Intelligent blood glucose monitoring method and system for nephrology department

Abstract

The invention discloses a nephrology department blood glucose intelligent monitoring method and system, and the method comprises the steps: collecting and analyzing blood glucose data of a nephrology department patient, obtaining a blood glucose change abnormal factor of each data, obtaining the attention of the data through the abnormal factors and the data deviation size, and distinguishing the importance degree of the blood glucose data, and finally, obtaining a final blood glucose level risk score according to the periodic expression and the overall attention of the important data, judging whether the blood glucose level of the patient has a risk or not, and adjusting a treatment scheme in time. According to the method, the influence caused by inaccurate blood glucose level threshold value due to individual difference can be reduced, the obtained risk score conforms to the blood glucose change characteristics of the patient, meanwhile, the blood glucose curve fluctuation condition of the patient can be mined through the change abnormal factor and periodic expression of the data, the change of the blood glucose state of the patient can be reflected more comprehensively, and the accuracy of the patient is improved. A more accurate real-time blood glucose level monitoring effect is obtained, and intelligent monitoring of blood glucose in the nephrology department is achieved.

Description

Technical Field

[0001] The invention belongs to the technical field of data processing and relates to a method and system for intelligent blood sugar monitoring in nephrology. Background Art

[0002] Blood glucose is an important indicator for assessing the normality of human glucose metabolism and is usually used to screen, diagnose and monitor a variety of abnormal glucose metabolism diseases such as diabetes and hypoglycemia. Blood glucose monitoring is of great significance in the work of nephrology. It can help doctors to timely discover and intervene in problems related to glucose metabolism and improve the treatment effect and quality of life of patients. In order to accurately understand the changes in patients' blood glucose levels, doctors usually use monitoring equipment such as blood glucose meters or external attached sensors to obtain patients' real-time blood glucose data, and judge whether there is abnormal blood glucose by the proportion of time when blood glucose is within the normal range. In the process of monitoring patients' blood glucose levels, doctors usually assess the risk of patients' illness based on the percentage of time when the patient's blood glucose reaches the standard. The percentage of time when the blood glucose reaches the standard is the percentage of time when the blood glucose value is in the normal range between the high and low thresholds. The higher the percentage, the lower the risk. However, the setting of normal blood glucose thresholds is often based on research data of large-scale populations and cannot be well applied to all patients. In addition, the fluctuation of blood glucose in patients is also very important for the assessment and diagnosis of the disease, and the percentage of time when the blood glucose reaches the standard cannot reflect this fluctuation. Therefore, although the method of using thresholds to judge whether blood glucose levels are normal is simple and easy, it has the defects of inaccuracy and incompleteness in practical application, which may lead to certain deviations in the analysis results and reduce the accuracy and real-time performance of monitoring. Summary of the invention

[0003] The purpose of the present invention is to solve the problem that the method of using the normal blood sugar threshold to judge whether the blood sugar level is normal in the prior art is simple and easy, but in actual application, there are defects of inaccuracy and incompleteness, which may cause certain deviations in the analysis results, reduce the accuracy and real-time performance of the monitoring, and provide a method and system for intelligent monitoring of blood sugar in nephrology. To achieve the above purpose, the present invention adopts the following technical scheme to achieve it: a method for intelligent monitoring of blood sugar in nephrology, including: collecting blood sugar data of patients that continuously change over a period of time; based on the local change characteristics of the collected blood sugar data, obtaining the corresponding abnormal blood sugar change factor; based on the change law of blood sugar data, obtaining the relative deviation of blood sugar data; based on the obtained abnormal blood sugar change factor and the relative deviation of blood sugar data, determining the attention of blood sugar data; based on the periodic performance and overall attention of blood sugar data, obtaining the final blood sugar level risk score; based on the size of the blood sugar level risk score, comparing the set blood sugar score threshold, evaluating whether the patient's blood sugar is abnormal; if so, issuing an early warning; if not, indicating that the patient is in good health.

[0004] A further improvement of the present invention is that: further, the patient's blood sugar data that changes continuously over a period of time is collected, specifically: a fixed collection frequency for the patient's blood sugar data is set based on a blood sugar meter; at the same time, the patient's daily meal time is recorded and the patient's collection cycle is set.

