S100) is characterized by organizing a list of patients to be managed in Excel format for Dexcom data collection and CareSense data collection, and executing Python code to perform automatic login and data download. Specifically, the Dexcom data collection step automatically logs in and downloads data based on subject information, and the CareSense data collection step collects data in the same manner. This enables efficient data collection through organizing the subject list and executing Python code, which simplifies the overall data management process and saves time.

[0045] The data generation step (S200) can use the measurement data to calculate the sensor wearing time, time within a specific blood sugar range, time below the first blood sugar value, time above the second blood sugar value, EhyperE (whether blood sugar continuously exceeds 250 mg / dL for more than 2 hours), occurrence of blood sugar below 54 mg / dL, and food intake time detection (FITD).

[0046] The data generation step (S200) may set a specific blood sugar range to 70 to 180 mg / dL, the first blood sugar value to 70 mg / dL or 54 mg / dL, and the second blood sugar value to 180 mg / dL or 250 mg / dL.

[0047] In one embodiment, the data generation step (S200) can generate sensor wearing time, time within the 70 to 180 mg / dL blood sugar range, time below 70 mg / dL blood sugar, time below 54 mg / dL blood sugar, time exceeding 180 mg / dL blood sugar, time exceeding 250 mg / dL blood sugar, EhyperE (whether blood sugar continuously exceeds 250 mg / dL for 2 hours or more), whether blood sugar below 54 mg / dL occurs, and food intake time detection (FITD).

[0048] The data generation step (S200) can calculate the time of food intake (FITD) as the time corresponding to the minimum blood sugar level 2 hours prior to the time point (GRID) at which the blood sugar change rate increases by 95 mg / dL per hour for two consecutive values ​​or by 90 mg / dL or more per hour for three consecutive values.

[0049] The time to food intake (FITD) is calculated by an algorithm that detects the starting point of blood sugar rise after eating. This algorithm is newly derived by utilizing the existing glucose rate increase detector (GRID). GRID detects when blood sugar is 130 mg / dL or higher and the rate of change increases by 95 mg / dL per hour for two consecutive values, or 90 mg / dL or higher per hour for three values. GRID can identify when blood sugar rises sharply above 130 mg / dL, but has the limitation of not knowing when actual food intake begins. FITD can detect the starting point of food intake when blood sugar rises after eating.

[0050] Unlike the existing GRID, the time to food intake (FITD) can detect the point in time corresponding to the lowest blood sugar level 2 hours prior to the point of rapid blood sugar rise across the entire blood sugar range, including blood sugar levels below 130 mg / dL.

[0051] The data classification step (S300) may include a matrix part that classifies into one or more cases based on the time of wearing the sensor for a week, the time within a specific blood sugar range, the time below the first blood sugar value, the time above the second blood sugar value, EhyperE (whether the blood sugar continuously exceeded 250 mg / dL for more than 2 hours), the occurrence of blood sugar below 54 mg / dL, and the time ratio of food intake time, and an insulin and lifestyle correction part that classifies into one or more cases based on the number of times a certain blood sugar level occurred in a certain time period.

[0052] The matrix part is classified as the first case when the time ratio within a specific blood sugar range is 70% or more, the time ratio of high blood sugar exceeding 180 mg / dL is less than 25%, the time ratio of high blood sugar exceeding 250 mg / dL is less than 5%, the time ratio of low blood sugar below 70 mg / dL is less than 4%, the time ratio of low blood sugar below 54 mg / dL is less than 1%, and the time ratio of sensor wearing is 70% or more, and the second case when the sensor wearing time ratio is less than 70%, and the time ratio within a specific blood sugar range is 70% or more, but the time ratio of high blood sugar exceeding 180 mg / dL is less than 25%, the time ratio of high blood sugar exceeding 250 mg / dL is less than 5%, the time ratio of low blood sugar below 70 mg / dL is less than 4%, and the time ratio of low blood sugar below 54 mg / dL is 1%. A case where at least one time ratio does not reach the corresponding value can be classified as a third case, and a case where the sensor wearing time ratio is 70% or more and the time ratio within a specific blood sugar range is less than 70% can be classified as a fourth case.

