WO2022114793A1 - Big data-based system, method, and program for predicting risk for diabetes incidence - Google Patents

Abstract

The present invention relates to a big data-based system, method, and program for predicting risk for disease incidence, wherein big data is produced on the basis of metabolism syndrome incidence factors accumulated with time and is analyzed to recognize or predict incidence or risk degrees of specific diseases, whereby risky conditions can be prevented in advance.

Description

Big data-based diabetes risk prediction system, prediction method, and program

The present invention relates to a big data-based diabetes risk prediction system, prediction method, and program.

Blood sugar in our body refers to the substances contained in the blood, and the blood sugar of animals is mainly glucose and becomes an energy source for the brain and red blood cells, and the amount is determined according to the amount of exercise and meal. Blood sugar, which is important for our body, is a sensitive metabolism that has a bad effect on health if it is too little or too much. It is of utmost importance to follow and keep blood sugar constant at all times.

The fasting blood sugar, not after a meal, is measured after maintaining the fasting state for at least 8 hours, and through this, it is possible to determine whether or not diabetes is present. However, since it is common for blood sugar to be lowered when fasting is maintained for more than 8 hours, it is difficult to accurately measure diabetes by measuring fasting blood sugar once. In addition, even when it is determined that diabetes is diabetes because the fasting blood sugar is higher than the reference level, there is a problem in that an additional test is required to accurately determine whether diabetes is present.

In order to solve the above problems, the present invention generates big data by accumulating diabetes onset factors that can be obtained during a basic health checkup over time, and analyzes it to accurately recognize or predict the risk of diabetes occurrence without additional examination. , to provide a big data-based diabetes risk prediction system, prediction method, and program that can prevent dangerous situations in advance.

The big data-based diabetes risk prediction system according to the present invention for achieving the above technical problem is composed of one or more computers, and collects input diabetes onset factor values for diabetes onset factors over time to form big data, , an analysis server that analyzes the big data to predict the risk of developing diabetes, and a client connected to the analysis server, wherein the client receives the input diabetes onset factor value and provides it to the analysis server, from the analysis server When the diabetes onset risk is provided and output, the input diabetes onset factor value includes a fasting blood sugar value, and the analysis server exceeds a reference value set based on the big data, the input diabetes onset factor value, the diabetes It is characterized by predicting the risk of disease.

In this case, the analysis server may use the deep learning learning model to learn the input diabetes onset factor value and the diabetes onset risk as a dataset, and predict the diabetes onset risk with the deep learning learning model.

That is, the analysis server accumulates the input diabetes onset factor value, generates learning data, calculates a normal diabetes onset factor value within a normal range through analysis of the learning data, and the input diabetes onset factor value is the normal It may be determined whether a specific range formed based on the diabetes onset factor value is exceeded. In addition, the analysis server may accumulate the input diabetes onset factor values, generate learning data, and extract the diabetes onset risk from the learning data.

In addition, the analysis server accumulates specific situation data by matching the abnormal characteristic information, recognizes specific abnormal characteristic information within the input diabetes onset factor value, and transmits situation data corresponding to the recognized abnormal characteristic information to the client can be sent to

Also, the analysis server may analyze the big data by logistic regression analysis.

On the other hand, the input diabetes onset factor values are high-density lipoprotein (HDL) cholesterol value, triglyceride value, alcohol consumption, smoking status, exercise status, family history, past medical history, current medical history, abdominal circumference, BMI, age, It may further include at least one of height, weight, blood pressure, and living environment.

In addition, the analysis server may predict the risk of developing type 2 diabetes.

In addition, the risk of developing diabetes may include at least one of an onset time and an onset rate.

Meanwhile, the client may include an input device that receives the input diabetes onset factor value and provides it to the analysis server, and an output device that receives and outputs the diabetes risk level from the analysis server.

In addition, the big data-based diabetes risk prediction method performed by the system according to the present invention for achieving the above technical problem includes the steps of obtaining an input diabetes onset factor value for a diabetes onset factor, and the input diabetes onset factor value A big data collection step of collecting and forming big data over time and a diabetes risk prediction step of predicting the risk of developing diabetes by analyzing the big data; includes, wherein the input diabetes onset factor value is a fasting blood sugar value In addition, the predicting risk of developing diabetes may predict the risk of developing diabetes when the input diabetes onset factor value exceeds a reference value set based on the big data.

