Method and device for predicting incidence of disease caused by parasites

Abstract

This method for predicting the incidence of disease caused by parasites comprises the steps in which: a prediction device receives information about a subject; the prediction device inputs the information about the subject to a prediction model; and the prediction device predicts the incidence of disease caused by parasites of the subject on the basis of an output value of the prediction model. The information about the subject may include at least one of sex information, age information, body mass index (BMI) information, or alcohol.

Description

Method and device for predicting the incidence of diseases caused by parasites

[0001] The technology described below relates to a method and device for predicting the probability of developing a disease caused by a parasite.

[0002] A parasite is an organism that lives inside another organism and steals its nutrients. Parasites live inside other organisms and feed on them. Parasites come in a variety of shapes and sizes. Parasites include both unicellular and multicellular organisms. When a person becomes infected with a parasite, it can cause disease. For example, a parasite infection can cause digestive problems such as abdominal pain and diarrhea, and malnutrition such as weight loss. Antiparasitic drugs such as quinine are sometimes administered to treat diseases caused by parasites.

[0003] Parasitic infections can occur through direct contact with parasites or through the consumption of food containing parasites. To prevent parasitic infections, it is essential to consume clean food and water. Maintaining proper hygiene is also crucial for preventing parasitic infections. Furthermore, when a person is infected with a parasite, it is crucial to predict whether the parasite will cause metabolic diseases or other conditions. The technology described below discloses a method for predicting the incidence of parasitic diseases based on various information from a subject.

[0004] In one embodiment, a method for predicting the incidence of a disease caused by a parasite includes a step in which a prediction device acquires information about a subject; a step in which the prediction device inputs the information about the subject into a prediction model; and a step in which the prediction device predicts the incidence of a disease caused by a parasite in the subject based on an output value of the prediction model. The information about the subject may include at least one of sex information, age information, body mass index (BMI) information, and alcohol consumption.

[0005] The technology described below can be used to predict the incidence of parasitic diseases based on information about the subject. Specifically, the technology described below can be used to predict the incidence of parasitic diseases based on various information about the subject.

[0006] Figure 1 is one of the embodiments in which a prediction device (100) performs a method for predicting the incidence of a disease caused by a parasite.

[0007] Figure 2 is a flowchart of one embodiment of a method (200) for predicting the incidence of a disease caused by a parasite.

[0008] Figures 3 and 4 are examples of three predictive models for predicting the incidence of metabolic diseases caused by pathogenic protozoa among parasites. Figure 3 shows the results of expressing the three predictive models (Patho model 1, Patho model 2, and Patho model 3) according to the example as a nomogram. Figure 4 shows the results of evaluating the performance of the three models of Figure 3 according to the example.

[0009] Figures 5 and 6 are examples of three models for predicting the incidence of metabolic diseases caused by non-pathogenic protozoa among parasites. Figure 5 shows the results of expressing the three models (non-patho model 1, non-patho model 2, and non-patho model 3) according to the example as a nomogram. Figure 6 shows the results of evaluating the performance of the three models of Figure 5 according to the example.

[0010] Figures 7 and 8 are examples of three models for predicting the incidence of metabolic diseases caused by foodborne trematodes (FBT), a parasite. Figure 7 shows the results of expressing the three models (FBT model 1, FBT model 2, and FBT model 3) according to the example as a nomogram. Figure 8 shows the results of evaluating the performance of the three models of Figure 7 according to the example.

[0011] Figures 9 and 10 are examples of three models for predicting the incidence of metabolic diseases caused by soil-transmitted helminths (STH) among parasites. Figure 9 shows the results of expressing the three models (STH model 1, STH model 2, and STH model 3) according to the example as a nomogram. Figure 10 shows the results of evaluating the performance of the three models of Figure 9 according to the example.

[0012] Fig. 11 is a configuration of one embodiment of a prediction device (300).

