KR102599840B1 - System for providing diabetes risk prediction, method, and program for the same - Google Patents

Abstract

The present invention relates to a diabetes development risk calculation system, which consists of one or more computers, calculates metabolic syndrome severity based on input metabolic syndrome onset factor values for metabolic syndrome onset factors, and calculates metabolic syndrome severity from the calculated metabolic syndrome severity. An analysis server that calculates the risk of developing diabetes based on techniques; and a client connected to the analysis server, wherein the client receives the input metabolic syndrome onset factor value and provides it to the analysis server, receives the diabetes development risk from the analysis server, and outputs the metabolic syndrome onset factor value. Pathogenic factors include fasting blood sugar, systolic blood pressure, waist circumference, high-density lipoprotein, and triglycerides.

Description

Diabetes development risk calculation system, calculation method, and program {SYSTEM FOR PROVIDING DIABETES RISK PREDICTION, METHOD, AND PROGRAM FOR THE SAME}

The present invention relates to a diabetes development risk calculation system, calculation method, and program.

As we enter the era of super-aging at the fastest rate around the world, life expectancy is increasing, but healthy life expectancy is decreasing little by little. For a “healthy age of centenarians,” the biggest key is to narrow the gap between the two.

Metabolic syndrome, which can be expressed as a collection of adult diseases, has been steadily increasing over the past 10 years, and the prevalence of metabolic syndrome has recently increased from 1 in 4 adults in 1998 to 1 in 3.

A way to increase healthy lifespan is to prevent and manage diabetes, which is one of the key chronic metabolic diseases among metabolic syndrome, coronary artery disease (CAD), cerebral vascular accident (CVA), and chronic kidney disease (CKD). It is the best way to prevent the occurrence of Chronic Kidney Disease and reduce deaths from it.

However, based on metabolic syndrome onset factors, only the severity of metabolic syndrome is predicted, and the risk of developing diabetes is not predicted based on the severity of metabolic syndrome.

Korean Patent Publication No. 10-2124249, 2020.06.11.

By calculating the severity of metabolic syndrome based on the onset factors of metabolic syndrome and recognizing or calculating the risk of developing diabetes based on the calculated severity of metabolic syndrome, the risk of developing diabetes is highly accurate and can quickly prevent dangerous situations in advance. We intend to provide calculation systems, calculation methods, and programs.

The purpose of the present invention is to calculate the severity of metabolic syndrome based on input metabolic syndrome onset factor values for metabolic syndrome onset factors, and to calculate the risk of developing diabetes based on statistical techniques from the calculated metabolic syndrome severity. An analysis server that calculates, and a client connected to the analysis server, wherein the client receives the input metabolic syndrome onset factor value and provides it to the analysis server, and receives the diabetes development risk from the analysis server and outputs it. And, the metabolic syndrome development factors can be achieved by a diabetes development risk calculation system including fasting blood sugar, systolic blood pressure, waist circumference, high-density lipoprotein, and triglycerides.

The purpose of the present invention is to obtain an input metabolic syndrome onset factor value for the metabolic syndrome onset factor, a metabolic syndrome severity calculation step of calculating the metabolic syndrome severity based on the input metabolic syndrome onset factor value, and the metabolic syndrome severity. Calculating the risk of developing diabetes, wherein the risk of developing diabetes is calculated based on statistical techniques, wherein the metabolic syndrome developing factors include fasting blood sugar, systolic blood pressure, waist circumference, high-density lipoprotein, and triglycerides. It can be achieved by this method.

The object of the present invention can be achieved by a diabetes development risk calculation program combined with a hardware computer and stored in a medium to execute the diabetes development risk calculation method.

According to the present invention, by calculating the severity of metabolic syndrome based on the factors causing the metabolic syndrome and recognizing or calculating the risk of developing diabetes based on the calculated severity of the metabolic syndrome, it is possible to prevent dangerous situations with high accuracy and quickly in advance. A diabetes development risk calculation system, calculation method, and program can be provided.

