Diabetic nephropathy incidence prediction method and system based on regional health data platform

Abstract

The invention relates to the field of medical data analysis, and discloses a diabetic nephropathy onset prediction method and system based on a regional health data platform, and the method comprises the steps: determining a plurality of medical institutions, extracting a plurality of medical evaluation data from a medical database of the medical institutions, carrying out the onset feature correlation of the plurality of medical evaluation data, and carrying out the prediction of the onset features. Obtaining a psychological weight, a life weight and a diet weight, obtaining medical coordinates of a medical institution, receiving a glycopathy prediction instruction, determining a physical examination person to be examined based on the glycopathy prediction instruction, performing oral sugar tolerance evaluation on the physical examination person to be examined, and obtaining a sugar tolerance evaluation value; and performing regional disease prediction on the initial evaluation data and the sugar tolerance evaluation value based on the regional analysis data set to obtain a sugar disease attack index, and generating a disease prediction text of the to-be-tested physical examinee based on the sugar disease attack index to complete diabetic nephropathy attack prediction. According to the invention, the accuracy and the automation degree of predicting the attack risk of diabetes mellitus can be improved.

Description

Technical Field

[0001] The present invention relates to the field of medical data analysis, and in particular, to a method and system for predicting the onset of diabetic nephropathy based on a regional health data platform. Background Art

[0002] Early prediction and intervention of diabetes are key means for preventing its development.

[0003] Currently, the methods for predicting the onset risk of diabetes mainly analyze the collected physical examination data (such as fasting blood glucose, glycated hemoglobin, etc.) through a single medical institution, and then confirm the onset risk of diabetes for the physical examinee.

[0004] Although the existing technology can achieve the prediction of the onset risk of diabetes, it is difficult to comprehensively and accurately evaluate the onset risk of physical examinees relying solely on a single index. In recent years, with the development of medical informatization and the construction of regional health data platforms, it has become feasible to combine medical data from multiple institutions. How to integrate medical data from multiple institutions and comprehensively analyze various indicators of physical examinees from multiple dimensions has become a research hotspot in diabetes prediction. Therefore, there is an urgent need for a method for predicting the onset of diabetes that can utilize regional health data to improve the accuracy and automation of predicting the onset risk of diabetes and provide a reliable basis for the prevention and timely intervention of diabetes. Summary of the Invention

[0005] The present invention provides a method for predicting the onset of diabetic nephropathy based on a regional health data platform, and its main purpose is to improve the accuracy and automation of predicting the onset risk of diabetes.

[0006] To achieve the above object, a method for predicting the onset of diabetic nephropathy based on a regional health data platform provided by the present invention includes:

[0007] Identify multiple medical institutions, where the medical institutions include: medical databases;

[0008] Perform the following operations on each of the multiple medical institutions:

[0009] Extract multiple medical evaluation data from the medical database of the medical institution, where the medical evaluation data includes: degree of diabetes, anxiety evaluation value, cortisol level, average number of steps, daily diet amount, daily diet frequency, average alcohol consumption, and sleep time;

[0010] Perform onset feature association on the multiple medical evaluation data to obtain a psychological weight, a lifestyle weight, and a diet weight, and obtain the medical coordinates of the medical institution;

[0011] Combine the psychological weight, the lifestyle weight, the diet weight, and the medical coordinates to obtain regional analysis data;

[0012] Summarize the regional analysis data to obtain a regional analysis data set;

[0013] Receive a diabetes prediction instruction, confirm the to-be-tested physical examinee based on the diabetes prediction instruction, conduct an oral glucose tolerance assessment on the to-be-tested physical examinee, and obtain a glucose tolerance assessment value;

[0014] Confirm the to-be-tested ID based on the to-be-tested physical examinee, and extract initial evaluation data from the pre-constructed physical examination database based on the to-be-tested ID. Among them, the initial evaluation data includes: current coordinates, number of genetic disease cases, current anxiety value, current cortisol level, current number of steps, current diet amount, current number of diet times, current alcohol consumption, and current sleep time;

[0015] Perform regional disease prediction on the initial evaluation data and the glucose tolerance assessment value based on the regional analysis data set to obtain a diabetes disease index;

[0016] Generate a disease prediction text for the to-be-tested physical examinee based on the diabetes disease index to complete the diabetes nephropathy disease prediction.

[0017] Optionally, the associating the disease characteristics of multiple medical evaluation data to obtain a psychological weight, a life weight, and a diet weight includes:

[0018] Perform the following operations on each of the multiple medical evaluation data:

[0019] Calculate the patient's anxiety level according to the anxiety assessment value and cortisol level in the medical evaluation data;

[0020] Calculate the patient's life health degree according to the average number of steps, average alcohol consumption, and sleep time in the medical evaluation data;

[0021] Calculate the patient's diet normality according to the single-day diet amount and single-day diet times in the medical evaluation data;

[0022] Calculate a diabetes evaluation value based on the diabetes degree. Among them, the diabetes degree includes: no diabetes, pre-diabetes, and diabetes. The calculation formula is as follows:

[0023]

[0024] Among them, ρ DM is the diabetes evaluation value, σ is the diabetes degree, and σ1, σ2, and σ3 respectively refer to no diabetes, pre-diabetes, and diabetes;

[0025] Calculate an anxiety characteristic value according to the patient's anxiety level and the diabetes evaluation value. The calculation formula is as follows:

[0026]

[0027] Among them, δP is the anxiety eigenvalue, P re is the patient's anxiety level;

[0028] Calculate the life eigenvalue based on the patient's life health degree and diabetes evaluation value, and calculate the diet eigenvalue based on the patient's diet normality and diabetes evaluation value;

[0029] Aggregate the anxiety eigenvalue, life eigenvalue, and diet eigenvalue respectively to obtain multiple anxiety eigenvalues, multiple life eigenvalues, and multiple diet eigenvalues;

[0030] Calculate the psychological weight based on multiple anxiety eigenvalues, calculate the life weight based on multiple life eigenvalues, and calculate the diet weight based on multiple diet eigenvalues.

[0031] Optionally, the calculation formula of the patient's anxiety level is as follows:

[0032]

[0033] where CORT x is the cortisol level, CORT0 is the preset reference cortisol level, SAS is the anxiety evaluation value, and e is the natural constant.

[0034] Optionally, the calculation formula of the patient's life health degree is as follows:

[0035]

[0036] where H ea is the patient's life health degree, Step is the average number of steps, Sl x is the sleep time, Sl0 is the preset reference sleep time, C x is the average alcohol consumption, and tanh is the hyperbolic tangent function.

[0037] Optionally, the calculation formula of the patient's diet normality is as follows:

[0038]

[0039] where D ie is the patient's diet normality, D c is the daily diet amount, D0 is the preset diet reference amount, k d is the number of daily meals, and || represents taking the absolute value.

[0040] Optionally, the calculation of the psychological weight based on multiple anxiety eigenvalues includes:

[0041] Calculate the anxiety average value based on multiple anxiety eigenvalues, where the anxiety average value is the average of multiple anxiety eigenvalues;

[0042] Calculate the psychological weight based on multiple anxiety eigenvalues and the average anxiety value. The calculation formula is as follows:

[0043]

[0044] Among them, μ p is the psychological weight, is the average anxiety value, is the i-th anxiety eigenvalue among multiple anxiety eigenvalues, and n is the number of anxiety eigenvalues among multiple anxiety eigenvalues.

[0045] Optionally, performing an oral glucose tolerance assessment on the subject to be examined to obtain a glucose tolerance assessment value, including:

[0046] Obtain the initial blood glucose of the subject to be examined, and based on the pre-constructed glucose solution and the subject to be examined, identify the subject who has taken the glucose;

[0047] Taking the time when the subject who has taken the glucose is identified as the starting point and recording the time in real time to obtain the glucose consumption time;

[0048] When the glucose consumption time reaches the preset first recording time, obtain the first blood glucose of the subject who has taken the glucose;

[0049] When the glucose consumption time reaches the preset second recording time, obtain the second blood glucose of the subject who has taken the glucose;

[0050] Calculate the glucose tolerance assessment value according to the initial blood glucose, the first blood glucose, the second blood glucose, the first recording time and the second recording time. The calculation formula is as follows:

[0051]

[0052] Among them, is the glucose tolerance assessment value, BG0, BG1 and BG2 are the initial blood glucose, the first blood glucose and the second blood glucose respectively, and t1 and t2 are the first recording time and the second recording time respectively.