[0053] In the insulin and lifestyle correction part, the first case is classified when the number of days on which hypoglycemia of less than 70 mg / dL occurred for more than 15 minutes between 00:00 and 06:00 is 2 times, the second case is classified when the time ratio of hyperglycemia exceeding 180 mg / dL between 00:00 and 06:00 is 25% or more, the food intake time between 23:00 and 06:00 is 1 or less, the lowest blood sugar between 00:00 and 06:00 is 100 mg / dL, and the number of days on which blood sugar between 06:00 and 08:00 is 150 mg / dL or higher is 3 consecutive times, the third case is classified when the number of days on which the time ratio of hypoglycemia of less than 70 mg / dL between 00:00 and 02:00 exceeds 4% is 3 times, and the third case is classified when the time ratio of hyperglycemia of more than 250 mg / dL between 10:00 and 02:00 exceeds 10%. Cases where the number of days is 4 are classified as case 4, cases where the maximum blood sugar level is 220 mg / dL or higher after food intake between 10:00 and 24:00 are 4 times classified as case 5, cases where the blood sugar level is 70 mg / dL or higher but 140 mg / dL or lower within 5 hours after food intake (after the maximum blood sugar level after a meal) at a point where the blood sugar level is 70 mg / dL or higher between 08:00 and 24:00 are classified as case 5-1, cases where the blood sugar level is 140 mg / dL or higher within 5 hours after food intake (after the maximum blood sugar level after a meal) at a point where the blood sugar level is 70 mg / dL or higher between 08:00 and 24:00 are classified as case 5-2, and cases where the number of days where the maximum blood sugar level between 00:00 and 03:00 starts from 250 mg / dL or higher and the difference from the lowest point within 4 hours is 100 mg / dL or higher is 2 times It can be classified as case 6, and if EhyperE (blood sugar level exceeds 250 mg / dL continuously for more than 2 hours) occurs 3 times a week, it can be classified as EhyperE.

[0054] The message generation step (S400) can generate sentences for each of the matrix part and the insulin and lifestyle correction parts according to the cases classified in the data classification unit.

[0055] The message generation step (S400) can generate the sentence "You did a great job. The wearing time and all blood sugar indicators reached the target value" if there is no improvement indicator compared to last week in the first case of the matrix part, and "You did a great job. The wearing time and all blood sugar indicators reached the target value. The most noticeable improvement is the decrease or increase in the percentage of x time (x1% -> x2%)" if there is an improvement indicator. Here, x time refers to the area that has changed the most based on the absolute value compared to the previous week, x1 can refer to the previous week value of x, and x2 can refer to the current week value of x.

[0056] The message generation step (S400) can generate the sentence "The total number of sensor wearing days this week is x days. The sensor wearing goal is about 5 days or more (70% or more) out of 7 days. To reach the sensor wearing goal, you need to wear the sensor for y more days." Here, x days is calculated as 7 days * sensor wearing rate (percentage) for a week, and y can be defined as 5-x.

[0057] The message generation step (S400) can produce the sentence "Good job. All blood sugar indicators have improved compared to last week in the third case of the matrix part. You have reached the target rate (>=70%) with a blood sugar rate a% within the range (70-180mg / dL) for one week. However, you must reduce x rate x1% to x2%." If there is at least one indicator that has decreased compared to last week, "Good job. You have reached the target rate (>=70%) with a blood sugar rate a% within the range (70-180mg / dL) for one week. However, you must reduce x rate x1% to x2%." If there are no indicators that have decreased or improved compared to last week, "Good job. You have reached the target rate (>=70%) with a blood sugar rate a% within the range (70-180mg / dL) for one week." Here, a represents the ratio of the current week's time within the range, x represents the indicator with the largest difference from the target among the matrices that have not reached the target range, x2 represents the x value of the current week, and x3 can represent the target ratio of the x ratio.

[0058] The message generation step (S400) can output the sentence "Thank you for your hard work. All blood sugar indicators have improved compared to last week in the fourth case of the matrix part. It is important to reduce the x time rate x2% to x3%." If there is at least one indicator that has decreased compared to last week, it can output the sentence "Thank you for your hard work. Compared to last week, the x time rate has increased by x1%. It is important to reduce the x time rate x2% to x3%." If there is no indicator that has decreased or improved compared to last week, it can output the sentence "Thank you for your hard work. It is important to reduce the x time rate x2% to x3%." Here, x refers to the indicator with the largest difference from the target among the matrices that have not reached the target range, x1 refers to the difference between the x indicator's value and last week's value, x2 refers to the x value of the current week, and x3 refers to the target rate of the x indicator.

