Fatty liver monitoring data processing system for type 2 diabetes mellitus in metabolic process

Abstract

The invention discloses a fatty liver monitoring data processing system used in the metabolic process of type 2 diabetes mellitus, and relates to the technical field of data processing. The fatty liver monitoring data processing system used in the metabolic process of type 2 diabetes mellitus comprises a data acquisition module, a basic characteristic data processing module, a fatty liver monitoring data processing module and a data processing comprehensive output module. And meanwhile, the output display label corresponding to the fatty liver monitoring data of each target object is obtained through processing, so that the rationality of the fatty liver monitoring data of each target object can be clearly known.

Description

Technical Field

[0001] The invention relates to the technical field of data processing, in particular to a data processing system for monitoring fatty liver in the metabolic process of type 2 diabetes. Background Art

[0002] At present, the number of patients with type 2 diabetes is increasing, and there is a close correlation between diabetes and fatty liver. As people's attention to health continues to increase, the demand for monitoring and processing of fatty liver-related data is growing. Only through more meticulous and rigorous processing can the relevant groups' needs for processing fatty liver data be fully guaranteed.

[0003] The prior art, such as the invention patent with publication number: CN114400085A, is a system for intelligent quantitative evaluation of fatty liver health status, including a patient user end, a doctor consultant end and a health data cloud platform; this invention provides a method and system for quantitatively evaluating fatty liver health status, and comprehensively evaluates the user's personal situation, physical indicators, diet quality and exercise quality, thereby helping the user to fully understand the current fatty liver health status.

[0004] The prior art, such as the invention patent with publication number: CN118553417A, is a fatty liver health management system and method based on lifestyle risk assessment, including: a standard database for storing healthy lifestyle data and physical examination data; a data collection module for collecting patients' physical examination data and lifestyle data, wherein the lifestyle data includes three days of lifestyle data obtained through a lifestyle questionnaire; a data analysis module for comparing the patient's physical examination data and lifestyle data with the physical examination data and lifestyle data in the standard database to obtain a physical examination data and lifestyle risk assessment report; a health management plan generation module for generating a first-stage multidimensional intervention plan and a first-stage expected value based on the lifestyle risk assessment report and the physical examination data, and the first-stage multidimensional intervention plan includes a medical prescription and a lifestyle medicine guidance plan.

[0005] It can be seen from the above scheme that the current processing of fatty liver monitoring data usually only focuses on quantitative data processing of fatty liver health status, or relatively simple analysis and processing of patients' physical examination data, and then derives fatty liver health status, while ignoring targeted data analysis of people with a high risk of fatty liver, namely patients with type 2 diabetes. For fatty liver monitoring data of type 2 diabetes, since the specific monitoring parameters involved are diverse and complex, simple processing cannot fully guarantee the comprehensiveness and accuracy of the processing of each fatty liver monitoring data. There may be a lag in data processing, which affects the accuracy of the fatty liver data processing results. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides a data processing system for monitoring fatty liver in the metabolic process of type 2 diabetes, which can effectively solve the problems involved in the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: The present invention provides a data processing system for monitoring fatty liver in the metabolic process of type 2 diabetes, including: a data acquisition module, used to record a number of type 2 diabetes people as target objects, and collect the basic feature data of each target object uploaded by the edge data transmission channel and the fatty liver monitoring data of each target object in the metabolic process.

[0008] The basic characteristic data processing module is used to input the basic characteristic data of each target object into the cloud processor for processing to obtain the fatty liver monitoring control data of each target object.

[0009] The fatty liver monitoring data processing module is used to process the fatty liver monitoring data of each target object in the metabolic process and the fatty liver monitoring control data of each target object to obtain the discrete coefficient corresponding to the fatty liver monitoring data of each target object.

[0010] The data processing and comprehensive output module is used to process the output display label corresponding to the fatty liver monitoring data of each target object according to the discrete coefficient corresponding to the fatty liver monitoring data of each target object, and output and display the fatty liver monitoring data of each target object based on the output display label.

[0011] As a preferred technical solution, the basic characteristic data of each target object includes the gender, age, height, weight and duration of various influencing behaviors of each target object.

[0012] As a preferred technical solution, the fatty liver monitoring control data of each target object is obtained, and the specific process is as follows: extract the basic indicator data corresponding to the sample groups of each gender stored in the database, and screen out the basic indicator data corresponding to the sample groups consistent with the gender of each target object, and record them as the sample basic indicator data of each target object.

[0013] The sample basic indicator data of each target object includes each fatty liver monitoring sample data of each sub-sample and a fatty liver monitoring parameter nomogram feature set of each sub-sample.

[0014] According to the basic characteristic data of each target object and the basic data of each sub-sample, a comparison process is performed to obtain the pre-evaluation embedding index between each target object and each sub-sample.

[0015] The pre-evaluated embedding index between each target object and each sub-sample is a numerical result of quantifying the basic feature data of each target object and the basic data of each sub-sample, and is used to characterize the degree of similarity and matching between the basic feature data of each target object and the corresponding basic data of each sub-sample.

[0016] Based on the pre-evaluation embedding index between each target object and each sub-sample, and extracting the pre-evaluation embedding index threshold stored in the database, each sub-sample basic data that is higher than or equal to the pre-evaluation embedding index threshold is marked as each valid sub-sample, thereby screening and counting the valid sub-sample fatty liver control data of each target object from the sub-sample fatty liver control data of each target object, and obtaining the fatty liver monitoring sample control data corresponding to each target object after mean processing.

[0017] The fatty liver monitoring sample control data includes mean value data of each fatty liver monitoring sample and a reference feature set of a fatty liver monitoring parameter nomogram.

[0018] As a preferred technical solution, the fatty liver monitoring data of each target object during the metabolic process includes each fatty liver monitoring mean parameter and a nomogram of each fatty liver monitoring parameter of each target object during the metabolic process.

[0019] As an optimal technical solution, the processing obtains the discrete coefficient corresponding to the fatty liver monitoring data of each target object. The specific process is as follows: based on the mean parameters of each fatty liver monitoring of each target object in the metabolic process and the mean data of each fatty liver monitoring sample, analysis and processing are performed to obtain the first discrete coefficient corresponding to the fatty liver monitoring data of each target object.

[0020] Based on the nomograms of fatty liver monitoring parameters of each target object during the metabolic process and the reference feature set of the nomograms of fatty liver monitoring parameters, the second discrete coefficient corresponding to the fatty liver monitoring data of each target object is obtained through analysis and processing.

[0021] Based on the first discrete coefficient corresponding to the fatty liver monitoring data of each target object and the second discrete coefficient corresponding to the fatty liver monitoring data of each target object, the discrete coefficient corresponding to the fatty liver monitoring data of each target object is obtained through comprehensive analysis and processing.

[0022] The dispersion coefficient corresponding to the fatty liver monitoring data of each target object is a numerical result of comprehensive quantification of the fatty liver monitoring data of each target object and the fatty liver monitoring sample control data, and is used to characterize the dispersion degree corresponding to the fatty liver monitoring data of each target object.