At this time, the diabetes risk prediction step is a learning step of learning the input diabetes onset factor value and the diabetes risk risk from a dataset by one or more computers, using a deep learning learning model, and the deep learning learning model. It may include predicting the risk of developing diabetes.

In this case, the learning step includes the steps of accumulating the input diabetes onset factor values to generate learning data, calculating a normal diabetes onset factor value within a normal range through analysis of the learning data, and the input diabetes onset factor value The method may include determining whether a specific range formed based on the normal diabetes onset factor value is exceeded.

In addition, the learning step may include accumulating the input diabetes onset factor values, generating learning data, and extracting the diabetes onset risk from the learning data.

In addition, the learning step includes the steps of matching and accumulating specific situation data with abnormal characteristic information, recognizing specific abnormal characteristic information within the input diabetes onset factor value, and obtaining situation data corresponding to the recognized abnormal characteristic information It may further include the step of transmitting to the client.

In addition, the step of predicting the risk of developing diabetes may analyze the big data by logistic regression analysis.

In addition, the input diabetes onset factor value is a high-density lipoprotein (HDL) cholesterol value, triglyceride value, alcohol consumption, smoking status, exercise status, family history, past medical history, current medical history, abdominal circumference, BMI, age, It may further include at least one of height, weight, blood pressure, and living environment.

In addition, the diabetes risk prediction step may predict the risk of developing type 2 diabetes.

In addition, the risk of developing diabetes may include at least one of an onset time and an onset rate.

In addition, in order to achieve the above technical problem, the present invention is combined with a computer that is hardware to provide a big data-based diabetes risk prediction program stored in the medium to execute the above-described big data-based diabetes risk prediction method. have.

According to the present invention, without additional examination, by accumulating diabetes onset factors that can be obtained during a basic health examination over time, big data is generated, and by analyzing it, the risk of diabetes occurrence is accurately recognized or predicted, so that the risk situation can be predicted in advance. It is possible to provide a big data-based diabetes risk prediction system, prediction method, and program that can prevent

1 is a block diagram schematically showing a big data-based diabetes risk prediction system according to an embodiment of the present invention.

2 is a flowchart schematically illustrating a method for predicting the risk of developing diabetes based on big data according to an embodiment of the present invention.

Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only these embodiments allow the disclosure of the present invention to be complete, and common 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 the purpose of describing the embodiments and is not intended to limit the present invention. In this specification, the singular also includes the plural unless specifically stated otherwise in the phrase. As used herein, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other components in addition to the stated components. Like reference numerals refer to like elements throughout, and "and/or" includes each and every combination of one or more of the recited elements. Although "first", "second", etc. are used to describe various elements, these elements are not limited by these terms, of course. These terms are only used to distinguish one component from another. Accordingly, it goes without saying that the first component mentioned below may be the second component within the spirit of the present invention.

In the present specification, the computer includes all of various devices capable of visually presenting a result to a user by performing arithmetic processing. For example, computers include desktop PCs and notebooks (Note Books) as well as smart phones, tablet PCs, cellular phones, PCS phones (Personal Communication Service phones), synchronous/asynchronous A mobile terminal of International Mobile Telecommunication-2000 (IMT-2000), a Palm Personal Computer (PC), a Personal Digital Assistant (PDA), and the like may also be applicable. Also, the computer may be a medical device for acquiring or observing a medical image. Also, the computer may correspond to a server computer connected to various client computers.

Unless otherwise defined, all terms (including technical and scientific terms) used herein will have the meaning commonly understood by those of ordinary skill in the art to which this invention belongs. In addition, terms defined in a commonly used dictionary are not to be interpreted ideally or excessively unless specifically defined explicitly.

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

1 is a block diagram schematically showing a big data-based diabetes risk prediction system according to an embodiment of the present invention.

Referring to FIG. 1 , the big data-based diabetes risk prediction system 10 according to an embodiment of the present invention includes an analysis server 100 and a client 200 .