Figure 1 is a block diagram schematically showing a diabetes risk calculation system according to an embodiment of the present invention.
Figure 2 illustrates the metabolic syndrome severity divided into three levels.
Figure 3 exemplarily shows the risk of developing diabetes calculated based on the Multivariable Cox proportional hazards regression model in the metabolic syndrome severity of Figure 2.
Figure 4 is a flowchart schematically showing a method for calculating the risk of developing diabetes according to an embodiment of the present invention.

The advantages and features of the present invention and methods for achieving them will become clear by referring to the embodiments described in detail below along with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms. The present embodiments are merely intended to make the disclosure of the present invention complete and to provide a general understanding of the technical field to which the present invention pertains. It is provided to fully inform those skilled in the art of the scope of the present invention, and the present invention is only defined by the scope of the claims.

The terminology used herein is for describing embodiments and is not intended to limit the invention. As used herein, singular forms also include plural forms, unless specifically stated otherwise in the context. As used in the specification, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other elements in addition to the mentioned elements. Like reference numerals refer to like elements throughout the specification, and “and/or” includes each and every combination of one or more of the referenced elements. Although “first”, “second”, etc. are used to describe various components, these components are of course not limited by these terms. These terms are merely used to distinguish one component from another. Therefore, it goes without saying that the first component mentioned below may also be a second component within the technical spirit of the present invention.

In this specification, a computer includes all various devices that can perform computational processing and visually present the results to the user. For example, computers include not only desktop PCs and laptops (Note Books), but also smart phones, tablet PCs, cellular phones, PCS phones (Personal Communication Service phones), and synchronous/asynchronous computers. This may also include IMT-2000 (International Mobile Telecommunication-2000) mobile terminals, Palm Personal Computers (Palm PCs), and personal digital assistants (PDAs). Additionally, computers may also refer to medical equipment that acquires or observes medical images. Additionally, the computer may be a server computer connected to various client computers.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those skilled in the art to which the present invention pertains. Additionally, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless clearly specifically defined.

Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings.

Figure 1 is a block diagram schematically showing a diabetes risk calculation system according to an embodiment of the present invention.

Referring to FIG. 1, the diabetes development risk calculation system 10 according to an embodiment of the present invention includes an analysis server 100 and a client 200.

The analysis server 100 consists of one or more computers. The analysis server 100 calculates the severity of metabolic syndrome based on the input metabolic syndrome onset factor value according to the metabolic syndrome onset factor. The analysis server 100 calculates the risk of developing diabetes using statistical techniques based on the severity of metabolic syndrome.

In the present specification, the term “metabolic syndrome” in the pathogenesis of metabolic syndrome may include, for example, at least one of hypertension, dyslipidemia, and diabetes.

Factors contributing to metabolic syndrome include, for example, fasting blood sugar, systolic blood pressure, waist circumference, high-density lipoprotein, and triglycerides.

For example, the analysis server 100 statistically analyzes the Korean Genome Epidemiology Study cohort data and calculates the metabolic syndrome severity using the metabolic syndrome severity formula (Equation 1 or Equation 2 below) based on health examination data. It is used to calculate the risk of developing diabetes. For example, when the input metabolic syndrome onset factor value is provided from a man over 40 years of age, the analysis server 100 can calculate the severity of metabolic syndrome using Equation 1 below.

In Equation 1, FPG is fasting blood sugar (mg/dL), SBP is systolic blood pressure (mmHg), WC is waist circumference (cm), HDL is high-density lipoprotein (mg/dL), and TG is triglyceride (mg/dL). )am.

For example, when the input metabolic syndrome onset factor value is provided from a woman aged 40 or older, the analysis server 100 may calculate the severity of metabolic syndrome using Equation 2 below.

In Equation 2, FPG is fasting blood sugar (mg/dL), SBP is systolic blood pressure (mmHg), WC is waist circumference (cm), HDL is high-density lipoprotein (mg/dL), and TG is triglyceride (mg/dL). )am.

For example, the analysis server 100 may classify the severity of metabolic syndrome into specific ranges and calculate the risk of developing diabetes using statistical techniques. For example, the analysis server 100 may divide the severity of metabolic syndrome into three ranges and calculate the risk of developing diabetes using statistical techniques. For example, Figure 2 shows that metabolic syndrome severity was calculated by providing metabolic syndrome onset factor values for men in their 40s and older and women in their 40s and older, and dividing this into three levels (quartiles). . In Figure 2, R (ansung) means countryside, and U (ansan) means city.