[0023] As a preferred technical solution, the specific analysis process of the first discrete coefficient corresponding to the fatty liver monitoring data of each target object is as follows: according to the mean data of each fatty liver monitoring parameter and the mean data of each fatty liver monitoring sample of each target object in the metabolic process, difference processing is performed to obtain the deviation value of each fatty liver monitoring mean parameter of each target object, and the allowable deviation value of each fatty liver monitoring mean parameter stored in the database is extracted, and the first discrete coefficient corresponding to the fatty liver monitoring data of each target object is obtained by comprehensive analysis and processing.

[0024] The first discrete coefficient corresponding to the fatty liver monitoring data of each target object is a numerical result of quantifying the deviation value of each fatty liver monitoring mean parameter and the allowable deviation value of each fatty liver monitoring mean parameter of each target object, and is used to characterize the degree of discreteness of the fatty liver monitoring parameters of each target object during the metabolic process.

[0025] As a preferred technical solution, the specific analysis process of the second discrete coefficient corresponding to the fatty liver monitoring data of each target object is as follows: based on the fatty liver monitoring parameter nomograms of each target object in the metabolic process, the feature set of each fatty liver monitoring parameter nomogram is extracted, wherein the feature set includes the peak value, valley value, peak-to-peak interval duration and kurtosis of each fatty liver monitoring parameter nomogram, and compared with the reference feature set of the fatty liver monitoring parameter nomogram to obtain the second discrete coefficient corresponding to the fatty liver monitoring data of each target object.

[0026] The fatty liver monitoring parameter nomogram reference feature set includes a reference peak value, a reference valley value, a reference peak-to-peak interval duration and a reference kurtosis of each fatty liver monitoring parameter sample nomogram.

[0027] The second discrete coefficient corresponding to the fatty liver monitoring data of each target object is a numerical result of quantifying the feature set of each fatty liver monitoring parameter nomogram and the reference feature set of the fatty liver monitoring parameter nomogram, and is used to characterize the degree of discreteness of each fatty liver monitoring parameter nomogram of each target object during the metabolic process.

[0028] As an optimal technical solution, the processing obtains the output display label corresponding to the fatty liver monitoring data of each target object. The specific processing process is as follows: according to the discrete coefficient corresponding to the fatty liver monitoring data of each target object, the data are arranged in order from high to low to obtain the arrangement order of the fatty liver monitoring data of each target object.

[0029] The arrangement order of the fatty liver monitoring data of each target object is used as the first output display label of the fatty liver monitoring data of each target object.

[0030] The discrete abnormality levels corresponding to each discrete coefficient interval stored in the database are extracted, and based on the discrete coefficient corresponding to the fatty liver monitoring data of each target object, the discrete level of the fatty liver monitoring data of each target object is matched.

[0031] The discrete level of the fatty liver monitoring data of each target object is used as the second output display label of the fatty liver monitoring data of each target object.

[0032] The first output display label of the fatty liver monitoring data of each target object and the second output display label of the fatty liver monitoring data of each target object are combined as the output display label corresponding to the fatty liver monitoring data of each target object.

[0033] As a preferred technical solution, the discrete coefficient corresponding to the fatty liver monitoring data of each target object is specifically formulated as follows:

[0034]

[0035] Among them, C i is the discrete coefficient corresponding to the fatty liver monitoring data of the i-th target object, A i is the first discrete coefficient corresponding to the fatty liver monitoring data of the i-th target object, B i is the second discrete coefficient corresponding to the fatty liver monitoring data of the i-th target object, α1 is the first discrete coefficient weight, α2 is the second discrete coefficient weight, i is the number of each target object, i=1,2,...,m, m is the number of target objects.

[0036] As a preferred technical solution, a data processing system for monitoring fatty liver in the metabolic process of type 2 diabetes also includes a data archiving module, which is used to archive the basic characteristic data of each target object and the fatty liver monitoring data of each target object in the metabolic process. The specific process is as follows: the basic characteristic data of each target object and the fatty liver monitoring data of each target object in the metabolic process are marked as the joint fatty liver data of each target object.

[0037] Extract the discrete threshold corresponding to the fatty liver monitoring data stored in the database.

[0038] If the discrete coefficient corresponding to the fatty liver monitoring data of a target object is greater than the discrete threshold corresponding to the fatty liver monitoring data, the fatty liver joint data of the target object is marked as hot data, and all hot data are counted and archived as a hot data set, thereby storing the hot data set locally.

[0039] If the discrete coefficient corresponding to the fatty liver monitoring data of a target object is less than or equal to the discrete threshold corresponding to the fatty liver monitoring data, the fatty liver joint data of the target object is marked as cold data, and all cold data are counted and archived as a cold data set, thereby storing the cold data set in the cloud.

[0040] Compared with the prior art, the embodiments of the present invention have at least the following beneficial effects:

[0041] (1) The present invention provides a fatty liver monitoring data processing system for type 2 diabetes during the metabolic process, which can concentrate resources to conduct in-depth analysis and processing of fatty liver monitoring data of the type 2 diabetes group, and is more accurate in the analysis and processing of fatty liver monitoring data.

[0042] (2) The present invention obtains the discrete coefficient corresponding to the fatty liver monitoring data of each target object through processing, which can clearly understand the degree of difference between the fatty liver data of each target object and the overall sample data, which helps to more deeply grasp the characteristics of the fatty liver data of the target object and improve the efficiency and accuracy of fatty liver monitoring data processing.

[0043] (3) The present invention can intuitively present the relative position of the fatty liver monitoring data of each target object by processing the output display label corresponding to the fatty liver monitoring data of each target object. At the same time, the relevant personnel can quickly understand the difference between the fatty liver monitoring data of different target objects and the fatty liver monitoring data of normal samples, and can clearly understand the discrete level of the fatty liver monitoring data of each target object, thereby improving the accuracy and effectiveness of data analysis.

[0044] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a schematic diagram of system module connection of the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] See also Figure 1As shown, an embodiment of the present invention provides a data processing system for monitoring fatty liver in the metabolic process of type 2 diabetes, including: a data acquisition module, used to record a number of type 2 diabetes people as target objects, and collect basic feature data of each target object uploaded by an edge data transmission channel and fatty liver monitoring data of each target object in the metabolic process.

[0048] It should be understood that the edge data transmission channel refers to a communication path connecting the data acquisition terminal and the data processing center, which is used to quickly and efficiently transmit the basic feature data and fatty liver monitoring data from each target object. It can receive data collected by various sensors, monitoring equipment, etc. in real time, and transmit the data to the central server for analysis and processing with low latency.

[0049] In this embodiment, the basic characteristic data of each target object includes the gender, age, height, weight and duration of various influencing behaviors of each target object.