[0059] The message generation step (S400) can produce the sentence "Be careful of hypoglycemia in the early morning on day x. If hypoglycemia is less than 70 mg / dL without additional injection during the night (00:00~06:00), reduce the long-acting insulin by 10%" in the first case of the insulin part. Here, day x refers to the date of occurrence. The message generation step (S400) can produce the sentence "The frequency of nighttime hyperglycemia is high on day x. If the rate of hyperglycemia is high during the night regardless of meals, you can try increasing the long-acting insulin by 10%" in the second case of the insulin part. Here, day x refers to the date of occurrence. The message generation step (S400) can produce the sentence "Hypoglycemia occurred on day x. The dose of rapid-acting insulin is high compared to the amount of carbohydrate intake. Reduce the insulin dose when eating small meals" in the third case of the insulin part. Here, day x refers to the date of occurrence. The message generation step (S400) can produce the sentence "High blood sugar levels of 250 or higher are frequent. The initial insulin dose is low compared to the meal amount, so when eating a high-carbohydrate meal, increase the initial insulin dose before the meal." in the fourth case of the insulin part.

[0060] The message generation step (S400) can generate the sentence "If your blood sugar level rises rapidly after meals on x days in the morning / x days at lunch / x days in the evening, take rapid-acting insulin 10-15 minutes before meals when eating meals high in carbohydrates that cause rapid blood sugar rises." Here, x days refers to the date of occurrence.

[0061] The message generation step (S400) can produce the sentence "The rapid-acting insulin dose on x day morning / x day lunch / x day dinner was less than the meal amount. Increase the insulin dose when eating a high-carbohydrate meal" in the 5-2 case of the insulin part. Here, x day means the date that occurred. If case 5-1 occurs even once, the message is generated based on case 5-1. The message generation step (S400) can produce the sentence "If rapid-acting insulin was administered to correct hyperglycemia late at night on x day, increase the dose of rapid-acting insulin before meals by 10% and take it 10 to 15 minutes before meals" in the 6th case of the insulin part. Here, x day means the date that occurred. The message generation step (S400) can generate the sentence "Severe hyperglycemia of 250 mg / dL or higher for more than 2 hours occurred on x days. Respond to the hyperglycemia alarm immediately. Follow the rapid insulin dose and time." Here, x days refers to the date of occurrence.

[0062] The message generation step (S400) can generate the sentence "Severe hypoglycemia of less than 54 mg / dL occurred on x days. Be careful of rapid insulin overcorrection and respond immediately to the hypoglycemia alarm" if hypoglycemia of less than 54 mg / dL occurs even once. Here, x days refers to the date of occurrence.

[0063] The message generation step (S400) always generates a sentence in the case where there is EhyperE and hypoglycemia less than 54 mg / dL in the insulin part, and in the case of the first and second cases, the first case may have priority, and in the case of the third, fourth, and fifth cases, the third, fourth, and fifth cases may have priority in that order. The message generation step (S400) may not output the first and second cases in the case where there is EhyperE and hypoglycemia less than 54. The message generation step (S400) may output the sentence if the second, third, fourth, and fifth cases do not occur in the case of the sixth case. In another embodiment, the data classification step (S300) may classify the five cases and the severe hypoglycemia less than 54 cases in diabetic patients who use oral medications other than rapid-acting insulin and long-acting insulin.

[0064] The data classification step (S300) can classify the number of days when hypoglycemia of less than 70 mg / dL occurred for more than 15 minutes between 00:00 and 06:00 as the first case if it occurred twice a week, and the message generation step (S400) can generate the sentence, "Be careful of hypoglycemia in the morning on day x. If hypoglycemia of less than 70 mg / dL occurs during the night (00:00 to 06:00) without additional injection, reduce long-acting insulin by 10%." Here, day x refers to the date of occurrence.