[0053] Optionally, performing regional disease incidence prediction on the initial assessment data and the glucose tolerance assessment value based on the regional analysis data set to obtain a diabetes incidence index, including:

[0054] Perform the following operations on each regional analysis data in the regional analysis data set:

[0055] Calculate the regional Euclidean distance according to the medical coordinates and the current coordinates in the regional analysis data. The calculation formula is as follows:

[0056]

[0057] Among them, d qy is the regional Euclidean distance, x1 and y1 are the longitude in the medical coordinates and the latitude in the medical coordinates respectively, xd and y d are the longitude in the current coordinates and the latitude in the current coordinates, respectively;

[0058] Summarize the Euclidean distances of the regions to obtain multiple Euclidean distances of the regions;

[0059] Sort the multiple Euclidean distances of the regions in ascending order to obtain a sequence of regional Euclidean distances;

[0060] Identify the first regional distance, the second regional distance, and the third regional distance based on the sequence of regional Euclidean distances. Among them, the first regional distance, the second regional distance, and the third regional distance are the regional Euclidean distances ranked first, second, and third in the sequence of regional Euclidean distances, respectively;

[0061] Take the regional analysis data corresponding to the first regional distance as the first regional data, the regional analysis data corresponding to the second regional distance as the second regional data, and the regional analysis data corresponding to the third regional distance as the third regional data;

[0062] Calculate the total distance value based on the first regional distance, the second regional distance, and the third regional distance. Among them, the total distance value is the sum of the first regional distance, the second regional distance, and the third regional distance;

[0063] Calculate the first regional weight based on the first regional distance and the total distance value. The calculation formula is as follows:

[0064]

[0065] where μ qy1 is the first regional weight, d qy1 and d qyx are the first regional distance and the total distance value, respectively;

[0066] Calculate the second regional weight based on the second regional distance and the total distance value, and calculate the third regional weight based on the third regional distance and the total distance value;

[0067] Calculate the current anxiety level based on the current anxiety value and the current cortisol level in the initial assessment data, calculate the current living degree based on the current number of steps, the current alcohol consumption, and the current sleep time in the initial assessment data, and calculate the current diet degree based on the current diet amount and the current number of diet times in the initial assessment data;

[0068] Calculate the first diabetes incidence index based on the number of genetic disease patients, the glucose tolerance assessment value, the current anxiety level, the current living degree, the current diet degree, the first regional weight, and the first regional data. The calculation formula is as follows:

[0069]

[0070] Among them, θ BG1 is the first diabetes onset index, and μ p1 , μ H1 and μ D1 are respectively the psychological weight, the life weight, and the diet weight in the first area data. P re * , H ea * and D ie * are respectively the current anxiety level, the current life level, and the current diet level. N x is the number of genetic disease patients;

[0071] Based on the number of genetic disease patients, the glucose tolerance assessment value, the current anxiety level, the current life level, the current diet level, the second area weight, and the second area data, calculate the second diabetes onset index. Based on the number of genetic disease patients, the glucose tolerance assessment value, the current anxiety level, the current life level, the current diet level, the third area weight, and the third area data, calculate the third diabetes onset index;

[0072] Calculate the diabetes onset index according to the first diabetes onset index, the second diabetes onset index, and the third diabetes onset index. Among them, the diabetes onset index is the sum of the first diabetes onset index, the second diabetes onset index, and the third diabetes onset index.

[0073] Optionally, generating the onset prediction text for the to-be-tested examinee based on the diabetes onset index includes:

[0074] Compare the diabetes onset index with a preset first onset threshold and compare the diabetes onset index with a preset second onset threshold, where the first onset threshold is less than the second onset threshold;

[0075] If the diabetes onset index is less than or equal to the first onset threshold, send the pre-constructed safe prediction text to the pre-constructed medical diagnosis terminal to obtain the onset prediction text;

[0076] If the diabetes onset index is greater than the first onset threshold and less than or equal to the second onset threshold, send the pre-constructed attention prediction text to the medical diagnosis terminal to obtain the onset prediction text;

[0077] If the diabetes onset index is greater than the second onset threshold, send the pre-constructed dangerous prediction text to the medical diagnosis terminal to obtain the onset prediction text.

[0078] To achieve the above object, the present invention also provides a diabetes nephropathy onset prediction system based on a regional health data platform, including:

[0079] A regional data acquisition module for identifying multiple medical institutions, where the medical institutions include: a medical database, and the following operations are performed on each of the multiple medical institutions: extracting multiple medical evaluation data from the medical database of the medical institution, where the medical evaluation data includes: diabetes degree, anxiety evaluation value, cortisol level, average number of steps, single-day diet amount, single-day diet frequency, average alcohol consumption, and sleep time;

[0080] A medical data association module for associating the morbidity characteristics of multiple medical evaluation data to obtain psychological weight, lifestyle weight, and diet weight, obtaining the medical coordinates of the medical institution, combining the psychological weight, lifestyle weight, diet weight, and medical coordinates to obtain regional analysis data, and summarizing the regional analysis data to obtain a regional analysis data set;

[0081] A test subject evaluation module for receiving a diabetes prediction instruction, identifying a test subject to be examined based on the diabetes prediction instruction, performing an oral glucose tolerance assessment on the test subject to be examined to obtain a glucose tolerance assessment value, identifying a test ID based on the test subject to be examined, and extracting initial evaluation data from a pre-constructed physical examination database based on the test ID, where the initial evaluation data includes: current coordinates, number of genetic disease cases, current anxiety value, current cortisol level, current number of steps, current diet amount, current diet frequency, current alcohol consumption, and current sleep time;

[0082] A diabetes morbidity prediction module for performing regional morbidity prediction on the initial evaluation data and the glucose tolerance assessment value based on the regional analysis data set to obtain a diabetes morbidity index, and generating a morbidity prediction text for the test subject to be examined based on the diabetes morbidity index to complete the diabetes nephropathy morbidity prediction.

[0083] To solve the above problems, the present invention also provides an electronic device, where the electronic device includes:

[0084] A memory storing at least one instruction;

[0085] A processor for executing the instructions stored in the memory to implement the above-mentioned diabetes nephropathy morbidity prediction method based on a regional health data platform.

[0086] To solve the above problems, the present invention also provides a computer-readable storage medium, where at least one instruction is stored in the computer-readable storage medium, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned diabetes nephropathy morbidity prediction method based on a regional health data platform.

[0087] To solve the problems described in the background art, the present invention identifies a plurality of medical institutions. Among them, the medical institutions include: a medical database. The following operations are performed on each of the plurality of medical institutions: Extract a plurality of medical evaluation data from the medical database of the medical institution. Among them, the medical evaluation data includes: diabetes degree, anxiety evaluation value, cortisol level, average number of steps, single-day diet amount, single-day diet frequency, average alcohol consumption, and sleep time. It can be seen that the embodiments of the present invention provide a data basis for subsequent morbidity feature association and regional morbidity prediction by identifying a plurality of medical institutions associated with the regional health data platform and extracting a plurality of medical evaluation data from them. Furthermore, morbidity feature association is performed on the plurality of medical evaluation data to obtain a psychological weight, a lifestyle weight, and a diet weight, obtain the medical coordinates of the medical institution, combine the psychological weight, the lifestyle weight, the diet weight, and the medical coordinates to obtain regional analysis data, and summarize the regional analysis data to obtain a regional analysis data set. It can be seen that the embodiments of the present invention calculate the psychological weight, the lifestyle weight, and the diet weight by performing morbidity feature association on the plurality of medical evaluation data, quantify the correlation between the patient's anxiety level, the patient's lifestyle health level, and the diet normality and the diabetes morbidity risk, and facilitate subsequent regional morbidity prediction of the to-be-tested examinee according to the psychological weight, the lifestyle weight, and the diet weight, thereby improving the accuracy of predicting diabetes morbidity. Receive a diabetes prediction instruction, identify the to-be-tested examinee based on the diabetes prediction instruction, perform an oral glucose tolerance assessment on the to-be-tested examinee to obtain a glucose tolerance assessment value, identify the to-be-tested ID based on the to-be-tested examinee, and extract initial evaluation data from the pre-constructed physical examination database based on the to-be-tested ID. Among them, the initial evaluation data includes: current coordinates, genetic morbidity number, current anxiety value, current cortisol level, current number of steps, current diet amount, current diet frequency, current alcohol consumption, and current sleep time. It can be seen that the embodiments of the present invention improve the automation of predicting diabetes morbidity risk by receiving a diabetes prediction instruction, automatically testing the to-be-tested examinee, and automatically retrieving the initial evaluation data related to the to-be-tested examinee. Perform regional morbidity prediction on the initial evaluation data and the glucose tolerance assessment value based on the regional analysis data set to obtain a diabetes morbidity index. It can be seen that the embodiments of the present invention comprehensively evaluate the initial evaluation data and the glucose tolerance assessment value by combining the data of different regions in the regional analysis data set, accurately calculate the diabetes morbidity index of the to-be-tested examinee, quantify the diabetes morbidity risk of the to-be-tested examinee, and improve the accuracy of predicting diabetes morbidity risk. Generate a morbidity prediction text for the to-be-tested examinee based on the diabetes morbidity index to complete the diabetes nephropathy morbidity prediction. It can be seen that the embodiments of the present invention automatically generate a morbidity prediction text for the to-be-tested examinee at the medical diagnosis end based on the diabetes morbidity index, so that the patient or examinee can timely understand their own conditions and adjust their living habits or provide a reference for the doctor's further diagnosis or intervention, and improve the automation of predicting diabetes morbidity risk.Therefore, the present invention can improve the accuracy and automation of predicting the risk of diabetes onset. Description of the Drawings

