Blood glucose prediction system and method based on artificial intelligence

Abstract

To propose a system and method for predicting blood glucose from salivary glucose to overcome the limitation that blood can be collected only by an invasive method for blood glucose measurement and solve disadvantages such as inconvenience, pain, and the like at the time of blood collection.SOLUTION: A blood glucose prediction system includes: a learning modeling section for training a blood glucose variability inference model to infer a correlation between a physical indicator and blood glucose variability, and training a blood glucose inference model to infer a correlation between salivary glucose and blood glucose in consideration of the blood glucose variability; a subject information acquisition section for acquiring a physical indicator and salivary glucose of a subject; a blood glucose variability estimation section for estimating blood glucose variability of the subject using the blood glucose variability inference model with the physical indicator of the subject as an input parameter; and a blood glucose prediction section for predicting blood glucose of the subject using the blood glucose inference model with the salivary glucose and the estimated blood glucose variability of the subject as an input parameter.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The following embodiments relate to a system and method for predicting blood glucose from salivary sugars. [Background technology]

[0002] Generally, blood glucose, which is the glucose concentration in the blood, or urinary glucose is used as an index for diagnosing diabetes.

[0003] However, in urine glucose tests, people with impaired glucose tolerance, who are on the borderline between diabetes and healthy people, are classified as diabetes patients, which reduces the accuracy of diabetes diagnosis.

[0004] For this reason, blood glucose measurement is the main method used to diagnose diabetes, as it ensures the accuracy of the test. However, the only method available for measuring blood glucose is invasive blood sampling, which has the drawback of being time-consuming and painful.

[0005] Therefore, there is a need to propose a technology that can overcome the limitations of blood glucose measurement and solve the drawbacks. Summary of the Invention [Problem to be solved by the invention]

[0006] One embodiment proposes a system and method for predicting blood glucose from salivary sugars in order to overcome the limitation that the only available method for measuring blood glucose is invasive blood sampling, and to resolve drawbacks such as the effort and pain involved in blood sampling.

[0007] More specifically, one embodiment proposes a system and method for predicting blood glucose from salivary sugars by utilizing a blood glucose inference model constructed by learning from experiments using artificial intelligence to infer the correlation between salivary sugars and blood glucose.

[0008] In particular, one embodiment proposes a system and method for constructing a blood glucose inference model that takes into account blood glucose variability, which is a factor that affects the correlation between salivary sugar and blood glucose.

[0009] In this regard, in order to solve the drawbacks of measuring blood glucose variability, such as the effort and complexity involved, one embodiment proposes a system and method for estimating blood glucose variability from physical indicators by utilizing a blood glucose variability inference model constructed by learning from experiments using an artificial intelligence platform to infer the correlation between a subject's physical indicators and blood glucose variability.

[0010] However, the technical problem to be solved by the present invention should not be limited to the above, and may be variously expanded within the scope that does not deviate from the technical idea and scope of the present invention. [Means for solving the problem]

[0011] According to one embodiment, the blood glucose prediction system may include a learning modeling unit that trains a blood glucose variability inference model to infer a correlation between a physical index and blood glucose variability and trains a blood glucose level inference model to infer a correlation between salivary sugar and blood glucose taking the blood glucose variability into consideration; a subject information acquisition unit that acquires the subject's physical index and salivary sugar; a blood glucose variability estimation unit that uses the subject's physical index as input parameters and estimates the subject's blood glucose variability using the blood glucose variability inference model; and a blood glucose prediction unit that uses the subject's salivary sugar and estimated blood glucose variability as input parameters and predicts the subject's blood glucose using the blood glucose inference model.

[0012] According to one aspect, the learning modeling unit may be characterized by inferring correlations between the physical indicators and HOMA-IR and HOMA β-cell, and training the blood glucose variability inference model to infer correlations between the HOMA-IR and HOMA β-cell and the blood glucose variability.

[0013] According to another aspect, the learning modeling unit may be characterized by training the blood glucose variability inference model to infer a correlation between the insulin resistance and insulin secretion capacity calculated by the HOMA-IR and HOMA β-cell and the blood glucose variability.

[0014] According to another aspect, the learning modeling unit may be characterized by: learning an experiment that infers a correlation between the physical index and the blood glucose variability using an artificial intelligence platform to construct the blood glucose variability inference model; and learning an experiment that infers a correlation between the salivary sugar and the blood glucose taking the blood glucose variability into consideration using an artificial intelligence platform to construct the blood glucose inference model.

[0015] According to yet another aspect, the subject's physical characteristics may be characterized as including the subject's body mass index (BMI) and waist circumference.

