A method and an apparatus for predicting the onset of pediatric asthma due to exposure to particulate matter in the fetus

Abstract

A computing device according to one aspect comprises at least one memory; and at least one processor; wherein the processor generates a group containing at least one biomarker associated with the onset of pediatric asthma using DNA obtained from subjects, extracts a biomarker corresponding to the biomarker included in the group from DNA obtained from a subject, confirms the degree of methylation of the extracted biomarker, and diagnoses whether the subject has developed pediatric asthma through the confirmed degree of methylation.

Description

Technology Field

[0001] The present disclosure relates to a method and apparatus for diagnosing whether pediatric asthma develops due to exposure to fine dust during the fetal period. Background Technology

[0002] Asthma is a disease affecting the bronchi. When an asthma patient is exposed to specific triggers, inflammation causes the bronchi to narrow severely, leading to recurring symptoms such as coughing, shortness of breath, and chest tightness. Symptoms of asthma include swelling of the bronchial mucosa and mucus secretion due to inflammation, as well as difficulty breathing caused by bronchial blockage resulting from the contraction of bronchial muscles.

[0003] Pediatric asthma refers to asthma that develops in children. The onset of pediatric asthma is influenced by environmental factors as well as genetic factors. In other words, asthma develops as the bronchi narrow when exposed to external irritants such as pollen and dust. While pediatric asthma is primarily diagnosed through tests such as pulmonary function tests and bronchial provocation tests, it is difficult to perform these tests on preschool-aged children; therefore, diagnosis is usually based solely on clinical history.

[0004] Recently, the incidence of respiratory diseases has been rising due to the increase in domestic fine dust emissions. In particular, research indicates that excessive maternal exposure to fine dust during the fetal period affects the development of respiratory diseases in children after birth. Therefore, there is a need to identify the causes triggering pediatric asthma due to fetal fine dust exposure and to develop technologies for diagnosing the condition. The problem to be solved

[0005] The invention provides a method and device for diagnosing whether pediatric asthma develops due to exposure to fine dust during the fetal period.

[0006] In addition, the invention provides a computer-readable recording medium that records a program for executing the above method on a computer. The technical problems to be solved are not limited to those described above, and other technical problems may exist. means of solving the problem

[0007] A computing device according to one aspect comprises at least one memory; and at least one processor; wherein the processor generates a group containing at least one biomarker associated with the onset of pediatric asthma using DNA obtained from subjects, extracts a biomarker corresponding to the biomarker included in the group from DNA obtained from a subject, checks the degree of methylation of the extracted biomarker, and diagnoses whether the subject has developed pediatric asthma through the measured degree of methylation.

[0008] According to another aspect, a method for diagnosing whether pediatric asthma develops due to exposure to fine dust during the fetal period comprises: a step of generating a group containing at least one biomarker associated with the development of pediatric asthma using DNA obtained from subjects; a step of extracting a biomarker corresponding to the biomarker included in the group from DNA obtained from a subject and confirming the degree of methylation of the extracted biomarker; and a step of diagnosing whether pediatric asthma develops in the subject through the measured degree of methylation.

[0009] A computer-readable recording medium according to another aspect includes a recording medium that records a program for executing the above-described method on a computer. Effects of the invention

[0010] According to the means for solving the problem of the present disclosure described above, in the present disclosure, a device for diagnosing the onset of pediatric asthma due to exposure to fine dust during the fetal period can diagnose subjects with a high probability of developing pediatric asthma by calculating biomarkers associated with pediatric asthma. Brief explanation of the drawing

[0011] FIG. 1 is a diagram illustrating an example of a system for diagnosing whether pediatric asthma develops due to exposure to fine dust during the fetal period according to one embodiment. FIG. 2 is a configuration diagram illustrating an example of a user terminal according to one embodiment. FIG. 3 is a flowchart illustrating an example of a method for diagnosing whether pediatric asthma has developed according to one embodiment. FIG. 4 is a flowchart illustrating an example of a method for generating a biomarker group according to one embodiment. FIG. 5a is a diagram illustrating an example of the correlation between clinical indicators and biomarkers of pediatric asthma according to one embodiment. FIG. 5b is a diagram illustrating an example of biomarkers included in a biomarker group according to one embodiment. FIG. 6 is a diagram illustrating an example of a method for checking the degree of methylation according to one embodiment. FIG. 7 is a diagram illustrating an example of a machine learning model according to one embodiment. FIG. 8 is a diagram illustrating an example of a method for evaluating the pediatric asthma diagnosis rate of a user terminal using a machine learning model according to one embodiment. Specific details for implementing the invention

[0012] The terms used in the embodiments have been selected to be as close as possible to currently widely used general terms; however, these may vary depending on the intent of those skilled in the art, case law, the emergence of new technologies, etc. Additionally, in specific cases, terms have been selected at the applicant's discretion, and in such cases, their meanings will be described in detail in the relevant description section. Therefore, terms used in the specification must be defined not merely by their names, but based on their meanings and the content throughout the specification.