[0050] It should be noted that the duration of various influencing behaviors refers to the length of time that the target object's behaviors that may affect the formation of fatty liver last, for example, the duration of lack of exercise, the duration of smoking, etc. The duration of these behaviors is closely related to the fatty liver monitoring data of the target object. In this embodiment, the duration of various influencing behaviors refers to the years of smoking and drinking.

[0051] The basic characteristic data processing module is used to input the basic characteristic data of each target object into the cloud processor for processing to obtain the fatty liver monitoring control data of each target object.

[0052] In this embodiment, the fatty liver monitoring control data of each target object is obtained, and the specific process is as follows: the basic indicator data corresponding to the sample groups of each gender stored in the database are extracted, and the basic indicator data corresponding to the sample groups consistent with the gender of each target object are screened out, and recorded as the sample basic indicator data of each target object.

[0053] It should be noted that the database is used to store reference indicator data, and the reference indicator data includes first reference indicator data, second reference indicator data and third reference indicator data.

[0054] The first reference indicator data include basic indicator data corresponding to each gender sample group, allowable deviation values ​​of each fatty liver monitoring mean parameter, and discrete abnormality levels corresponding to each discrete coefficient interval.

[0055] The second reference indicator data includes a pre-evaluation embedding index threshold and a discrete threshold corresponding to fatty liver monitoring data.

[0056] The third reference indicator data include age weight, body mass index weight, smoking years weight and drinking years weight, peak value weight, valley value weight, peak-to-peak interval duration weight and kurtosis weight, as well as first discrete coefficient weight and second discrete coefficient weight.

[0057] The sample basic indicator data of each target object includes each fatty liver monitoring sample data of each sub-sample and a fatty liver monitoring parameter nomogram feature set of each sub-sample.

[0058] According to the basic characteristic data of each target object and the basic data of each sub-sample, a comparison process is performed to obtain the pre-evaluation embedding index between each target object and each sub-sample.

[0059] The basic data of each subsample include age, body mass index, years of smoking and years of drinking.

[0060] It should be noted that the body mass index of each subsample refers to the weight of each subsample divided by the square of the height.

[0061] The pre-evaluation embedding index between each target object and each sub-sample is a numerical result of quantifying the basic feature data of each target object and the basic data of each sub-sample, and is used to characterize the degree of similarity and matching between the basic feature data of each target object and the corresponding basic data of each sub-sample.

[0062] In a specific embodiment, the pre-evaluation embedding index between each target object and each sub-sample is specifically formulated as follows:

[0063] Among them, γ it is the pre-evaluated embedding index between the i-th target object and the t-th subsample, θ i is the age of the i-th target object, θ t is the age of the t-th subsample, is the height of the i-th target object, ω i is the weight of the i-th target object, ε t is the body mass index of the t-th subsample, ρ i is the smoking years of the i-th target object, ρ t is the smoking years of the t-th sub-sample, τ i is the drinking years of the i-th target object, τ t is the drinking years of the t-th sub-sample, y1 is the age weight, y2 is the body mass index weight, y3 is the smoking years weight, y4 is the drinking years weight, i is the number of each target object, i = 1, 2, ..., m, m is the number of target objects, t is the number of each sub-sample, t = 1, 2, ..., x, x is the number of sub-samples, and e is a natural constant.

[0064] It should be noted that the age weight, body mass index weight, smoking years weight and drinking years weight all have a value range between 0 and 1. In this embodiment, the age weight is the age weight preset in the database, which represents the numerical value of the influence of age on the pre-assessed embedding index between each target object and each sub-sample. The body mass index weight is the body mass index weight preset in the database, which represents the numerical value of the influence of body mass index on the pre-assessed embedding index between each target object and each sub-sample. The smoking years weight is the smoking years weight preset in the database, which represents the numerical value of the influence of smoking years on the pre-assessed embedding index between each target object and each sub-sample. The drinking years weight is the drinking years weight preset in the database. The drinking years weight represents the numerical value of the influence of drinking years on the pre-assessed embedding index between each target object and each sub-sample. When used, the preset age weight, body mass index weight, smoking years weight and drinking years weight can be directly obtained from the database, and the corresponding relationship can be a pre-set mapping relationship. For example, age, body mass index, smoking years and drinking years respectively form a mapping set with the preset age weight, body mass index weight, smoking years weight and drinking years weight in the database, and the real-time age, body mass index, smoking years and drinking years are respectively input into the mapping set to obtain age weight, body mass index weight, smoking years weight and drinking years weight, and the mapping relationship is one-to-one correspondence.

[0065] It should also be noted that in this embodiment, the pre-evaluation embedding index between each target object and each sub-sample is obtained by processing according to the age, height, weight and duration of various influencing behaviors of each target object. This is based on the mutual influence between these parameters. For example, with age, metabolism gradually slows down, which may lead to weight gain. Higher height may also mean heavier weight. At the same time, longer years of smoking and drinking may also affect metabolism and thus weight. When obtaining the pre-evaluation embedding index between each target object and each sub-sample, it is necessary to fully consider the interaction between these parameters in order to more accurately evaluate the similarity between the target object and each sub-sample.

[0066] Based on the pre-evaluation embedding index between each target object and each sub-sample, and extracting the pre-evaluation embedding index threshold stored in the database, each sub-sample basic data that is higher than or equal to the pre-evaluation embedding index threshold is marked as each valid sub-sample, thereby screening and counting the valid sub-sample fatty liver control data of each target object from the sub-sample fatty liver control data of each target object, and obtaining the fatty liver monitoring sample control data corresponding to each target object after mean processing.

[0067] It should be understood that when the pre-evaluation embedding index between each target object and each sub-sample is less than the pre-evaluation embedding index threshold, it means that the fatty liver monitoring data of each target object is poorly correlated with the fatty liver monitoring data of the sub-sample, and the sub-sample is not of reference value. When the pre-evaluation embedding index between each target object and each sub-sample is greater than or equal to the pre-evaluation embedding index threshold, it means that the fatty liver monitoring data of each target object is highly similar to the fatty liver monitoring data of the sub-sample and has a greater reference value. The sub-sample can be marked as a valid sub-sample to provide accurate reference data for subsequent analysis and processing.

[0068] It should be noted that the mean processing obtains the fatty liver monitoring sample control data corresponding to each target object. The specific process is: according to the fatty liver control data of each valid sub-sample of each target object, wherein the fatty liver control data of each valid sub-sample includes the fatty liver monitoring sample data of each valid sub-sample and the peak value, valley value, peak-to-peak interval duration and kurtosis of each fatty liver monitoring parameter nomogram, the fatty liver monitoring sample data of each valid sub-sample is respectively processed by mean to obtain the mean data of each fatty liver detection sample, and the mean data of each fatty liver detection sample are integrated to obtain the fatty liver monitoring sample control data corresponding to each target object. By way of example, if a certain fatty liver monitoring sample data of each valid sub-sample of a certain target object is liver fat content, the mean value of the sample liver fat content of the target object is obtained by mean processing, and in this way, the mean data of each fatty liver monitoring sample corresponding to each target object is obtained by analyzing one by one.