[0016] According to one embodiment, a blood glucose prediction method may include steps of acquiring a subject's physical indicators and salivary sugar, estimating the subject's blood glucose variability using a blood glucose variability inference model (the blood glucose variability inference model is trained to infer a correlation between the physical indicators and blood glucose variability) using the subject's physical indicators as input parameters, and predicting the subject's blood glucose using a blood glucose inference model (the blood glucose inference model is trained to infer a correlation between the salivary sugar and blood glucose taking the blood glucose variability into consideration) using the subject's salivary sugar and the estimated blood glucose variability as input parameters.

[0017] According to one aspect, the blood glucose variability inference model may be characterized by being trained to infer correlations between the physical indicators and HOMA-IR and HOMA β-cell, and to infer correlations between the HOMA-IR and HOMA β-cell and the blood glucose variability.

[0018] According to another aspect, the blood glucose variability inference model may be characterized by being trained to infer a correlation between the blood glucose variability and the insulin resistance and insulin secretory capacity calculated by the HOMA-IR and HOMA β-cell.

[0019] According to another aspect, the blood glucose prediction method may further include a step of constructing the blood glucose variability inference model by learning, using an artificial intelligence platform, an experiment that infers a correlation between the physical index and the blood glucose variability, and a step of constructing the blood glucose level inference model by learning, using an artificial intelligence platform, an experiment that infers a correlation between the salivary sugar and the blood glucose level taking the blood glucose variability into consideration.

[0020] According to one embodiment, the blood glucose variability estimation system may include a learning modeling unit that trains a blood glucose variability inference model to infer a correlation between a physical index and blood glucose variability, a subject information acquisition unit that acquires the physical index of a subject, and a blood glucose variability estimation unit that uses the physical index of the subject as input parameters and estimates the blood glucose variability of the subject using the blood glucose variability inference model.

[0021] According to one aspect, the learning modeling unit may be characterized by inferring correlations between the physical indicators and HOMA-IR and HOMA β-cell, and training the blood glucose variability inference model to infer correlations between the HOMA-IR and HOMA β-cell and the blood glucose variability.

[0022] According to another aspect, the learning modeling unit may be characterized by training the blood glucose variability inference model to infer a correlation between the insulin resistance and insulin secretion capacity calculated by the HOMA-IR and HOMA β-cell and the blood glucose variability.

[0023] According to another aspect, the learning modeling unit may be characterized by learning experiments for inferring a correlation between the physical index and the blood glucose variability based on artificial intelligence to construct the blood glucose variability inference model.

[0024] According to yet another aspect, the subject's physical characteristics may be characterized as including the subject's body mass index (BMI) and waist circumference.

[0025] According to one embodiment, a method for estimating blood glucose variability may include acquiring physical indicators of a subject, and estimating the blood glucose variability of the subject using the physical indicators of the subject as input parameters and utilizing a blood glucose variability inference model (the blood glucose variability inference model is trained to infer a correlation between the physical indicators and blood glucose variability).

[0026] According to one aspect, the blood glucose variability inference model may be characterized by being trained to infer correlations between the physical indicators and HOMA-IR and HOMA β-cell, and to infer correlations between the HOMA-IR and HOMA β-cell and the blood glucose variability.

[0027] According to another aspect, the blood glucose variability inference model may be characterized by being trained to infer a correlation between the blood glucose variability and the insulin resistance and insulin secretory capacity calculated by the HOMA-IR and HOMA β-cell.

[0028] According to another aspect, the blood glucose variability estimation method may further include a step of constructing the blood glucose variability inference model by learning an experiment for inferring a correlation between the physical index and the blood glucose variability based on artificial intelligence. [Effects of the Invention]

[0029] One embodiment proposes a system and method for predicting blood glucose from salivary sugars, thereby overcoming the limitation that the only available method for measuring blood glucose is invasive blood sampling, and resolving drawbacks such as the effort and pain involved in blood sampling.

[0030] More specifically, one embodiment proposes a system and method for predicting blood glucose from salivary sugars by utilizing a blood glucose inference model constructed by learning from experiments using an artificial intelligence platform to infer the correlation between salivary sugars and blood glucose.

[0031] In particular, one embodiment can propose a system and method for constructing a blood glucose inference model that takes into account blood glucose variability, which is a factor that affects the correlation between salivary sugar and blood glucose.

[0032] In this case, one embodiment proposes a system and method for estimating blood glucose variability from physical indices by utilizing a blood glucose variability inference model constructed by learning from experiments using an artificial intelligence platform to infer the correlation between a subject's physical indices and blood glucose variability, thereby resolving drawbacks such as the effort and complexity of measuring blood glucose variability.