[0005] Furthermore, based on the local variation characteristics of the collected blood sugar data, the corresponding blood sugar variation abnormality factor is obtained, specifically: any blood sugar data is set as reference data, and a fixed-size neighborhood is set for the reference data. for: ,in, For reference data, Represents the first individual data; represents the first-order difference of blood glucose data, where ; and are two adjacent blood sugar change values, is a symbolic function; Indicates the degree of blood sugar change in the neighborhood of the reference data. The larger the value, the more drastic the blood sugar change around the reference data. Also bigger; Indicates the number of blood glucose data in the neighborhood; Represents the number of pairwise combinations of adjacent blood glucose data in the neighborhood; It indicates the frequency of blood sugar fluctuation in the neighborhood of the reference data. If the directions of two adjacent changes are consistent, 1 if the direction is inconsistent, -1; The smaller the value of, the higher the blood sugar fluctuation frequency in the reference data neighborhood, and the higher the corresponding blood sugar abnormality factor The bigger.

[0006] Furthermore, based on the variation pattern of blood sugar data, the relative deviation of blood sugar data is obtained, specifically: ,in, is the mean of all blood sugar data in the sample, is the maximum blood sugar data in the sample, is the minimum blood sugar data in the sample; is the difference between the reference data and the mean, It represents the maximum difference between all the data in the sample and the mean. It is the ratio of the mean deviation of the reference data to the maximum mean deviation. The larger the value is, the greater the relative deviation of the reference data is, and the higher the corresponding attention is.

[0007] Furthermore, the attention level of blood sugar data is determined as follows: ,in, is the time point of the reference data, The closest to the reference data Meal time points, Indicates the abnormal blood sugar change factor based on the reference data at meal time. is the abnormal blood sugar change factor of the reference data, The larger the value, the more attention the reference data receives. It represents the time interval between the two meals closest to the reference data. The smaller the interval, the higher the attention.

[0008] Further, the periodic performance based on blood sugar data is as follows: ,in, The intensity of the blood glucose curve cycle of the patient; Indicates the number of days from the time of recording. Blood sugar data, The total number of blood sugar data in one day; Indicates the number of the same time point every day in the past u days. individual data; Indicates the attention level of the j-th blood sugar data in the past k-th day; For the past u days Mean blood sugar data at time points, In the past days Mean value of attention to blood glucose data at a time point; Indicates that blood sugar data samples The similarity of data based on attention at a time point, The smaller the value of The smaller the difference in blood sugar data at each time point, the stronger the blood sugar curve cycle performance. The greater the blood sugar level risk score The larger the for The smaller the value, the closer the data attention is to each time point. The closer the blood sugar data at each time point are, the The greater the difference in blood glucose data at each time point, the greater the impact on the intensity of the blood glucose curve cycle performance.

[0009] Furthermore, based on the periodic performance and overall attention of blood sugar data, the final blood sugar level risk score is obtained, specifically: ,in, to create a risk score for the final blood sugar level; Indicates the first data, Indicates the total number of data in the sample; is the attention variance of all blood glucose data in the sample; Indicates the overall attention level of all blood sugar data in the sample. The larger the value is, the worse the stability of the blood sugar data in the blood sugar data sample is, the lower the blood sugar regulation speed is, and the corresponding blood sugar level risk score is The bigger.

[0010] Further, based on the size of the blood sugar level risk score, the set blood sugar score threshold is compared, specifically: setting the blood sugar score threshold and ;like , it means that the patient's blood sugar level is normal; , it reminds the patient that the blood sugar condition is poor and needs to be adjusted in time; if , it means that the patient's blood sugar condition is abnormal and needs to be treated by a doctor.

[0011] A blood sugar intelligent monitoring system for nephrology comprises: a collection module, the collection module collects blood sugar data of patients that continuously changes over a period of time; a first acquisition module, the first acquisition module acquires corresponding blood sugar change abnormal factors based on the local change characteristics of the collected blood sugar data; a second acquisition module, the second acquisition module acquires the relative deviation of the blood sugar data based on the change law of the blood sugar data; a determination module, the determination module determines the attention of the blood sugar data based on the acquired blood sugar change abnormal factors and the relative deviation of the blood sugar data; a third acquisition module, the third acquisition module derives a final blood sugar level risk score based on the periodic performance and overall attention of the blood sugar data; an evaluation module, the evaluation module evaluates whether the patient's blood sugar is abnormal based on the size of the blood sugar level risk score and the set blood sugar score threshold; if so, an early warning is issued; if not, it indicates that the patient is in good health.