[0088] Figure 1 It is a schematic flowchart of a method for predicting the onset of diabetic nephropathy based on a regional health data platform provided by an embodiment of the present invention;

[0089] Figure 2 It is a functional module diagram of a system for predicting the onset of diabetic nephropathy based on a regional health data platform provided by an embodiment of the present invention;

[0090] Figure 3 It is a schematic structural diagram of an electronic device for implementing the method for predicting the onset of diabetic nephropathy based on the regional health data platform provided by an embodiment of the present invention.

[0091] Description of the Reference Numerals:

[0092] 1. Electronic device; 10. Processor; 11. Memory; 12. Bus.

[0093] The realization, functional characteristics and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. Detailed Embodiments

[0094] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0095] An embodiment of the present application provides a method for predicting the onset of diabetic nephropathy based on a regional health data platform. The execution subject of the method for predicting the onset of diabetic nephropathy based on the regional health data platform includes, but is not limited to, at least one of electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for predicting the onset of diabetic nephropathy based on the regional health data platform can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to: a single server, a server cluster, a cloud server, or a cloud server cluster, etc.

[0096] Refer to Figure 1 As shown, it is a schematic flowchart of a method for predicting the onset of diabetic nephropathy based on a regional health data platform provided by an embodiment of the present invention. In this embodiment, the method for predicting the onset of diabetic nephropathy based on the regional health data platform includes:

[0097] S1. Identify a plurality of medical institutions, where the medical institutions include: medical databases.

[0098] In the embodiments of the present invention, the regional health data platform is a comprehensive information system for integrating and managing various medical data from multiple medical institutions to achieve cross-institutional and cross-regional medical data sharing and application.

[0099] It should be explained that a medical institution refers to a professional institution legally established to engage in medical and health services such as disease diagnosis, treatment, nursing, prevention, health care or rehabilitation, for example: hospitals, clinics, physical examination centers and rehabilitation centers. The identification of multiple medical institutions means: identifying all medical institutions currently managed by the regional health data platform to obtain multiple medical institutions.

[0100] It should be understood that a medical database refers to a database used by a medical institution to store medical assessment data. And in the embodiments of the present invention, the medical databases of multiple medical institutions have all achieved interconnection and interoperability with the regional health data platform, and data can be transmitted in real time or at regular intervals between multiple medical databases and the regional health data platform to provide support for subsequent analysis of medical assessment data. For the specific application of medical assessment data, please refer to the subsequent embodiments.

[0101] S2. Perform the following operations on each of the multiple medical institutions: Extract multiple medical assessment data from the medical database of the medical institution, where the medical assessment data includes: diabetes degree, anxiety assessment value, cortisol level, average number of steps, single-day diet amount, single-day diet times, average alcohol consumption and sleep time.

[0102] In the embodiments of the present invention, the medical assessment data refers to data stored in the medical database and related to the health status of patients or examinees, and the medical assessment data includes: diabetes degree, anxiety assessment value, cortisol level, average number of steps, single-day diet amount, single-day diet times, average alcohol consumption and sleep time. The diabetes degree is used to reflect the current diabetes status of patients or examinees. The diabetes degree includes: no diabetes, pre-diabetes and having diabetes. No diabetes means that the patient or examinee does not have diabetes. Pre-diabetes means that the patient or examinee is in the pre-diabetes stage. Having diabetes means that the patient or examinee has diabetes, and the diabetes degree is pre-diagnosed and confirmed by a doctor in a medical institution.

[0103] For example, Xiao Zhang is a diabetic patient, that is, Xiao Zhang's diabetes level is diabetes. When he went to a hospital for a follow-up visit, he first filled out a health assessment questionnaire, where the content of the health assessment questionnaire included: the average number of steps walked per day, the average total weight of food consumed per day, the average number of meals per day, the average daily alcohol consumption and the average daily sleep time, where the average number of steps walked per day is the average number of steps, the average total weight of food consumed per day is the daily diet, the average number of meals per day is the daily diet, the average daily alcohol consumption is the average alcohol consumption, and the average daily sleep time is the sleep time. After that, Xiao Zhang filled out an anxiety self-report questionnaire. The score of the anxiety self-rating scale is the anxiety assessment value, and the score of the anxiety self-rating scale is calculated by the doctor according to the established scoring criteria of the anxiety self-rating scale. Then the medical staff took blood from Xiao Zhang and tested Xiao Zhang's blood to obtain the concentration of cortisol in Xiao Zhang's serum, where the concentration of cortisol in serum is the cortisol level. Finally, the hospital staff entered the above indicators (degree of diabetes, anxiety assessment value, cortisol level, average number of steps, daily food intake, number of daily meals, average alcohol intake and sleep time) into the medical database of the medical institution, forming a complete set of medical assessment data corresponding to the patient. It should be noted that the scoring method of the anxiety self-rating scale is an existing mature technology and will not be repeated here.

[0104] S3. Correlate the disease characteristics of multiple medical evaluation data to obtain psychological weights, life weights and dietary weights, and obtain the medical coordinates of medical institutions.

[0105] It should be explained that medical coordinates refer to the longitude and latitude of the location of a medical institution in the real world. For example, the medical institution is Shanghai First People's Hospital. Since the longitude of the location of Shanghai First People's Hospital is 121.49592 and the latitude is 31.25908, the medical coordinates of the medical institution are (121.49592, 31.25908). Optionally, the medical coordinates of the medical institution are queried through the pick-up coordinate system of Baidu Maps.

[0106] Specifically, the plurality of medical evaluation data are associated with disease characteristics to obtain psychological weights, life weights and dietary weights, including:

[0107] The following operations are performed on each of the multiple medical evaluation data:

[0108] Calculate the patient's anxiety level based on the anxiety assessment value and cortisol level in the medical assessment data;

[0109] Calculate the patient's life health based on the average number of steps, average alcohol consumption and sleep time in the medical evaluation data;

[0110] Calculate the patient's diet normality based on the daily diet volume and daily diet frequency in the medical evaluation data;

[0111] Calculate the diabetes evaluation value based on the degree of diabetes. Among them, the degree of diabetes includes: no diabetes, pre-diabetes, and diabetes. The calculation formula is as follows:

[0112]

[0113] Among them, ρ DM is the diabetes evaluation value, σ is the degree of diabetes, and σ1, σ2, and σ3 respectively refer to no diabetes, pre-diabetes, and diabetes;

[0114] Calculate the anxiety characteristic value based on the patient's anxiety level and the diabetes evaluation value. The calculation formula is as follows:

[0115]

[0116] Among them, δ P is the anxiety characteristic value, and P re is the patient's anxiety level;

[0117] Calculate the life characteristic value based on the patient's life health level and the diabetes evaluation value, and calculate the diet characteristic value based on the patient's diet normality and the diabetes evaluation value;

[0118] Summarize the anxiety characteristic value, life characteristic value, and diet characteristic value respectively to obtain multiple anxiety characteristic values, multiple life characteristic values, and multiple diet characteristic values;

[0119] Calculate the psychological weight based on multiple anxiety characteristic values, calculate the life weight based on multiple life characteristic values, and calculate the diet weight based on multiple diet characteristic values.

[0120] It should be understood that the cortisol level generally rises under the anxious and tense emotions of an individual. Therefore, the patient's anxiety level is a value used to quantify the anxiety level and psychological stress level of a patient or a physical examinee in daily life. The greater the patient's anxiety level, the more anxious the patient or physical examinee is in daily life and the greater the psychological stress. The patient's life health level reflects the health level of the patient's or physical examinee's lifestyle. The greater the patient's life health level, the healthier the patient's or physical examinee's lifestyle. The diet normality reflects the health level of the patient's or physical examinee's eating habits. The greater the diet normality, the healthier the patient's or physical examinee's eating habits. The anxiety characteristic value refers to the ratio of the patient's anxiety level to the diabetes evaluation value, which is used for subsequent calculation of the psychological weight. That is, the smaller the difference between multiple anxiety characteristic values, the greater the psychological weight, indicating a higher correlation between the patient's anxiety level and the degree of diabetes.