[0033] However, the effects of the present invention should not be limited to those described above, and may be variously expanded within the scope of the technical idea and scope of the present invention. [Brief explanation of the drawings]

[0034] [Figure 1] FIG. 1 illustrates an example of a network environment in one embodiment. [Figure 2] FIG. 1 is a diagram illustrating the internal configuration of an electronic device and a server according to an embodiment. [Figure 3] FIG. 1 is a block diagram illustrating an example of a blood glucose prediction system implemented on a processor of a server in one embodiment. [Figure 4] 1 is a flowchart illustrating a blood glucose prediction method in one embodiment. [Figure 5] FIG. 1 is a conceptual diagram for explaining a blood glucose variability inference model used in a blood glucose prediction method in one embodiment. [Figure 6] FIG. 1 is a block diagram illustrating an example of a glycemic variability estimation system implemented on a processor of a server in one embodiment. [Figure 7] 1 is a flowchart illustrating a method for estimating glycemic variability, in one embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0035]

[0036]

[0037]

[0038]

[0039]

[0040]

[0041] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, the present invention should not be limited or restricted by these drawings. The same reference numerals in the drawings denote the same elements.

[0042] Furthermore, the terminology used herein is intended to appropriately describe preferred embodiments of the present invention, but may vary depending on the intentions of viewers and operators, the practices of the field to which the present invention pertains, and other factors. Therefore, definitions of such terms should be based on the overall content of this specification. For example, the singular forms used herein also include the plural forms unless otherwise specified in the context. Furthermore, the terms "comprises" and / or "comprising" used herein do not imply that a referenced component, step, action, and / or element excludes the presence or addition of one or more other components, steps, actions, and / or elements. Furthermore, although terms such as "first" and "second" are used herein to describe various regions, directions, shapes, and the like, these regions, directions, and shapes should not be construed as being limited by such terms. These terms are merely used to distinguish a given region, direction, or shape from other regions, directions, or shapes. Therefore, a portion referred to as a "first portion" in one embodiment may be referred to as a "second portion" in another embodiment.

[0043] Furthermore, it should be understood that the various embodiments of the present invention, although different from one another, are not necessarily mutually exclusive. For example, a particular shape, structure, and characteristic described in this specification may be implemented in other embodiments without departing from the spirit and scope of the present invention. Furthermore, the location, arrangement, or configuration of individual components within the scope of each presented embodiment may be changed without departing from the spirit and scope of the present invention. It should be understood that the present invention is subject to change without departing from the spirit and scope of the present invention.

[0044]

[0045] Hereinafter, salivary sugar means glucose contained in saliva, and blood glucose means glucose contained in blood. Furthermore, hereinafter, obtaining salivary sugar means obtaining information about salivary sugar (e.g., salivary sugar concentration, index, numerical value, etc.), and predicting blood glucose means predicting information about blood glucose (e.g., blood glucose concentration, index, numerical value, etc.).

[0046]

[0047] Fig. 1 is a diagram showing an example of a network environment according to an embodiment. The network environment in Fig. 1 includes a plurality of electronic devices 110, 120, 130, 140, and 150, a server 160, and a network 170. Fig. 1 is merely an example for explaining the present invention, and the number of electronic devices and the number of servers should not be limited to those shown in Fig. 1.

[0048] The multiple electronic devices 110, 120, 130, 140, and 150 are terminals carried by each sample subject, and each of the multiple electronic devices 110, 120, 130, 140, and 150 may include a collection device 111, a biosensor 112, and a measurement device 113 as a sample measurement system for collecting salivary sugar from the subject.

[0049] The collection device 111 is a device for collecting a specimen (e.g., saliva) and may include a specimen collection section, a filter, and a compression tube. When the specimen is saliva, the collection device 111 may remove interfering substances from the collected saliva through a filter in the compression tube and provide the interfering substance-removed saliva to the outside, i.e., to the biosensor 112.

[0050] Biosensor 112 is a component that performs the function of sensing information to be measured (e.g., glucose) from a sample (e.g., saliva) collected by collection device 111 when the sample is inserted into collection device 111 and interfering substances have been removed.A biosensor strip is inserted into measurement device 113, and biosensor 112 recognizes the sample based on a sample recognition signal received from measurement device 113, and may provide measurement device 113 with a response signal for the glucose contained in the sample via a sample measurement signal applied separately from the sample recognition signal.

[0051] The measuring device 113 recognizes the insertion of the biosensor 112 and provides a sample recognition signal to the biosensor 112 to determine whether a sample has come into contact with the biosensor 112. If it determines that a sample has come into contact, the measuring device 113 provides a sample measurement signal, receives a response signal for the sample to be measured, and measures the sample.

