Type 1 diabetes treatment risk assessment system based on multi-source data

Abstract

The invention discloses a type 1 diabetes treatment risk assessment system based on multi-source data, particularly relates to the technical field of multi-source data, and comprises a time region division module, a diabetes information acquisition module, a preprocessing module, a diabetes information analysis module, a comprehensive assessment module, a comprehensive judgment module and a man-machine interaction module. A target area is divided into sub-areas according to equal time areas, and first information texts of the sub-areas are acquired; a physiological index coefficient value, an immune index coefficient value, a concurrent correlation value and a metabolic fluctuation coefficient value are imported into a comprehensive evaluation model to obtain a comprehensive evaluation safety degree index value, and the comprehensive evaluation safety degree index value through a comprehensive judgment module is compared with a preset evaluation safety degree threshold value and fed back. And the accuracy and comprehensiveness of the risk assessment result of the type 1 diabetes mellitus can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of multi-source data, and more specifically, to a type 1 diabetes treatment risk assessment system based on multi-source data. Background Art

[0002] With the advancement of science and technology, multi-source data collection technology has flourished, and various wearable devices, high-sensitivity biosensors, and advanced imaging detection methods have emerged, creating opportunities to break the "deadlock" of traditional assessment. Continuous blood glucose monitoring systems can track blood glucose "traces" in real time and record fluctuations every minute and every second; immunoassay technology based on microfluidic chips can conveniently and frequently detect immune indicators; smart wearable devices monitor sleep and exercise parameters, and combine metabolic analysis technology to quantify the impact of lifestyle on metabolism. It is urgent to integrate these multi-source heterogeneous data, use big data analysis and artificial intelligence algorithms to mine the deep value of data, and build a comprehensive, dynamic, and accurate type 1 diabetes treatment risk assessment system to fill the gaps in traditional assessments and achieve the goals of early warning of risks, optimizing treatment pathways, and improving patients' quality of life and prognosis.

[0003] An existing type 1 diabetes treatment risk assessment system includes a data acquisition module, a data analysis module, and a risk assessment module. The data acquisition module uses various advanced medical monitoring equipment and convenient data interfaces to widely collect massive data closely related to the treatment process of type 1 diabetes. The data analysis module uses deep learning algorithms to deeply mine complex monitoring data, eliminate interference information such as detection errors and physiological noise, and transform the messy original medical data into clear and clearly directed analysis results. This can clearly present the current state of the patient's pancreatic islet function and the activity of the autoimmune response, accurately identify early abnormal signs that may indicate the development of diabetic complications, and provide an intuitive basis for judging the course of the disease and identifying potential treatment risks; the risk assessment module relies on a massive case data resource library accumulated over a long period of time, combined with an authoritative and rigorous diabetes medical diagnosis and treatment theoretical model, to carry out rigorous, meticulous, scientific and quantitative assessment of the patient's current treatment risk level; carefully calculate key indicators such as the disease progression risk coefficient, treatment tolerance, and the probability of complication outbreaks, accurately define the risk level and possible high-risk directions, so as to provide targeted guidance for the subsequent optimization of personalized treatment plans and the formulation of preventive intervention measures, and effectively ensure the safety and effectiveness of diabetes treatment.

[0004] However, in practical applications, the type 1 diabetes treatment risk assessment system based on multi-source data still reveals many shortcomings. For example, when the data collection module collects patient data, it is troubled by various interference factors. Medical monitoring devices may cause inaccuracies in key data such as blood glucose and insulin due to problems such as calibration deviation, electrode aging, and signal transmission obstruction, reducing the integrity and accuracy of the original data. During the process of using data analysis algorithms to analyze monitoring data by the data analysis module, given the complex condition of type 1 diabetes and significant individual differences, under the influence of age, gender, and lifestyle habits of different patients, the physiological data fluctuations during the treatment process are irregular and vary greatly. For example, due to growth and development, the insulin requirements of adolescent patients change frequently in the short term; elderly patients often have multiple underlying diseases, and the decline of physical functions interferes with the interpretation of metabolic indicators. This leads to the analysis results often deviating from the true condition of the disease, misjudging the recovery status of pancreatic islet function or the immune regulation effect, and in the complex data operation process, data loss is likely to occur, such as the inexplicable loss of key metabolic data and immune response data under special stress states, breaking the data chain, seriously damaging data coherence, greatly reducing the reference value of data for disease assessment and risk judgment, and making it difficult to accurately detect the hidden treatment risks. The existing risk assessment system lacks a complete, scientific, and comprehensive data index system to comprehensively measure the treatment effectiveness and risks of diabetes. The traditional assessment method focusing on a single index completely fails to fully consider the comprehensive impact of multiple complex factors such as the patient's lifestyle, psychological state, long-term disease evolution trend, and the synergistic effect of different treatment drugs on treatment risks. When assessing treatment risks, it is easy to one-sidedly focus on blood glucose control and ignore potential risks such as continuous damage to pancreatic islets caused by immune regulation imbalance and aggravated metabolic disorders caused by disrupted living routines, resulting in subjective and one-sided assessment results, inaccurate and unfair, greatly increasing the difficulty of accurately controlling the treatment direction and reasonably adjusting the treatment strategy, and bringing many obstacles and potential risks to the effective treatment and health recovery of type 1 diabetes patients.