[0121] It is understandable that the method for calculating the life characteristic value based on the patient's life health degree and diabetes evaluation value and the method for calculating the diet characteristic value based on the patient's diet normality and diabetes evaluation value are the same as the method for calculating the anxiety characteristic value according to the patient's anxiety degree and diabetes evaluation value, which will not be elaborated here. The method for calculating the life weight based on multiple life characteristic values and the method for calculating the diet weight based on multiple diet characteristic values are the same as the method for calculating the psychological weight according to multiple anxiety characteristic values, which will not be elaborated here.

[0122] It should be understood that the induction of diabetes may be related to various factors. For example, bad living habits (overeating, staying up late, lack of exercise, excessive drinking, etc.) and individual psychological factors (long-term anxiety, tension and other mental states) may all induce diabetes. Therefore, in the embodiments of the present invention, by calculating the psychological weight, life weight and diet weight, the correlation between the patient's anxiety degree, the patient's life health degree and diet normality and the degree of diabetes is quantified, which is convenient for subsequent regional disease prediction of the to-be-tested physical examinee according to the psychological weight, life weight and diet weight, so as to improve the accuracy of predicting the onset of diabetes.

[0123] Specifically, the calculation formula of the patient's anxiety degree is as follows:

[0124]

[0125] Among them, CORT x is the cortisol level, CORT0 is the preset reference cortisol level, SAS is the anxiety evaluation value, and e is the natural constant.

[0126] Optionally, the average value of the cortisol levels of multiple physical examinees without diabetes is used as the reference cortisol level. For example, the reference cortisol level is 10 micrograms per 100 milliliters.

[0127] Specifically, the calculation formula of the patient's life health degree is as follows:

[0128]

[0129] Among them, H ea is the patient's life health degree, Step is the average number of steps, Sl x is the sleep time, Sl0 is the preset reference sleep time, C x is the average alcohol consumption, and tanh is the hyperbolic tangent function.

[0130] Optionally, the reference sleep time is 7.5 hours.

[0131] Specifically, the calculation formula of the patient's diet normality is as follows:

[0132]

[0133] Among them, D ie is the normal degree of the patient's diet, D c is the daily diet amount, D0 is the preset diet reference amount, k d is the number of daily meals, and || represents taking the absolute value.

[0134] Optionally, the average value of the daily diet amounts of multiple non-diabetic examinees is used as the diet reference amount. For example, the diet reference amount is 1 kg.

[0135] Specifically, calculating the psychological weight according to multiple anxiety eigenvalues includes:

[0136] Calculating the average anxiety value based on multiple anxiety eigenvalues, where the average anxiety value is the average of multiple anxiety eigenvalues;

[0137] Calculating the psychological weight based on multiple anxiety eigenvalues and the average anxiety value, and the calculation formula is as follows:

[0138]

[0139] Among them, μ p is the psychological weight, is the average anxiety value, is the i-th anxiety eigenvalue among multiple anxiety eigenvalues, and n is the number of anxiety eigenvalues among multiple anxiety eigenvalues.

[0140] S4. Combine the psychological weight, the life weight, the diet weight, and the medical coordinates to obtain regional analysis data, and summarize the regional analysis data to obtain a regional analysis data set.

[0141] Exemplarily, the psychological weight is 3.2, the life weight is 6.9, the diet weight is 2.1, and the medical coordinates are (121.49592, 31.25908), then the regional analysis data is: {3.2, 6.9, 2.1, (121.49592, 31.25908)}.

[0142] S5. Receive a diabetes prediction instruction, confirm the examinee to be tested based on the diabetes prediction instruction, and conduct an oral glucose tolerance assessment on the examinee to be tested to obtain a glucose tolerance assessment value.

[0143] It should be noted that the diabetes prediction instruction is initiated by the staff of a medical institution when predicting the diabetes onset risk of a subject to be tested. A subject to be tested is an individual in a fasting state who needs to have their diabetes onset risk predicted. The fasting state means that the individual has fasted for 8 - 12 hours. Exemplarily, Xiao Wang wants to predict his own diabetes onset risk. So one day, he comes to a physical examination center in a fasting state. At this time, Xiao Wang is a subject to be tested. Then the staff of this physical examination center initiates a diabetes prediction instruction for Xiao Wang, and subsequently conducts a physical examination on Xiao Wang and combines the regional analysis data set in the regional health data platform to predict Xiao Wang's diabetes onset risk. Moreover, this diabetes prediction instruction contains the name of the subject to be tested who needs to have their diabetes onset risk predicted. Therefore, the corresponding subject to be tested can be identified based on the diabetes prediction instruction.

[0144] Specifically, the oral glucose tolerance assessment of the subject to be tested to obtain a glucose tolerance assessment value includes:

[0145] Obtain the initial blood glucose of the subject to be tested, and based on the pre - constructed glucose solution and the subject to be tested, identify the glucose - taking subject;

[0146] Taking the time when the glucose - taking subject is identified as the starting point and recording the time in real - time to obtain the glucose consumption time;

[0147] When the glucose consumption time reaches the preset first recording time, obtain the first blood glucose of the glucose - taking subject;

[0148] When the glucose consumption time reaches the preset second recording time, obtain the second blood glucose of the glucose - taking subject;

[0149] Calculate the glucose tolerance assessment value according to the initial blood glucose, the first blood glucose, the second blood glucose, the first recording time, and the second recording time. The calculation formula is as follows:

[0150]

[0151] Wherein, is the glucose tolerance assessment value, BG0, BG1, and BG2 are the initial blood glucose, the first blood glucose, and the second blood glucose respectively, and t1 and t2 are the first recording time and the second recording time respectively.

[0152] It should be explained that the initial blood glucose refers to the blood glucose concentration in the blood of the examinee to be tested. The glucose solution refers to a solution containing a certain concentration of glucose. The sugar-consuming examinee identified based on the pre-constructed glucose solution and the examinee to be tested means that when it is confirmed that the examinee to be tested has taken a preset test volume of the glucose solution, the examinee to be tested at this time is the sugar-consuming examinee. The test volume is manually set by a doctor in a medical institution. Optionally, the test volume is 200 ml. The first blood glucose refers to the blood glucose concentration in the blood of the sugar-consuming examinee when the sugar-consuming time reaches the first recording time. The second blood glucose refers to the blood glucose concentration in the blood of the sugar-consuming examinee when the sugar-consuming time reaches the second recording time.

[0153] Exemplarily, if the time when the sugar-consuming examinee is identified is 10:00, then starting from 10:00 and recording the time in real time, when it is 10:01, the sugar-consuming time is 1 minute, and when it is 10:06, the sugar-consuming time is 6 minutes.

[0154] It should be explained that both the first recording time and the second recording time are manually set by a doctor in a medical institution. Preferably, the first recording time is half an hour and the second recording time is 1 hour.

[0155] It should be understood that the glucose tolerance assessment value reflects the glucose metabolism ability of the examinee to be tested. The larger the glucose tolerance assessment value, the worse the glucose metabolism ability of the examinee to be tested.

[0156] S6. Based on the examinee to be tested, confirm the ID to be tested, and extract the initial assessment data from the pre-constructed physical examination database based on the ID to be tested. The initial assessment data includes: current coordinates, number of genetic disease patients, current anxiety value, current cortisol level, current number of steps, current diet amount, current number of meals, current alcohol consumption, and current sleep time.

[0157] In the embodiment of the present invention, when the staff of a medical institution predicts the diabetes onset risk of an examinee to be tested, a number will be generated for the examinee to be tested in the physical examination database to identify the examinee to be tested. The number is the ID to be tested, and the IDs to be tested of different examinees to be tested are all different. Each ID to be tested corresponds to one examinee to be tested.