[0052] Furthermore, measurement device 113 may include a communication module to communicate with server 160 via network 170. However, instead of directly connecting to network 170 and communicating with server 160, multiple electronic devices 110, 120, 130, 140, and 150 each including measurement device 113 may be configured to connect to network 170 via a terminal carried by the subject (e.g., a smartphone, a mobile phone, a tablet, a navigation system, a PC, a laptop PC, a digital broadcasting terminal, a PDA (Personal Digital Assistant), a PMP (Portable Multimedia Player), etc.) and communicate with server 160.

[0053] The communication method is not limited, and may include not only communication methods using communication networks (for example, a mobile communication network, a wired Internet, a wireless Internet, and a broadcast network) that can be included in network 170, but also short-range wireless communication between devices. For example, network 170 may include any one or more of networks such as a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), a broadband network (BBN), and the Internet. Furthermore, network 170 may include any one or more of network topologies including, but not limited to, a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree or hierarchical network, etc.

[0054] The above describes the multiple electronic devices 110, 120, 130, 140, 150 as each including a collection device 111, a biosensor 112, and a measurement device 113, but this is not limited to this and the devices may also be terminals (e.g., smartphones, mobile phones, tablets, navigation systems, PCs, notebook PCs, digital broadcasting terminals, PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), etc.) that store information related to the subject's physical indicators and salivary sugars.

[0055] The server 160 may be realized as a computer device or multiple computer devices that communicate with multiple electronic devices 110, 120, 130, 140, and 150 via a network 170, receives information about the samples (saliva) measured from the measuring devices 113 of each of the multiple electronic devices 110, 120, 130, 140, and 150, and provides a blood glucose prediction service that predicts the subject's blood glucose based on the received information about the samples (saliva).

[0056] That is, each of the multiple electronic devices 110, 120, 130, 140, and 150 may connect to the server 160 under the control of a pre-installed operating system (OS) or at least one program (for example, a browser or the installed application) and receive the blood glucose prediction service provided by the server 160.

[0057]

[0058] Fig. 2 is a block diagram illustrating the internal configuration of an electronic device and a server in one embodiment. Fig. 2 illustrates the internal structure of a first electronic device 110 as an example of an electronic device owned by a subject who receives the blood glucose prediction service, and the internal configuration of a server 160 that communicates with the first electronic device 110 to provide the blood glucose prediction service. In the following description of the first electronic device 110, for convenience, descriptions of the collection device 111, biosensor 112, and measurement device 113 included in the first electronic device 110 will be omitted.

[0059] The first electronic device 110 and the server 160 may include memories 211 and 221, processors 212 and 222, communication modules 213 and 223, and input / output interfaces 214 and 224. The memories 211 and 221 are computer-readable recording media, and may include RAM (random access memory), ROM (read only memory), and the like. The memories 211 and 221 may include a memory, a permanent mass storage device such as a disk drive, and an operating system and at least one program code (for example, a program code that is installed and executed in the first electronic device 110). The software components may be stored in the memories 211, 221, for example, in the form of software components (such as code for an application). Such software components may be loaded from a computer-readable recording medium separate from the memories 211, 221. The separate computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, a disk, a tape, a DVD / CD-ROM drive, or a memory card. In other embodiments, the software components may be loaded into the memories 211, 221 through a communication module 213, 223 that is not a computer-readable recording medium. For example, at least one program may be loaded into the memories 211, 221 based on a program (such as the application described above) to be installed by a file provided over the network 170 by a developer or a file distribution system that distributes application installation files.

[0060] The processors 212, 222 may be configured to process computer program instructions by performing basic arithmetic, logic, and input / output operations. The instructions may be provided to the processors 211, 221 by the memories 211, 221 or the communication modules 213, 223. For example, the processors 212, 222 may be configured to execute instructions received according to program code stored in a storage device such as the memories 211, 221.

[0061] The communication modules 213 and 223 may provide a function for the first electronic device 110 and the server 160 to communicate with each other via the network 170, and may also provide a function for communicating with other electronic devices (e.g., the second electronic device 120, the third electronic device 130, the fourth electronic device, the fifth electronic device 150, etc.) or other servers. For example, a request (e.g., a blood glucose prediction service request) generated by the processor 212 of the first electronic device 110 according to program code recorded in a recording device such as the memory 211 may be transmitted to the server 160 via the network 170 under the control of the communication module 213. Conversely, control signals, commands, content, files, etc. provided under the control of the processor 222 of the server 160 may be received by the first electronic device 110 via the communication module 213 of the first electronic device 110 via the communication module 223 and the network 170. For example, control signals and commands from the server 160 received through the communication module 213 may be transmitted to the processor 212 and the memory 211, and content and files may be recorded on a recording medium that the first electronic device 110 may further include.