For example, the metabolic syndrome severity value for men in their 40s is the metabolic syndrome severity value of the first quartile group: less than -0.4869; The metabolic syndrome severity value of the 2nd quartile group: -0.4868 and above +0.1875, and the 3rd quartile group's metabolic syndrome severity value: 0.1875 and above. For example, the severity of metabolic syndrome for women in their 40s is the metabolic syndrome severity value of the first quartile group: less than 0.0140; The metabolic syndrome severity value of the 2nd quartile group: 0.0140 or more and less than 0.7100, and the 3rd quartile group's metabolic syndrome severity value: 0.7100 or more.

The statistical technique may be, for example, a Multivariable Cox proportional hazards regression model. The Cox proportional hazards regression model is a model that calculates the relative hazard for specific variables. Through the above model, the influence of multiple prognostic variables related to the survival probability of a group (or the probability of occurrence of a certain disease), for example, the probability of occurrence of T2DM, can be viewed simultaneously while controlling for multiple confounding variables. Referring to Figure 3, it can be seen that the risk of developing diabetes is calculated based on the Multivariable Cox proportional hazards regression model in the metabolic syndrome severity of Figure 2 as an example.

Figure 3 shows analysis according to Model A, Model B, and Model C, correcting the effects of confounding variables. Model A is an analysis that corrects only two confounding variables of region and age, and Model B is an analysis that additionally corrects for the effects of confounding variables such as drinking, smoking, exercising, and family history in addition to Model A. C is an analysis in which a confounding variable called BMI was additionally adjusted for model B. The diabetes development risk calculation system according to an embodiment of the present invention may be based on Model C, in which confounding variables are corrected as much as possible.

For example, referring to Figures 2 and 3, compared to the 1st quartile group, which is the reference group, the probability of developing diabetes is 1.53 times higher in the male 2nd quintile group, 3.01 times higher in the 3rd quartile group, and 3.01 times higher in the female 2nd quintile group. The probability of this occurring can be interpreted as 2.00 times, and for the 3rd quartile group, 3.98 times.

For example, if the metabolic syndrome severity value of a 45-year-old female individual is calculated to be 0.57, it can be interpreted that she falls in the second quartile of metabolic syndrome severity group and has about twice the risk of developing diabetes compared to people with a metabolic syndrome severity value of less than 0.0140. .

Referring again to FIG. 1, the risk of developing diabetes may include, for example, at least one of the timing of onset of diabetes and the incidence of diabetes.

The diabetes risk calculation system 10 according to an embodiment of the present invention can calculate the diabetes risk using a deep learning model using one or more computers.

Below, the deep learning learning model is explained.

The analysis server 100 is composed of one or more computers to form a deep learning model, and determines the risk of developing diabetes based on the input metabolic syndrome onset factor value or the calculated metabolic syndrome severity.

In one embodiment, the analysis server 100 may form a plurality of deep learning learning models. For example, a first deep learning model that calculates the severity of metabolic syndrome based on the input metabolic syndrome onset factor value, and a second deep learning model that determines the risk of developing diabetes based on the calculated metabolic syndrome severity. May include learning models.

A deep learning learning model according to embodiments of the present invention refers to a system or network that builds one or more layers in one or more computers and makes decisions based on a plurality of data. For example, a deep learning learning model can be implemented as a set of layers including a convolutional pooling layer, a locally-connected layer, and a fully-connected layer. . A convolutional pooling layer or a local connection layer may be configured to extract features within the image. The fully connected layer can determine correlations between features of the image. In some embodiments, the overall structure of a deep learning learning model may be composed of a convolutional pooling layer followed by a local connection layer, and a local connection layer followed by a fully connected layer. A deep learning learning model may include various judgment criteria (i.e., parameters), and new judgment criteria (i.e., parameters) can be added through analysis of input images. Parameters may include, for example, fasting blood sugar, systolic blood pressure, waist circumference, high-density lipoprotein, and triglycerides. Parameters further include at least one of, for example, HDL (High-Density Lipoprotein) cholesterol value, drinking status, smoking status, exercise status, family history, past medical history, current medical history, BMI, age, height, weight, and living environment. can do.