[0005] Therefore, there is an urgent need for a type 1 diabetes treatment risk assessment system based on multi-source data to solve the above problems. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a type 1 diabetes treatment risk assessment system based on multi-source data, through the multi-source data technology field, to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solution: A type 1 diabetes treatment risk assessment system based on multi-source data, including a time region division module, a diabetes information collection module, a preprocessing module, a diabetes information analysis module, a comprehensive assessment module, a comprehensive judgment module, and a human-computer interaction module:

[0008] Time Region Division Module: It is used to divide the diabetes information data of the target region stored in the system database into sub-regions according to equal time regions, and sequentially number the sub-regions within the target region as 1, 2, ……, i, ……, n;

[0009] Diabetes Information Collection Module: It collects data from any sub-region of the target region through multi-source devices, obtains the first information text of the sub-region, and transmits the first information text to the preprocessing module;

[0010] Preprocessing Module: It receives the first information text transmitted by the diabetes information collection module and is used to perform preprocessing operations on the first information text;

[0011] Diabetes Information Analysis Module: It is used to obtain an information analysis model, input the first information text into the information analysis model to obtain physiological index coefficient values, immune index coefficient values, concurrent correlation coefficient values, and metabolic fluctuation coefficient values; it includes a physiological index analysis unit, an immune index analysis unit, a concurrent correlation analysis unit, and a metabolic index analysis unit;

[0012] Comprehensive Evaluation Module: It is used to obtain a comprehensive evaluation model, import the physiological index coefficient values, immune index coefficient values, concurrent correlation coefficient values, and metabolic fluctuation coefficient values into the comprehensive evaluation model to obtain a comprehensive evaluation safety degree index value, and transmit the data to the comprehensive judgment module; it includes a comprehensive analysis unit;

[0013] Comprehensive Judgment Module: It obtains a preset evaluation safety degree threshold, compares the comprehensive evaluation safety degree index value with the preset evaluation safety degree threshold to obtain an intelligent signal, and transmits the intelligent signal to the human-computer interaction module;

[0014] Human-Computer Interaction Module: It is used to receive the abnormal signal from the comprehensive judgment module, manage the personnel to perform corresponding intelligent adjustments and optimizations, and display them to relevant management personnel in a visual manner.

[0015] Preferably, the first information text specifically includes the following: the range of blood glucose content is denoted as Sx, the coefficient of variation of glycated hemoglobin is denoted as St, the rate of blood ketone body generation is denoted as Sv, the titer value of glutamic acid decarboxylase antibody is denoted as Mg, the content of insulin antibody is denoted as My, the activation concentration of complement C3 is denoted as Mb, the excretion content of urinary microalbumin is denoted as Bp, the nerve conduction velocity is denoted as Bv, the intima-media thickness of the cardiovascular system is denoted as Bm, the secretion content of melatonin is denoted as Dt, the energy consumption metabolism content is denoted as Dj, and the carbohydrate absorption rate is denoted as Dx.