[0013] When a part of the specification is described as "comprising" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. Furthermore, terms such as "~ unit" or "~ module" as used in the specification refer to a unit that processes at least one function or operation, and this may be implemented in hardware or software, or as a combination of hardware and software.

[0014] Additionally, terms including ordinal numbers, such as "first" or "second," used in the specification may be used to describe various components, but said components should not be limited by said terms. The terms may be used for the purpose of distinguishing one component from another.

[0015] The term "fetal period" in this specification refers to the period from the time of fertilization of the fetus until birth.

[0016] The term "subject" in this specification refers to a child born in Korea whose development of pediatric asthma has been tracked. Specifically, a subject may refer to a child born between 37 and 41 weeks of gestation to a mother without underlying diseases. For example, children born to pregnant women carrying multiple fetuses or congenital malformations, pregnant women with medical complications such as tuberculosis, pregnant women who developed hypertension before 20 weeks of gestation, and pregnant women with a history of psychiatric illness may be excluded from being subjects.

[0017] The term "subject" in this specification refers to a child who is the subject of a diagnosis regarding the onset of pediatric asthma (hereinafter referred to as pediatric asthma) due to exposure to fine dust during the fetal period.

[0018] The term "biomarker" in this specification refers to a substance capable of diagnosing the onset of pediatric asthma, and may mean a gene that shows an increase or decrease in the degree of methylation in subjects who have developed pediatric asthma. It may also refer to organic biomolecules such as proteins, nucleic acids, lipids, glycolipids, glycoproteins, or sugars. For example, a biomarker may be a gene in which the methylation level changes in subjects at risk of developing pediatric asthma, but is not limited thereto.

[0019] The term "methylation" in this specification means the addition of a methyl group (-CH3) to a biomarker. For example, if the biomarker refers to a gene, the degree of expression of the gene may vary depending on the degree of methylation of the gene.

[0020] The term “diagnosis” in this specification may include at least one of determining a subject’s susceptibility to a specific disease or condition, determining whether a subject currently has a specific disease or condition, determining the prognosis of a subject with a specific disease or condition, and therametrics (e.g., monitoring the subject’s condition to provide information on therapeutic efficacy). Specifically, diagnosis is to predict whether or when pediatric asthma will develop. Prediction means a prospect or preliminary evaluation regarding the progression of the disease or recovery. Specifically, prediction is to determine whether or when pediatric asthma will develop in a subject at risk of developing pediatric asthma.

[0021] Embodiments are described in detail below with reference to the attached drawings. However, embodiments may be implemented in various different forms and are not limited to the examples described herein.

[0022] FIG. 1 is a diagram illustrating an example of a system for diagnosing whether pediatric asthma develops due to exposure to fine dust during the fetal period according to one embodiment.

[0023] The user terminal (10) can generate a group of biomarkers (20) associated with the onset of pediatric asthma using DNA obtained from subjects.

[0024] For example, the user terminal (10) can obtain information about DNA extracted from placental tissue during the fetal period from subjects.

[0025] The fetal period is the time when the fetus's bodily organs begin to form. Furthermore, the fetal period is a time when genetic damage from exposure to various external environmental factors is easily sustained, and DNA repair capabilities are reduced. Consequently, exposure to harmful external environments during the fetal stage can have a significant impact on fetal growth and the development of various diseases after birth. For example, research suggests that it can affect not only the process of fetal lung development but also the occurrence of respiratory diseases after birth.

[0026] In particular, exposure to fine dust during the fetal period is known to be a major cause of the onset of pediatric asthma. However, conventionally, the specific mechanism causing the onset of pediatric asthma has not been identified. The user terminal (10) can identify the cause of pediatric asthma caused by exposure to fine dust during the fetal period by generating a group of biomarkers (20) that cause the onset of pediatric asthma.

[0027] Additionally, the user terminal (10) can determine the degree of methylation (40) of a biomarker corresponding to a biomarker included in the biomarker group (20) through DNA obtained from the subject (30). Additionally, the user terminal (10) can diagnose whether pediatric asthma has developed through the degree of methylation (40).