The deep learning learning model according to embodiments of the present invention is a structure called a convolutional neural network suitable for image analysis, and is a feature extraction layer that automatically learns the feature with the greatest discriminative power from the given image data. It can be composed of an integrated structure of a prediction layer and a prediction layer that learns a calculation model to produce the highest calculation performance based on the extracted features.

The feature extraction layer is a convolution layer that creates a feature map by applying multiple filters to each area of the image and spatially integrates the feature map to extract features that are invariant to changes in position or rotation. It can be formed in a structure in which the pooling layer that allows extraction is alternately repeated several times. Through this, various levels of features can be extracted, from low-level features such as points, lines, and surfaces to complex and meaningful high-level features.

The convolution layer obtains a feature map by taking a non-linear activation function as the inner product of the filter and the local receptive field for each patch of the input image, and compares it with other network structures. Therefore, CNN is characterized by using filters with sparse connectivity and shared weights. This connection structure reduces the number of parameters to be learned, makes learning through the backpropagation algorithm efficient, and ultimately improves calculation performance.

The integration layer (Pooling Layer or Sub-sampling Layer) creates a new feature map using the local information of the feature map obtained from the previous convolution layer. In general, the feature map newly created by the integration layer is reduced to a smaller size than the original feature map. Representative integration methods include max pooling, which selects the maximum value of the corresponding area within the feature map, and There is average pooling, which calculates the average value of an area. The feature map of the integrated layer is generally less affected by the location of arbitrary structures or patterns present in the input image than the feature map of the previous layer. In other words, the integration layer can extract features that are more robust to local changes such as noise or distortion in the input image or previous feature map, and these features can play an important role in classification performance. Another role of the integration layer is to reflect the characteristics of a wider area as you go up to the higher learning layer in the deep structure. As the feature extraction layer accumulates, local characteristics are reflected in the lower layers, and as you go up to the upper layer, you can reflect the characteristics of a wider area. Features that reflect the characteristics of the entire abstract image can be generated.

In this way, the features finally extracted through repetition of the convolutional layer and the integration layer are classified into fully connected layers such as a classification model such as a multi-layer perception (MLP) or a support vector machine (SVM). -connected layer) and can be used to learn and calculate classification models.

However, the structure of the deep learning model according to embodiments of the present invention is not limited to this, and may be formed of a neural network of various structures.

The client 200 receives the input metabolic syndrome onset factor value and provides it to the analysis server 100. The client 200 receives the risk of developing diabetes from the analysis server 100 and outputs it.

The client 200 may include an input device 210 and an output device 220. The input device 210 and the output device 220 may be implemented as one device or as separate devices.

The input device 210 may be a device that receives metabolic syndrome onset factors and transmits the corresponding input metabolic syndrome onset factor values to the analysis server 100 .

In one embodiment, the input device 210 may receive blood from a user whose risk of developing diabetes needs to be analyzed and calculate factors for developing metabolic syndrome.

There may be one input device 210 or there may be multiple input devices 210.

The output device 220 may receive the diabetes development risk results from the analysis server 100 and provide the judgment results to the user in various ways. For example, the output device 220 may include a display unit to visually display the risk of developing diabetes and provide it to the user.

Additionally, when receiving a determination result that the risk of developing diabetes is high, the output device 220 may generate vibration to inform the user that the risk of developing diabetes is high.

However, the method by which the output device 220 provides the user with the determination result of the risk of developing diabetes is not limited to this, and various output methods that can be provided to the user, such as audio output, can be used. Additionally, the output device 220 according to an embodiment of the present invention may include a mobile terminal.

There may be one output device 220 or there may be multiple output devices 220.

Hereinafter, a method for calculating the risk of developing diabetes according to an embodiment of the present invention will be described. Below, the differences from the diabetes development risk calculation system according to an embodiment of the present invention mentioned above will be described in detail, and parts not described may be the same as the diabetes development risk calculation system according to an embodiment of the present invention. there is.

Figure 4 is a flowchart schematically showing a method for calculating the risk of developing diabetes according to an embodiment of the present invention.