[0013] The technology described below is susceptible to various modifications and embodiments. Specific embodiments of the technology described below may be illustrated in the drawings of the specification. However, these are intended to illustrate the technology described below and are not intended to limit the technology described below to any specific embodiments. Therefore, it should be understood that all modifications, equivalents, or alternatives that fall within the spirit and scope of the technology described below are encompassed by the technology described below.

[0014] In the terms used hereinafter, singular expressions should be understood to include plural expressions unless the context clearly dictates otherwise, and terms such as "comprises" should be understood to mean the presence of a described feature, number, step, operation, component, part, or combination thereof, but not to exclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0015] Before going into a detailed description of the drawings, it should be made clear that the division of components in this specification is merely a division based on the main function of each component. That is, two or more components described below may be combined into one component, or one component may be further divided into two or more components with more detailed functions. In addition to its own main function, each component described below may additionally perform some or all of the functions of other components, and of course, some of the main functions of each component may be exclusively performed by other components.

[0016] Additionally, in performing a method or method of operation, each process constituting the method may occur in a different order than the stated order, unless the context clearly indicates a specific order. That is, each process may occur in the same order as the stated order, may be performed substantially simultaneously, or may be performed in the opposite order.

[0017] In the technology described below, the parasite may include unicellular organisms and multicellular organisms. The unicellular organisms may include protozoa. The multicellular organisms may include helminths and arthropods. The helminths may include nematodes, trematodes, and cestodes. For example, the parasite may include at least one of pathogenic protozoa, non-pathogenic protozoa, foodborne trematodes (FBT), and soil-transmitted helminths (STH).

[0018] Figure 1 is one of the embodiments in which a prediction device (100) performs a method for predicting the incidence of a disease caused by a parasite.

[0019] The prediction device (100) may be a device that performs a method for predicting the incidence of a disease caused by a parasite. The prediction device (100) may obtain information about the subject. Based on the information about the subject, the prediction device (100) may predict the incidence of the disease caused by a parasite in the subject. To predict the incidence of the disease caused by a parasite in the subject, the prediction device (100) may utilize a prediction model.

[0020] The prediction device (100) can be physically implemented in various forms. For example, the prediction device (100) can take the form of a PC, laptop, smart device, server, or data processing-dedicated chipset.

[0021] There may be at least one prediction device (100). That is, the method for predicting the incidence of a disease caused by a parasite may be performed by one prediction device or may be performed separately by at least one device.

[0022] Figure 2 is a flowchart of one embodiment of a method (200) for predicting the incidence of a disease caused by a parasite.

[0023] The prediction device can obtain information about the subject (210).

[0024] The subject may be someone seeking to be tested for a parasitic disease. Alternatively, the subject may be someone seeking to be tested for a high risk of developing a parasitic disease. For example, the subject may be seeking to be tested for a parasitic metabolic disease.

[0025] The subject's information may include at least one of sex, age, body mass index (BMI), and alcohol consumption. Furthermore, the subject's information may further include, in addition to the aforementioned information, at least one of gamma-glutamyl transferase (GGT) information and eosinophil information. Furthermore, the subject's information may further include, in addition to the aforementioned information, at least one of smoking information, surveillance information, hypertension information, and diabetes information.

[0026] In one embodiment, the gender information may include information regarding the gender of the subject. In one embodiment, the age information may include information regarding the age of the subject. In one embodiment, the body mass information may include information regarding the body mass index of the subject. In one embodiment, the drinking information may include information regarding the blood alcohol level of the subject, whether the subject has been drinking, the frequency of drinking, and the amount of drinking of the subject. In one embodiment, the GGT information may include information regarding the GGT level of the subject. In one embodiment, the eosinophil information may include information regarding the level of eosinophils of the subject. For example, the eosinophil information may include information regarding the presence or absence of eosinophilia. In one embodiment, the smoking information may include information regarding the blood nicotine level of the subject, whether the subject has been smoking, the frequency of smoking, and the amount of smoking of the subject. In one embodiment, the surveillance information may include information on whether or not the area is endemic. In one embodiment, the hypertension information may include information on whether the subject has hypertension and the subject's blood pressure level. In one embodiment, the diabetes information may include information on whether the subject has diabetes and the subject's blood sugar level.