[0016] Preferably, the physiological index analysis unit is used to establish a physiological index analysis model, import the first information text processed by the preprocessing module into the physiological index analysis model, and calculate the physiological index coefficient values of each sub-region, specifically expressed as:

[0017]

[0018] S i represents the physiological index coefficient value of the i-th sub-region, Sx i represents the range of blood glucose content in the i-th sub-region, Sx max represents the maximum value of the blood glucose content in the target region, Sx mim represents the minimum value of the blood glucose content in the target region, St i represents the coefficient of variation of glycated hemoglobin in the i-th sub-region, St0 represents the initial value of the coefficient of variation of glycated hemoglobin in the target region, Sv i represents the rate of blood ketone body production in the i-th sub-region, Sv0 represents the maximum value of the rate of blood ketone body production in the target region, e represents the natural constant, and n represents the total number of sub-regions.

[0019] Preferably, the immune index analysis unit is used to establish an immune index analysis model, import the first information text processed by the preprocessing module into the immune index analysis model, and calculate the immune index coefficient values of each sub-region, specifically expressed as:

[0020]

[0021] M i represents the immune index coefficient value of the i-th sub-region, Mg i represents the titer value of glutamic acid decarboxylase antibody in the i-th sub-region, My i represents the content of insulin antibody in the i-th sub-region, Mb i represents the activated concentration of complement C3 in the i-th sub-region, Mb max represents the maximum value of the activated concentration of complement C3 in the target region, e represents the natural constant, and n represents the total number of sub-regions.

[0022] Preferably, the concurrent association analysis unit is used to establish a concurrent association analysis model, import the first information text processed by the preprocessing module into the concurrent association analysis model, and calculate the concurrent association values of each sub-region, specifically expressed as:

[0023]

[0024] B i represents the operation time efficiency coefficient value of the i-th sub-region, Bp i represents the urinary microalbumin excretion content in the i-th sub-region, Bv i represents the nerve conduction velocity in the i-th sub-region, yc i represents the intima-media thickness of the cardiovascular system in the i-th sub-region, π represents the natural constant, and n represents the total number of sub-regions.

[0025] Preferably, the metabolic index analysis unit is used to establish a metabolic index analysis model, import the first information text processed by the preprocessing module into the metabolic index analysis model, and calculate the metabolic index coefficient values of each sub-region, specifically expressed as:

[0026]

[0027] D i represents the environmental characteristic coefficient value of the i-th sub-region, Dt i represents the melatonin secretion content of the i-th sub-region, Dt0 represents the initial value of the melatonin secretion content of the target region, Dj i represents the energy consumption metabolism content of the i-th sub-region, Dx i represents the carbohydrate absorption rate of the i-th sub-region, and n represents the total number of sub-regions.

[0028] Preferably, the comprehensive analysis unit is used to establish a comprehensive evaluation model, import the physiological index coefficient value, immune index coefficient value, concurrent correlation coefficient value, and metabolic fluctuation coefficient value into the comprehensive evaluation model, and calculate the comprehensive evaluation safety degree index value, specifically expressed as:

[0029]

[0030] where P represents the comprehensive evaluation safety degree index value, S i represents the physiological index coefficient value of the i-th sub-region, M i represents the immune index coefficient value of the i-th sub-region, B i represents the operation time efficiency coefficient value of the i-th sub-region, D i represents the environmental characteristic coefficient value of the i-th sub-region, α1, α2, α3, α4 represent weight coefficients and are all greater than zero, and the sum of α1, α2, α3, α4 is equal to one, where μ represents other influencing factors of the comprehensive evaluation safety degree index value, and n represents the total number of sub-regions.

[0031] Preferably, the preset evaluation safety degree threshold is obtained by systematically evaluating the data collected in the system database for type 1 diabetes in previous years; the specific discrimination is as follows:

[0032] The intelligent signals include: abnormal signals and safety signals;

[0033] B1: If the comprehensive evaluation safety degree index value is greater than the preset evaluation safety degree threshold, an abnormal signal is issued;

[0034] B2: If the comprehensive evaluation safety degree index value is less than the preset evaluation safety degree threshold, a safety signal is issued, and the data is stored in the system database.

[0035] Preferably, the visualization methods include text display, image display, and audio display.

[0036] Technical effects and advantages of the present invention:

[0037] 1. Through the time zone division module of the present invention, the diabetes information data of the target area is divided into sub-areas according to equal time zones, and the first information text of the sub-areas is collected; the pretreatment module processes the first information text, which helps to improve the accuracy of type 1 diabetes information and remove outliers in the subsequent process; then, through the diabetes information analysis module, the physiological index coefficient value, immune index coefficient value, complication correlation coefficient value, and metabolic fluctuation coefficient value are obtained, which helps to refine the comprehensiveness of type 1 diabetes and greatly reduce the risk level.