Referring to Figures 1 and 4, the method for calculating the risk of developing diabetes according to an embodiment of the present invention includes the step of acquiring the input metabolic syndrome onset factor value for the onset factor of metabolic syndrome (S100), and the step of calculating the severity of metabolic syndrome (S100). S200), and a diabetes development risk calculation step (S300).

Obtain the input metabolic syndrome onset factor value for the metabolic syndrome onset factor (S100). The input metabolic syndrome onset factor value may be input from the client 200 and provided to the analysis server 100. The input metabolic syndrome onset factor value may be input into the input device 210 and provided to the analysis server 100.

The metabolic syndrome severity is calculated based on the input metabolic syndrome onset factor values (S200). The metabolic syndrome severity calculation step (S200) may be performed in the analysis server 100.

In one embodiment, the metabolic syndrome severity calculation step (S200) may calculate the metabolic syndrome severity using a metabolic syndrome severity formula derived based on data from the Korean Genome Epidemiology Study cohort (Ansung-Ansan cohort).

In one embodiment, in the metabolic syndrome severity calculation step (S200), when the input metabolic syndrome onset factor value is provided from a man aged 40 or older, the metabolic syndrome severity can be calculated using Equation 1 described above.

In one embodiment, in the metabolic syndrome severity calculation step (S200), when the input metabolic syndrome onset factor value is provided from a woman aged 40 or older, the metabolic syndrome severity can be calculated using Equation 2 described above.

From the severity of metabolic syndrome, the risk of developing diabetes is calculated using statistical techniques (S300). The risk of developing diabetes may be provided from the analysis device 100 to the output device 220. The output device 220 and the input device 210 may be implemented as one device or may be implemented as separate devices.

In one embodiment, in the diabetes development risk calculation step (S300), the metabolic syndrome severity can be divided into specific ranges and the diabetes development risk can be calculated using statistical techniques.

In one embodiment, in the diabetes development risk calculation step (S300), the metabolic syndrome severity can be divided into three ranges and the diabetes development risk can be calculated using statistical techniques. For example, in Figure 2, metabolic syndrome onset factor values are provided for men in their 40s or older and women in their 40s or older, and Equation 1 and Equation 2 are applied to individuals included in the Kocht data to determine metabolic syndrome. It indicates that the syndrome severity was calculated and divided into three levels.

For example, the metabolic syndrome severity value for men in their 40s is the metabolic syndrome severity value of the first quartile group: less than -0.4869; The metabolic syndrome severity value of the 2nd quartile group: -0.4868 and above +0.1875, and the 3rd quartile group's metabolic syndrome severity value: 0.1875 and above. For example, the severity of metabolic syndrome for women in their 40s is the metabolic syndrome severity value of the first quartile group: less than 0.0140; The metabolic syndrome severity value of the 2nd quartile group: 0.0140 or more and less than 0.7100, and the 3rd quartile group's metabolic syndrome severity value: 0.7100 or more.

In one embodiment, the statistical technique used in the diabetes development risk calculation step (S300) may be a Multivariable Cox proportional hazards regression model. The Cox proportional hazards regression model is a model that calculates the relative hazard for specific variables. Through the above model, the influence of multiple prognostic variables related to the survival probability of a group (or the probability of occurrence of a certain disease), for example, the probability of occurrence of T2DM, can be viewed simultaneously while controlling for multiple confounding variables.

Referring to Figure 3, it can be seen that the risk of developing diabetes is calculated based on the Multivariable Cox proportional hazards regression model in the metabolic syndrome severity of Figure 2 as an example.

For example, referring to Figures 2 and 3, compared to the 1st quartile group, which is the reference group, the probability of developing diabetes is 1.53 times higher in the male 2nd quintile group, 3.01 times higher in the 3rd quartile group, and 3.01 times higher in the female 2nd quintile group. The probability of this occurring can be interpreted as 2.00 times, and for the 3rd quartile group, 3.98 times.

For example, if the metabolic syndrome severity value of a 45-year-old female individual is calculated to be 0.57, it can be interpreted that she falls in the second quartile of metabolic syndrome severity group and has about twice the risk of developing diabetes compared to people with a metabolic syndrome severity value of less than 0.0140. .