[0069] As a further example, the method for obtaining the reference feature set of the fatty liver monitoring parameter nomogram is as follows: the reference feature set of the fatty liver monitoring parameter nomogram includes the reference peak value, reference valley value, reference peak-to-peak interval duration and reference kurtosis of each fatty liver monitoring parameter sample nomogram, and taking the peak value of the liver fat content sample nomogram of each valid sub-sample of a certain target object as an example, the peak values ​​of the liver fat content sample nomogram of each valid sub-sample of the target object are counted and averaged to obtain the reference peak value of the liver fat content sample nomogram of the target object, and in this way, the reference feature set of the fatty liver monitoring parameter nomogram is obtained by analyzing them one by one.

[0070] The fatty liver monitoring sample control data includes the mean data of each fatty liver monitoring sample and the reference feature set of the fatty liver monitoring parameter nomogram.

[0071] The fatty liver monitoring data processing module is used to process the fatty liver monitoring data of each target object in the metabolic process and the fatty liver monitoring control data of each target object to obtain the discrete coefficient corresponding to the fatty liver monitoring data of each target object.

[0072] In this embodiment, the fatty liver monitoring data of each target object during the metabolic process includes each fatty liver monitoring mean parameter and a nomogram of each fatty liver monitoring parameter of each target object during the metabolic process.

[0073] It should be understood that the mean parameters for fatty liver monitoring refer to the average values ​​reflecting the fatty liver status of each target object calculated by a specific detection method during the fatty liver monitoring process. These parameters include but are not limited to the percentage of liver fat content, total cholesterol content, and glycosylated total hemoglobin content. These measured mean parameters for fatty liver monitoring can reflect the fatty liver status of the target object from different aspects, and provide specific data basis for further analysis and evaluation of the fatty liver status of the target object. In this embodiment, the mean parameters for fatty liver monitoring refer to the mean liver fat content, the mean liver cholesterol content, the mean glycosylated total hemoglobin content, and the mean 25-hydroxyvitamin D content.

[0074] It should be noted that the specific detection method refers to a special monitoring method for various parameters reflecting the condition of fatty liver. For example, the percentage of liver fat content can be calculated through magnetic resonance spectroscopy analysis.

[0075] In this embodiment, the discrete coefficient corresponding to the fatty liver monitoring data of each target object is obtained by processing, and the specific process is as follows: based on the mean parameters of each fatty liver monitoring of each target object during the metabolic process and the mean data of each fatty liver monitoring sample, the first discrete coefficient corresponding to the fatty liver monitoring data of each target object is obtained by analysis and processing.

[0076] In this embodiment, the specific analysis process of the first discrete coefficient corresponding to the fatty liver monitoring data of each target object is as follows: according to the mean data of each fatty liver monitoring parameter and the mean data of each fatty liver monitoring sample of each target object in the metabolic process, difference processing is performed to obtain the deviation value of each fatty liver monitoring mean parameter of each target object, and the allowable deviation value of each fatty liver monitoring mean parameter stored in the database is extracted, and the first discrete coefficient corresponding to the fatty liver monitoring data of each target object is obtained through comprehensive analysis and processing.

[0077] Exemplarily, when the mean parameter of fatty liver monitoring of the target object during the metabolic process is the mean liver fat content, the liver fat content deviation value of the target object refers to the mean liver fat content of the target object during the metabolic process minus the reference liver fat content.

[0078] The first discrete coefficient corresponding to the fatty liver monitoring data of each target object is a numerical result of quantifying the deviation value of each fatty liver monitoring mean parameter and the allowable deviation value of each fatty liver monitoring mean parameter of each target object, and is used to characterize the degree of discreteness of the fatty liver monitoring parameters of each target object during the metabolic process.

[0079] In a specific embodiment, the first discrete coefficient corresponding to the fatty liver monitoring data of each target object is specifically expressed as follows:

[0080] Among them, A i is the first discrete coefficient corresponding to the fatty liver monitoring data of the i-th target object, a ij is the jth measured mean parameter deviation of fatty liver monitoring for the i-th target object, Δa j is the allowable deviation value of the j-th fatty liver monitoring mean parameter, i is the number of each target object, i=1,2,...,m, m is the number of target objects, j is the number of each fatty liver monitoring mean parameter, j=1,2,...,n, n is the number of measured fatty liver monitoring mean parameters.

[0081] In this embodiment, by analyzing the first discrete coefficient corresponding to the fatty liver monitoring data of each target object, the degree of deviation between the mean parameter of fatty liver monitoring of the target object during the metabolic process and the mean data of each fatty liver monitoring sample can be clearly reflected, making the fatty liver monitoring data of the object more intuitive.

[0082] Based on the nomograms of fatty liver monitoring parameters of each target object during the metabolic process and the reference feature set of the nomograms of fatty liver monitoring parameters, the second discrete coefficient corresponding to the fatty liver monitoring data of each target object is obtained through analysis and processing.

[0083] In this embodiment, the nomogram of each fatty liver monitoring parameter of each target object during the metabolic process is a chart used to intuitively display the changing trend of the fatty liver monitoring parameters of the target object. It presents different fatty liver monitoring parameters, such as liver fat content, certain specific liver enzyme indicators, blood lipid indicators, etc. in a graphical manner. For example, in this embodiment, the liver fat content nomogram has one coordinate axis representing time, which is used to show the changes in liver fat content over time, and the other coordinate axis represents the specific numerical range of fatty liver content. By drawing a curve on the nomogram, the values ​​of liver fat content at different time points can be clearly seen.

[0084] In this embodiment, the specific analysis process of the second discrete coefficient corresponding to the fatty liver monitoring data of each target object is as follows: based on the fatty liver monitoring parameter nomograms of each target object in the metabolic process, the feature set of each fatty liver monitoring parameter nomogram is extracted, wherein the feature set includes the peak value, valley value, peak-to-peak interval duration and kurtosis of each fatty liver monitoring parameter nomogram, and compared with the reference feature set of the fatty liver monitoring parameter nomogram to obtain the second discrete coefficient corresponding to the fatty liver monitoring data of each target object.

[0085] It should be understood that the peak-to-peak interval duration of each fatty liver monitoring parameter nomogram refers to the length of time between the maximum and minimum values ​​of each fatty liver monitoring mean parameter. The peak-to-peak interval duration can reflect the fluctuation range of each fatty liver monitoring parameter over a period of time. For example, if the peak-to-peak interval duration is short, it means that the fatty liver monitoring parameter has experienced a change from the maximum value to the minimum value in a short period of time. The change range of this parameter is large and may require further monitoring. On the contrary, if the peak-to-peak interval duration is long, it means that the change of this parameter is relatively stable.