[0038] 2. Through the comprehensive evaluation module of the present invention, the comprehensive evaluation safety index value is obtained from the comprehensive evaluation model, which helps to present a more intuitive effect and the integrity of data analysis to the management personnel, and can perform more refined and in-depth calculation and analysis on information analysis, providing multi-angle and multi-dimensional result analysis; by comparing the comprehensive evaluation safety index value with the preset evaluation safety threshold, it helps to improve the accuracy of the risk assessment result of type 1 diabetes.

[0039] 3. Through the human-computer interaction module of the present invention, once an abnormal signal is received, the system will feedback the processing result to the management personnel and optimize and adjust the system, timely discover the risk assessment situation of type 1 diabetes, and greatly improve the accuracy and integrity of the assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a schematic structural diagram of the system of the present invention.

[0041] Figure 2 It is a schematic structural diagram of the diabetes information analysis module of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0043] As shown in the attached Figure 1 figure is a schematic structural diagram of a type 1 diabetes treatment risk assessment system based on multi-source data, including a time zone division module, a diabetes information collection module, a pretreatment module, a diabetes information analysis module, a comprehensive evaluation module, a comprehensive judgment module, and a human-computer interaction module.

[0044] As shown in the Figure 2 accompanying drawings is a schematic structural diagram of the diabetes information analysis module.

[0045] Time region division module: Used to store the diabetes information data of the target region in the system database and divide it into sub-regions according to equal time regions, and sequentially number each sub-region in the target region as 1, 2, ……, i, ……, n.

[0046] In this embodiment, specifically, dividing time according to equal time regions includes but is not limited to: half a day, one day, and one week.

[0047] Diabetes information collection module: Collects from any sub-region of the target region through multi-source devices, obtains the first information text of the sub-region, and transmits the first information text to the preprocessing module.

[0048] In this embodiment, specifically, the first information text specifically includes the following: the range of blood glucose content is denoted as Sx, the coefficient of variation of glycated hemoglobin is denoted as St, the rate of blood ketone body formation is denoted as Sv, the titer value of glutamic acid decarboxylase antibody is denoted as Mg, the content of insulin antibody is denoted as My, the activation concentration of complement C3 is denoted as Mb, the excretion content of urinary microalbumin is denoted as Bp, the nerve conduction velocity is denoted as Bv, the intima-media thickness of blood vessels is denoted as Bm, the secretion content of melatonin is denoted as Dt, the energy consumption metabolism content is denoted as Dj, and the carbohydrate absorption rate is denoted as Dx.

[0049] Preprocessing module: Receives the first information text transmitted by the diabetes information collection module and is used to perform preprocessing operations on the first information text.

[0050] In this example, specifically, it should be noted that: The specific steps of the preprocessing operation include:

[0051] A1: Text cleaning: Remove special characters, punctuation marks, and numerical symbols from the first information text, and then perform case conversion on the text;

[0052] A2: Outlier removal: After text cleaning, detect and remove the abnormal outliers in the first information text;

[0053] A3: Data extraction: Extract the most representative and key data from the first information text, that is, the preprocessed first information text.

[0054] Diabetes information analysis module: used to obtain an information analysis model, input the first information text into the information analysis model to obtain physiological index coefficient values, immune index coefficient values, complication correlation coefficient values, and metabolic fluctuation coefficient values; includes a physiological index analysis unit, an immune index analysis unit, a complication correlation analysis unit, and a metabolic index analysis unit.

[0055] In this embodiment, specifically, the information analysis model specifically includes: a physiological index analysis model, an immune index analysis model, a complication correlation analysis model, and a metabolic index analysis model.

[0056] In this embodiment, specifically, the physiological index analysis unit is used to establish a physiological index analysis model, import the first information text processed by the preprocessing module into the physiological index analysis model, and calculate the physiological index coefficient values of each sub-region, specifically expressed as:

[0057]

[0058] S i represents the physiological index coefficient value of the i-th sub-region, Sx i represents the range of blood glucose content of the i-th sub-region, Sx max represents the maximum value of the blood glucose content of the target region, Sx mim represents the minimum value of the blood glucose content of the target region, St i represents the coefficient of variation of glycated hemoglobin of the i-th sub-region, St0 represents the initial value of the coefficient of variation of glycated hemoglobin of the target region, Sv i represents the rate of blood ketone body generation of the i-th sub-region, Sv0 represents the maximum value of the rate of blood ketone body generation of the target region, e represents the natural constant, and n represents the total number of sub-regions.