[0028] The degree of methylation (40) of the biomarker is a biological standard that changes due to exposure to harmful factors in the external environment (e.g., fine dust). Therefore, the degree of methylation (40) is suitable for diagnosing whether pediatric asthma develops due to exposure to fine dust during the fetal stage of the subject (30).

[0029] When a biomarker is hypermethylated, its expression may be suppressed. For example, if a biomarker is hypermethylated, protein binding necessary for gene expression at the biomarker's CpG site may become difficult. A CpG site refers to the point where a cytosine base and a guanine base are linked. Therefore, methylation of a biomarker suppresses expression by making it difficult for DNA to maintain its existing structure.

[0030] For example, if a biomarker that causes the onset of childhood asthma is hypermethylated during the fetal stage of the subject (30), the expression of the biomarker is suppressed, and normal lung development during the fetal stage may be inhibited.

[0031] Accordingly, the user terminal (10) can diagnose that a subject (30) in which the biomarker within the biomarker group (20) is hypermethylated corresponds to a subject (50) at risk of developing pediatric asthma. Additionally, the user terminal (10) can diagnose that a subject (30) in which the biomarker within the biomarker group (20) exhibits a normal degree of methylation corresponds to a normal subject (50).

[0032] Hereinafter, an example of how a user terminal (10) operates will be described with reference to FIGS. 2 to 8.

[0033] FIG. 2 is a configuration diagram illustrating an example of a user terminal according to one embodiment.

[0034] The user terminal (100) includes a processor (110), memory (120), an input / output interface (130), and a communication module (140). For convenience of explanation, only components related to the present invention are illustrated in FIG. 2. Accordingly, other general-purpose components may be included in the user terminal (100) in addition to the components illustrated in FIG. 2. Furthermore, it is obvious to those skilled in the art that the processor (110), memory (120), input / output interface (130), and communication module (140) illustrated in FIG. 2 may be implemented as independent devices. Additionally, the user terminal (100) of FIG. 2 may be the same device as the user terminal (10) of FIG. 1.

[0035] The processor (110) can process instructions of a computer program by performing basic arithmetic, logic, and input / output operations. Here, instructions may be provided from memory (120) or an external device (not shown). Additionally, the processor (110) can control the overall operation of other components included in the user terminal (100).

[0036] For example, the processor (110) can generate a group of biomarkers (20) associated with the onset of pediatric asthma. Additionally, by using the biomarkers included in the group (20), it can diagnose whether the subject (30) has developed pediatric asthma.

[0037] The processor (110) may be implemented as an array of multiple logic gates, or as a combination of a general-purpose microprocessor and memory storing a program that can be executed on the microprocessor. For example, the processor (110) may include a general-purpose processor, a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a controller, a microcontroller, a state machine, etc. In some environments, the processor (110) may include an application-specific integrated circuit (ASIC), a programmable logic device (PLD), a field programmable gate array (FPGA), etc. For example, the processor (110) may refer to a combination of processing devices such as a combination of a digital signal processor (DSP) and a microprocessor, a combination of multiple microprocessors, a combination of one or more microprocessors combined with a digital signal processor (DSP) core, or any other combination of such configurations.

[0038] The memory (120) may include any non-transient computer-readable recording medium. As an example, the memory (120) may include a permanent mass storage device such as RAM (Random Access Memory), ROM (Read Only Memory), a disk drive, an SSD (Solid State Drive), or flash memory. As another example, a permanent mass storage device such as ROM, an SSD, flash memory, or a disk drive may be a separate permanent storage device distinct from the memory. Additionally, the memory (210) may store an operating system (OS) and at least one program code (e.g., code for the processor (110) to perform an operation described later with reference to FIGS. 3 through 8).

[0039] The input / output interface (130) may be a means for interfacing with a device for input and / or output (e.g., keyboard, mouse, etc.) that may be connected to or included in the user terminal (100). In FIG. 2, the input / output interface (130) is shown as an element configured separately from the processor (110), but is not limited thereto, and the input / output interface (130) may be configured to be included in the processor (110).

[0040] The communication module (140) may provide a configuration or function for the user terminal (100) to communicate with an external device (not shown) through a network. For example, control signals, commands, data, etc. provided under the control of the processor (110) may be transmitted to an external device via the communication module (140) and the network.

[0041] Meanwhile, although not shown in FIG. 2, the user terminal (100) may further include a display device. Alternatively, the user terminal (100) may be connected to an independent display device via wired or wireless communication to transmit and receive data to and from each other.