[0158] It should be explained that the physical examination database is a database used to store initial assessment data. The initial assessment data includes: current coordinates, number of genetic disease patients, current anxiety value, current cortisol level, current number of steps, current diet volume, current number of diet times, current alcohol consumption, and current sleep time. The current coordinates refer to the longitude and latitude of the location of the medical institution where the physical examination subject to be tested is located in the real world. The number of genetic disease patients refers to the number of people with diabetes among the direct blood relatives of the physical examination subject to be tested. The current anxiety value, current cortisol level, current number of steps, current diet volume, current number of diet times, current alcohol consumption, and current sleep time respectively refer to the anxiety assessment value of the physical examination subject to be tested, the cortisol level of the physical examination subject to be tested, the average number of steps of the physical examination subject to be tested, the single-day diet volume of the physical examination subject to be tested, the single-day number of diet times of the physical examination subject to be tested, the average alcohol consumption of the physical examination subject to be tested, and the sleep time of the physical examination subject to be tested. The number of genetic disease patients, current number of steps, current diet volume, current number of diet times, current alcohol consumption, and current sleep time are all obtained by the physical examination subject to be tested filling out a questionnaire by themselves. The current anxiety value and current cortisol level are respectively obtained by the medical institution corresponding to the physical examination subject to be tested conducting a self-assessment scale test and blood test on the physical examination subject to be tested. The current coordinates are obtained by positioning the medical institution corresponding to the physical examination subject to be tested through GPS. After obtaining the above current coordinates, number of genetic disease patients, current anxiety value, current cortisol level, current number of steps, current diet volume, current number of diet times, current alcohol consumption, and current sleep time, they are integrated into initial assessment data and stored in the physical examination database. And since one initial assessment data corresponds to one physical examination subject to be tested, the corresponding initial assessment data can be extracted from the pre-constructed physical examination database based on the ID to be tested.

[0159] S7. Perform regional disease incidence prediction on the initial assessment data and glucose tolerance assessment value based on the regional analysis dataset to obtain a diabetes incidence index.

[0160] Specifically, the performing regional disease incidence prediction on the initial assessment data and glucose tolerance assessment value based on the regional analysis dataset to obtain a diabetes incidence index includes:

[0161] Perform the following operations on each regional analysis data in the regional analysis dataset:

[0162] Calculate the regional Euclidean distance according to the medical coordinates and current coordinates in the regional analysis data. The calculation formula is as follows:

[0163]

[0164] where, d qy is the regional Euclidean distance, x1 and y1 are respectively the longitude in the medical coordinates and the latitude in the medical coordinates, x d and y d are respectively the longitude in the current coordinates and the latitude in the current coordinates;

[0165] Aggregate the Euclidean distances of the regions to obtain multiple regional Euclidean distances;

[0166] Sort the multiple regional Euclidean distances in ascending order to obtain a regional Euclidean distance sequence;

[0167] Based on the regional Euclidean distance sequence, confirm the first regional distance, the second regional distance, and the third regional distance. Among them, the first regional distance, the second regional distance, and the third regional distance are the regional Euclidean distances ranked first, second, and third in the regional Euclidean distance sequence respectively;

[0168] Take the regional analysis data corresponding to the first regional distance as the first regional data, the regional analysis data corresponding to the second regional distance as the second regional data, and the regional analysis data corresponding to the third regional distance as the third regional data;

[0169] Calculate the total distance value according to the first regional distance, the second regional distance, and the third regional distance. Among them, the total distance value is the sum of the first regional distance, the second regional distance, and the third regional distance;

[0170] Calculate the first regional weight according to the first regional distance and the total distance value. The calculation formula is as follows:

[0171]

[0172] Among them, μ qy1 is the first regional weight, d qy1 and d qyx are the first regional distance and the total distance value respectively;

[0173] Calculate the second regional weight based on the second regional distance and the total distance value, and calculate the third regional weight based on the third regional distance and the total distance value;

[0174] Calculate the current anxiety level based on the current anxiety value and the current cortisol level in the initial assessment data, calculate the current living degree based on the current number of steps, the current alcohol consumption, and the current sleep time in the initial assessment data, and calculate the current diet degree based on the current diet amount and the current number of diet times in the initial assessment data;

[0175] Calculate the first diabetes incidence index according to the number of genetic disease patients, the glucose tolerance assessment value, the current anxiety level, the current living degree, the current diet degree, the first regional weight, and the first regional data. The calculation formula is as follows:

[0176]

[0177] Among them, θ BG1 is the first diabetes incidence index, μp1 , μ H1 and μ D1 are respectively the psychological weight, the life weight, and the diet weight in the first region data. P re * , H ea * and D ie * are respectively the current anxiety level, the current life level, and the current diet level. N x is the number of genetic disease patients.

[0178] Calculate the second diabetes incidence index based on the number of genetic disease patients, the glucose tolerance assessment value, the current anxiety level, the current life level, the current diet level, the second region weight, and the second region data, and calculate the third diabetes incidence index based on the number of genetic disease patients, the glucose tolerance assessment value, the current anxiety level, the current life level, the current diet level, the third region weight, and the third region data;

[0179] Calculate the diabetes incidence index according to the first diabetes incidence index, the second diabetes incidence index, and the third diabetes incidence index. Among them, the diabetes incidence index is the sum of the first diabetes incidence index, the second diabetes incidence index, and the third diabetes incidence index.

[0180] It should be explained that the regional Euclidean distance reflects the distance between the medical institution corresponding to the regional analysis data and the medical institution corresponding to the to-be-tested physical examinee in the real world. The greater the regional Euclidean distance, the farther the distance between the medical institution corresponding to the regional analysis data and the medical institution corresponding to the to-be-tested physical examinee in the real world.

[0181] It can be understood that there are significant differences in eating habits and living habits among people in different regions. For example: people in some regions may be more adapted to heavy-taste foods. Therefore, the glucose metabolism ability of people in this region will be slightly stronger, and thus the glucose tolerance assessment values of people in this region will generally be lower. At the same time, due to different living rhythms in different regions, the degree of physical fatigue is also different. Therefore, there may also be differences in sleep time. Therefore, when predicting the incidence of diabetes in individuals in different regions, it is necessary to consider the influence brought by regional differences. Therefore, in the embodiments of the present invention, by selecting the first, second, and third distances in the regional Euclidean distance sequence, the regional data corresponding to the three medical institutions closest to the location of the to-be-tested physical examinee are used to predict the incidence of diabetes in the to-be-tested physical examinee, thereby improving the accuracy of diabetes incidence prediction. Furthermore, by calculating the first region weight, the second region weight, and the third region weight, the weight of the regional data corresponding to the medical institution closer to the region where the to-be-tested physical examinee is located is made larger, so that the subsequent calculated diabetes incidence index can better reflect the true situation of the to-be-tested physical examinee.

[0182] It should be understood that the method for calculating the current anxiety level based on the current anxiety value and current cortisol level in the initial assessment data is the same as the method for calculating the patient's anxiety level based on the anxiety assessment value and cortisol level in the medical assessment data. The method for calculating the current living degree based on the current number of steps, current alcohol consumption, and current sleep duration in the initial assessment data is the same as the method for calculating the patient's living health degree based on the average number of steps, average alcohol consumption, and sleep duration in the medical assessment data. The method for calculating the current diet degree based on the current diet amount and current diet frequency in the initial assessment data is the same as the method for calculating the patient's normal diet degree based on the single-day diet amount and single-day diet frequency in the medical assessment data, which will not be elaborated here.

[0183] It can be understood that the first diabetes incidence index refers to the probability that the to-be-tested physical examinee has diabetes when only considering the data in the first region. The larger the first diabetes incidence index, the greater the probability that the to-be-tested physical examinee has diabetes.

[0184] It should be understood that the method for calculating the weight of the second region based on the distance of the second region and the total distance value and the method for calculating the weight of the third region based on the distance of the third region and the total distance value are both the same as the method for calculating the weight of the first region based on the distance of the first region and the total distance value, which will not be elaborated here. The diabetes incidence index reflects the probability that the to-be-tested physical examinee has diabetes. The larger the diabetes incidence index, the greater the probability that the to-be-tested physical examinee has diabetes.

[0185] S8. Generate a disease prediction text for the to-be-tested physical examinee based on the diabetes incidence index to complete the diabetes nephropathy disease prediction.

[0186] Specifically, generating a disease prediction text for the to-be-tested physical examinee based on the diabetes incidence index includes:

[0187] Compare the diabetes incidence index with a preset first incidence threshold and compare the diabetes incidence index with a preset second incidence threshold;

[0188] If the diabetes incidence index is less than or equal to the first incidence threshold, send the pre-constructed safe prediction text to the pre-constructed medical diagnosis terminal to obtain the disease prediction text;

[0189] If the diabetes incidence index is greater than the first incidence threshold and less than or equal to the second incidence threshold, send the pre-constructed attention prediction text to the medical diagnosis terminal to obtain the disease prediction text;

[0190] If the diabetes incidence index is greater than the second incidence threshold, send the pre-constructed dangerous prediction text to the medical diagnosis terminal to obtain the disease prediction text.