[0086] It is also necessary to understand that the kurtosis of each fatty liver monitoring parameter nomogram can reflect the data distribution pattern in the nomogram, which describes the peak degree or flatness of the data distribution. Specifically, if the kurtosis is high, it means that the data distribution is more concentrated in the center and the tail is relatively heavy, showing a peak shape. If the kurtosis is low, the data distribution is relatively flat and the tail is lighter. In the fatty liver monitoring mean parameter nomogram, the kurtosis can help analysts understand the distribution characteristics of the data and determine whether there are abnormal values ​​or special distribution patterns in the fatty liver monitoring data. In a specific embodiment, professional statistical software, such as Statistical Analysis System, etc., can be used to input the fatty liver monitoring data of each target object into the software to calculate the kurtosis value.

[0087] The fatty liver monitoring parameter nomogram reference feature set includes a reference peak value, a reference valley value, a reference peak-to-peak interval duration and a reference kurtosis of each fatty liver monitoring parameter nomogram.

[0088] It should be noted that the reference feature set of the fatty liver monitoring parameter nomogram stored in the database is obtained by averaging the historical data of the peak value, valley value, peak-to-peak interval duration and kurtosis of each fatty liver monitoring parameter nomogram before establishing the database.

[0089] The second discrete coefficient corresponding to the fatty liver monitoring data of each target object is the numerical result of quantifying the feature set of each fatty liver monitoring parameter nomogram and the reference feature set of the fatty liver monitoring parameter nomogram, and is used to characterize the degree of discreteness of each fatty liver monitoring parameter nomogram of each target object during the metabolic process.

[0090] In a specific embodiment, the second discrete coefficient corresponding to the fatty liver monitoring data of each target object is specifically expressed as follows:

[0091]

[0092] Among them, B i is the second discrete coefficient corresponding to the fatty liver monitoring data of the i-th target object, b ikis the peak value of the kth fatty liver monitoring parameter nomogram of the i-th target object, Δb k is the reference peak value of the kth fatty liver monitoring parameter nomogram, c ik is the valley value of the kth fatty liver monitoring parameter nomogram of the i-th target subject, Δc k is the reference valley value of the kth fatty liver monitoring parameter nomogram, d ik is the peak-to-peak interval duration of the kth fatty liver monitoring parameter nomogram of the i-th target object, Δd k is the reference peak-to-peak interval length of the kth fatty liver monitoring parameter nomogram, f ik is the kurtosis of the kth fatty liver monitoring parameter nomogram of the i-th target subject, Δf k is the reference kurtosis of the kth fatty liver monitoring parameter nomogram, β1 is the peak weight, β2 is the valley weight, β3 is the peak-to-peak interval duration weight, β4 is the kurtosis weight, i is the number of each target object, i=1,2,...,m, m is the number of target objects, k is the number of the nomogram corresponding to each fatty liver monitoring parameter, k=1,2,...,s, s is the number of nomograms corresponding to the fatty liver monitoring parameter, and e is a natural constant.

[0093] It should be noted that the peak weight, valley weight, peak-to-peak interval duration weight and kurtosis weight all have value ranges between 0 and 1. In this embodiment, the peak weight is the peak weight preset in the database, which indicates the numerical value of the influence of the peak on the second discrete coefficient corresponding to the fatty liver monitoring data of the target object. The valley weight is the valley weight preset in the database, which indicates the numerical value of the influence of the valley on the second discrete coefficient corresponding to the fatty liver monitoring data of the target object. The peak-to-peak interval duration weight is the peak-to-peak interval duration weight preset in the database, which indicates the numerical value of the influence of the peak-to-peak interval duration on the second discrete coefficient corresponding to the fatty liver monitoring data of the target object. The kurtosis weight is the peak weight preset in the database. The preset kurtosis weight in represents the numerical value of the influence degree of kurtosis on the second discrete coefficient corresponding to the fatty liver monitoring data of the target object. When used, the preset peak weight, valley weight, peak-to-peak interval duration weight and kurtosis weight can be directly obtained from the database, and the corresponding relationship can be a pre-set mapping relationship. For example, the peak value, valley value, peak-to-peak interval duration and kurtosis are respectively mapped with the peak weight, valley weight, peak-to-peak interval duration weight and kurtosis weight preset in the database to form a mapping set, and the real-time peak value, valley value, peak-to-peak interval duration and kurtosis are respectively input into the mapping set to obtain the peak weight, valley weight, peak-to-peak interval duration weight and kurtosis weight, and the mapping relationship is one-to-one correspondence.

[0094] It should also be noted that in this embodiment, the second discrete coefficient corresponding to the fatty liver monitoring data of the target object is obtained by processing the peak value, valley value, peak-to-peak value interval time and kurtosis of the fatty liver monitoring parameter nomogram, taking into account the mutual influence between these parameters. For example, when the peak value of the fatty liver monitoring parameter nomogram is higher, it means that the data has a larger value at this point, which means that in certain specific cases, the fatty liver monitoring parameter value of the target object is at a higher level. If the valley value is also high at this time, it means that the fluctuation range of the overall data is larger, which increases the difficulty of judging the fatty liver condition of the target object. When the peak-to-peak value interval time is longer, it means that the change process from the valley value to the peak value is relatively slow, and the fluctuation range of the data is relatively small. Conversely, if the peak-to-peak value interval time is short, it means that the data rises quickly from the valley value to the peak value in a shorter period of time, and the fluctuation change The amplitude is large, and the kurtosis reflects the peak degree of the data distribution. The high kurtosis means that the data is concentrated in the center and has a thick tail, which may imply that there are some special circumstances in the fatty liver monitoring parameters of the target object, such as the possibility of extreme values. If the kurtosis is combined with the peak value, trough value, and peak-to-peak interval duration, when the kurtosis is high and the peak value is also high and the trough value is low, it means that the data distribution is more concentrated in the high-value area and has a large gap with the low-value area. On the contrary, if the kurtosis is low and the peak-to-peak interval duration is long, it may indicate that the data distribution is relatively flat, and the fatty liver monitoring parameters of the target object are relatively stable. The second discrete coefficient corresponding to the fatty liver monitoring data of the target object obtained by comprehensively considering these parameters can more comprehensively reflect the characteristics and distribution of the fatty liver monitoring parameters of the target object, and provide an important reference for further analysis and diagnosis of the fatty liver condition of the target object.

[0095] Based on the first discrete coefficient corresponding to the fatty liver monitoring data of each target object and the second discrete coefficient corresponding to the fatty liver monitoring data of each target object, the discrete coefficient corresponding to the fatty liver monitoring data of each target object is obtained through comprehensive analysis and processing.

[0096] The dispersion coefficient corresponding to the fatty liver monitoring data of each target object is a numerical result of comprehensive quantification of the fatty liver monitoring data of each target object and the fatty liver monitoring sample control data, and is used to characterize the dispersion degree corresponding to the fatty liver monitoring data of each target object.