[0027] The prediction device can input the subject's information into the prediction model (220).

[0028] A predictive model may be a model that calculates the incidence of a disease caused by a parasite in a subject based on the subject's information.

[0029] In one embodiment, the predictive model may be a machine learning (ML)-based model. The machine learning model may be of various types. For example, the machine learning model may include linear regression, logistic regression, decision tree, random forest (RF), k-nearest neighbor (KNN), naive Bayes, support vector machine (SVM), artificial neural network (ANN), etc. The ANN may be a deep neural network (DNN), which may include a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted boltzmann machine (RBM), a deep belief network (DBN), a generative adversarial network (GAN), and a relational network (RL).

[0030] In one embodiment, the predictive model may be a regression analysis-based model. Alternatively, the predictive model may be generated by analyzing training data using multiple linear regression analysis. Multiple linear regression analysis is a method for analyzing the relationship between two or more independent variables and a dependent variable. The predictive model can calculate the incidence of parasitic diseases by assigning different weights to the input information.

[0031] In one embodiment, Mathematical Formulas 1 to 4 are among the mathematical formulas used when calculating the incidence of a disease caused by a parasite based on the information input by the prediction model. In Mathematical Formulas 1 to 3 below, each input piece of information can be converted into a number and input into each mathematical formula. In Mathematical Formulas 1 to 3 below, k1 to k11 can be regression coefficients. The Y value calculated from Mathematical Formulas 1 to 3 below can be input into Mathematical Formula 4 to calculate the incidence of a disease caused by a parasite.

[0032] [Mathematical Formula 1]

[0033] Y = k1 + k2*(gender information) + k3*(age information) + k4*(body mass index information) + k5*(alcohol information)

[0034] [Equation 2]

[0035] Y = k1 + k2*(gender information) + k3*(age information) + k4*(body mass index information) + k5*(alcohol information) + k6*(GGT information) + k7*(eosinophil information)

[0036] [Mathematical Formula 3]

[0037] Y = k1 + k2*(gender information) + k3*(age information) + k4*(body mass index information) + k5*(alcohol information) + k6*(GGT information) + k7*(eosinophil information) + k8*(smoking information) + k9*(surveillance information) + k10*(hypertension information) + k11*(diabetes information)

[0038] [Equation 4]

[0039] Probability of parasite infection = 1 / (1+exp(-Y))

[0040] In one embodiment, k1 in Equations 1 to 3 can be a value between -10 and 0. k2 in Equations 1 to 3 can be a value between -2 and +1. k3 in Equations 1 to 3 can be a value between -2 and +1. k4 in Equations 1 to 3 can be a value between -1 and +1. k5 in Equations 1 to 3 can be a value between 0 and +2. k6 in Equations 2 and 3 can be a value between -2 and 0. k7 in Equations 2 and 3 can be a value between -1 and 0. k8 in Equation 3 can be a value between -2 and +1. k9 in Equation 3 can be a value between -2 and +2. k10 in Equation 3 can be a value between -1 and +1. k11 in Equation 3 can be a value between 0 and +2.

[0041] In one embodiment, in Mathematical Formulas 1 to 3, the gender information may have a value of 0 if male and 1 if female. The age information in Mathematical Formulas 1 to 3 may have a value of 0 if under 40 years old and 1 if over 40 years old. The body mass index information in Mathematical Formulas 1 to 3 may have a value of 0 if BMI is less than 25 and 1 if BMI is 25 or more. The drinking information in Mathematical Formulas 1 to 3 may have a value of 0 if not drinking and 1 if drinking. In Mathematical Formulas 2 and 3, the GGT information may have a value of 0 if GGT is normal and 1 if not. The eosinophil information in Mathematical Formulas 2 and 3 may have a value of 0 if there is no eosinophilia and 1 if there is eosinophilia. The smoking information in Mathematical Formula 3 may have a value of 0 if not smoking and 1 if smoking. In Equation 3, surveillance information can have a value of 0 if the area is not endemic, and a value of 1 if it is. In Equation 3, hypertension information can have a value of 0 if there is no hypertension, and a value of 1 if there is hypertension. In Equation 3, diabetes information can have a value of 0 if there is no diabetes, and a value of 1 if there is diabetes.