[0059] In this embodiment, specifically, the immune index analysis unit is used to establish an immune index analysis model, import the first information text processed by the preprocessing module into the immune index analysis model, and calculate the immune index coefficient values of each sub-region, specifically expressed as:

[0060]

[0061] M i represents the immune index coefficient value of the i-th sub-region, Mg i represents the titer value of glutamic acid decarboxylase antibody of the i-th sub-region, My i represents the content of insulin antibody of the i-th sub-region, Mb i represents the activation concentration of complement C3 of the i-th sub-region, Mb maxrepresents the maximum value of the complement C3 activation concentration in the target area, e represents the natural constant, and n represents the total number of sub-areas.

[0062] In this embodiment, specifically, the concurrent correlation analysis unit is used to establish a concurrent correlation analysis model, import the first information text processed by the preprocessing module into the concurrent correlation analysis model, and calculate the concurrent correlation values of each sub-area, specifically expressed as:

[0063]

[0064] B i represents the operation aging coefficient value of the i-th sub-area, Bp i represents the urinary microalbumin excretion content of the i-th sub-area, Bv i represents the nerve conduction velocity of the i-th sub-area, yc i represents the intima-media thickness of the cardiovascular system in the i-th sub-area, π represents the natural constant, and n represents the total number of sub-areas.

[0065] In this embodiment, specifically, the metabolic index analysis unit is used to establish a metabolic index analysis model, import the first information text processed by the preprocessing module into the metabolic index analysis model, and calculate the metabolic index coefficient values of each sub-area, specifically expressed as:

[0066]

[0067] D i represents the environmental characteristic coefficient value of the i-th sub-area, Dt i represents the melatonin secretion content of the i-th sub-area, Dt0 represents the initial value of the melatonin secretion content in the target area, Dj i represents the energy consumption metabolism content of the i-th sub-area, Dx i represents the carbohydrate absorption rate of the i-th sub-area, and n represents the total number of sub-areas.

[0068] Comprehensive evaluation module: used to obtain a comprehensive evaluation model, import the physiological index coefficient value, immune index coefficient value, concurrent correlation value, and metabolic fluctuation coefficient value into the comprehensive evaluation model to obtain a comprehensive evaluation safety degree index value, and transmit the data to the comprehensive judgment module; includes a comprehensive analysis unit.

[0069] In this embodiment, specifically, the comprehensive analysis unit is used to establish a comprehensive evaluation model, import the physiological index coefficient value, immune index coefficient value, concurrent correlation value, and metabolic fluctuation coefficient value into the comprehensive evaluation model, and calculate the comprehensive evaluation safety degree index value, specifically expressed as:

[0070]

[0071] Among them, P represents the comprehensive evaluation safety degree index value, and S i represents the physiological index coefficient value of the i-th sub-region, M i represents the immune index coefficient value of the i-th sub-region, B i represents the operation time efficiency coefficient value of the i-th sub-region, D i represents the environmental characteristic coefficient value of the i-th sub-region. α1, α2, α3, and α4 represent weight coefficients and are all greater than zero. The sum of α1, α2, α3, and α4 is equal to one. Among them, μ represents other influencing factors of the comprehensive evaluation safety degree index value, and n represents the total number of sub-regions.

[0072] Comprehensive judgment module: Obtain the preset evaluation safety degree threshold, compare the comprehensive evaluation safety degree index value with the preset evaluation safety degree threshold to obtain an intelligent signal, and transmit the intelligent signal to the human-computer interaction module.

[0073] In this embodiment, specifically, it should be noted that the preset evaluation safety degree threshold is the mean value obtained through system evaluation based on the data collected for type 1 diabetes in previous years in the system database; the specific discrimination is as follows:

[0074] The intelligent signal includes: an abnormal signal and a safety signal;

[0075] B1: If the comprehensive evaluation safety degree index value is greater than the preset evaluation safety degree threshold, an abnormal signal is issued;

[0076] B2: If the comprehensive evaluation safety degree index value is less than the preset evaluation safety degree threshold, a safety signal is issued, and the data is stored in the system database.