[0097] In a specific embodiment, the discrete coefficient corresponding to the fatty liver monitoring data of each target object is specifically expressed as follows:

[0098] Among them, C i is the discrete coefficient corresponding to the fatty liver monitoring data of the i-th target object, A i is the first discrete coefficient corresponding to the fatty liver monitoring data of the i-th target object, B iis the second discrete coefficient corresponding to the fatty liver monitoring data of the i-th target object, α1 is the first discrete coefficient weight, α2 is the second discrete coefficient weight, i is the number of each target object, i=1,2,...,m, m is the number of target objects.

[0099] It should be noted that the value range of the first discrete coefficient weight and the second discrete coefficient weight is between 0 and 1. In this embodiment, the first discrete coefficient weight is the first discrete coefficient weight preset in the database, which represents the numerical value of the influence of the first discrete coefficient on the discrete coefficient corresponding to the fatty liver monitoring data of the target object. The second discrete coefficient weight is the second discrete coefficient weight preset in the database, which represents the numerical value of the influence of the second discrete coefficient on the discrete coefficient corresponding to the fatty liver monitoring data of the target object. When used, the preset first discrete coefficient weight and the second discrete coefficient weight can be directly obtained from the database, and the corresponding relationship can be a pre-set mapping relationship. For example, the first discrete coefficient and the second discrete coefficient respectively form a mapping set with the first discrete coefficient weight and the second discrete coefficient weight preset in the database, and the real-time first discrete coefficient and the second discrete coefficient are respectively input into the mapping set to obtain the first discrete coefficient weight and the second discrete coefficient weight, wherein the mapping relationship is one-to-one correspondence.

[0100] It should also be noted that in this embodiment, the discrete coefficient corresponding to the fatty liver monitoring data of each target object is obtained by comprehensive analysis and processing based on the first discrete coefficient corresponding to the fatty liver monitoring data of each target object and the second discrete coefficient corresponding to the fatty liver monitoring data of each target object, taking into account the mutual influence between these parameters. For example, when the first discrete coefficient is large, it means that the deviation value of the measured fatty liver monitoring mean parameter of the target object is more significant relative to the reference difference value, which may reflect that the fatty liver monitoring result of the target object is significantly different from the normal situation, which may suggest that its fatty liver condition is more special or unstable. If the second discrete coefficient is also large at this time, it indicates that the nomogram of each fatty liver monitoring parameter of the target object deviates greatly from the reference value in terms of peak value, valley value, peak-to-peak interval duration and kurtosis. For example, a large difference in peak value may indicate that the fatty liver monitoring value of the target object is abnormally high under certain specific circumstances, and the difference in valley value may affect the overall distribution range of the data. The change in the peak-to-peak interval duration reflects the different fluctuation amplitudes of the data. When the first dispersion coefficient is large, it means that the deviation value of the measured fatty liver monitoring mean parameter of the target object is large relative to the reference difference. If the mean parameter deviation is large, the peak value, valley value, peak-to-peak interval duration and kurtosis of the fatty liver monitoring parameter nomogram relative to the reference value may also change. For example, if the mean parameter is too high, the peak value may also be relatively high, thereby increasing the second dispersion coefficient. The dispersion coefficient corresponding to the fatty liver monitoring data of each target object obtained by comprehensively considering these two dispersion coefficients can more comprehensively reflect the characteristics of the target object's fatty liver monitoring data and the degree of difference from the reference value, and provide a more accurate analysis and processing method for accurately analyzing and diagnosing the target object's fatty liver monitoring data.

[0101] Taking the four groups of different target objects involved in this embodiment as an example, the first discrete coefficient weight is defined as 0.6, and the second discrete coefficient weight is defined as 0.4. On the basis that the first discrete coefficient corresponding to the fatty liver monitoring data of the target object and the second discrete coefficient corresponding to the fatty liver monitoring data of the target object are different, the discrete coefficient corresponding to the fatty liver monitoring data of the target object obtained by processing is as follows:

[0102] Table 1 Dispersion coefficient corresponding to the fatty liver monitoring data of the target object

[0103]

[0104]

[0105] Combined with the above table, it can be seen that the dispersion coefficient corresponding to the fatty liver monitoring data of the fourth group of target objects is at the highest value, indicating that compared with other groups, the fatty liver monitoring parameters of the fourth group of target objects have a larger gap with the reference monitoring data, and the fatty liver monitoring data of the target objects need to be more closely monitored and analyzed in depth to ensure the accuracy of their fatty liver monitoring data.

[0106] In this example, by analyzing the discrete coefficient corresponding to the fatty liver monitoring data of each target object, the difference between the fatty liver monitoring data of the target object and the sample fatty liver monitoring data can be clearly shown, and at the same time, clear data support can be provided for the subsequent analysis and processing of fatty liver monitoring data.

[0107] The data processing and comprehensive output module is used to process the output display label corresponding to the fatty liver monitoring data of each target object according to the discrete coefficient corresponding to the fatty liver monitoring data of each target object, and output and display the fatty liver monitoring data of each target object based on the output display label.

[0108] In this embodiment, the output display label corresponding to the fatty liver monitoring data of each target object is processed, and the specific processing process is as follows: according to the discrete coefficient corresponding to the fatty liver monitoring data of each target object, the data are arranged in order from high to low to obtain the arrangement order of the fatty liver monitoring data of each target object.

[0109] The arrangement order of the fatty liver monitoring data of each target object is used as the first output display label of the fatty liver monitoring data of each target object.

[0110] The discrete abnormality levels corresponding to each discrete coefficient interval stored in the database are extracted, and based on the discrete coefficient corresponding to the fatty liver monitoring data of each target object, the discrete level of the fatty liver monitoring data of each target object is matched.

[0111] The discrete level of the fatty liver monitoring data of each target object is used as the second output display label of the fatty liver monitoring data of each target object.

[0112] The first output display label of the fatty liver monitoring data of each target object and the second output display label of the fatty liver monitoring data of each target object are combined as the output display label corresponding to the fatty liver monitoring data of each target object.

[0113] Exemplarily, when the arrangement order of the discrete coefficient corresponding to the fatty liver monitoring data of a target object is 3 and the discrete level of its fatty liver monitoring data is high, the output display label corresponding to the fatty liver monitoring data of the target object is "3", "high".

[0114] In a specific embodiment, the fatty liver monitoring data processing system for type 2 diabetes during the metabolic process also includes a data archiving module, which is used to archive the basic characteristic data of each target object and the fatty liver monitoring data of each target object during the metabolic process. The specific process is as follows: the basic characteristic data of each target object and the fatty liver monitoring data of each target object during the metabolic process are marked as the fatty liver joint data of each target object.

[0115] Extract the discrete threshold corresponding to the fatty liver monitoring data stored in the database.

[0116] If the discrete coefficient corresponding to the fatty liver monitoring data of a target object is greater than the discrete threshold corresponding to the fatty liver monitoring data, the fatty liver joint data of the target object is marked as hot data, and all hot data are counted and archived as a hot data set, thereby storing the hot data set locally.