[0062] The input / output interface 214 may be a means for interfacing with the input / output device 215. For example, the input device may include a device such as a keyboard or a mouse, and the output device may include a device such as a display for displaying a communication session of an application. As another example, the input / output interface 214 may be a means for interfacing with a device that integrates input and output functions into one, such as a touch screen. As a more specific example, when the processor 212 of the first electronic device 110 processes instructions of a computer program loaded in the memory 211, service screens and content configured using data provided by the server 160 or the second electronic device 120 may be displayed on the display through the input / output interface 214. Similarly, the input / output interface 224 may output information configured using data provided by the server 160 when the processor 222 of the server 160 processes instructions of a computer program loaded in the memory 221.

[0063] Also, in other embodiments, the first electronic device 110 and the server 160 may include more components than those shown in Figure 2. However, most prior art components need not be explicitly shown in the figures.

[0064] Specific embodiments of a blood glucose prediction method and system for providing a blood glucose prediction service are described below.

[0065]

[0066] FIG. 3 is a block diagram showing an example of a blood glucose prediction system implemented in a server processor in one embodiment, FIG. 4 is a flowchart showing a blood glucose prediction method in one embodiment, and FIG. 5 is a conceptual diagram for explaining a blood glucose variability inference model used in the blood glucose prediction method in one embodiment.

[0067] A blood glucose prediction system realized by a computer may be configured in the server 160 according to an embodiment. The server 160 is an entity that provides a blood glucose prediction service to a plurality of electronic devices 110, 120, 130, 140, and 150 that are clients, and may provide the blood glucose prediction service to each of the plurality of electronic devices 110, 120, 130, 140, and 150 by executing steps 410 to 430 shown in Fig. 4 .

[0068] 3, the processor 222 of the server 160 may include, as components, a learning modeling unit 310, a subject information acquisition unit 320, a blood glucose variability estimation unit 330, and a blood glucose prediction unit 340. Depending on the embodiment, the components of the processor 222 may be selectively included or excluded from the processor 222. Also, depending on the embodiment, the components of the processor 222 may be separated or combined to express the functions of the processor 222. For example, at least some of the components of the processor 222 may be implemented in the processor 212 included in the first electronic device 110, which is the terminal of the first subject, or in the processor included in the second electronic device 120, which is the terminal of the second subject.

[0069] Such processor 222 and components of processor 222 may control server 160 to execute steps 410 to 430 included in the blood glucose prediction method of Fig. 4. For example, processor 222 and components of processor 222 may be implemented to execute instructions from operating system code and at least one program code included in memory 221.

[0070] Here, the components of the processor 222 may be representations of different functions of the processor 222 that are executed by the processor 222 according to instructions provided by the program code recorded on the server 160. For example, a blood glucose prediction unit 330 may be used as a functional representation of the processor 222 that predicts the blood glucose of a subject.

[0071] Prior to step 410, the processor 222 may read necessary instructions (not shown) from the memory 221 into which instructions related to the control of the server 160 are loaded. In this case, the read instructions may include instructions for controlling the processor 222 to execute steps 410 to 430 described below.

[0072] Furthermore, before step 410, the learning modeling unit 310 may pre-construct a blood glucose variability inference model by learning it to infer the correlation between physical indicators and blood glucose variability, or may pre-construct a blood glucose inference model by learning it to infer the correlation between salivary sugar and blood glucose taking blood glucose variability into account.

[0073] The correlation between salivary sugars and blood glucose is affected by blood glucose variability, and therefore, blood glucose variability must be taken into account in order to accurately infer and define the correlation between salivary sugars and blood glucose.

[0074] On the other hand, the physical indices body mass index (BMI) and waist circumference correlate with HOMA-IR and HOMA β-cell (hereinafter, the physical indices typically include body mass index (BMI) and waist circumference). Insulin resistance and insulin secretory capacity can be calculated from HOMA-IR and HOMA β-cell, and insulin resistance and insulin secretory capacity correlate with blood glucose variability.

[0075] Using these characteristics, the learning modeling unit 310 can construct a blood glucose inference model by learning, using an artificial intelligence platform, experiments that infer the correlation between salivary glucose and blood glucose taking blood glucose variability into consideration, and can also construct a blood glucose variability inference model that infers blood glucose variability to be reflected in the blood glucose inference model. For example, as shown in Figure 5, the learning modeling unit 310 may construct a blood glucose variability inference model by learning through experiments that infer the correlation between physical indices and HOMA-IR and HOMA β-cell (step 510), and infer the correlation between insulin resistance and insulin secretion capacity calculated from HOMA-IR and HOMA β-cell and blood glucose variability (step 520).