[0077] Human-computer interaction module: Used to receive the abnormal signal from the comprehensive judgment module, manage the corresponding intelligent adjustment and optimization by the management personnel, and display it to the relevant management personnel in a visual manner.

[0078] In this embodiment, specifically, it should be noted that the visual manner includes: text display, image display, and audio display.

[0079] Through the time zone division module, the diabetes information data of the target area is divided into sub-areas according to equal time zones, and the first information text of the sub-areas is collected and obtained; through the preprocessing module, the first information text is processed, which helps to improve the accuracy of type 1 diabetes information and remove outliers in the follow-up; then, through the diabetes information analysis module, the physiological index coefficient value, immune index coefficient value, complication correlation coefficient value, and metabolic fluctuation coefficient value are obtained, which helps to refine the comprehensiveness of type 1 diabetes and greatly reduce the risk level; through the comprehensive evaluation module, which is used to obtain the comprehensive evaluation safety index value by the comprehensive evaluation model, which helps to present a more intuitive effect and the integrity of data analysis to the management personnel, and can perform more refined and in-depth calculation and analysis on information analysis, providing multi-angle and multi-dimensional result analysis; by comparing the comprehensive evaluation safety index value of the comprehensive judgment module with the preset evaluation safety threshold, it helps to improve the accuracy of the risk assessment result of type 1 diabetes; through the human-computer interaction module, once an abnormal signal is received, the system will feedback the processing result to the management personnel and optimize and adjust the system, timely discover the risk assessment situation of type 1 diabetes, and greatly improve the accuracy and integrity of the assessment.

[0080] Secondly, in the attached drawings of the disclosed embodiments of the present invention, only the structures related to the disclosed embodiments of the present disclosure are involved, and other structures can refer to the general design. Without conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0081] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A type 1 diabetes treatment risk assessment system based on multi-source data, characterized in that: include: Time zone division module: used to divide the diabetes information data in the target area stored in the system database into sub-areas according to equal time zones, and number the sub-areas in the target area as 1, 2, ..., i, ..., n in sequence; Diabetes information acquisition module: collects information from any sub-area of ​​the target area through multi-source devices, obtains the first information text of the sub-area, and transmits the first information text to the pre-processing module; A preprocessing module is used for receiving the first information text transmitted by the diabetes information acquisition module and performing a preprocessing operation on the first information text; Diabetes information analysis module: used to obtain an information analysis model, input the first information text into the information analysis model to obtain the physiological index coefficient value, immune index coefficient value, concurrent correlation coefficient value and metabolic fluctuation coefficient value; It includes physiological index analysis unit, immune index analysis unit, concurrent correlation analysis unit and metabolic index analysis unit; Comprehensive evaluation module: used to obtain a comprehensive evaluation model, import the physiological index coefficient value, immune index coefficient value, concurrent correlation value and metabolic fluctuation coefficient value into the comprehensive evaluation model to obtain a comprehensive evaluation safety index value, and transmit the data to the comprehensive judgment module; Includes comprehensive analysis unit; Comprehensive judgment module: obtains the preset safety assessment threshold, obtains an intelligent signal based on the comparison between the comprehensive safety assessment index value and the preset safety assessment threshold, and transmits the intelligent signal to the human-computer interaction module; Human-computer interaction module: used to receive abnormal signals from the comprehensive judgment module, and the management personnel will make corresponding intelligent adjustments and optimizations, and display them to relevant management personnel in a visual manner.

2. A type 1 diabetes treatment risk assessment system based on multi-source data according to claim 1, characterized in that: The first information text specifically includes the following: the extreme difference of blood glucose content is recorded as Sx, the coefficient of variation of glycated hemoglobin is recorded as St, the blood ketone body production rate is recorded as Sv, the glutamic acid decarboxylase antibody titer is recorded as Mg, the insulin antibody content is recorded as My, the complement C3 activation concentration is recorded as Mb, the urine microalbumin excretion content is recorded as Bp, the nerve conduction velocity is recorded as Bv, the cardiovascular intima-media thickness is recorded as Bm, the melatonin secretion content is recorded as Dt, the energy consumption metabolism content is recorded as Dj and the carbohydrate absorption rate is recorded as Dx.