[0117] If the discrete coefficient corresponding to the fatty liver monitoring data of a target object is less than or equal to the discrete threshold corresponding to the fatty liver monitoring data, the fatty liver joint data of the target object is marked as cold data, and all cold data are counted and archived as a cold data set, thereby storing the cold data set in the cloud.

[0118] It should be noted that the fatty liver monitoring data processing system for type 2 diabetes in the metabolic process can be connected to different types of liver detection instruments (such as ultrasound equipment, magnetic resonance imaging equipment, etc.), blood testing equipment, hospital information systems (HIS), electronic medical record systems (EMR), etc. The output data of the equipment is analyzed and processed, and the fatty liver monitoring data and the basic characteristic data of the target object are accurately imported into this system. At the same time, the data is synchronized with the hospital's database regularly to obtain the latest patient basic characteristic data and fatty liver monitoring data. For the data archived in this system, corresponding modifications and supplements are made according to the update of the hospital data to maintain the accuracy and completeness of the data.

[0119] In a specific embodiment, by conducting in-depth statistical analysis on a large amount of fatty liver monitoring data stored in the system, it can provide valuable resources for medical research and provide a scientific basis for relevant personnel to explore the pathogenesis, risk factors and treatment effects of fatty liver in patients with type 2 diabetes.

[0120] It should be understood that when the discrete coefficient corresponding to the fatty liver monitoring data of a target object is greater than the discrete threshold corresponding to the fatty liver monitoring data, it means that the fatty liver monitoring data of the target object is significantly different from the reference data, and more in-depth monitoring and analysis are needed. In order to facilitate the subsequent processing of the data by relevant personnel, the data can be stored locally. When the discrete coefficient corresponding to the fatty liver monitoring data of a target object is less than or equal to the discrete threshold corresponding to the fatty liver monitoring data, it means that the fatty liver monitoring data of the target object is slightly different from the reference data, that is, the fatty liver monitoring data of the target object is relatively normal, and the demand for subsequent monitoring and analysis is relatively small. In order to save storage resources, it can be compressed and stored in the cloud.

[0121] It should be noted that this system needs to be connected to the Internet, and can be connected to the following systems:

[0122] Liver testing equipment: such as ultrasound equipment, magnetic resonance imaging equipment, etc. By connecting to these devices, data related to liver testing can be obtained, including but not limited to average values ​​reflecting fatty liver conditions such as liver fat content percentage, total cholesterol content, and glycosylated total hemoglobin content (i.e., various fatty liver monitoring mean parameters), as well as liver fat content nomograms, certain specific liver enzyme index nomograms, blood lipid index nomograms, etc. (i.e., various fatty liver monitoring parameter nomograms of each target object during the metabolic process).

[0123] Blood testing equipment: obtains data related to blood testing, such as the content of some components in the blood. These data can be used as basic characteristic data or data to assist in determining the condition of fatty liver.

[0124] Hospital information system: obtains the patient's basic information data, including the patient's basic personal information (gender, age, etc.) and medical-related information, among which gender, age, height, weight and the duration of various influencing behaviors are used as basic characteristic data.

[0125] Electronic medical record system (EMR): Obtain detailed medical record information of patients, including medical history, treatment process records, etc. These data can be used as basic characteristic data or data to assist in analyzing fatty liver conditions.

[0126] It should also be noted that the system interface settings are as follows:

[0127] Interface with liver detection instrument: used to receive fatty liver monitoring data output by the liver detection instrument, including the data formats such as the mean parameters and parameter nomograms mentioned above.

[0128] Interface with blood testing equipment: Receives blood testing data output by the blood testing equipment. The data format depends on different testing items.

[0129] Interface with hospital information system (HIS): Obtain basic patient information in the hospital information system, and the data format complies with the standard format of the hospital information system.

[0130] Interface with the electronic medical record system (EMR): Obtain patient medical record information in the electronic medical record system, and the data format complies with the standard format of the electronic medical record system.

[0131] Through the above networking and interface settings, the data sets obtained by this system include the following categories:

[0132] Basic feature data set: including the patient's gender, age, height, weight and duration of various influencing behaviors (such as years of smoking, years of drinking, etc.), as well as the patient's basic information and medical record information obtained from the hospital information system (HIS) and electronic medical record system (EMR).

[0133] Fatty liver monitoring data set: including the mean parameters of fatty liver monitoring obtained from liver detection instruments and the nomograms of fatty liver monitoring parameters of each target object during the metabolic process, as well as related auxiliary judgment data obtained from blood testing equipment.

[0134] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0135] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that technicians in the relevant technical field can understand and use the present invention well. As long as they do not deviate from the structure of the present invention or exceed the scope defined by the present invention, they should all belong to the protection scope of the present invention.

Claims

1. A data processing system for monitoring fatty liver in the metabolic process of type 2 diabetes, characterized by: include: A data collection module is used to record a number of people with type 2 diabetes as target objects, and collect basic characteristic data of each target object uploaded by the edge data transmission channel and fatty liver monitoring data of each target object during the metabolic process; A basic characteristic data processing module is used to input the basic characteristic data of each target object into the cloud processor for processing to obtain fatty liver monitoring control data of each target object; A fatty liver monitoring data processing module is used to process the fatty liver monitoring data of each target object in the metabolic process and the fatty liver monitoring control data of each target object to obtain a discrete coefficient corresponding to the fatty liver monitoring data of each target object; The data processing and comprehensive output module is used to process the output display label corresponding to the fatty liver monitoring data of each target object according to the discrete coefficient corresponding to the fatty liver monitoring data of each target object, and output and display the fatty liver monitoring data of each target object based on the output display label.

2. The fatty liver monitoring data processing system for type 2 diabetes in the metabolic process according to claim 1, characterized in that: The basic characteristic data of each target object include the gender, age, height, weight and duration of various influencing behaviors of each target object.

3. The fatty liver monitoring data processing system for type 2 diabetes in the metabolic process according to claim 1, characterized in that: The specific process of obtaining the fatty liver monitoring control data of each target object is as follows: Extract the basic indicator data corresponding to the sample groups of each gender stored in the database, and screen out the basic indicator data corresponding to the sample groups consistent with the gender of each target object, and record them as the sample basic indicator data of each target object; The sample basic index data of each target object includes each fatty liver monitoring sample data of each sub-sample and a fatty liver monitoring parameter nomogram feature set of each sub-sample; According to the basic characteristic data of each target object and the basic data of each sub-sample, a comparison process is performed to obtain a pre-assessed embedding index between each target object and each sub-sample; The pre-assessed embedding index between each target object and each sub-sample is a numerical result of quantifying the basic feature data of each target object and the basic data of each sub-sample, and is used to characterize the similarity and matching degree between the basic feature data of each target object and the corresponding basic data of each sub-sample; Based on the pre-assessment embedding index between each target object and each sub-sample, and extracting the pre-assessment embedding index threshold stored in the database, each sub-sample basic data that is higher than or equal to the pre-assessment embedding index threshold is marked as each valid sub-sample, thereby screening and counting each valid sub-sample fatty liver control data of each target object from each sub-sample fatty liver control data of each target object, and obtaining the fatty liver monitoring sample control data corresponding to each target object through mean processing; The fatty liver monitoring sample control data includes mean value data of each fatty liver monitoring sample and a reference feature set of fatty liver monitoring parameter nomograms.