[0065] The data classification step (S300) can classify the case as the second case when the time ratio of hyperglycemia exceeding 180 mg / dL between 00:00 and 06:00 is 25% or more, the food intake time between 23:00 and 06:00 is 1 or less, the lowest blood sugar between 00:00 and 06:00 is 100 mg / dL, and the number of days when the blood sugar between 06:00 and 08:00 is 150 mg / dL or higher is 3 consecutive times, and the message generation step (S400) can generate the sentence, "The frequency of nighttime hyperglycemia is high on x days. If the blood sugar is high regardless of meals during the night, you can try increasing the dose of long-acting insulin by 10%."

[0066] The data classification step (S300) can classify it as the third case if the number of days in which blood sugar levels exceed 4% below 70 mg / dL between 8:00 and 24:00 occurs more than 3 times a week, and the message generation step (S400) can generate the sentence, "The number of days in which hypoglycemia below 70 mg / dL occurred for a long time is x. If you are taking a sulfonylurea (Amaryl, Diamicron, Daigrin) among the oral medications, split it in half or stop taking it." Here, x day refers to the date of occurrence.

[0067] The data classification step (S300) can classify it as the 4th case if the number of days with TAR (>250) exceeding 10% between 08:00 and 24:00 occurs for 3 or more days, and the message production step (S400) can produce the sentence, "High blood sugar levels above 250 are frequent. Reduce the amount of carbohydrates (rice, bread, noodles, rice cakes, fruit) at meals to about 50% of total food and consume plenty of protein and vegetables. Do some light exercise for about 30 minutes after eating. The target blood sugar level before each meal is 80-130 mg / dL."

[0068] The data classification step (S300) can be classified as case 5 if the number of times the maximum postprandial blood sugar level exceeds 250 mg / dL between 8:00 and 24:00 is 4 or more times a week, and the message generation step (S400) can be generated as sentences such as "Since there is a pattern of rapid rise in postprandial hyperglycemia, eat slowly and avoid high carbohydrate index foods. Examples: Avoid simple sugars and refined sugars, eat salad and protein first, eat carbohydrates, reduce soup."

[0069] The message generation step (S400) can generate the sentence "Severe hypoglycemia of less than 54 mg / dL occurred on day x. Reduce the dose of long-acting insulin by 20% or discontinue any oral sulfonylureas (Amaryl, Diamicron, Dygrin) if there is severe hypoglycemia of less than 54 mg / dL." Here, day x refers to the date of occurrence.

[0070] The message generation step (S400) may not generate cases 3, 4, 5, and 6 in the case of severe hypoglycemia below 54 mg / dL, and instead send a message for severe hypoglycemia below 54 mg / dL. In the message generation step (S400), case 1 may have priority in the case of cases 1 and 2, and cases 3, 4, and 5 may have priority in the order of cases 3, 4, and 5.

[0071] The message recalculation step (S500) can recalculate sentences that have the same meaning as the message sentences produced in the message production step (S400) but are composed of different words. Based on the classified cases, the message recalculation step (S500) can divide each sentence for each matrix case into a portion that must be fixedly produced and a portion where alternative words can be applied. The message recalculation step (S500) can randomly select words and produce sentences based on a file containing alternative words for replaceable words.

[0072] For example, the message recalculation step (S500) can recalculate the basic message in the first case of the matrix part, "Thank you for your hard work. All blood sugar indicators, including the wearing time, have all reached the target level." into a sentence composed of replaced words, such as "Congratulations. All blood sugar indicators, including the wearing time, have successfully reached the target level." The message recalculation step (S500) is applied to all sentences in each mattress case, and even in the same matrix case, messages with different contents can be produced for each individual week.

[0073] The figure generation step (S600) can generate a graph of blood sugar levels by time zone, an average blood sugar pattern for each time zone, and a percentage change in one or more key matrices based on measurement data received over a week.

[0074] The graphic generation step (S600) can generate three graphs based on one week's blood sugar data. In the first region, the ratios of five key metrics from the previous week to the current week are represented as bar graphs, and the change in values ​​between the previous week and the current week can be expressed as text. In the second region, the average blood sugar pattern for each time period over the week is expressed, and the range of values ​​from 5% to 95% can be graphically represented. In the third region, blood sugar graphs for each time period can be displayed by date.

[0075] The message sending step (S700) can automatically send the final message and picture to the relevant person.