[0012] Compared with the prior art, the present invention has the following beneficial effects: the present invention obtains the abnormal blood sugar change factor of each data by collecting and analyzing the blood sugar data of patients in the Department of Nephrology, and obtains the attention of the data by using the abnormal factors and the deviation size of the data, so as to distinguish the importance of the blood sugar data, and finally obtains the final blood sugar level risk score by the periodic performance and overall attention of the important data, judges whether the patient's blood sugar level is at risk and adjusts the treatment plan in time. The present invention can reduce the impact of inaccurate blood sugar level thresholds caused by individual differences, so that the obtained risk score conforms to the patient's own blood sugar change characteristics, and at the same time can mine the patient's blood sugar curve fluctuation through the abnormal factors and periodic performance of the data change, more comprehensively reflect the changes in the patient's blood sugar state, obtain a more accurate real-time blood sugar level monitoring effect, and realize the intelligent monitoring of blood sugar in the Department of Nephrology. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0014] Figure 1 It is a schematic diagram of the process of the intelligent blood glucose monitoring method of the nephrology department of the present invention; Figure 2 It is a structural schematic diagram of the intelligent blood glucose monitoring system for nephrology of the present invention. DETAILED DESCRIPTION

[0015] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0016] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0018] In the description of the embodiments of the present invention, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. indicate an orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the invention is usually placed when in use, it is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0019] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", which does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0020] In the description of the embodiments of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0021] The present invention is further described in detail below in conjunction with the accompanying drawings: Figure 1 , the present invention discloses an intelligent blood glucose monitoring method for nephrology, including: S101, collecting blood glucose data of patients that continuously change over a period of time; setting a fixed collection frequency for the patient's blood glucose data based on a blood glucose meter; and recording the patient's daily meal time and setting the patient's collection cycle. Specifically, it can be: using a blood glucose meter or externally attached sensor and other monitoring equipment to obtain the continuous u-day blood glucose data of nephrology patients in real time, and the data collection frequency is once every 10 minutes. In addition, it is also necessary to record the patient's daily meal time, and then construct the corresponding blood glucose data sample and upload it to the cloud for real-time monitoring and analysis. Among them, the collection duration and collection frequency are both empirically set, and the value of u can be set to 15 days; it can be adjusted according to actual conditions in specific applications.

[0022] S102, based on the local change characteristics of the collected blood sugar data, the corresponding abnormal blood sugar change factor is obtained; due to individual differences between different patients, each person's normal blood sugar range has different standards, and the conventional method of blood sugar monitoring method for risk assessment based on the percentage of blood sugar reaching the standard time of the patient uses a fixed threshold suitable for most people, which is not suitable for all people, and is prone to deviations in the analysis results. Not only that, the patient's blood sugar fluctuation is also very important for the evaluation and diagnosis of blood sugar status, and the percentage of blood sugar reaching the standard time cannot reflect this fluctuation, resulting in poor final monitoring effect. Therefore, it is first necessary to calculate the abnormal blood sugar change factor of each data according to the fluctuation characteristics and change trend of blood sugar, and then use the abnormal factor and data deviation to obtain the attention of the data, and finally obtain the final blood sugar level risk score according to the periodic performance and overall attention of the blood sugar data.

[0023] The conventional method of evaluating blood sugar levels relies more on some special blood sugar data, that is, analyzing whether the patient's blood sugar level is normal by the size of the data exceeding the threshold and the duration of the data. However, the limitations of threshold judgment and the existence of individual differences lead to low accuracy of this method, and it is easy to ignore the blood sugar data that may be abnormal. In practice, there are also large differences in the fluctuation of blood sugar data between normal individuals and abnormal individuals. The blood sugar data of abnormal individuals has poor stability and a relatively large range of variation. Therefore, in order to better mine these data that may be abnormal, the corresponding blood sugar change abnormality factor can be calculated according to the local change characteristics of each data to reflect the fluctuation of the data and distinguish the degree of attention to different data.