[0042] In one example, the predictive model can be expressed as a nomogram. The predictive model converts each piece of information contained in the input subject's information into a score (Point), and then calculates the incidence rate (probability) of parasitic metabolic diseases based on the total points obtained by summing all of the converted scores.

[0043] The prediction device can predict the incidence of a disease caused by a parasite in a subject based on the output value of the prediction model (230).

[0044] FIG. 3 and FIG. 4 are examples of three prediction models for predicting the incidence of metabolic diseases caused by pathogenic protozoa among parasites.

[0045] Figure 3 shows the results of expressing three prediction models (Patho model 1, Patho model 2, and Patho model 3) as a nomogram according to an embodiment.

[0046] As shown in Figure 3(a), the prediction model can receive information such as sex, age, body mass index (BMI), and alcohol consumption. The prediction model can convert each piece of information into a score (Point). The model then adds up the converted scores (Total Points), and based on this total, it can calculate the probability of occurrence of metabolic disease caused by pathogenic protozoa (Probability of Event).

[0047] As shown in Fig. 3(b), the prediction model can calculate the incidence of metabolic diseases caused by pathogenic protozoa based on the input information after receiving GGT information and eosinophil information in addition to the aforementioned information.

[0048] As shown in Fig. 3(c), the prediction model can calculate the incidence of metabolic diseases caused by pathogenic protozoa based on the input information after receiving information on smoking, surveillance, hypertension, and diabetes along with the aforementioned information.

[0049] Figure 4 is the result of evaluating the performance of the three models of Figure 3 according to an embodiment.

[0050] As shown in Figure 4, the AUC (Area Under the Curve) values ​​of the three prediction models are 0.6509, 0.6566, and 0.6866, respectively. Therefore, the performance of the three prediction models is confirmed to be excellent.

[0051] FIG. 5 and FIG. 6 are examples of three models for predicting the incidence of metabolic diseases caused by non-pathogenic protozoa among parasites.

[0052] Figure 5 shows the results of expressing three models (non-patho model 1, non-patho model 2, and non-patho model 3) as a nomogram according to an embodiment.

[0053] As shown in Figure 5(a), the prediction model can receive information such as sex, age, body mass index (BMI), and alcohol consumption. The prediction model can convert each piece of information into a score (Point). The model then adds up the converted scores (Total Points), and based on this total, it can calculate the probability of occurrence of metabolic disease caused by non-pathogenic protozoa (Probability of Event).

[0054] As shown in Fig. 5(b), the prediction model can calculate the incidence of metabolic diseases caused by non-pathogenic protozoa based on the input information after receiving GGT information and eosinophil information in addition to the aforementioned information.

[0055] As shown in Fig. 5(c), the prediction model can calculate the incidence of metabolic diseases caused by non-pathogenic protozoa based on the input information after receiving information on smoking, surveillance, hypertension, and diabetes along with the aforementioned information.

[0056] Figure 6 is a result of evaluating the performance of three models of Figure 5 according to an embodiment.

[0057] As shown in Figure 6, the AUC values ​​of the three prediction models are 0.5584, 0.5802, and 0.5967, respectively. Therefore, it can be confirmed that the three prediction models perform well.

[0058] FIGS. 7 and 8 are examples of three models for predicting the incidence of metabolic diseases caused by foodborne trematodes (FBT) among parasites.