[0076] FIG. 3 is a block diagram of a device (100) for managing a diabetic patient using a continuous glucose monitoring device, which is another embodiment of the present invention. Referring to FIG. 11, the configuration of the device (100) for managing a diabetic patient using a continuous glucose monitoring device illustrated is merely a simplified example. In one embodiment of the present invention, the device (100) for managing a diabetic patient using a continuous glucose monitoring device may include other components for performing the computing environment of the device (100), and only some of the disclosed components may constitute the device (100).

[0077] A device (100) for managing a diabetic patient using a continuous blood glucose monitoring device may include a processor (110) including one or more cores, a memory (120), and a network (130).

[0078] The processor (110) may be configured with one or more cores, and may include a processor for data analysis and deep learning, such as a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device. The processor (110) may read a computer program stored in the memory (120) and perform data processing for machine learning according to an embodiment of the present disclosure. According to an embodiment of the present disclosure, the processor (110) may perform operations for learning a neural network. The processor (110) may perform calculations for learning a neural network, such as processing input data for learning in deep learning (DL), extracting features from input data, calculating errors, and updating weights of a neural network using backpropagation. At least one of the CPU, GPGPU, and TPU of the processor (110) may process learning of a network function. For example, a CPU and a GPGPU can jointly process network function learning and data classification using network functions. Furthermore, in one embodiment of the present disclosure, processors of multiple computing devices can be jointly used to process network function learning and data classification using network functions. Furthermore, a computer program executed on a computing device according to one embodiment of the present disclosure may be a CPU, GPGPU, or TPU executable program.

[0079] The processor (110) can receive measurement data from a continuous blood glucose meter. The processor (110) can perform the data receiving step (S100) described above.

[0080] The processor (110) can use the measurement data to calculate the sensor wearing time, the time within a specific blood sugar range, the time below the first blood sugar value, the time above the second blood sugar value, EhyperE (whether the blood sugar continuously exceeds 250 mg / dL for more than 2 hours), and the food intake time detection (FITD). The processor (110) can perform the data calculation step (S200) described above.

[0081] The processor (110) can classify the data into one or more cases based on the time ratio of sensor wearing time, time within a specific blood sugar range, time below the first blood sugar level, time exceeding the second blood sugar level, EhyperE (whether blood sugar level continuously exceeds 250 mg / dL for more than 2 hours), and food intake time for a week, and can classify the data into one or more cases based on the number of times a certain blood sugar level occurs in a certain time interval. The processor (110) can perform the data classification step (S300) described above.

[0082] The memory (120) can store any form of information generated or determined by the processor (110) and any form of information received by the network (130).

[0083] The memory (120) may include at least one type of storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk. The computing device (100) may also operate in relation to web storage that performs the storage function of the memory (120) on the internet. The description of the above-described memory is merely an example, and the present disclosure is not limited thereto.

[0084] The network (130) may use any known wired or wireless communication system. The network (130) may receive blood sugar measurement data and the like from related devices or systems.

[0085] The network (130) can transmit and receive information, user interfaces, etc. processed by the processor (110) through communication with other terminals. For example, the network (130) can provide a user interface generated by the processor (100) to a client (e.g., a user terminal). In addition, the network (130) can receive external input from a user authorized as a client and transmit it to the processor (110). At this time, the processor (110) can process operations such as outputting, modifying, changing, and adding information provided through the user interface based on the external input of the user received from the network (130).

[0086] Meanwhile, a device (100) for managing a diabetic patient using a continuous blood glucose monitoring device according to one embodiment of the present disclosure may include a server as a computing system that transmits and receives information through communication with a client. In this case, the client may be any type of terminal capable of accessing the server.

[0087] In an additional embodiment, a device (100) for managing a diabetic patient using a continuous blood glucose monitoring device may include any type of terminal that receives data resources generated from any server and performs additional information processing.

[0088] Another embodiment of the present invention, a computer program for managing a diabetic patient using a continuous glucose monitoring device, may include data reception operations, data generation operations, and data classification operations. The computer program for managing a diabetic patient using a continuous glucose monitoring device may be stored on a computer-readable storage medium and include commands that cause the computer to perform the following operations.

[0089] The data reception operation can receive measurement data from a continuous blood glucose meter. The data reception operation refers to the operation performed in the data reception step (S100) described above.