[0076] That is, the learning modeling unit 310 can construct a blood glucose variability inference model by learning experiments that infer the correlation between physical indicators and blood glucose variability using an artificial intelligence platform, and can construct a blood glucose inference model by learning experiments that infer the correlation between saliva sugar and blood glucose taking blood glucose variability into consideration using an artificial intelligence platform.

[0077] Various known machine learning algorithms may be used in the learning process of each of the blood glucose variability inference model and the blood glucose level inference model.

[0078] In step 410, the subject information acquisition unit 320 may acquire the subject's physical indicators and salivary sugars. For example, the subject information acquisition unit 320 may receive and acquire information about saliva measured by the measuring devices 113 of the plurality of electronic devices 110, 120, 130, 140, and 150, as described above, or may acquire input physical indicators of each subject from each of the plurality of electronic devices 110, 120, 130, 140, and 150.

[0079] In step 420, the blood glucose variability estimator 330 may estimate the blood glucose variability of the subject using the subject's physical indicators as input parameters and a blood glucose variability inference model.

[0080] In step 430, the blood glucose prediction unit 340 may use the subject's salivary glucose and the estimated blood glucose variability as input parameters to predict the subject's blood glucose using a blood glucose inference model. The predicted blood glucose of the subject may be provided to an electronic device corresponding to the subject.

[0081] In this way, the blood glucose prediction system and method of one embodiment overcomes the limitation that the only available method for measuring blood glucose is invasive blood sampling by using a blood glucose inference model to predict blood glucose levels from salivary sugars, and solves drawbacks such as the effort and pain involved in blood sampling.In addition, the accuracy of blood glucose prediction can be improved by taking blood glucose variability into account in the blood glucose inference model.

[0082] In addition, the blood glucose prediction system and method of one embodiment can solve the drawbacks of measuring blood glucose variability, such as the effort and complexity involved, by estimating blood glucose variability, which is used as an input parameter for the blood glucose inference model, using a blood glucose variability inference model.

[0083] Although a blood glucose prediction system and method have been described above, the present invention can also be used as a standalone application for estimating blood glucose variability, which will be described in more detail with reference to Figures 6 and 7.

[0084] Although the above describes predicting blood glucose from salivary sugar, the blood glucose prediction system according to one embodiment can also predict salivary sugar from blood glucose. In such a case, in response to the subject information acquisition unit 320 acquiring blood glucose instead of salivary sugar, the blood glucose prediction unit 340 can predict salivary sugar from the acquired blood glucose.

[0085]

[0086] FIG. 6 is a block diagram illustrating an example of a blood glucose variability estimation system implemented in a processor of a server in one embodiment, and FIG. 7 is a flowchart illustrating a blood glucose variability estimation method in one embodiment.

[0087] 6 and 7, a blood glucose variability estimation system implemented by a computer may be configured in a server 160 according to an embodiment. The server 160 is an entity that provides a blood glucose variability estimation service to multiple client electronic devices 110, 120, 130, 140, and 150, and may provide the blood glucose estimation service to each of the multiple electronic devices 110, 120, 130, 140, and 150 by performing steps 710 to 720 shown in FIG.

[0088] 6, the processor 222 of the server 160 may include, as components, a learning modeling unit 610, a subject information acquisition unit 620, and a blood glucose variability estimation unit 630. Depending on the embodiment, the components of the processor 222 may be selectively included or excluded from the processor 222. Also, depending on the embodiment, the components of the processor 222 may be separated or combined to express the functions of the processor 222. For example, at least some of the components of the processor 222 may be implemented in the processor 212 included in the first electronic device 110, which is the terminal of the first subject, or in the processor included in the second electronic device 120, which is the terminal of the second subject.

[0089] Such processor 222 and components of processor 222 may control server 160 to execute steps 710 to 720 included in the blood glucose variability estimation method of Fig. 7. For example, processor 222 and components of processor 222 may be implemented to execute instructions from operating system code and at least one program code included in memory 221.

[0090] Here, the components of the processor 222 may be representations of different functions of the processor 222 that are executed by the processor 222 according to instructions provided by program code stored on the server 160. For example, a blood glucose variability estimator 630 may be used as a functional representation of the processor 222 that estimates the blood glucose variability of the subject.

[0091] Prior to step 710, the processor 222 may read necessary instructions (not shown) from the memory 221 into which instructions related to the control of the server 160 are loaded. In this case, the read instructions may include instructions for controlling the processor 222 to execute steps 710 to 720 described below.

[0092] Furthermore, before step 710, the learning modeling unit 610 may previously construct a blood glucose variability inference model by training it to infer the correlation between the physical index and blood glucose variability.