[0042] FIG. 3 is a flowchart illustrating an example of a method for diagnosing whether pediatric asthma has developed according to one embodiment.

[0043] A method for diagnosing the onset of pediatric asthma in a subject (30) consists of steps processed sequentially in a user terminal (10, 100) or processor (110) as illustrated in FIGS. 1 and 2. Therefore, even if details are omitted below, the content described above regarding the user terminal (10, 100) or processor (110) as illustrated in FIGS. 1 and 2 can also be applied to a method for diagnosing the onset of pediatric asthma in a subject (30) as illustrated in FIG. 3.

[0044] In step 310, the processor (110) can use DNA obtained from subjects to generate a group (20) containing at least one biomarker associated with the onset of pediatric asthma.

[0045] Referring to FIGS. 4 to 5b below, a method by which a processor (110) generates a biomarker group (20) is described.

[0046] FIG. 4 is a flowchart illustrating an example of a method for generating a biomarker group according to one embodiment.

[0047] In step 410, the processor (110) can classify the subjects into one of the pre-set comparison groups based on the degree of exposure to fine dust and whether or not they have developed childhood asthma.

[0048] For example, the processor (110) can obtain regional fine dust generation values ​​from a Statistical Geographical Information System (SGIS).

[0049] Additionally, the processor (110) can obtain the subject's fine dust exposure value by using the regional fine dust generation value obtained from the statistical geographic information system. For example, the processor (110) can obtain the subject's fine dust exposure value by using the fine dust generation value of the region where the mother resided during the subject's fetal period.

[0050] Additionally, the processor (110) can determine the degree of fine dust exposure according to a predetermined standard. For example, the processor (110) can classify the degree of fine dust exposure during the fetal period of the subject into a first level and a second level based on the subject's fine dust exposure value obtained through the fine dust generation value of the area where the mother resides. The first level may refer to a case where the subject's fine dust exposure value is less than or equal to a predetermined value. Additionally, the second level may refer to a case where the subject's fine dust exposure value exceeds a predetermined value. For example, the predetermined value may be arbitrarily determined by the user.

[0051] Accordingly, the comparison group may include a first comparison group exposed to fine dust at a level 1 and not developing pediatric asthma, a second comparison group exposed to fine dust at a level 1 and not developing pediatric asthma, a third comparison group exposed to fine dust at a level 2 and not developing pediatric asthma, and a fourth comparison group exposed to fine dust at a level 2 and not developing pediatric asthma.

[0052] The processor (110) can classify the subject into any one of the first to fourth comparison groups described above.

[0053] In step 420, the processor (110) can measure the degree of methylation (40) of a specific type of biomarker contained in the DNA extracted from each subject. Here, the biomarker may mean a gene.

[0054] For example, the processor (110) can measure the degree of methylation (40) of a gene present in a promoter region that affects the regulation of gene expression in the extracted DNA.

[0055] The promoter region can determine under what conditions and at what time a gene present in DNA is expressed. Additionally, the promoter region is located at the beginning of the DNA sequence and refers to the site where proteins necessary for gene expression bind.

[0056] In step 430, the processor (110) can first screen for hypermethylated biomarkers in subjects included in the control group that developed pediatric asthma using the measured degree of methylation (40).

[0057] For example, the processor (110) is among the genes of the promoter region contained in the DNA obtained from subjects of a control group who developed pediatric asthma. Genes with a ∇β value and a significance probability (P-value) of less than 0.05 can be selected in the first stage.

[0058] ∇β is one of the indicators representing the degree of methylation (40) of a gene. Here, β represents the degree of methylation (40) at a CpG site, and ∇β represents the rate of change of β. For example, the processor (110) can calculate the ∇β value of a gene by calculating the difference between the β values ​​of genes in the promoter region contained in DNA obtained from subjects with pediatric asthma and the β values ​​of genes in the promoter region contained in DNA obtained from subjects in a control group without pediatric asthma. Accordingly, the processor (110) Genes having ∇β can be selected in the first stage.

[0059] The significance probability value is one of the indicators representing the degree of methylation of a gene (40). The significance probability is used to evaluate the statistical significance of the methylation status of a gene. The significance probability value is a real number between 0 and 1.

[0060] For example, the processor (110) can calculate the significance probability values ​​of the genes in the promoter region included in the DNA obtained from subjects who have developed pediatric asthma. Additionally, the processor (110) can first select genes having a significance probability value of less than 0.05.