[0024] According to the above logic, first calculate the corresponding abnormal blood sugar change factor for all blood sugar data in the sample. Take any blood sugar data as reference data, set a fixed-size neighborhood for the reference data, and the neighborhood contains 5 adjacent blood sugar data before and after. The abnormal blood sugar change factor of this data for: ,in, For reference data, Represents the first individual data; represents the first-order difference of blood glucose data, where ; and are two adjacent blood sugar change values, is a symbolic function; Indicates the degree of blood sugar change in the neighborhood of the reference data. The larger the value, the more drastic the blood sugar change around the reference data. Also bigger; Indicates the number of blood glucose data in the neighborhood; Represents the number of pairwise combinations of adjacent blood glucose data in the neighborhood. The value of is set to 10, which means that the neighborhood contains 5 adjacent blood glucose data before and after. The value of should be 9; It represents the frequency of blood sugar fluctuation in the neighborhood of the reference data. If the directions of two adjacent changes are consistent, then 1 if the direction is inconsistent, -1; The smaller the value of, the higher the blood sugar fluctuation frequency in the reference data neighborhood, and the higher the corresponding blood sugar abnormality factor The bigger.

[0025] At this point, the blood sugar abnormality factor of all data in the sample can be obtained through the above steps, and then the next step of calculation can be performed.

[0026] S103, based on the changing pattern of blood sugar data, obtain the relative deviation of blood sugar data; when monitoring the patient's blood sugar data, more attention should be paid to the data of some special time nodes, such as the peak value, valley value or blood sugar value exceeding the threshold of the blood sugar curve. These special data can better reflect the patient's blood sugar health level. For patients with nephrology who may have physical abnormalities, their blood sugar may rise or fall too much after a meal due to the deterioration of the reabsorption function of the kidneys. Therefore, the relative deviation of blood sugar data rather than a fixed threshold can be used to measure the attention of the data. In addition, the insulin secretion time and total amount of nephrology patients may be different from those of normal people, which makes their blood sugar regulation abnormal for a period of time after a meal. Therefore, the blood sugar data before and after meals also have a high analytical value.

[0027] Based on the changing pattern of blood sugar data, the relative deviation of blood sugar data is obtained, specifically: ,in, is the mean of all blood sugar data in the sample, is the maximum blood sugar data in the sample, is the minimum blood sugar data in the sample; is the difference between the reference data and the mean, It represents the maximum difference between all the data in the sample and the mean. It is the ratio of the mean deviation of the reference data to the maximum mean deviation. The larger the value is, the greater the relative deviation of the reference data is, and the higher the corresponding attention is.

[0028] S104, based on the acquired blood sugar change abnormality factor and the relative deviation of the blood sugar data, determine the attention level of the blood sugar data; the attention level of the blood sugar data is recorded as , we can get: ,in, is the time point of the reference data, The closest to the reference data Meal time points; Indicates the abnormal blood sugar change factor based on the reference data at meal time. is the abnormal blood sugar change factor of the reference data, The larger the value, the more attention the reference data receives. It represents the time interval between the two closest meals of the reference data. The smaller the interval, the higher the attention. So far, the attention of all data in the sample can be obtained through the above steps, and then the next step of calculation can be carried out.

[0029] S105, based on the periodic performance and overall attention of blood glucose data, the final blood glucose level risk score is obtained; since the blood glucose level of the human body is closely related to the daily rhythm, the change of blood glucose data has a strong daily periodicity, and the stronger the periodicity, the lower the possibility of risk. However, there are more or less differences in people's diet, exercise, and environment every day. The existence of these differences will weaken the periodic performance of blood glucose data, which may lead to deviations in the assessment of patient blood glucose risk. In order to solve the above problem, the previously obtained data attention can be used for weighting when calculating the patient's blood glucose cycle performance. Data with similar attention are likely to be blood glucose data under similar conditions. When calculating, a higher weight is given, and vice versa. In addition, the blood glucose level of a normal individual is usually relatively stable and flat during the day, and only changes greatly before and after meals, and the speed of blood glucose regulation is also faster; and the blood glucose level of an abnormal individual will not only undergo more unstable changes, but also slow down the blood glucose regulation speed due to the weakening of the body's absorption and metabolic functions. Therefore, abnormal individuals have more high-attention blood glucose data than normal individuals, and the overall attention is higher.

[0030] The cycle performance based on blood sugar data is as follows: ,in, The intensity of the blood glucose curve cycle of the patient; Indicates the number of days from the time of recording. Blood sugar data, is the total number of blood sugar data in one day; here the value of u is 15 days; Indicates the number of times at the same time every day in the past 15 days. individual data; Indicates the attention level of the j-th blood sugar data in the past k-th day; For the past 15 days Mean blood sugar data at time points, In the past 15 days Mean value of attention to blood glucose data at a time point; Indicates that blood sugar data samples The similarity of data based on attention at a time point, The smaller the value of The smaller the difference in blood sugar data at each time point, the stronger the blood sugar curve cycle performance. The greater the blood sugar level risk score The larger the for The smaller the value, the closer the data attention is to each time point. The closer the blood sugar data at each time point are, the The greater the difference in blood glucose data at each time point, the greater the impact on the intensity of the blood glucose curve cycle performance.