[0093] The physical indicators, body mass index (BMI) and waist circumference, were used to evaluate HOMA-IR and HOM. (Hereinafter, physical indices typically include body mass index (BMI) and waist circumference.) Insulin resistance and insulin secretion capacity can be calculated from HOMA-IR and HOMA β-cell, and insulin resistance and insulin secretion capacity are correlated with blood glucose variability.

[0094] Using such characteristics, the learning modeling unit 610 may construct a blood glucose variability inference model that infers blood glucose variability. For example, as shown in Fig. 5, the learning modeling unit 610 may construct a blood glucose variability inference model by learning through experiments, which infers correlations between physical indices and HOMA-IR and HOMA β-cell (step 510), and infers correlations between insulin resistance and insulin secretory capacity calculated by HOMA-IR and HOMA β-cell and blood glucose variability (step 520).

[0095] That is, the learning modeling unit 610 can construct a blood glucose variability inference model by learning an experiment that infers the correlation between physical indices and blood glucose variability based on artificial intelligence.

[0096] A variety of known machine learning algorithms may be used in the learning process of such a blood glucose variability inference model.

[0097] In step 710, the subject information acquiring unit 620 may acquire physical indices of the subject. For example, the subject information acquiring unit 620 may acquire input as physical indices of each subject from each of the plurality of electronic devices 110, 120, 130, 140, and 150.

[0098] In step 720, the glycemic variability estimator 630 may estimate the glycemic variability of the subject using the subject's physical indicators as input parameters and utilizing a glycemic variability inference model.

[0099] In this way, the blood glucose variability estimation system and method of one embodiment can solve the drawbacks of blood glucose variability measurement, such as the effort and complexity, by estimating blood glucose variability using a blood glucose variability inference model.

[0100] The blood glucose variability estimated as described above can be utilized in a variety of tasks and fields, as well as in the blood glucose level estimation system and method described above.

[0101]

[0102] The above-described devices may be implemented using hardware components, software components, and / or a combination of hardware and software components. For example, the devices and components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable array (FPA), a programmable logic unit (PLU), a microprocessor, or various devices capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the OS. The processing device may also access, record, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, a single processing device may be described. However, those skilled in the art will understand that a processing device may include multiple processing elements and / or multiple types of processing elements. For example, a processing device may include multiple processors or one processor and one controller. Other processing configurations, such as parallel processors, are also possible.

[0103] Software may include computer programs, codes, instructions, or a combination of one or more of these, which may configure a processing device to operate as desired or may independently or collectively instruct the processing device. The software and / or data may be embodied in any type of machine, component, physical device, virtual device, computer storage medium, or device to be interpreted by the processing device or to provide instructions or data to the processing device. The software may be distributed and stored and executed in a distributed manner on computer systems connected by a network. The software and data may be stored on one or more computer-readable storage media.

[0104] Methods according to embodiments may be embodied in the form of program instructions executable by various computer means and stored on a computer-readable medium. The computer-readable medium may include, alone or in combination, program instructions, data files, data structures, and the like. The program instructions stored on the medium may be specially designed and constructed for the embodiments, or may be available and known to those skilled in the art of computer software. Examples of computer-readable media include magnetic media such as hard disks, floppy disks, and magnetic tape; optical media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices configured to store program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include not only machine code, such as that generated by a compiler, but also high-level language code executed by a computer using an interpreter, for example.

[0105] Although the embodiments have been described above based on limited examples and drawings, those skilled in the art will appreciate that various modifications and variations may be made from the above description. For example, the described techniques may be performed in an order different from that described, and / or the described system, structure, device, circuit, or other element may be coupled or combined in a manner different from that described, or may be substituted or replaced by other elements or equivalents, and still achieve suitable results.

[0106] Therefore, different embodiments are within the scope of the appended claims, provided that they are equivalent to the claims.

Claims

1. a learning modeling unit that trains a blood glucose variability inference model to infer the correlation between a physical index and blood glucose variability, and trains a blood glucose inference model to infer the correlation between saliva sugar and blood glucose taking into account the blood glucose variability; a subject information acquisition unit that acquires the subject's physical index and saliva sugar; a blood glucose variability estimation unit that estimates the blood glucose variability of the subject using the blood glucose variability inference model with the subject's physical index as an input parameter; and a blood glucose prediction unit that predicts the blood glucose of the subject using the blood glucose inference model, with the salivary sugar of the subject and the estimated blood glucose variability as input parameters; A blood glucose prediction system, including:

2. The learning modeling unit The blood glucose prediction system of claim 1, characterized in that the blood glucose variability inference model is trained to infer correlations between the physical indicators and HOMA-IR and HOMAβ-cell, and to infer correlations between the HOMA-IR and HOMAβ-cell and the blood glucose variability.