[0191] It should be explained that both the first onset threshold and the second onset threshold are values artificially set by doctors in medical institutions based on historical data, and the first onset threshold is less than the second onset threshold. Optionally, the average value of the diabetes onset indices of multiple test subjects measured historically is used as the first onset threshold, and the average value of the diabetes onset indices of multiple patients in the pre-diabetes stage is used as the second onset threshold. The onset prediction text refers to the safety prediction text, attention prediction text, or danger prediction text sent to the medical diagnosis terminal.

[0192] It can be understood that the medical diagnosis terminal is a device with information receiving and presenting functions, such as a computer, a tablet, or a mobile phone. It is used to receive the safety prediction text, attention prediction text, or danger prediction text and present it to doctors, patients, or test subjects. The safety prediction text, attention prediction text, and danger prediction text are three different pre-set text contents. For example, the safety prediction text is: "The test subject has no risk of diabetes onset. Please continue to maintain good living habits." The attention prediction text is: "The test subject has a low risk of diabetes onset. It is recommended to appropriately adjust living habits and maintain a healthy state." The danger prediction text is: "The test subject has a great risk of diabetes onset. It is recommended to immediately adjust living habits and contact a doctor in time for further diagnosis." When the medical diagnosis terminal receives the safety prediction text, attention prediction text, or danger prediction text, the text content will be presented on the screen of the medical diagnosis terminal, so that patients or test subjects can timely understand their own conditions and adjust their living habits or provide reference for doctors' further diagnosis or intervention.

[0193] Exemplarily, if the first onset threshold is 30 and the second onset threshold is 50, and Xiao Wang is a test subject. After he fills out the questionnaire and completes the physical examination in the physical examination center, if his diabetes onset index is measured to be 40, the attention prediction text will be sent to the self-service inquiry machine corresponding to Xiao Wang in the physical examination center, and the self-service inquiry machine will present the content of the attention prediction text on the screen to remind Xiao Wang to adjust his living habits in time.

[0194] To solve the problems described in the background art, the present invention identifies multiple medical institutions. Among them, the medical institutions include: a medical database. The following operations are performed on each of the multiple medical institutions: Extract multiple medical evaluation data from the medical database of the medical institution. Among them, the medical evaluation data includes: diabetes degree, anxiety evaluation value, cortisol level, average number of steps, single-day diet amount, single-day diet times, average alcohol consumption, and sleep time. It can be seen that in the embodiment of the present invention, by identifying multiple medical institutions associated with the regional health data platform and extracting multiple medical evaluation data from them, a data basis is provided for subsequent incidence feature association and regional incidence prediction. Furthermore, incidence feature association is performed on the multiple medical evaluation data to obtain psychological weight, lifestyle weight, and diet weight, obtain the medical coordinates of the medical institution, combine the psychological weight, lifestyle weight, diet weight, and medical coordinates to obtain regional analysis data, and summarize the regional analysis data to obtain a regional analysis data set. It can be seen that in the embodiment of the present invention, by performing incidence feature association on multiple medical evaluation data, the psychological weight, lifestyle weight, and diet weight are calculated, quantifying the correlation between the patient's anxiety level, the patient's lifestyle health level, and the normalcy of diet and the risk of diabetes onset, facilitating subsequent regional incidence prediction of the to-be-tested examinee based on the psychological weight, lifestyle weight, and diet weight, thereby improving the accuracy of predicting diabetes onset. Receive a diabetes prediction instruction, identify the to-be-tested examinee based on the diabetes prediction instruction, perform an oral glucose tolerance assessment on the to-be-tested examinee to obtain a glucose tolerance assessment value, confirm the to-be-tested ID based on the to-be-tested examinee, and extract initial evaluation data from the pre-constructed physical examination database based on the to-be-tested ID. Among them, the initial evaluation data includes: current coordinates, number of genetically diseased people, current anxiety value, current cortisol level, current number of steps, current diet amount, current diet times, current alcohol consumption, and current sleep time. It can be seen that in the embodiment of the present invention, by receiving a diabetes prediction instruction, the to-be-tested examinee is automatically tested and the initial evaluation data related to the to-be-tested examinee is automatically retrieved, improving the automation degree of predicting the risk of diabetes onset. Perform regional incidence prediction on the initial evaluation data and the glucose tolerance assessment value based on the regional analysis data set to obtain a diabetes incidence index. It can be seen that in the embodiment of the present invention, by comprehensively evaluating the initial evaluation data and the glucose tolerance assessment value by combining data from different regions in the regional analysis data set, the diabetes incidence index of the to-be-tested examinee is accurately calculated, quantifying the diabetes onset risk of the to-be-tested examinee and improving the accuracy of predicting the risk of diabetes onset. Generate an incidence prediction text for the to-be-tested examinee based on the diabetes incidence index to complete the prediction of diabetes nephropathy onset. It can be seen that in the embodiment of the present invention, by automatically generating an incidence prediction text for the to-be-tested examinee at the medical diagnosis end based on the diabetes incidence index, the patient or examinee can timely understand their own condition and adjust their lifestyle or provide a reference for the doctor's further diagnosis or intervention, improving the automation degree of predicting the risk of diabetes onset.Therefore, the present invention can improve the accuracy and automation of predicting the risk of diabetes onset.

[0195] As Figure 2 shown, it is a functional module diagram of a diabetic nephropathy onset prediction system based on a regional health data platform provided by an embodiment of the present invention.

[0196] The diabetic nephropathy onset prediction system 100 based on the regional health data platform of the present invention can be installed in the electronic device 1. According to the functions achieved, the diabetic nephropathy onset prediction system 100 based on the regional health data platform can include a regional data acquisition module 101, a medical data association module 102, a to-be-tested individual evaluation module 103, and a diabetes onset prediction module 104. The modules of the present invention can also be referred to as units, which refer to a series of computer program segments that can be executed by the processor of the electronic device and can complete fixed functions, and are stored in the memory of the electronic device.

[0197] The regional data acquisition module 101 is used to identify multiple medical institutions. Among them, the medical institutions include: medical databases, and the following operations are performed on each of the multiple medical institutions: extract multiple medical evaluation data from the medical databases of the medical institutions, where the medical evaluation data includes: diabetes degree, anxiety evaluation value, cortisol level, average number of steps, single-day diet amount, single-day diet times, average alcohol consumption, and sleep time;

[0198] The medical data association module 102 is used to perform onset feature association on multiple medical evaluation data to obtain psychological weight, lifestyle weight, and diet weight, obtain the medical coordinates of the medical institutions, combine the psychological weight, lifestyle weight, diet weight, and medical coordinates to obtain regional analysis data, and summarize the regional analysis data to obtain a regional analysis data set;

[0199] The to-be-tested individual evaluation module 103 is used to receive a diabetes prediction instruction, identify a to-be-tested physical examinee based on the diabetes prediction instruction, perform an oral glucose tolerance assessment on the to-be-tested physical examinee to obtain a glucose tolerance assessment value, identify a to-be-tested ID based on the to-be-tested physical examinee, and extract initial evaluation data from a pre-constructed physical examination database based on the to-be-tested ID, where the initial evaluation data includes: current coordinates, number of genetic onset cases, current anxiety value, current cortisol level, current number of steps, current diet amount, current diet times, current alcohol consumption, and current sleep time;

[0200] The diabetes onset prediction module 104 is used to perform regional onset prediction on the initial evaluation data and the glucose tolerance assessment value based on the regional analysis data set to obtain a diabetes onset index, and generate an onset prediction text for the to-be-tested physical examinee based on the diabetes onset index to complete the prediction of diabetic nephropathy onset.

[0201] Specifically, when the modules in the diabetes nephropathy onset prediction system 100 based on the regional health data platform in the embodiments of the present invention are used, they adopt the same technical means as those in the above-mentioned Figure 1 diabetes nephropathy onset prediction method based on the regional health data platform, and can produce the same technical effects, which will not be elaborated here.

[0202] As Figure 3 shown, it is a schematic structural diagram of an electronic device 1 for implementing the diabetes nephropathy onset prediction method based on the regional health data platform provided by an embodiment of the present invention.

[0203] The electronic device 1 may include a processor 10, a memory 11, and a bus 12, and may further include a computer program stored in the memory 11 and executable on the processor 10, such as a diabetes nephropathy onset prediction method program based on the regional health data platform.

[0204] Among them, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as the mobile hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the electronic device 1. Further, the memory 11 also includes the internal storage unit of the electronic device 1 and the external storage device. The memory 11 can not only be used to store application software installed on the electronic device 1 and various types of data, such as the code of the diabetes nephropathy onset prediction method program based on the regional health data platform, but also be used to temporarily store data that has been output or will be output.