[0031] Based on the periodic performance and overall attention of blood sugar data, the final blood sugar level risk score is obtained, specifically: ,in, to create a risk score for the final blood sugar level; Indicates the first data, Indicates the total number of data in the sample; is the attention variance of all blood glucose data in the sample; Indicates the overall attention level of all blood sugar data in the sample. The larger the value is, the worse the stability of the blood sugar data in the blood sugar data sample is, the lower the blood sugar regulation speed is, and the corresponding blood sugar level risk score is The bigger.

[0032] At this point, the corresponding blood sugar level risk score can be obtained through the patient's blood sugar data for the past 15 days. This score can reflect the patient's blood sugar health status in the past 15 days. The higher the score, the worse the health status and the more likely there is a risk of disease.

[0033] S106, based on the size of the blood sugar level risk score, compare it with the set blood sugar score threshold to evaluate whether the patient's blood sugar is abnormal; if so, issue a warning; if not, it means that the patient is in good health.

[0034] Setting blood sugar score thresholds and ; is 0.6, is 0.8, if ,Right now , it means that the patient's blood sugar level is normal; ,Right now , it means that the patient's blood sugar condition is poor and needs to be adjusted in time; if ,Right now , it means that the patient's blood sugar condition is abnormal and needs to be treated by a doctor.

[0035] See also Figure 2The present invention discloses an intelligent blood glucose monitoring system for nephrology, comprising: an acquisition module, wherein the acquisition module acquires blood glucose data of a patient that changes continuously over a period of time; a first acquisition module, wherein the first acquisition module acquires corresponding abnormal blood glucose change factors based on the local change characteristics of the acquired blood glucose data; a second acquisition module, wherein the second acquisition module acquires the relative deviation of the blood glucose data based on the change law of the blood glucose data; a determination module, wherein the determination module determines the attention of the blood glucose data based on the acquired abnormal blood glucose change factors and the relative deviation of the blood glucose data; a third acquisition module, wherein the third acquisition module derives a final blood glucose level risk score based on the periodic performance and overall attention of the blood glucose data; an evaluation module, wherein the evaluation module evaluates whether the patient's blood glucose is abnormal based on the size of the blood glucose level risk score and the set blood glucose score threshold; if so, an early warning is issued; if not, it indicates that the patient is in good health.

[0036] A terminal device is provided in one embodiment of the present invention. The terminal device of this embodiment includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0037] The computer program may be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to accomplish the present invention.

[0038] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0039] The processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0040] The memory may be used to store the computer programs and / or modules, and the processor implements various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory.

[0041] If the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0042] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for intelligent blood sugar monitoring in nephrology, characterized in that: include: Collect the patient's blood sugar data that changes continuously over a period of time; Based on the local change characteristics of the collected blood sugar data, corresponding blood sugar change abnormal factors are obtained; Based on the changing pattern of blood sugar data, the relative deviation of blood sugar data is obtained; based on the obtained abnormal blood sugar change factors and the relative deviation of blood sugar data, the attention of blood sugar data is determined; based on the periodic performance and overall attention of blood sugar data, the final blood sugar level risk score is obtained; Based on the size of the blood sugar level risk score, the blood sugar score threshold is set to assess whether the patient's blood sugar is abnormal; If yes, a warning is given; if no, it means the patient is in good health.

2. The method for intelligent blood sugar monitoring in nephrology according to claim 1, characterized in that: The method of collecting the patient's blood sugar data that changes continuously over a period of time specifically includes: setting a fixed collection frequency for the patient's blood sugar data based on a blood sugar meter; and simultaneously recording the patient's daily meal time and setting the patient's collection cycle.