[0059] Figure 7 shows the results of expressing three models (FBT model 1, FBT model 2, and FBT model 3) as nomograms according to an embodiment.

[0060] As shown in Figure 7(a), the prediction model can receive information such as sex, age, body mass index (BMI), and alcohol consumption. The prediction model can convert each piece of information into a score (Point). The model then adds up the converted scores (Total Points), and based on this total, it can calculate the probability of metabolic disease caused by foodborne trematodes (Probability of Event).

[0061] As shown in Fig. 7(b), the prediction model can calculate the incidence of metabolic diseases caused by foodborne trematodes based on the input information after receiving GGT information and eosinophil information in addition to the aforementioned information.

[0062] As shown in Fig. 7(c), the prediction model can calculate the incidence of metabolic diseases caused by foodborne trematodes based on the input information after receiving information on smoking, surveillance, hypertension, and diabetes along with the aforementioned information.

[0063] Figure 8 is the result of evaluating the performance of the three models of Figure 7 according to an embodiment.

[0064] As shown in Figure 8, the AUC values ​​of the three prediction models are 0.6202, 0.6341, and 0.6817, respectively. Therefore, it can be confirmed that the performance of the three prediction models is good.

[0065] FIGS. 9 and 10 are examples of three models for predicting the incidence of metabolic diseases caused by soil-transmitted helminths (STH) among parasites.

[0066] Figure 9 shows the results of expressing three models (STH model 1, STH model 2, and STH model 3) as a nomogram according to an embodiment.

[0067] As shown in Figure 9(a), the prediction model can receive information such as sex, age, body mass index (BMI), and alcohol consumption. The prediction model can convert each piece of information into a score (Point). The model then sums the converted scores (Total Points), and based on this total, it can calculate the probability of occurrence of metabolic disease caused by soil-borne helminths (Probability of Event).

[0068] As shown in Fig. 9(b), the prediction model can calculate the incidence of metabolic diseases caused by soil-borne helminths based on the input information after receiving GGT information and eosinophil information in addition to the aforementioned information.

[0069] As shown in Fig. 9(c), the prediction model can calculate the incidence of metabolic diseases caused by soil-borne helminths based on the input information after receiving information on smoking, surveillance, hypertension, and diabetes along with the aforementioned information.

[0070] Figure 10 shows the results of evaluating the performance of the three models of Figure 9 according to an embodiment.

[0071] As shown in Figure 10, the AUC values ​​of the three prediction models are 0.5665, 0.5712, and 0.5853, respectively. Therefore, it can be confirmed that the performance of the three prediction models is good.

[0072] Fig. 11 is a configuration of one embodiment of a prediction device (300).

[0073] The prediction device (300) may correspond to the prediction device (100) described above in FIG. 1. That is, the prediction device (300) may be a device that performs the method for predicting the incidence of a disease caused by a parasite described above.

[0074] The prediction device (300) may include at least one input device (310), storage device (320), operation device (330), output device (340), interface device (350), and communication device (360).

[0075] The input device (310) can receive data, information, or models necessary for performing the aforementioned method for predicting the incidence of a disease caused by a parasite. The input device (310) can receive information about the subject. The input device (310) can receive information about sex, age, body mass index (BMI), alcohol, gamma-glutamyl transferase (GGT), eosinophil, smoke, surveillance, hypertension, and diabetes. The input device (310) can receive a prediction model. The input device (310) can receive training data necessary for training the prediction model.

[0076] The input device (310) may include a device for inputting a certain command or data (such as a keyboard, mouse, touch screen, joystick, trackball, touchpad, scanner, or webcam). The input device (310) may also include a configuration for receiving data through a separate storage device (such as a USB, CD, or hard disk). The input device (310) may also receive data through a separate measuring device or a separate database. The input device (310) may also receive data through a communication device (360) via a wired or wireless connection. The input device (310) may also receive a control signal for controlling the prediction device (300).