3. A type 1 diabetes treatment risk assessment system based on multi-source data according to claim 1, characterized in that: The physiological index analysis unit is used to establish a physiological index analysis model, import the first information text processed by the preprocessing module into the physiological index analysis model, and calculate the physiological index coefficient value of each sub-region, which is specifically expressed as: S i represents the physiological index coefficient value of the ith sub-region, Sx i Indicates that the blood sugar content in the ith sub-region is extremely poor, Sx max Indicates the maximum blood sugar content in the target area, Sx mim Indicates the minimum value of blood sugar content in the target area, St i represents the coefficient of variation of glycated hemoglobin in the i-th sub-region, St0 represents the initial value of the coefficient of variation of glycated hemoglobin in the target region, Sv i represents the blood ketone body production rate of the i-th sub-region, Sv0 represents the maximum blood ketone body production rate of the target region, e represents the natural constant, and n represents the total number of sub-regions.

4. A type 1 diabetes treatment risk assessment system based on multi-source data according to claim 1, characterized in that: The immune index analysis unit is used to establish an immune index analysis model, import the first information text processed by the preprocessing module into the immune index analysis model, and calculate the immune index coefficient value of each sub-region, which is specifically expressed as: M i represents the immune index coefficient value of the i-th sub-region, Mg i My represents the glutamic acid decarboxylase antibody titer value of the i-th sub-region, i represents the content of insulin antibody in the ith subregion, Mb i represents the complement C3 activation concentration in the ith subregion, Mb max represents the maximum complement C3 activation concentration in the target area, e represents the natural constant, and n represents the total number of sub-areas.

5. The type 1 diabetes treatment risk assessment system based on multi-source data according to claim 1, characterized in that: The concurrent correlation analysis unit is used to establish a concurrent correlation analysis model, import the first information text processed by the preprocessing module into the concurrent correlation analysis model, and calculate the concurrent correlation value of each sub-region, which is specifically expressed as: B i represents the operating efficiency coefficient value of the i-th sub-area, Bp i represents the urinary microalbumin excretion content of the ith sub-region, Bv i represents the nerve conduction velocity of the ith sub-region, yc i represents the thickness of the cardiovascular intima-media layer in the ith sub-region, π represents a natural constant, and n represents the total number of sub-regions.

6. A type 1 diabetes treatment risk assessment system based on multi-source data according to claim 1, characterized in that: The metabolic index analysis unit is used to establish a metabolic index analysis model, import the first information text processed by the preprocessing module into the metabolic index analysis model, and calculate the metabolic index coefficient value of each sub-region, which is specifically expressed as: D i represents the environmental characteristic coefficient value of the ith sub-area, Dt i represents the melatonin secretion content of the i-th sub-region, Dt0 represents the initial value of the melatonin secretion content of the target region, and Dj i represents the energy consumption metabolic content of the ith sub-region, Dx i represents the carbohydrate absorption rate of the ith sub-region, and n represents the total number of sub-regions.

7. The type 1 diabetes treatment risk assessment system based on multi-source data according to claim 1, characterized in that: The comprehensive analysis unit is used to establish a comprehensive evaluation model, import the physiological index coefficient value, the immune index coefficient value, the concurrent correlation coefficient value and the metabolic fluctuation coefficient value into the comprehensive evaluation model, and calculate the comprehensive evaluation safety index value, which is specifically expressed as: Where P represents the comprehensive safety evaluation index value, S i represents the physiological index coefficient value of the ith sub-region, M i represents the immune index coefficient value of the ith sub-region, B i represents the operating efficiency coefficient value of the ith sub-area, D i represents the environmental characteristic coefficient value of the i-th sub-area, α1, α2, α3, α4 represent weight coefficients and are all greater than zero, the sum of α1, α2, α3, α4 is equal to one, where μ represents other influencing factors of the comprehensive evaluation safety index value, and n represents the total number of sub-areas.

8. The type 1 diabetes treatment risk assessment system based on multi-source data according to claim 1, characterized in that: The preset safety threshold is the mean value obtained by systematic evaluation based on the data collected in the system database of diabetes type 1 in previous years; the specific judgment is as follows: The intelligent signals include: abnormal signals and safety signals; B1: If the comprehensive safety evaluation index value is greater than the preset safety evaluation threshold, an abnormal signal is issued; B2: If the comprehensive assessment safety index value is less than the preset assessment safety threshold, a safety signal is issued and the data is stored in the system database.

9. The type 1 diabetes treatment risk assessment system based on multi-source data according to claim 1, characterized in that: The visualization methods include text display, image display and audio display.

Images