3. The method for intelligent blood sugar monitoring in nephrology according to claim 2, characterized in that: The method of obtaining the corresponding abnormal blood sugar change factor based on the local change characteristics of the collected blood sugar data is specifically as follows: setting any blood sugar data as reference data, and setting a neighborhood of a fixed size for the reference data, and the abnormal blood sugar change factor of the blood sugar data for: ,in, For reference data, Represents the first individual data; represents the first-order difference of blood glucose data, where ; and are two adjacent blood sugar change values, is a symbolic function; Indicates the degree of blood sugar change within the reference data neighborhood, The larger the value, the more drastic the blood sugar changes around the reference data. Also bigger; Indicates the number of blood glucose data in the neighborhood; Represents the number of pairwise combinations of adjacent blood glucose data in the neighborhood; It indicates the frequency of blood sugar fluctuation in the neighborhood of the reference data. If the directions of two adjacent changes are consistent, 1 if the direction is inconsistent, -1; The smaller the value of, the higher the blood sugar fluctuation frequency in the reference data neighborhood, and the higher the corresponding blood sugar abnormality factor The bigger.

4. The method for intelligent blood sugar monitoring in nephrology according to claim 3, characterized in that: The relative deviation of the blood sugar data is obtained based on the variation rule of the blood sugar data, specifically: ,in, is the mean of all blood sugar data in the sample, is the maximum blood sugar data in the sample, is the minimum blood sugar data in the sample; is the difference between the reference data and the mean, It represents the maximum difference between all the data in the sample and the mean. It is the ratio of the mean deviation of the reference data to the maximum mean deviation. The larger the value is, the greater the relative deviation of the reference data is, and the higher the corresponding attention is.

5. The method for intelligent blood sugar monitoring in nephrology according to claim 4, characterized in that: The determining of the attention level of the blood sugar data is specifically as follows: ,in, is the time point of the reference data, The closest to the reference data Meal time points, Indicates the abnormal blood sugar change factor based on the reference data at meal time. is the abnormal blood sugar change factor of the reference data, The larger the value, the more attention the reference data receives. It represents the time interval between the two meals closest to the reference data. The smaller the interval, the higher the attention.

6. The method for intelligent blood sugar monitoring in nephrology according to claim 5, characterized in that: The periodic performance based on blood sugar data is specifically: ,in, The intensity of the blood glucose curve cycle of the patient; Indicates the number of days from the time of recording. Blood sugar data, The total number of blood sugar data in one day; Indicates the number of the same time point every day in the past u days. individual data; Indicates the attention level of the j-th blood sugar data in the past k-th day; For the past u days Mean blood sugar data at time points, In the past days Mean value of attention to blood glucose data at a time point; Indicates that blood sugar data samples The similarity of data based on attention at a time point, The smaller the value of The smaller the difference in blood sugar data at each time point, the stronger the blood sugar curve cycle performance. The greater the blood sugar level risk score The larger the for The smaller the value, the closer the data attention is to each time point. The closer the blood sugar data at each time point are, the The greater the difference in blood glucose data at each time point, the greater the impact on the intensity of the blood glucose curve cycle performance.

7. The method for intelligent blood sugar monitoring in nephrology according to claim 6, characterized in that: The final blood sugar level risk score is obtained based on the periodic performance and overall attention of the blood sugar data, specifically: ,in, to create a risk score for the final blood sugar level; Indicates the first data, Indicates the total number of data in the sample; is the attention variance of all blood glucose data in the sample; Indicates the overall attention level of all blood sugar data in the sample. The larger the value is, the worse the stability of the blood sugar data in the blood sugar data sample is, the lower the blood sugar regulation speed is, and the corresponding blood sugar level risk score is The bigger.

8. The method for intelligent blood sugar monitoring in nephrology according to claim 7, characterized in that: The blood glucose level risk score is compared with the set blood glucose score threshold, specifically: setting the blood glucose score threshold and ;like , it means that the patient's blood sugar level is normal; , it reminds the patient that the blood sugar condition is poor and needs to be adjusted in time; if , it means that the patient's blood sugar condition is abnormal and needs to be treated by a doctor.

9. An intelligent blood sugar monitoring system for nephrology, characterized in that: include: A collection module, which collects blood sugar data of a patient that changes continuously over a period of time; A first acquisition module, which acquires corresponding blood sugar change abnormality factors based on local change characteristics of the collected blood sugar data; a second acquisition module, which acquires the relative deviation of the blood sugar data based on the variation law of the blood sugar data; a determination module, which determines the attention level of the blood sugar data based on the acquired abnormal blood sugar variation factor and the relative deviation of the blood sugar data; a third acquisition module, wherein the third acquisition module obtains a final blood sugar level risk score based on the periodic performance and overall attention of the blood sugar data; An evaluation module, which evaluates whether the patient's blood sugar is abnormal based on the size of the blood sugar level risk score and the set blood sugar score threshold; If yes, a warning is given; if no, it means the patient is in good health.

Images