[0205] In some embodiments, the processor 10 may be composed of an integrated circuit. For example, it may be composed of a single packaged integrated circuit, or may be composed of multiple packaged integrated circuits with the same or different functions, including a combination of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control core (Control Unit) of the electronic device, connecting various components of the entire electronic device through various interfaces and circuits, and by running or executing programs or modules stored in the memory 11 (such as the program for predicting the onset of diabetic nephropathy based on the regional health data platform, etc.), and calling the data stored in the memory 11, to perform various functions of the electronic device 1 and process data.

[0206] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. This bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is arranged to enable connection communication between the memory 11 and at least one processor 10, etc.

[0207] Figure 3 Only the electronic device with components is shown. Those skilled in the art can understand that Figure 3 the shown structure does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have a different component arrangement.

[0208] For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for powering each component. Preferably, the power source can be logically connected to the at least one processor 10 through a power management device, so as to implement functions such as charge management, discharge management, and power consumption management through the power management device. The power source may also include any components such as one or more DC or AC power sources, a recharge device, a power failure detection circuit, a power converter or inverter, and a power status indicator. The electronic device 1 may also include various sensors, a Bluetooth module, a Wi-Fi module, etc., which will not be elaborated here.

[0209] Furthermore, the electronic device 1 may further include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used to establish a communication connection between the electronic device 1 and other electronic devices.

[0210] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) toucher, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display the information processed in the electronic device 1 and to display a visual user interface.

[0211] The program of the diabetes nephropathy onset prediction method based on the regional health data platform stored in the memory 11 of the electronic device 1 is a combination of multiple instructions, which can be implemented when running in the processor 10:

[0212] Identify multiple medical institutions, where the medical institutions include: medical databases;

[0213] Perform the following operations on each of the multiple medical institutions:

[0214] Extract multiple medical evaluation data from the medical databases of the medical institutions, where the medical evaluation data includes: diabetes degree, anxiety evaluation value, cortisol level, average number of steps, single-day diet amount, single-day diet times, average alcohol consumption, and sleep time;

[0215] Perform onset feature association on the multiple medical evaluation data to obtain a psychological weight, a life weight, and a diet weight, and obtain the medical coordinates of the medical institution;

[0216] Combine the psychological weight, the life weight, the diet weight, and the medical coordinates to obtain regional analysis data;

[0217] Summarize the regional analysis data to obtain a regional analysis data set;

[0218] Receive a diabetes prediction instruction, identify the to-be-tested physical examinee based on the diabetes prediction instruction, and perform an oral glucose tolerance assessment on the to-be-tested physical examinee to obtain a glucose tolerance assessment value;

[0219] Identify the to-be-tested ID based on the to-be-tested physical examinee, and extract initial evaluation data from the pre-constructed physical examination database based on the to-be-tested ID, where the initial evaluation data includes: current coordinates, number of genetic onset people, current anxiety value, current cortisol level, current number of steps, current diet amount, current diet times, current alcohol consumption, and current sleep time;

[0220] Perform regional onset prediction on the initial evaluation data and the glucose tolerance assessment value based on the regional analysis data set to obtain a diabetes onset index;

[0221] Generate a disease prediction text for the subject to be examined based on the diabetes onset index to complete the diabetes nephropathy onset prediction.

[0222] Specifically, for the specific implementation method of the above instructions by the processor 10, reference can be made to Figures 1 to 3 the description of the relevant steps in the corresponding embodiment, which will not be elaborated here.

[0223] Furthermore, if the modules / units integrated in the electronic device 1 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory).

[0224] The present invention also provides a computer-readable storage medium, and the readable storage medium stores a computer program. When the computer program is executed by the processor of the electronic device, it can implement:

[0225] Identify multiple medical institutions, where the medical institutions include: medical databases;

[0226] Perform the following operations on each of the multiple medical institutions:

[0227] Extract multiple medical evaluation data from the medical database of the medical institution, where the medical evaluation data includes: diabetes degree, anxiety evaluation value, cortisol level, average number of steps, single-day diet amount, single-day diet frequency, average alcohol consumption, and sleep time;

[0228] Perform onset feature association on the multiple medical evaluation data to obtain a psychological weight, a lifestyle weight, and a diet weight, and obtain the medical coordinates of the medical institution;

[0229] Combine the psychological weight, the lifestyle weight, the diet weight, and the medical coordinates to obtain regional analysis data;

[0230] Summarize the regional analysis data to obtain a regional analysis data set;

[0231] Receive a diabetes prediction instruction, identify the subject to be examined based on the diabetes prediction instruction, and perform an oral glucose tolerance assessment on the subject to be examined to obtain a glucose tolerance assessment value;

[0232] Based on the confirmed ID of the subject to be examined, extract the initial assessment data from the pre-constructed physical examination database based on the ID to be examined. Among them, the initial assessment data includes: current coordinates, number of genetic disease patients, current anxiety value, current cortisol level, current number of steps, current diet amount, current number of diet times, current alcohol consumption, and current sleep time;

[0233] Based on the regional analysis data set, perform regional disease prediction on the initial assessment data and the glucose tolerance assessment value to obtain the diabetes incidence index;

[0234] Generate the disease prediction text of the subject to be examined based on the diabetes incidence index to complete the diabetes nephropathy incidence prediction.

[0235] In several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative, and there may be other division methods in actual implementation.

[0236] The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0237] In addition, the functional modules in each embodiment of the present invention can be integrated in one processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware, or in the form of hardware plus software functional modules.

[0238] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention.

[0239] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for predicting the onset of diabetic nephropathy based on a regional health data platform, characterized in that, The method includes: Identify multiple medical institutions, where a medical institution includes a medical database; Perform the following operations on each of the multiple medical institutions: Extract multiple medical evaluation data from the medical database of the medical institution, where the medical evaluation data includes: diabetes degree, anxiety evaluation value, cortisol level, average number of steps, daily diet amount, daily diet frequency, average alcohol consumption, and sleep time; Perform morbidity feature association on the multiple medical evaluation data to obtain a psychological weight, a lifestyle weight, and a diet weight, and obtain the medical coordinates of the medical institution; Combine the psychological weight, the lifestyle weight, the diet weight, and the medical coordinates to obtain regional analysis data; Summarize the regional analysis data to obtain a regional analysis data set; Receive a diabetes prediction instruction, identify a to-be-tested physical examinee based on the diabetes prediction instruction, and perform an oral glucose tolerance assessment on the to-be-tested physical examinee to obtain a glucose tolerance assessment value; Identify a to-be-tested ID based on the to-be-tested physical examinee, and extract initial evaluation data from a pre-constructed physical examination database based on the to-be-tested ID, where the initial evaluation data includes: current coordinates, number of genetic morbidity cases, current anxiety value, current cortisol level, current number of steps, current diet amount, current diet frequency, current alcohol consumption, and current sleep time; Perform regional morbidity prediction on the initial evaluation data and the glucose tolerance assessment value based on the regional analysis data set to obtain a diabetes morbidity index; Generate a morbidity prediction text for the to-be-tested physical examinee based on the diabetes morbidity index to complete the morbidity prediction of diabetic nephropathy.

2. The method for predicting the onset of diabetic nephropathy based on a regional health data platform according to claim 1, wherein, The performing morbidity feature association on the multiple medical evaluation data to obtain a psychological weight, a lifestyle weight, and a diet weight includes: Perform the following operations on each of the multiple medical evaluation data: Calculate the patient's anxiety level according to the anxiety evaluation value and the cortisol level in the medical evaluation data; Calculate the patient's lifestyle health level according to the average number of steps, the average alcohol consumption, and the sleep time in the medical evaluation data; Calculate the patient's diet normality according to the daily diet amount and the daily diet frequency in the medical evaluation data; Calculate a diabetes evaluation value based on the diabetes degree, where the diabetes degree includes: no diabetes, pre-diabetes, and having diabetes, and the calculation formula is as follows: Among them, ρ DM is the diabetes evaluation value, σ is the diabetes degree, and σ1, σ2, and σ3 respectively refer to no diabetes, pre-diabetes, and having diabetes; Calculate an anxiety feature value according to the patient's anxiety level and the diabetes evaluation value, and the calculation formula is as follows: Among them, δ P is the anxiety eigenvalue, and P re is the patient's anxiety level; Calculate a lifestyle feature value based on the patient's lifestyle health level and the diabetes evaluation value, and calculate a diet feature value based on the patient's diet normality and the diabetes evaluation value; Summarize the anxiety feature values, the lifestyle feature values, and the diet feature values respectively to obtain multiple anxiety feature values, multiple lifestyle feature values, and multiple diet feature values; Calculate a psychological weight according to the multiple anxiety feature values, calculate a lifestyle weight based on the multiple lifestyle feature values, and calculate a diet weight based on the multiple diet feature values.