The analysis server 100 is composed of one or more computers. The analysis server 100 collects the input diabetes onset factor values according to the diabetes onset factors over time to form the big data 110 . The analysis server 100 analyzes the big data 110 to predict the risk of developing diabetes.

In the present specification, the input diabetes onset factor value means a value obtainable through a basic health checkup, and does not mean a value obtainable through an additional checkup. For example, "additional check-up" may mean a check-up to check whether diabetes is present in addition to the basic health check-up.

In the present specification, "collection over time" may mean, for example, receiving the input diabetes onset factor value at least once or more before receiving the current input diabetes onset factor value. For example, collection according to time may mean that input diabetes onset factor values provided in the past 3 years are collected.

In one embodiment, the big data 110 may be big data of the National Health Insurance Corporation.

The factors for developing diabetes may include, for example, a fasting blood glucose level. Diabetes development factors include, for example, high-density lipoprotein (HDL) cholesterol level, triglyceride level, alcohol consumption, smoking status, exercise status, family history, past medical history, current medical history, abdominal circumference, BMI, age, height , weight, blood pressure, and may further include at least one of a living environment.

The analysis server 100 may accumulate and collect the values of the input diabetes onset factors during a specific period. For example, the analysis server 100 may accumulate and collect the values of the input diabetes onset factors for the past 3 years. For example, the analysis server 100 may accumulate and collect values of input diabetes onset factors for the past 5 years.

The analysis server 100 analyzes the big data 110 . The analysis server 100 may analyze the big data 110 by, for example, logistic regression analysis.

The analysis server 100 may predict the risk of developing diabetes when the input diabetes onset factor value exceeds a reference value set based on big data.

The reference value may be, for example, a reference for evaluating the absolute value of the input diabetes onset factor value, or a reference for evaluating the difference between the input diabetes onset factor value and a normal value set based on big data.

In one embodiment, the analysis server 100 determines, for example, whether the fasting blood glucose value among the input diabetes onset factor values exceeds or does not exceed a reference value set based on big data to determine the risk of diabetes onset predictable.

In an embodiment, the analysis server 100 may predict the risk of developing diabetes according to a difference value between the input diabetes onset factor value and a reference value set based on big data.

The risk of developing diabetes may include, for example, at least one of an onset time of diabetes and an incidence of diabetes.

As an embodiment, the big data-based diabetes risk prediction system 10 according to an embodiment of the present invention may predict the risk of developing type 2 diabetes.

The big data-based diabetes risk prediction system 10 according to an embodiment of the present invention may predict the risk of diabetes onset by using one or more computers and the deep learning learning model 120 . Hereinafter, the deep learning learning model 120 will be described.

The analysis server 100 is composed of one or more computers to form the deep learning learning model 120, and plays a role of determining how high the risk of diabetes onset is the input diabetes onset factor value.

The deep learning learning model 120 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 performs judgment based on a plurality of data. For example, the deep learning learning model 120 is implemented as a set of layers including a convolutional pooling layer, a locally-connected layer, and a fully-connected layer. can be A convolutional pooling layer or a local access layer may be configured to extract features in an image. The fully connected layer can determine the correlation between features of the image. In some embodiments, the overall structure of the deep learning learning model 120 may be formed in a form in which a local access layer is connected to a convolutional pooling layer, and a fully connected layer is formed in the local access layer.

The deep learning learning model 120 may include various judgment criteria (ie, parameters), and may add new judgment criteria (ie, parameters) through input image analysis. The parameter may include, for example, fasting blood sugar. Parameters include, for example, high-density lipoprotein (HDL) cholesterol value, triglyceride value, alcohol consumption, smoking status, exercise status, family history, past medical history, current medical history, abdominal circumference, BMI, age, height, and weight. , blood pressure, and may further include at least one of a living environment.

In one embodiment, for example, if the parameter includes fasting blood glucose and the fasting blood glucose value is 100 mg/dL or more, it may be a risk of diabetes, and if it is less than it, it may be normal.

In one embodiment, for example, if the parameter includes HDL cholesterol, and the HDL cholesterol value is 240 mg/dL or more, it may be a risk of diabetes, and if it is less than it, it may be normal. At this time, whether or not to take hyperlipidemia drugs can be learned together.