[0061] In step 440, the processor (110) can secondarily select biomarkers from the first selected biomarkers through pathway analysis.

[0062] Pathway analysis is an analytical method that identifies signaling pathways in which biological elements, such as genes, participate. For example, the Notch signaling pathway is a signaling pathway that regulates cell proliferation, differentiation, and apoptosis through intercellular interactions. The neuronal differentiation / proliferation pathway involves neural tube formation, forebrain development, cortical organization, and myelination through the proliferation and differentiation of neurons, and is a process that integrates numerous signals to induce electrophysiological, morphological, and transcriptional changes.

[0063] For example, the processor (110) can secondarily select biomarkers present in the Notch signaling pathway and neuronal proliferation and differentiation pathways through pathway analysis among the first selected biomarkers.

[0064] In step 450, the processor (110) can generate a group (20) of at least one biomarker associated with a clinical indicator of pediatric asthma among the second set of selected biomarkers.

[0065] Hereinafter, a method is described in which the processor (110) in FIG. 5a generates a group (20) of biomarkers related to clinical indicators of pediatric asthma among the second selected biomarkers.

[0066] FIG. 5a is a diagram illustrating an example of the correlation between clinical indicators and biomarkers of pediatric asthma according to one embodiment.

[0067] For example, clinical indicators of pediatric asthma may include at least one of airway hyperresponsiveness levels (PC20 values), lung function levels, total serum IgE (immunoglobulin E) levels in the blood, egg-specific IgE levels in the blood, and milk-specific IgE levels in the blood.

[0068] Graph (511) shows the correlation between the degree of methylation of the NOTCH1, PAX6, OLIG2, ZBTB7A, NOTCH3, REST, GLI1, and NOTCH4 genes and the airway hyperresponsiveness level. The X-axis of graph (511) represents the degree of methylation of the genes, and the Y-axis represents the value of the PC20 index.

[0069] Airway hyperresponsiveness is an indicator representing the degree to which the bronchi abnormally spasm and contract. Additionally, the PC20 (Provocative Concentration of Methacholine Causing a 20% Decrease in Forced Expiratory Volume in 1 second) index represents the concentration of methacholine that causes a 20% decrease in a patient's forced expiratory volume compared to baseline upon inhalation. Methacholine is a chemical substance that narrows the subjects' bronchi. A decrease in the PC20 value signifies an increase in airway hyperresponsiveness.

[0070] In graph (511), as the degree of methylation (40) of the NOTCH1, NOTCH3, NOTCH4, GLI1, OLIG2, REST, PAX6, and ZBTB7A genes increases, the value of PC20 decreases. This may mean that if the NOTCH1, PAX6, OLIG2, ZBTB7A, NOTCH3, REST, GLI1, and NOTCH4 genes are hypermethylated and not expressed, the airway hyperresponsiveness level increases. If the airway hyperresponsiveness level increases, pediatric asthma may develop due to abnormal constriction of the bronchi. Accordingly, the processor (110) can generate a group (20) of the NOTCH1, PAX6, OLIG2, ZBTB7A, NOTCH3, REST, GLI1, and NOTCH4 genes as biomarkers associated with the development of pediatric asthma.

[0071] Graph (512) shows the correlation between the degree of methylation of the NOTCH1, PAX6, OLIG2, ZBTB7A, NOTCH3, REST, GLI1, and NOTCH4 genes and the total serum IgE levels in the blood. The X-axis of the graph (512) represents the degree of methylation of the genes, and the Y-axis represents the total serum IgE levels in the blood.

[0072] IgE is a type of immunoglobulin involved in allergic reactions. When a subject is exposed to an external antigen, IgE levels increase systemically or locally. It binds to effector cells, such as mast cells and basophils—the primary cells involved in allergic inflammation—and promotes the inflammatory response by secreting inflammatory mediators. Excessive secretion of inflammatory substances can trigger the onset of asthma in children.

[0073] In the graph (512), as the degree of methylation (40) of the NOTCH1, PAX6, OLIG2, ZBTB7A, NOTCH3, REST, GLI1, and NOTCH4 genes increases, the total serum IgE level in the blood increases. This may mean that when the NOTCH1, PAX6, OLIG2, ZBTB7A, NOTCH3, REST, GLI1, and NOTCH4 genes are hypermethylated and not expressed, the total serum IgE level in the blood increases, which may indicate that an excessive amount of inflammatory substances are secreted inside the bronchi. Since the secretion of excessive inflammatory substances causes the onset of pediatric asthma in the subject, the processor (110) can generate a group (20) of the NOTCH1, PAX6, OLIG2, ZBTB7A, NOTCH3, REST, GLI1, and NOTCH4 genes as biomarkers associated with the onset of pediatric asthma.