3. The method for predicting the onset of diabetic nephropathy based on the regional health data platform according to claim 2, wherein, The calculation formula of the patient's anxiety level is as follows: Among them, CORT x is the cortisol level, CORT0 is the preset reference cortisol level, SAS is the anxiety assessment value, and e is the natural constant.

4. The method for predicting the onset of diabetic nephropathy based on a regional health data platform according to claim 3, wherein, The calculation formula of the patient's lifestyle health level is as follows: Among them, H ea is the patient's life health level, Step is the average number of steps, Sl x is the sleep time, Sl0 is the preset reference sleep time, C x is the average alcohol consumption, and tanh is the hyperbolic tangent function.

5. The method for predicting the onset of diabetic nephropathy based on the regional health data platform according to claim 4, characterized in that, The calculation formula of the patient's diet normality is as follows: Among them, D ie is the normal degree of the patient's diet, D c is the daily diet amount, D0 is the preset diet reference amount, k d is the number of daily meals, and | | represents taking the absolute value.

6. The method for predicting the onset of diabetic nephropathy based on the regional health data platform according to claim 5, wherein The calculating a psychological weight according to the multiple anxiety feature values includes: Calculate an anxiety average value based on the multiple anxiety feature values, where the anxiety average value is the average value of the multiple anxiety feature values; Calculate a psychological weight based on the multiple anxiety feature values and the anxiety average value, and the calculation formula is as follows: Among them, μ p is the psychological weight, is the average anxiety value, is the i-th anxiety eigenvalue among multiple anxiety eigenvalues, and n is the number of anxiety eigenvalues among multiple anxiety eigenvalues.

7. The method for predicting the onset of diabetic nephropathy based on the regional health data platform according to claim 6, wherein Performing an oral glucose tolerance assessment on the subject to be tested to obtain a glucose tolerance assessment value, including: Obtaining the initial blood glucose of the subject to be tested, and identifying the glucose-taking subject based on the pre-constructed glucose solution and the subject to be tested; Taking the time when the glucose-taking subject is identified as the starting point and recording the time in real time to obtain the glucose consumption time; When the glucose consumption time reaches the preset first recording time, obtaining the first blood glucose of the glucose-taking subject; When the glucose consumption time reaches the preset second recording time, obtaining the second blood glucose of the glucose-taking subject; Calculating the glucose tolerance assessment value according to the initial blood glucose, the first blood glucose, the second blood glucose, the first recording time and the second recording time. The calculation formula is as follows: Wherein, is the glucose tolerance evaluation value, BG0, BG1, and BG2 are the initial blood glucose, the first blood glucose, and the second blood glucose respectively, and t1 and t2 are the first recording time and the second recording time respectively.

8. The method for predicting the onset of diabetic nephropathy based on a regional health data platform according to claim 7, characterized in that, Performing regional disease incidence prediction on the initial assessment data and the glucose tolerance assessment value based on the regional analysis data set to obtain a diabetes incidence index, including: Performing the following operations on each regional analysis data in the regional analysis data set: Calculating the regional Euclidean distance according to the medical coordinates and the current coordinates in the regional analysis data. The calculation formula is as follows: Among them, d qy is the regional Euclidean distance, x1 and y1 are the longitude in the medical coordinates and the latitude in the medical coordinates respectively, x d and y d are the longitude in the current coordinates and the latitude in the current coordinates respectively; Summarizing the regional Euclidean distances to obtain multiple regional Euclidean distances; Performing a sorting operation on the multiple regional Euclidean distances in ascending order to obtain a regional Euclidean distance sequence; Identifying the first regional distance, the second regional distance and the third regional distance based on the regional Euclidean distance sequence. Among them, the first regional distance, the second regional distance and the third regional distance are the regional Euclidean distance ranked first, the regional Euclidean distance ranked second and the regional Euclidean distance ranked third in the regional Euclidean distance sequence respectively; Taking the regional analysis data corresponding to the first regional distance as the first regional data, taking the regional analysis data corresponding to the second regional distance as the second regional data, and taking the regional analysis data corresponding to the third regional distance as the third regional data; Calculating the total distance value according to the first regional distance, the second regional distance and the third regional distance, where the total distance value is the sum of the first regional distance, the second regional distance and the third regional distance; Calculating the first regional weight according to the first regional distance and the total distance value. The calculation formula is as follows: Among them, μ qy1 is the weight of the first region, d qy1 and d qyx are the distance of the first region and the total distance value respectively; Calculating the second regional weight based on the second regional distance and the total distance value, and calculating the third regional weight based on the third regional distance and the total distance value; Calculating the current anxiety level based on the current anxiety value and the current cortisol level in the initial assessment data, calculating the current life level based on the current number of steps, the current alcohol consumption and the current sleep time in the initial assessment data, and calculating the current diet level based on the current diet amount and the current number of diet times in the initial assessment data; Calculating the first diabetes incidence index according to the number of genetic disease cases, the glucose tolerance assessment value, the current anxiety level, the current life level, the current diet level, the first regional weight and the first regional data. The calculation formula is as follows: Among them, θ BG1 is the first diabetes incidence index, μ p1 , μ H1 and μ D1 are respectively the psychological weight, the life weight and the diet weight in the data of the first region, P re * , H ea * and D ie * are respectively the current anxiety level, the current life level and the current diet level, N x is the number of genetic disease patients; Calculating the second diabetes incidence index based on the number of genetic disease cases, the glucose tolerance assessment value, the current anxiety level, the current life level, the current diet level, the second regional weight and the second regional data, and calculating the third diabetes incidence index based on the number of genetic disease cases, the glucose tolerance assessment value, the current anxiety level, the current life level, the current diet level, the third regional weight and the third regional data; Calculate the diabetes onset index based on the first diabetes onset index, the second diabetes onset index, and the third diabetes onset index. Among them, the diabetes onset index is the sum of the first diabetes onset index, the second diabetes onset index, and the third diabetes onset index.

9. The method for predicting the onset of diabetic nephropathy based on the regional health data platform according to claim 8, wherein, Generating a disease onset prediction text for the to-be-tested examinee based on the diabetes onset index includes: Compare the diabetes onset index with a preset first onset threshold and compare the diabetes onset index with a preset second onset threshold, where the first onset threshold is less than the second onset threshold; If the diabetes onset index is less than or equal to the first onset threshold, send the pre-constructed safety prediction text to the pre-constructed medical diagnosis terminal to obtain the disease onset prediction text; If the diabetes onset index is greater than the first onset threshold and less than or equal to the second onset threshold, send the pre-constructed attention prediction text to the medical diagnosis terminal to obtain the disease onset prediction text; If the diabetes onset index is greater than the second onset threshold, send the pre-constructed danger prediction text to the medical diagnosis terminal to obtain the disease onset prediction text.

10. A diabetes nephropathy onset prediction system based on a regional health data platform, characterized in that, The system includes: A regional data acquisition module for identifying multiple medical institutions. Among them, the medical institutions include: a medical database. The following operations are performed on each of the multiple medical institutions: Extract multiple medical evaluation data from the medical database of the medical institution. Among them, the medical evaluation data includes: diabetes degree, anxiety evaluation value, cortisol level, average number of steps, single-day diet amount, single-day diet times, average alcohol consumption, and sleep time; A medical data association module for associating the onset characteristics of multiple medical evaluation data to obtain a psychological weight, a lifestyle weight, and a diet weight, obtaining the medical coordinates of the medical institution, combining the psychological weight, the lifestyle weight, the diet weight, and the medical coordinates to obtain regional analysis data, and summarizing the regional analysis data to obtain a regional analysis data set; A to-be-tested individual evaluation module for receiving a diabetes prediction instruction, identifying the to-be-tested examinee based on the diabetes prediction instruction, performing an oral glucose tolerance assessment on the to-be-tested examinee to obtain a glucose tolerance assessment value, identifying the to-be-tested ID based on the to-be-tested examinee, and extracting initial evaluation data from the pre-constructed physical examination database based on the to-be-tested ID. Among them, the initial evaluation data includes: current coordinates, number of genetic disease cases, current anxiety value, current cortisol level, current number of steps, current diet amount, current diet times, current alcohol consumption, and current sleep time; A diabetes onset prediction module for performing regional onset prediction on the initial evaluation data and the glucose tolerance assessment value based on the regional analysis data set to obtain a diabetes onset index, and generating a disease onset prediction text for the to-be-tested examinee based on the diabetes onset index to complete the diabetes nephropathy onset prediction.

Images