3. The learning modeling unit The blood glucose prediction system of claim 2, wherein the blood glucose variability inference model is trained to infer a correlation between the insulin resistance and insulin secretion capacity calculated by the HOMA-IR and HOMAβ-cell and the blood glucose variability.

4. The learning modeling unit The blood glucose prediction system of claim 1, characterized in that the blood glucose variability inference model is constructed by learning, using an artificial intelligence platform, from an experiment to infer the correlation between the physical indicators and the blood glucose variability, and the blood glucose inference model is constructed by learning, using an artificial intelligence platform, from an experiment to infer the correlation between the salivary sugar and the blood glucose taking into account the blood glucose variability.

5. The subject's physical index is The blood glucose prediction system of claim 1 , further comprising the subject's body mass index (BMI) and waist circumference.

6. obtaining the subject's physical indices and salivary sugars; estimating the blood glucose variability of the subject using a blood glucose variability inference model (the blood glucose variability inference model is trained to infer a correlation between the body index and blood glucose variability) using the subject's physical index as input parameters; and Predicting the blood glucose of the subject using a blood glucose inference model (the blood glucose inference model is trained to infer the correlation between salivary sugar and blood glucose taking into account the blood glucose variability) with the subject's salivary sugar and the estimated blood glucose variability as input parameters. A blood glucose prediction method comprising:

7. The blood glucose variability inference model comprises: The blood glucose prediction method according to claim 6, characterized in that it is trained to infer correlations between the physical indicators and HOMA-IR and HOMAβ-cell, and to infer correlations between the HOMA-IR and HOMAβ-cell and the blood glucose variability.

8. The blood glucose variability inference model comprises: The system is trained to infer the correlation between the insulin resistance and insulin secretory capacity calculated by the HOMA-IR and HOMAβ-cell and the blood glucose variability. The blood glucose prediction method according to claim 7 .

9. A step of constructing the blood glucose variability inference model by learning an experiment for inferring the correlation between the physical index and the blood glucose variability using an artificial intelligence platform; and and constructing the blood glucose level inference model by learning an experiment based on artificial intelligence to infer the correlation between the saliva sugar and the blood glucose level while taking into account the variability of the blood glucose level. The blood glucose prediction method according to claim 6, further comprising:

10. a learning modeling unit that trains a blood glucose variability inference model to infer a correlation between a physical index and blood glucose variability; a subject information acquisition unit that acquires physical indices of the subject; and a blood glucose variability estimation unit that estimates the blood glucose variability of the subject using the blood glucose variability inference model with the subject's physical index as an input parameter; A blood glucose variability estimation system comprising:

11. The learning modeling unit The blood glucose variability estimation system of claim 10, characterized in that the blood glucose variability inference model is trained to infer correlations between the physical indicators and HOMA-IR and HOMAβ-cell, and to infer correlations between the HOMA-IR and HOMAβ-cell and the blood glucose variability.

12. The learning modeling unit The blood glucose variability estimation system of claim 10, characterized in that the blood glucose variability inference model is trained to infer a correlation between the insulin resistance and insulin secretion capacity calculated by the HOMA-IR and HOMAβ-cell and the blood glucose variability.

13. The learning modeling unit The blood glucose variability estimation system according to claim 10, characterized in that the blood glucose variability inference model is constructed by learning experiments for inferring the correlation between the physical indicators and the blood glucose variability using an artificial intelligence platform.

14. The subject's physical index is The blood glucose variability estimation system of claim 10, further comprising the subject's body mass index (BMI) and waist circumference.

15. acquiring physical indices of the subject; and estimating the blood glucose variability of the subject using a blood glucose variability inference model (the blood glucose variability inference model is trained to infer a correlation between the body index and blood glucose variability) using the subject's physical index as input parameters; A method for estimating blood glucose variability, comprising:

16. The blood glucose variability inference model comprises: The blood glucose variability estimation method of claim 15, characterized in that it infers correlations between the physical indicators and HOMA-IR and HOMAβ-cell, and is trained to infer correlations between the HOMA-IR and HOMAβ-cell and the blood glucose variability.

17. The blood glucose variability inference model comprises: The blood glucose variability estimation method according to claim 16, characterized in that the method is trained to infer a correlation between the insulin resistance and insulin secretion capacity calculated by the HOMA-IR and HOMAβ-cell and the blood glucose variability.

18. constructing the blood glucose variability inference model by learning an experiment for inferring the correlation between the physical index and the blood glucose variability based on artificial intelligence; The method of claim 15, further comprising:

Images