[0074] FIG. 5b is a diagram illustrating an example of biomarkers included in a biomarker group according to one embodiment.

[0075] The graph (520) shows the degree (40) of methylation of the biomarkers of the group (20) contained in the DNA obtained from the subjects.

[0076] The biomarker included in group (20) may show a higher degree of methylation (40) in subjects of the comparison group that developed pediatric asthma compared to subjects of the comparison group that did not develop pediatric asthma among subjects of the comparison group exposed to the same level of fine dust.

[0077] For example, the NOTCH 1 gene in the graph (520) shows a higher degree of methylation (40) in subjects of the comparison group (522) that developed pediatric asthma among the comparison groups (521, 522) that were exposed to the first level of fine dust, compared to subjects of the comparison group (521) that did not develop pediatric asthma.

[0078] In addition, the NOTCH 1 gene of the graph (520) shows a higher degree of methylation (40) in subjects of the comparison group (524) who developed pediatric asthma among subjects of the comparison group (523, 524) who were exposed to a second level of fine dust, compared to subjects of the comparison group (523) who did not develop pediatric asthma.

[0079] Referring again to FIG. 3, in step 320, the processor (110) can extract a biomarker corresponding to a biomarker included in group (20) from DNA obtained from the subject (30), and check the degree of methylation (40) of the extracted biomarker.

[0080] Hereinafter, with reference to FIG. 6, a method for determining the degree of methylation (40) of a biomarker will be described.

[0081] FIG. 6 is a diagram illustrating an example of a method for checking the degree of methylation according to one embodiment.

[0082] Methods for determining the degree of methylation (600) may include, but are not limited to, methylated DNA immunoprecipitation (MeDIP; methylated DNA immunoprecipitation) (610), DNA methylation microarray (620), bisulfite sequencing (630), bisulfite sequencing (640), combined bisulfite restriction analysis (COBRA; combined bisulfite restriction analysis) (650), real-time methylation specific PCR (660), and pyrosequencing (670).

[0083] For example, the methylation DNA immunoprecipitation method (610) can determine the degree of methylation (40) by using an antibody that specifically recognizes a site where a methyl group (-CH3) is bound within the DNA. Additionally, the DNA methylation microarray (620) can determine the degree of methylation (40) by using a microarray capable of analyzing multiple DNA fragments simultaneously. Additionally, bisulfite sequencing (630) can determine the degree of methylation (40) by determining the base sequence after amplifying the DNA using a chemiluminescence method. Additionally, the hydrogen sulfite base sequencing method (640) can determine the degree of methylation (40) by determining the base sequence without amplifying the DNA, although it uses a chemiluminescence method. Additionally, the Cobra method (650) can determine the degree of methylation (40) by maintaining methylated cytosine bases and dissolving hypermethylated cytosine bases. In addition, the real-time methylation-specific polymerase chain reaction method (660) can determine the degree of DNA methylation (40) by using a methylation-specific polymerase to distinguish between methylated DNA regions and non-methylated DNA regions. In addition, pyrosequencing (670) replicates DNA and measures the amount of light generated during the replication process to perform base sequence analysis. The degree of methylation (40) can be determined through the analyzed base sequence.

[0084] The processor (110) can determine the methylation degree (40) of a biomarker corresponding to a biomarker included in a group (20) extracted from DNA obtained from a subject (30) using any one of the methylation degree measurement methods.

[0085] Referring again to FIG. 3, in step 330, the processor (110) can diagnose whether the subject (30) has developed pediatric asthma through the confirmed degree of methylation (40).

[0086] Hereinafter, with reference to FIGS. 7 and 8, a method for diagnosing whether a subject (30) has developed pediatric asthma will be described.

[0087] FIG. 7 is a diagram illustrating an example of a pediatric asthma diagnosis method according to one embodiment.

[0088] The processor (110) can diagnose whether the subject (30) has developed pediatric asthma using a machine learning model (700).

[0089] A machine learning model (700) means a statistical learning algorithm implemented based on the structure of a biological neural network or a structure that executes the algorithm in machine learning technology and cognitive science.

[0090] For example, a machine learning model (700) can represent a model with problem-solving ability by learning to reduce the error between the correct output corresponding to a specific input and the inferred output through the repeated adjustment of synaptic weights of nodes, which are artificial neurons that form a network through the combination of synapses as in a biological neural network.