In one embodiment, for example, if the parameter includes triglycerides and the triglyceride value is 150 mg/dL or more, the risk may be diabetes, and if the parameter is less than 150 mg/dL, it may be normal. At this time, whether or not to take diabetes medication can be learned together.

In one embodiment, for example, if the parameter includes blood pressure and the systolic blood pressure (SBP) value is 130 mmHg or more or the diastolic blood pressure (DBP) value is 80 mmHg or more, it may be a risk of diabetes, If it is outside the above range, it may be normal. At this time, whether or not to take a high blood pressure drug may be learned together.

In one embodiment, for example, if the parameter includes abdominal circumference and gender, if the abdominal circumference is 90 cm or more for males and 85 cm or more for females, the risk of diabetes may be higher, and less than that may be normal . At this time, whether or not to take diabetes medication can be learned together.

The deep learning learning model 120 according to embodiments of the present invention is a structure called a convolutional neural network suitable for image analysis, and a feature extraction layer that learns by itself the feature with the greatest discriminative power from given image data. (Feature Extraction Layer) and a prediction layer that learns a prediction model to obtain the highest prediction performance based on the extracted features may be configured in an integrated structure.

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

The convolutional layer obtains a feature map by taking a nonlinear activation function on the dot product of the filter and the local receptive field for each patch of the input image. Therefore, CNNs are 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 consequently improves prediction performance.

The integration layer (Pooling Layer or Sub-sampling Layer) generates a new feature map by using local information of the feature map obtained from the previous convolutional layer. In general, the newly created feature map 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 region in the feature map, and the corresponding feature map in the feature map. There is an average pooling method that obtains the average value of a region. In general, the feature map of the integrated layer may be less affected by the position of an arbitrary structure or pattern existing in the input image than the feature map of the previous layer. That is, the integration layer can extract features that are more robust to regional 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 upper learning layer in the deep structure. It is possible to generate features that reflect the characteristics of the abstract image as a whole.

In this way, the features finally extracted through repetition of the convolutional layer and the integration layer are fully connected to the classification model such as multi-layer perception (MLP) or support vector machine (SVM). -connected layer) and can be used for classification model training and prediction.

However, the structure of the deep learning learning model 120 according to embodiments of the present invention is not limited thereto, and may be formed of a neural network of various structures.

The client 200 receives the input diabetes onset factor value and provides it to the analysis server 100 . The client 200 receives the diabetes risk 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 the diabetes onset factor and transmits the corresponding input diabetes onset factor value to the analysis server 100 .

In an embodiment, the input device 210 may receive the blood of a user who needs to analyze the risk of developing diabetes, and may calculate factors for developing diabetes.

There may be one input device 210 or a plurality of input devices 210 .

The output device 220 may receive the diabetes onset risk result from the analysis server 100 and provide the determination result 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. Also, when receiving the determination result that the risk of developing diabetes is high, the output device 220 may generate a vibration to notify the user that the risk of developing diabetes is high. However, the method in which the output device 220 provides the determination result of the risk of diabetes to the user is not limited thereto, and various output methods that can be provided to the user, such as sound output, may be used. Also, 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 a plurality of output devices 220 .

Hereinafter, a method for predicting the risk of developing diabetes based on big data according to an embodiment of the present invention will be described. Hereinafter, differences from the above-mentioned big data-based diabetes onset risk prediction system according to an embodiment of the present invention will be described in detail, and parts that have not been described are big data-based diabetes onset according to an embodiment of the present invention. It may be the same as the risk prediction system.

2 is a flowchart schematically illustrating a method for predicting the risk of developing diabetes based on big data according to an embodiment of the present invention.

1 and 2, the big data-based diabetes risk prediction method according to an embodiment of the present invention includes the steps of acquiring an input diabetes onset factor value for the diabetes onset factor (S100), and collecting big data ( S200), and a diabetes risk prediction step (S300).

An input diabetes onset factor value for the diabetes onset factor is acquired (S100). The input diabetes onset factor value may be input from the client 200 and provided to the analysis server 100 . The input diabetes onset factor value may be input to the input device 210 and provided to the analysis server 100 .