[0077] The storage device (320) can store data, information, models, etc. required to perform the method for predicting the incidence of a disease caused by a parasite described above. The storage device can store information of the subject. The storage device (320) can store sex information, age information, body mass index (BMI) information, alcohol information, GGT (Gamma-glutamyl transferase) information, eosinophil information, smoke information, surveillance information, hypertension information, and diabetes information. The storage device (320) can store a prediction model. The storage device (320) can store training data required to train the prediction model. The storage device (320) may be a device that stores certain data, information, models, etc. The storage device (320) can store data, information, models, etc. input through the input device (310). The storage device (320) can store commands that cause the computing device (330) to perform operations necessary for a method for predicting the incidence of a disease caused by a parasite. The storage device (320) can store information generated during the computing process of the computing device (330). That is, the storage device (320) can include memory. For example, the storage device can include a hard disk drive (HDD), a solid state drive (SSD), a ROM, a RAM, a CD-ROM, a magnetic tape, or a floppy disk.

[0078] The computational unit (330) can perform the calculations necessary to perform the aforementioned method for predicting the incidence of a disease caused by a parasite. The computational unit (330) can input information about the subject into a prediction model. Based on the output value of the prediction model, the computational unit (330) can predict the incidence of a disease caused by a parasite in the subject.

[0079] The computing device (330) may be a device such as a processor, an application processor (AP), or a chip embedded with a program that processes data and performs certain operations. For example, the computing device (330) may include a central processing unit (CPU), a graphics processing unit (GPU), or a neural processing unit (NPU). The computing device (330) may generate a control signal that controls the prediction device (300). The computing device (330) may generate a control signal that controls the input device (310), the storage device (320), the output device (340), the interface device (350), and the communication device (360) included in the prediction device (300).

[0080] The output device (340) may be a device that outputs certain data, information, and models. The output device (340) may be a device that outputs certain data, information, and models to the outside of the prediction device (300). The output device (340) may output interfaces, input data, analysis results, etc. required for the data processing process. The output device (340) may include a device that outputs data, etc. through tactile, visual, auditory, gustatory, and olfactory methods. The output device (340) may be physically implemented in various forms, such as a display, a speaker, a vibration motor, or a document output device. The output device (340) may output data, information, or models stored in the storage device (320). The output device (340) may output data, information, and models generated during the computation process of the computation device (330). The output device (340) may output the results of the computation of the computation device (330).

[0081] The interface device (350) may be a device that receives certain commands and data from the outside. The interface device (350) may receive a control signal for controlling the prediction device (300). The interface device (350) may output the results analyzed by the prediction device (300). The interface device (350) may receive information necessary for performing the aforementioned method for predicting the incidence of a disease caused by a parasite from a physically connected input device or an external storage device.

[0082] The communication device (360) can receive information necessary for performing the aforementioned method for predicting the incidence of a disease caused by a parasite. The communication device (360) can receive a model necessary for performing the aforementioned method for predicting the incidence of a disease caused by a parasite. The communication device (360) can transmit and receive sex information, age information, body mass index (BMI) information, alcohol information, GGT (Gamma-glutamyl transferase) information, eosinophil information, smoke information, surveillance information, hypertension information, and diabetes information. The communication device (360) can transmit and receive a prediction model. The communication device (360) can receive a control signal necessary for controlling the prediction device (300). The communication device (360) can transmit the results analyzed by the prediction device (300). A communication device (360) may refer to a configuration that receives and transmits certain data, information, models, etc. through a wired or wireless network.

[0083] The communication device (360) can perform network communication such as Wi-Fi (Wireless Fidelity), Wi-Fi Direct, Bluetooth, UWB (Ultra-Wide Band), NFC (Near Field Communication), USB (Universal Serial Bus), HDMI (High Definition Multimedia Interface), LAN (Local Area Network), etc.

[0084] The method for predicting the incidence of a disease caused by a parasite described above can be implemented as a program (or application) including an executable algorithm that can be executed on a computer.

[0085] The above program may be provided stored on a non-transitory computer readable medium.