[0091] For example, the machine learning model (700) may be implemented as a multilayer perceptron (MLP) composed of multiple layers of nodes and connections between them. The machine learning model (700) according to the present embodiment may be implemented using one of various artificial neural network model structures including an MLP. For example, the machine learning model (700) may be composed of an input layer that receives an input signal or data from the outside, an output layer that outputs an output signal or data corresponding to the input data, and at least one hidden layer located between the input layer and the output layer, which receives a signal from the input layer, extracts a feature, and transmits it to the output layer. The output layer receives a signal or data from the hidden layer and outputs it to the outside.

[0092] For example, the processor (110) may diagnose whether a subject (30) has developed pediatric asthma using any one of the machine learning models (700) of the K-Nearest Neighbor algorithm (710), extreme gradient boosting algorithm (720), random forest algorithm (730), support vector machine algorithm (740), Naive Bayes algorithm (750), and linear discriminant analysis algorithm (760), but is not limited thereto.

[0093] Additionally, the processor (110) can diagnose pediatric asthma in the subject (30) using the model (700) and evaluate the diagnosis rate accordingly.

[0094] Hereinafter, with reference to FIG. 8, a method by which a processor (110) evaluates a model (700) is described.

[0095] FIG. 8 is a diagram illustrating an example of a method for evaluating the pediatric asthma diagnosis rate of a user terminal using a machine learning model according to one embodiment.

[0096] For example, the processor (110) can evaluate the model (700) using the degree of methylation (40) of the biomarker included in the group (20) of DNA obtained from the subject and whether the subject has developed pediatric asthma.

[0097] Indicators for evaluating the diagnostic rate include sensitivity, specificity, F1 score, and AUC (area under the ROC curve).

[0098] For example, sensitivity refers to the ratio of subjects among those who actually developed pediatric asthma that the processor (110) diagnoses as having developed pediatric asthma using the model (700). The higher the value of sensitivity, the more accurately the processor (110) can diagnose the onset of pediatric asthma in the subject (30) using the machine learning model. Additionally, sensitivity corresponds to a real number between 0 and 1.

[0099] The graph (810) shows the sensitivity of the processor (110) using each machine learning model (700). For example, if the processor (110) uses the K-nearest neighbor algorithm (710), it may show the highest sensitivity of 0.93.

[0100] Additionally, specificity refers to the ratio of subjects among those who have not developed pediatric asthma that the processor (110) diagnoses as not developing pediatric asthma using the model (700). The higher the value of specificity, the more accurately the processor (110) can diagnose the onset of pediatric asthma in the subject (30) using the machine learning model. Additionally, specificity corresponds to a real number between 0 and 1.

[0101] The graph (820) shows the specificity of the processor (110) using each machine learning model (700). For example, if the processor (110) uses the Naive Bayes algorithm (750), it can show the highest specificity of 0.90.

[0102] Additionally, the F1 score represents the harmonic mean of sensitivity and precision. Precision refers to the ratio of subjects who actually developed asthma among those whom the processor (110) diagnosed as likely to develop pediatric asthma using the model (700). A higher F1 score indicates that the processor (110) can accurately diagnose the onset of pediatric asthma in the subject (30) using the machine learning model. Additionally, the F1 score corresponds to a real number between 0 and 1.

[0103] The graph (830) shows the F1 score of the processor using each machine learning model (700). For example, if the processor (110) uses the K-nearest neighbor algorithm (710), it may show the highest F1 score of 0.93.

[0104] Additionally, AUC represents the area under the ROC (Receiver Operating Characteristic) curve. Here, the ROC curve is a curve representing the change in specificity according to the change in sensitivity. A higher AUC value indicates that the processor (110) can accurately diagnose the onset of pediatric asthma in the subject (30) using the machine learning model. Additionally, the AUC value corresponds to a real number between 0 and 1.

[0105] The graph (830) shows the AUC value of the processor (110) using each machine learning model (700). For example, if the processor (110) uses the K-nearest neighbor algorithm (710), it may show the highest AUC value of 0.96.

[0106] The processor (110) can diagnose whether pediatric asthma has developed by using a model that shows a high diagnostic rate based on the evaluation results.

[0107] For example, the processor (110) can diagnose whether pediatric asthma has developed by using the K-nearest neighbor algorithm (710) which shows the highest values ​​in the sensitivity index, specificity index, and AUC index.