In one embodiment, in the diabetes development risk calculation step (S300), the input metabolic syndrome onset factor value, metabolic syndrome severity, and at least one and the risk of developing diabetes are learned as a dataset by one or more computers using a deep learning learning model. It may include a learning step, and a step of calculating the risk of developing diabetes using a deep learning learning model.

In one embodiment, the diabetes development risk calculation step (S300) is a learning step in which metabolic syndrome severity and diabetes development risk are learned from a dataset using a deep learning learning model by one or more computers, and a deep learning learning model. It may include calculating the risk of developing diabetes.

For example, the risk of developing diabetes can be determined by the parameters of the deep learning model mentioned above.

The method for calculating the risk of developing diabetes according to an embodiment of the present invention may be implemented as a program (or application) to be executed in conjunction with a computer, which is hardware, and stored in a medium included in the risk calculating system for developing diabetes.

A program is a code coded in a computer language such as C, C++, JAVA, or machine language that the computer's processor (CPU) can read through the computer's device interface in order for the computer to read the program and execute the methods implemented in the program. (Code) may be included. These codes may include functional codes related to functions that define the necessary functions for executing methods, and may include control codes related to execution procedures necessary for the computer's processor to execute the functions according to predetermined procedures. . In addition, these codes may further include memory reference-related codes that indicate from which location (address address) in the computer's internal or external memory additional information or media required for the computer's processor to execute functions should be referenced. Additionally, if the computer's processor needs to communicate with any other remote computer or server to execute functions, how should the code communicate with any other remote computer or server using the computer's communication module? , It may further include communication-related codes regarding what information or media should be transmitted and received during communication.

A storage medium is not a medium that stores data for a short period of time, such as a register, cache, or memory, but a medium that stores data semi-permanently and can be read by a device. Specifically, examples of storage media include, but are not limited to, ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage devices. That is, the program can be stored in various recording media on various servers that the computer can access or in various recording media on the user's computer. Additionally, the medium may be distributed across computer systems connected to a network, and computer-readable code may be stored in a distributed manner.

Diabetes development risk calculation system, calculation method, and program according to an embodiment of the present invention calculate metabolic syndrome severity based on metabolic syndrome onset factors, and recognize or calculate diabetes development risk based on the calculated metabolic syndrome severity. As a result, accuracy is high and dangerous situations can be quickly prevented in advance.

Above, embodiments of the present invention have been described with reference to the attached drawings, but those skilled in the art will understand that the present invention can be implemented in other specific forms without changing its technical idea or essential features. You will understand that it exists. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive.

10: Diabetes development risk calculation system
100: Analysis server
200: Client
210: input device
220: output device

Claims (19)