Input diabetes onset factor values are collected over time to form big data (S200). The big data collection step ( S200 ) may be performed in the analysis server 100 .

By analyzing the big data, the risk of developing diabetes is predicted (S300). The risk of developing diabetes may be provided from the analysis device 100 to the output device 220 . The output device 220 may be implemented as a single device with the input device 210 , or may be implemented as separate devices.

In one embodiment, the diabetes risk prediction step (S300) is a learning step of learning the input diabetes onset factor value and the risk of diabetes as a dataset by one or more computers, using a deep learning learning model, and deep learning learning It may include predicting the risk of developing diabetes with the model 120 .

The risk of developing diabetes may be determined as a parameter of the deep learning learning model 120 mentioned above.

In an embodiment, the learning step may include accumulating input diabetes onset factor values to generate learning data. Normal diabetes onset factor values are calculated through the analysis of the learning data. It may be determined whether the input diabetes onset factor value exceeds a specific range formed based on the normal diabetes onset factor value.

In an embodiment, the learning step may include generating learning data by accumulating input diabetes onset factor values provided from the client 200 . The input diabetes onset factor value may correspond to the diabetes onset factor. In the learning step, abnormal feature information may be extracted from the training data.

In an embodiment, the learning step may include accumulating specific situation data by matching it with abnormal characteristic information. The abnormal characteristic information may mean, for example, that an input diabetes onset factor value, for example, a fasting blood sugar value, has a value that is less than a normal range. The abnormal characteristic information may mean, for example, that a difference between an input diabetes onset factor value and a reference value exceeds a predetermined value and has a value that does not fall within a normal range.

Abnormality characteristic information includes, for example, high-density lipoprotein (HDL) cholesterol value, triglyceride value, alcohol consumption, smoking status, exercise status, family history, past medical history, current medical history, abdominal circumference, BMI, age, height , weight, blood pressure, and living environment may mean that at least one has a value that is less than a normal range.

It is possible to recognize specific abnormal characteristic information within the input diabetes onset factor value. Context data corresponding to the recognized abnormal characteristic information may be transmitted to the client. The context data corresponding to the abnormal characteristic information may be, for example, a risk of diabetes.

The big data-based diabetes risk prediction method according to an embodiment of the present invention is implemented as a program (or application) to be executed in combination with a computer, which is hardware. can be saved.

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 as the program. (Code) may be included. Such code may include functional code related to a function defining functions necessary for executing the methods, etc. . In addition, the code may further include additional information necessary for the processor of the computer to execute functions or code related to memory reference for which location (address address) in the internal or external memory of the computer should be referenced. In addition, when the computer's processor needs to communicate with any other remote computer or server to execute functions, the code uses the computer's communication module to determine how to communicate with any other remote computer or server. , may further include a communication-related code for which information or media should be transmitted and received during communication.

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

The big data-based diabetes risk prediction system, prediction method, and program according to an embodiment of the present invention generate big data by accumulating diabetes onset factors that can be obtained during a basic health checkup over time without additional examination, By analyzing this, a risk situation can be prevented in advance by recognizing or predicting the risk of developing diabetes.

In the above, embodiments of the present invention have been described with reference to the accompanying drawings, but those skilled in the art to which the present invention pertains can practice the present invention in other specific forms without changing its technical spirit or essential features. You can understand that there is Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

Claims (20)