[0090] The data production operation can use the measurement data to produce the sensor wearing time, time within a specific blood sugar range, time below the first blood sugar value, time above the second blood sugar value, EhyperE (whether blood sugar continuously exceeds 250 mg / dL for more than 2 hours), blood sugar below 54 mg / dL, and food intake time detection (FITD). The data production operation refers to the operation performed in the data production step (S200) described above.

[0091] The data classification operation may include a matrix part that classifies into one or more cases based on the time ratio of sensor wearing time, time within a specific blood sugar range, time below the first blood sugar value, time above the second blood sugar value, EhyperE (whether blood sugar continuously exceeds 250 mg / dL for more than 2 hours), blood sugar below 54 mg / dL, and food intake time for a week, and an insulin and lifestyle correction part that classifies into one or more cases based on the number of times a certain blood sugar level occurred in a certain time period. The data classification operation refers to the operation performed in the data classification step (S300) described above.

[0092] While the present invention has been described in detail through representative examples above, those skilled in the art will understand that various modifications to the above-described embodiments are possible without departing from the scope of the present invention. Therefore, the scope of the present invention should not be limited to the described embodiments, but should be defined not only by the claims described below but also by all changes or modifications derived from the claims and equivalent concepts.

[0093]

[0094] The purpose of the present invention is to automatically generate a report based on blood sugar patterns that patients can understand on a weekly basis in addition to the date of treatment, to automatically interpret the contents of the report to patients based on their blood sugar patterns and suggest areas for improvement, and to provide patients with customized suggestions for insulin control, diet, and exercise based on their blood sugar patterns.

Claims

1. A method for managing a diabetic patient using a continuous blood glucose monitoring device, A data receiving step for receiving measurement data from a continuous blood glucose meter; A data generation step for calculating sensor wearing time, time within a specific blood sugar range, time below the first blood sugar value, time above the second blood sugar value, EhyperE (whether blood sugar continuously exceeds 250 mg / dL for more than 2 hours), blood sugar below 54 mg / dL, and food intake time detection (FITD) using the above measurement data; and A data classification step including a matrix part that classifies the data into one or more cases based on the time of wearing the sensor for a week, time within a specific blood sugar range, time below the first blood sugar value, time above the second blood sugar value, EhyperE (whether blood sugar continuously exceeded 250 mg / dL for more than 2 hours), and time ratio of food intake time, and an insulin and lifestyle modification part that classifies the data into one or more cases based on the number of times a certain blood sugar level occurred in a certain time interval; How to include.

2. In paragraph 1, The above data receiving step is, A method for receiving the time at which blood sugar was measured and the blood sugar value using the above measurement data.

3. In paragraph 1, The above data receiving step is a method including a user directly downloading measurement data in a specific file format from a continuous blood glucose meter server.

4. In paragraph 1, The above data receiving step is, After logging in by automatically submitting your login information to the homepage that manages the server, A method comprising: retrieving a list of patients to be managed from the above homepage and automatically downloading the time of blood sugar measurement and blood sugar value stored in the server corresponding to the patient list.

5. In paragraph 4, The above automatic download method further includes a step of extracting data including the time at which blood sugar was measured and the blood sugar value from the logged-in account, excluding unnecessary information, and converting it into a format usable by a data analysis program.

6. In paragraph 1, The above data production step is, A method wherein the specific blood sugar range is set to 70 mg / dL to 180 mg / dL, the first blood sugar value is set to 70 mg / dL or 54 mg / dL, and the second blood sugar value is set to 180 mg / dL or 250 mg / dL.

7. In paragraph 1, The above data production step is, A method for calculating the time of food intake as the time corresponding to the lowest blood sugar level 2 hours prior to the point at which the blood sugar change rate increases by 95 mg / dL per hour for two consecutive values ​​or by 90 mg / dL or more per hour for three consecutive values.

8. In paragraph 1, The above matrix part is, Case 1 is classified as a case in which the time ratio within a specific blood sugar range is 70% or more, the time ratio of high blood sugar exceeding 180 mg / dL is less than 25%, the time ratio of high blood sugar exceeding 250 mg / dL is less than 5%, the time ratio of low blood sugar below 70 mg / dL is less than 4%, the time ratio of low blood sugar below 54 mg / dL is less than 1%, and the time ratio of sensor wearing is 70% or more. Cases where the sensor wearing time ratio is less than 70% are classified as the second case. The third case is classified as a case in which the sensor wearing time ratio is 70% or more, the time ratio within a specific blood sugar range is 70% or more, but at least one of the time ratios among the time ratio of hyperglycemia exceeding 180 mg / dL is less than 25%, the time ratio of hyperglycemia exceeding 250 mg / dL is less than 5%, the time ratio of hypoglycemia below 70 mg / dL is less than 4%, and the time ratio of hypoglycemia below 54 mg / dL is less than 1% does not reach below the corresponding value. A method of classifying a case in which the sensor wearing time ratio is 70% or more and the time ratio within a specific blood sugar range is less than 70% as the fourth case.