[0086] The above-mentioned temporarily readable medium refers to various RAMs such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous DRAM (Synclink DRAM (SLDRAM), and direct Rambus RAM (DRRAM).

[0087] The above non-transitory readable medium refers to a medium that stores data semi-permanently and can be read by a device, rather than a medium that stores data for a short period of time, such as a register, cache, or memory. Specifically, the various applications or programs described above may be stored and provided in a non-transitory readable medium, such as a CD, DVD, hard disk, Blu-ray disk, USB, memory card, ROM (read-only memory), PROM (programmable read only memory), EPROM (Erasable PROM, EPROM), EEPROM (Electrically EPROM), or flash memory.

[0088] The present embodiment and the drawings attached to the present specification only clearly illustrate a part of the technical idea included in the above-described technology, and it will be obvious that all modified examples and specific embodiments that can be easily inferred by a person skilled in the art within the scope of the technical idea included in the specification and drawings of the above-described technology are included in the scope of the rights of the above-described technology.

Claims

1. A step in which the prediction device receives information about the subject; A step in which the prediction device inputs the information of the subject into the prediction model; and A step in which the above prediction device predicts the incidence of a disease caused by a parasite in the subject based on the output value of the above prediction model; including; A method for predicting the incidence of a disease caused by a parasite, wherein the information of the subject includes at least one of sex information, age information, body mass index (BMI) information, and alcohol consumption.

2. In paragraph 1, A method for predicting the incidence of a disease caused by a parasite, wherein the information of the subject further includes at least one of GGT (Gamma-glutamyl Transferase) information and eosinophil information.

3. In paragraph 2, A method for predicting the incidence of a disease caused by a parasite, wherein the information of the subject further includes at least one of smoke information, surveillance information, hypertension information, and diabetes information.

4. In paragraph 1, The above prediction model is a machine learning (ML)-based model, and includes a model learned to predict the incidence of a disease caused by a parasite in a subject from information about the subject based on learning data. A method for predicting the incidence of a disease caused by a parasite.

5. In paragraph 1, The above prediction model is a nomogram-based model, which is a method for predicting the incidence of a disease caused by a parasite in the subject by converting each piece of information included in the subject's information into a score and then predicting the incidence of a disease caused by a parasite in the subject based on the sum of the converted scores.

6. In paragraph 1, A method for predicting the incidence of a disease caused by a parasite, wherein the incidence of a disease caused by the parasite includes the incidence of a metabolic disease caused by at least one parasite among pathogenic protozoa, non-pathogenic protozoa, foodborne trematodes (FBT), and soil-transmitted helminths (STH).

7. Input device for receiving information from the subject; A computing device that inputs the information of the subject to a prediction model and predicts the incidence of a disease caused by a parasite in the subject based on the output value of the prediction model; and A storage device for storing the above prediction model; including: A prediction device, wherein the information of the subject includes at least one of sex information, age information, body mass index (BMI) information, and alcohol.

8. In paragraph 7, A prediction device wherein the information of the subject further includes at least one of GGT (Gamma-glutamyl Transferase) information and eosinophil information.

9. In paragraph 8, A prediction device wherein the information of the subject further includes at least one of smoke information, surveillance information, hypertension information, and diabetes information.

10. In paragraph 7, The above prediction model is a machine learning (ML)-based model, and includes a prediction device that learns to predict the incidence of a disease caused by a parasite in a subject from information about the subject based on learning data.

11. In paragraph 7, A prediction device, wherein the incidence of disease caused by the parasite includes the incidence of disease caused by at least one parasite among pathogenic protozoa, non-pathogenic protozoa, foodborne trematodes (FBT), and soil-transmitted helminths (STH).

12. In paragraph 7, The above prediction model is a nomogram-based model, which is a prediction device that converts each piece of information included in the information of the subject into a score and then predicts the incidence of a disease caused by a parasite of the subject based on the sum of the converted scores.

Images