4. The fatty liver monitoring data processing system for type 2 diabetes in the metabolic process according to claim 3, characterized in that: The fatty liver monitoring data of each target object during the metabolic process includes each fatty liver monitoring mean parameter and a nomogram of each fatty liver monitoring parameter of each target object during the metabolic process.

5. The fatty liver monitoring data processing system for type 2 diabetes in the metabolic process according to claim 4, characterized in that: The processing obtains the discrete coefficient corresponding to the fatty liver monitoring data of each target object, and the specific process is as follows: Based on the mean value parameters of each fatty liver monitoring of each target object during the metabolic process and the mean value data of each fatty liver monitoring sample, analyzing and processing to obtain the first discrete coefficient corresponding to the fatty liver monitoring data of each target object; Based on the nomograms of the fatty liver monitoring parameters of each target object in the metabolic process and the reference feature set of the nomograms of the fatty liver monitoring parameters, analyzing and processing to obtain the second discrete coefficient corresponding to the fatty liver monitoring data of each target object; Based on the first discrete coefficient corresponding to the fatty liver monitoring data of each target object and the second discrete coefficient corresponding to the fatty liver monitoring data of each target object, a comprehensive analysis and processing is performed to obtain the discrete coefficient corresponding to the fatty liver monitoring data of each target object; The dispersion coefficient corresponding to the fatty liver monitoring data of each target object is a numerical result of comprehensive quantification of the fatty liver monitoring data of each target object and the fatty liver monitoring sample control data, and is used to characterize the dispersion degree corresponding to the fatty liver monitoring data of each target object.

6. The fatty liver monitoring data processing system for type 2 diabetes during the metabolic process according to claim 5, characterized in that: The specific analysis process of the first discrete coefficient corresponding to the fatty liver monitoring data of each target object is as follows: According to the mean value parameters of each fatty liver monitoring of each target object in the metabolic process and the mean data of each fatty liver monitoring sample, difference processing is performed to obtain the deviation value of each fatty liver monitoring mean parameter of each target object, and the allowable deviation value of each fatty liver monitoring mean parameter stored in the database is extracted, and the first discrete coefficient corresponding to the fatty liver monitoring data of each target object is obtained by comprehensive analysis and processing; The first discrete coefficient corresponding to the fatty liver monitoring data of each target object is a numerical result of quantifying the deviation value of each fatty liver monitoring mean parameter and the allowable deviation value of each fatty liver monitoring mean parameter of each target object, and is used to characterize the degree of discreteness of the fatty liver monitoring parameters of each target object during the metabolic process.

7. The fatty liver monitoring data processing system for type 2 diabetes during the metabolic process according to claim 5, characterized in that: The specific analysis process of the second discrete coefficient corresponding to the fatty liver monitoring data of each target object is as follows: Based on each fatty liver monitoring parameter nomogram of each target object in the metabolic process, extracting a feature set of each fatty liver monitoring parameter nomogram, wherein the feature set includes the peak value, valley value, peak-to-peak interval duration and kurtosis of each fatty liver monitoring parameter nomogram, and comparing with the reference feature set of the fatty liver monitoring parameter nomogram to obtain a second discrete coefficient corresponding to the fatty liver monitoring data of each target object; The fatty liver monitoring parameter nomogram reference feature set includes reference peak values, reference valley values, reference peak-to-peak interval durations, and reference kurtosis of each fatty liver monitoring parameter sample nomogram; The second discrete coefficient corresponding to the fatty liver monitoring data of each target object is a numerical result of quantifying the feature set of each fatty liver monitoring parameter nomogram and the reference feature set of the fatty liver monitoring parameter nomogram, and is used to characterize the degree of discreteness of each fatty liver monitoring parameter nomogram of each target object during the metabolic process.

8. The fatty liver monitoring data processing system for type 2 diabetes during the metabolic process according to claim 1, characterized in that: The processing obtains the output display label corresponding to the fatty liver monitoring data of each target object, and the specific processing process is as follows: Arrange the fatty liver monitoring data of each target object in descending order according to the discrete coefficient corresponding to the fatty liver monitoring data of each target object, and obtain the arrangement order of the fatty liver monitoring data of each target object; The arrangement order of the fatty liver monitoring data of each target object is used as the first output display label of the fatty liver monitoring data of each target object; Extracting the discrete abnormality level corresponding to each discrete coefficient interval stored in the database, and matching the discrete level of the fatty liver monitoring data of each target object based on the discrete coefficient corresponding to the fatty liver monitoring data of each target object; using the discrete level of the fatty liver monitoring data of each target object as a second output display label of the fatty liver monitoring data of each target object; The first output display label of the fatty liver monitoring data of each target object and the second output display label of the fatty liver monitoring data of each target object are combined as the output display label corresponding to the fatty liver monitoring data of each target object.

9. The fatty liver monitoring data processing system for type 2 diabetes during the metabolic process according to claim 5, characterized in that: The specific formula of the discrete coefficient corresponding to the fatty liver monitoring data of each target object is as follows: Among them, C i is the discrete coefficient corresponding to the fatty liver monitoring data of the i-th target object, A i is the first discrete coefficient corresponding to the fatty liver monitoring data of the i-th target object, B i is the second discrete coefficient corresponding to the fatty liver monitoring data of the i-th target object, α1 is the first discrete coefficient weight, α2 is the second discrete coefficient weight, i is the number of each target object, i=1,2,...,m, m is the number of target objects.

10. A data processing system for monitoring fatty liver in the metabolic process of type 2 diabetes, characterized by: It also includes a data archiving module, which is used to archive the basic characteristic data of each target object and the fatty liver monitoring data of each target object during the metabolic process. The specific process is as follows: Marking the basic characteristic data of each target object and the fatty liver monitoring data of each target object during the metabolic process as the fatty liver joint data of each target object; Extracting discrete thresholds corresponding to fatty liver monitoring data stored in a database; If the discrete coefficient corresponding to the fatty liver monitoring data of a target object is greater than the discrete threshold corresponding to the fatty liver monitoring data, the fatty liver joint data of the target object is marked as hot data, and all hot data are counted and archived as a hot data set, thereby storing the hot data set locally; If the discrete coefficient corresponding to the fatty liver monitoring data of a target object is less than or equal to the discrete threshold corresponding to the fatty liver monitoring data, the fatty liver joint data of the target object is marked as cold data, and all cold data are counted and archived as a cold data set, thereby storing the cold data set in the cloud.

Images