An analysis server that consists of one or more computers, calculates the severity of metabolic syndrome based on input metabolic syndrome onset factor values, and calculates the risk of developing diabetes based on statistical techniques from the calculated metabolic syndrome severity. ; and
Includes a client connected to the analysis server,
The client receives the input metabolic syndrome onset factor value, provides it to the analysis server, and receives and outputs the diabetes development risk from the analysis server,
The metabolic syndrome onset factors include fasting blood sugar, systolic blood pressure, waist circumference, high-density lipoprotein, and triglycerides,
The metabolic syndrome severity is classified into a plurality of groups based on a preset range,
The analysis server calculates the user's diabetes onset time using a deep learning model learned from a dataset of the metabolic syndrome severity classified by group and the risk of developing diabetes, and uses the learning model to calculate the user's metabolic rate. Diabetes onset, which determines which group the syndrome severity belongs to among the plurality of groups and calculates the onset time of diabetes by using as a parameter whether the user's residential environment is urban or rural within the determined group. Risk calculation system. According to paragraph 1,
The analysis server is
Diabetes development risk calculation system that statistically analyzes the Korean Genome Epidemiology Study cohort data and calculates the risk of developing diabetes through metabolic syndrome severity formula. According to paragraph 2,
The analysis server is
When the input metabolic syndrome onset factor value is provided from a man over 40 years of age, a diabetes development risk calculation system that calculates the diabetes development risk based on Equation 1 below:
[Equation 1]
-8.2939 + 0.0126 × FPG + 0.0063 × SBP + 0.0382 × WC - 0.0210 × HDL + 0.8432 × ln(TG),
In Equation 1, FPG is fasting blood sugar (mg/dL), SBP is systolic blood pressure (mmHg), WC is waist circumference (cm), HDL is high-density lipoprotein (mg/dL), and TG is triglyceride (mg/dL). )am. According to paragraph 2,
The analysis server is
When the input metabolic syndrome onset factor value is provided from a woman over 40 years of age, a diabetes development risk calculation system that calculates the diabetes development risk based on Equation 2 below:
[Equation 2]
-7.5210 + 0.0156 × FPG + 0.0073 × SBP + 0.0292 × WC - 0.0207 × HDL + 0.9065 × ln(TG),
In Equation 2, FPG is fasting blood sugar (mg/dL), SBP is systolic blood pressure (mmHg), WC is waist circumference (cm), HDL is high-density lipoprotein (mg/dL), and TG is triglyceride (mg/dL). )am. delete According to paragraph 1,
The statistical technique above is
A diabetes risk calculation system that is a multivariable Cox proportional hazards regression model. delete delete According to paragraph 1,
The client is
an input device that receives the input metabolic syndrome onset factor values and provides them to the analysis server; and
A diabetes development risk calculation system including an output device that receives the diabetes development risk from the analysis server and outputs it. In the method of calculating the risk of developing diabetes performed by the analysis server,
Obtaining, by the analysis server, an input metabolic syndrome onset factor value for the metabolic syndrome onset factor;
A metabolic syndrome severity calculation step in which the analysis server calculates metabolic syndrome severity based on the input metabolic syndrome onset factor value; and
A diabetes development risk calculation step in which the analysis server calculates the risk of developing diabetes based on statistical techniques based on the metabolic syndrome severity,
The metabolic syndrome onset factors include fasting blood sugar, systolic blood pressure, waist circumference, high-density lipoprotein, and triglycerides,
The metabolic syndrome severity is classified into a plurality of groups based on a preset range,
The step of calculating the risk of developing diabetes is,
The analysis server calculates the user's onset of diabetes using a deep learning model learned from a dataset of the metabolic syndrome severity classified by group and the risk of developing diabetes, and uses the learning model to calculate the user's metabolic syndrome. The risk of developing diabetes is calculated by determining which of the plurality of groups the severity belongs to, and calculating the timing of diabetes onset by using as a parameter whether the user's residential environment is urban or rural within the determined group. Calculation method. According to clause 10,
The risk of developing diabetes is
A method of calculating the risk of developing diabetes using the metabolic syndrome severity formula by statistically analyzing the Korean Genome Epidemiology Study cohort data. According to clause 11,
The risk of developing diabetes is
When the input metabolic syndrome onset factor value is provided from a man over 40 years of age, the diabetes development risk calculation method is calculated based on Equation 1 below:
[Equation 1]
-8.2939 + 0.0126 × FPG + 0.0063 × SBP + 0.0382 × WC - 0.0210 × HDL + 0.8432 × ln(TG),
In Equation 1, FPG is fasting blood sugar (mg/dL), SBP is systolic blood pressure (mmHg), WC is waist circumference (cm), HDL is high-density lipoprotein (mg/dL), and TG is triglyceride (mg/dL). )am. According to clause 11,
The risk of developing diabetes is
When the input metabolic syndrome onset factor value is provided by a woman over 40 years of age, the diabetes development risk calculation method is calculated based on Equation 2 below:
[Equation 2]
-7.5210 + 0.0156 × FPG + 0.0073 × SBP + 0.0292 × WC - 0.0207 × HDL + 0.9065 × ln(TG),
In Equation 2, FPG is fasting blood sugar (mg/dL), SBP is systolic blood pressure (mmHg), WC is waist circumference (cm), HDL is high-density lipoprotein (mg/dL), and TG is triglyceride (mg/dL). )am. delete According to clause 10,
The statistical technique above is
A method for calculating the risk of developing diabetes using the multivariable Cox proportional hazards regression model. delete delete According to clause 10,
A method for calculating the risk of developing diabetes, further comprising the step of the analysis server receiving and outputting the calculated risk of developing diabetes. A diabetes development risk calculation program combined with a hardware computer and stored in a medium to execute the diabetes development risk calculation method of any one of claims 10 to 13, 15, and 18.

Images