9. In paragraph 1, The above insulin and lifestyle correction part is, Case 1 is classified as the case in which hypoglycemia of less than 70 mg / dL occurred twice between 00:00 and 06:

00. Case 2 is classified as a case in which the proportion of time with high blood sugar exceeding 180 mg / dL between 00:00 and 06:00 is 25% or more, the food intake time between 23:00 and 06:00 is 1 or less, the lowest blood sugar between 00:00 and 06:00 is 100 mg / dL, and the number of days in which the blood sugar between 06:00 and 08:00 is 150 mg / dL or higher is 3 consecutive times. Case 3 is classified as the case in which the number of days in which the hypoglycemic time ratio of less than 70 mg / dL between 00:00 and 24:00 exceeds 4%, and Case 4 is classified as the case in which the number of days in which the hyperglycemia time ratio exceeds 250 mg / dL between 10:00 and 24:00 exceeds 5%, and Case 5 is when the maximum blood sugar level is 220 mg / dL or higher 4 times after eating between 10:00 and 24:

00. A method of classifying a case as the 6th case when the number of days in which the highest blood sugar level between 00:00 and 03:00 is 250 mg / dL or higher and the difference from the lowest level within 4 hours is 100 mg / dL or higher is 2 times.

10. In paragraph 1, A message generation step for generating sentences for each of the matrix part and the insulin and lifestyle correction parts according to the cases classified in the above data classification section; A method comprising:

11. In paragraph 10, A message re-calculation step that re-calculates a sentence that has the same meaning as the sentence of the message produced in the above message production step but is composed of different words; A method comprising:

12. In paragraph 11, A graph generation step for generating a graph of blood glucose by time zone, average blood glucose pattern by time zone, and percentage change of one or more key metrics based on measurement data received over a week; A method comprising:

13. A device for managing diabetic patients using a continuous blood glucose meter, a processor comprising one or more cores; and memory; Including, The above processor, Receive measurement data from a continuous glucose monitoring device, Using the above measurement data, the sensor wearing time, time within a specific blood sugar range, time below the first blood sugar value, time above the second blood sugar value, EhyperE (whether blood sugar continuously exceeds 250 mg / dL for more than 2 hours), blood sugar below 54 mg / dL, and food intake time detection (FITD) are calculated, and A device that classifies into one or more cases based on the time of wearing the sensor for a week, time within a specific blood sugar range, time below the first blood sugar value, time above the second blood sugar value, EhyperE (whether blood sugar continuously exceeds 250 mg / dL for more than 2 hours), blood sugar below 54 mg / dL, and time ratio of food intake time, and classifies into one or more cases based on the number of times a certain blood sugar level occurs in a certain time interval.

14. A computer program stored in a computer-readable storage medium and including commands that cause a computer to perform the following operations, wherein the operations are: Data receiving operation for receiving measurement data from a continuous blood glucose meter; Using the above measurement data, a data generation operation for calculating the sensor wearing time, time within a specific blood sugar range, time below the first blood sugar value, time above the second blood sugar value, EhyperE (whether blood sugar continuously exceeds 250 mg / dL for more than 2 hours), blood sugar below 54 mg / dL, and food intake time detection (FITD); and A computer program stored in a computer-readable storage medium, comprising a data classification operation including a matrix part that classifies data into one or more cases based on the time of wearing the sensor, the time within a specific blood sugar range, the time below the first blood sugar value, the time above the second blood sugar value, EhyperE (whether the blood sugar continuously exceeded 250 mg / dL for more than 2 hours), the time ratio of blood sugar below 54 mg / dL, and the time of food intake, and an insulin and lifestyle modification part that classifies data into one or more cases based on the number of times a certain blood sugar level occurred in a certain time period.

Images