an analysis server comprising one or more computers, collecting input diabetes onset factor values for diabetes onset factors over time to form big data, and analyzing the big data to predict the risk of diabetes onset; and Including; a client connected to the analysis server; the client, receiving the input diabetes onset factor value and providing it to the analysis server, Receive and output the diabetes onset risk from the analysis server, The input diabetes onset factor value includes a fasting blood sugar value, The analysis server, A big data-based diabetes risk prediction system for predicting the risk of developing diabetes when the input diabetes onset factor value exceeds a reference value set based on the big data. According to claim 1, The analysis server, Using a deep learning learning model, learning the input diabetes onset factor value and the diabetes onset risk as a dataset, A big data-based diabetes risk prediction system that predicts the risk of developing diabetes with the deep learning learning model. 3. The method of claim 2, The analysis server, By accumulating the input diabetes onset factor values to generate learning data, Calculating a normal diabetes onset factor value in a normal range through the analysis of the learning data, A big data-based diabetes risk prediction system for determining whether the input diabetes onset factor value exceeds a specific range formed based on the normal diabetes onset factor value. 3. The method of claim 2, The analysis server, By accumulating the input diabetes onset factor values to generate learning data, A big data-based diabetes risk prediction system for extracting the risk of developing diabetes from the learning data. 5. The method of claim 4, The analysis server, Matching and accumulating specific situation data with the abnormal characteristic information, Recognizing specific abnormal characteristic information within the input diabetes onset factor value, A big data-based diabetes risk prediction system for transmitting situation data corresponding to the recognized abnormal characteristic information to the client. According to claim 1, The analysis server, A big data-based diabetes risk prediction system that analyzes the big data by logistic regression analysis. According to claim 1, The input diabetes onset factor value is, High-Density Lipoprotein (HDL) cholesterol level, triglyceride level, alcohol consumption, smoking status, exercise status, family history, past medical history, current medical history, abdominal circumference, BMI, age, height, weight, blood pressure, and living environment A big data-based diabetes risk prediction system further comprising at least one of. According to claim 1, The analysis server, A big data-based diabetes risk prediction system that predicts the risk of developing type 2 diabetes. According to claim 1, The risk of developing diabetes is A big data-based diabetes risk prediction system, including at least one of the onset time and the onset rate. According to claim 1, the client, an input device receiving the input diabetes onset factor value and providing it to the analysis server; and A big data-based diabetes risk prediction system, comprising an output device that receives and outputs the diabetes risk from the analysis server. obtaining an input diabetes incidence factor value for the diabetes incidence factor; a big data collection step of collecting the input diabetes onset factor values over time to form big data; and A diabetes risk prediction step of predicting the risk of developing diabetes by analyzing the big data; The input diabetes onset factor value includes a fasting blood sugar value, The step of predicting the risk of developing diabetes is When the input diabetes onset factor value exceeds a reference value set based on the big data, predicting the diabetes onset risk, a big data-based diabetes risk prediction method. 12. The method of claim 11, The step of predicting the risk of developing diabetes is a learning step of learning, by one or more computers, the input diabetes onset factor value and the diabetes onset risk as a dataset using a deep learning learning model; and Predicting the risk of developing diabetes with the deep learning learning model; Containing, a big data-based risk prediction method for diabetes. 13. The method of claim 12, The learning step is accumulating the input diabetes onset factor values to generate learning data; calculating a normal diabetes onset factor value within a normal range through analysis of the learning data; and Determining whether the input diabetes onset factor value exceeds a specific range formed based on the normal diabetes onset factor value; including, a big data-based diabetes risk prediction method. 13. The method of claim 12, The learning step is accumulating the input diabetes onset factor values to generate learning data; and Extracting the risk of developing diabetes from the learning data; Containing, a big data-based risk prediction method for diabetes. 15. The method of claim 14, The learning step is accumulating specific situation data by matching it with abnormal characteristic information; recognizing specific abnormal characteristic information within the input diabetes onset factor value; and Transmitting situation data corresponding to the recognized abnormal characteristic information to the client; further comprising, a big data-based diabetes risk prediction method. 13. The method of claim 12, The step of predicting the risk of developing diabetes is A big data-based diabetes risk prediction method for analyzing the big data by logistic regression analysis. 13. The method of claim 12, The input diabetes onset factor value is, High-Density Lipoprotein (HDL) cholesterol value, triglyceride value, alcohol consumption, smoking status, exercise status, family history, past medical history, current medical history, abdominal circumference, BMI, age, height , weight, blood pressure, and at least one of a living environment, big data-based diabetes risk prediction method. 13. The method of claim 12, The step of predicting the risk of developing diabetes is A big data-based diabetes risk prediction method that predicts the risk of developing type 2 diabetes. 13. The method of claim 12, The risk of developing diabetes is A big data-based diabetes risk prediction method, including at least one of an onset time and an onset rate. In combination with a computer that is hardware, the big data-based diabetes risk prediction program stored in a computer-readable recording medium to execute the big data-based diabetes risk prediction method of claim 11 .

Images