[0108] Meanwhile, the above-described method can be written as a program executable on a computer and can be implemented on a general-purpose digital computer that operates the program using a computer-readable recording medium. In addition, the structure of the data used in the above-described method can be recorded on a computer-readable recording medium through various means. The computer-readable recording medium includes storage media such as magnetic storage media (e.g., ROM, RAM, USB, floppy disk, hard disk, etc.) and optical reading media (e.g., CD-ROM, DVD, etc.).

[0109] A person skilled in the art related to the present embodiment will understand that it may be implemented in modified forms without departing from the essential characteristics of the description above. Therefore, the disclosed methods should be considered in an illustrative rather than a restrictive sense, and the scope of rights is defined in the claims rather than the description above, and should be interpreted to include all differences within the scope of equivalence. Explanation of the symbols

[0111] 10: User terminal 20: Biomarker Group 30: Object 40: Degree of methylation 50: Individuals at risk of developing childhood asthma 60: Normal subject

Claims

Claim 1 A method for providing information for diagnosing whether pediatric asthma develops due to exposure to fine dust during the fetal period, comprising: a step of generating a group containing biomarkers associated with the development of pediatric asthma using DNA obtained from subjects; a step of extracting a biomarker corresponding to a biomarker included in the group from DNA obtained from a subject and confirming the degree of methylation of the extracted biomarker; and a step of providing information for diagnosing whether pediatric asthma develops due to exposure to fine dust during the fetal period of the subject through the confirmed degree of methylation; wherein the group containing the biomarkers includes NOTCH1, PAX6, OLIG2, ZBTB7A, NOTCH3, REST, GLI1, and NOTCH4. Claim 2 A method according to claim 1, wherein the generating step comprises: classifying the subjects into one of a set of comparison groups according to the degree of exposure to fine dust and whether pediatric asthma has developed; measuring the degree of methylation of a promoter region included in DNA extracted from each subject; using the measured degree of methylation, first selecting genes containing hypermethylated promoter regions as biomarkers for subjects included in the comparison group in which pediatric asthma has developed among the comparison groups; secondly selecting biomarkers through pathway analysis among the firstly selected biomarkers; and generating the group with biomarkers related to clinical indicators of pediatric asthma among the secondly selected biomarkers. Claim 3 A method according to claim 2, wherein the degree of fine dust exposure is determined as either a first level or a second level by comparing the fine dust exposure value of each subject, obtained using regional fine dust generation values ​​obtained from a Statistical Geographic Information System (SGIS), with a predetermined reference value. Claim 4 In claim 3, the comparison group comprises a first comparison group exposed to the fine dust at a first level and having no development of pediatric asthma, a second comparison group exposed to the fine dust at a first level and having developed pediatric asthma, a third comparison group exposed to the fine dust at a second level and having no development of pediatric asthma, and a fourth comparison group exposed to the fine dust at a second level and having developed pediatric asthma. Claim 5 In claim 2, the method wherein the DNA is extracted from placental tissue obtained at the time of birth of each of the subjects. Claim 6 A method according to claim 2, wherein the clinical indicator comprises at least one of airway hyperresponsiveness level, serum total IgE (immunoglobulin E) level in blood, egg-specific IgE level in blood, and milk-specific IgE level in blood. Claim 7 In claim 1, the confirming step is a method using any one of methylation DNA immunoprecipitation, DNA methylation microarray, bisulfite sequencing, bisulfite sequencing, COBRA (combined bisulfite restriction analysis), real-time methylation specific PCR, and pyrosequencing. Claim 8 A method according to claim 1, wherein the step of providing information for diagnosis is performed using any one of the K-Nearest Neighbor algorithm, extreme gradient boosting algorithm, random forest algorithm, support vector machine algorithm, Naive Bayes algorithm, and linear discriminant analysis algorithm. Claim 9 A computer-readable recording medium storing a program for executing the method of paragraph 1 on a computer. Claim 10 A computing device comprising at least one memory; and at least one processor; wherein the processor generates a group containing biomarkers associated with the onset of pediatric asthma due to exposure to fine dust during the fetal period using DNA obtained from subjects, extracts a biomarker corresponding to the biomarker included in the group from DNA obtained from a subject, confirms the methylation degree of the extracted biomarker, and provides information for diagnosing whether pediatric asthma due to exposure to fine dust during the fetal period of the subject has developed through the confirmed methylation degree, and wherein the group containing the biomarkers includes NOTCH1, PAX6, OLIG2, ZBTB7A, NOTCH3, REST, GLI1, and NOTCH4.

Images