JP2016177678A - Allergy onset risk prediction system, method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an allergy onset risk prediction system, a method and a program capable of predicting an allergy onset risk while considering circumstance factors.SOLUTION: The allergy onset risk prediction system includes a first prediction section and a second prediction section. The first prediction section predicts a first onset risk of an allergy based on a piece of data which represents the type of gene and amount of antibody of a subject. The second prediction section predicts a second onset risk in each area based on the first onset risk and a piece of data which represents the amount of allergen in each of plural areas preset in a room.SELECTED DRAWING: Figure 1

Description

  Embodiments described herein relate generally to an allergy risk prediction apparatus, method, and program.

  In recent years, genetic factors obtained by genome analysis have been used to predict the risk of developing allergies. However, genetic factors are only part of an individual's constitution, and it has been pointed out that environmental factors such as lifestyles are greatly involved in the onset depending on the disease. In particular, allergic asthma develops largely depending on environmental factors, so it is difficult to predict the onset risk.

JP 2000-15031 A JP-A-2005-331128

  An allergy risk prediction apparatus, method, and program capable of predicting the risk of developing allergy in consideration of environmental factors are provided.

  The allergy onset risk prediction apparatus according to an embodiment includes a first prediction unit and a second prediction unit. The first prediction unit predicts the first risk of developing allergy based on data indicating the genotype and antibody amount of the subject. The second predicting unit predicts the second onset risk for each area based on the first onset risk and the data indicating the allergen amount for each of the plurality of areas set indoors.

The figure which shows the function structure of the allergy onset risk prediction apparatus. The figure which shows an example of gene variation data. The figure which shows an example of antibody amount data. The figure which shows an example of onset history data. The figure which shows an example of allergen amount data. The figure which shows an example of the floor plan of the area set indoors. The figure which shows an example of indoor map data. The figure which shows an example of a 2nd onset risk. The figure which shows an example of the prediction result displayed on a display apparatus. The figure which shows the hardware constitutions of the allergy onset risk prediction apparatus. The flowchart which shows the construction method of a prediction model. The flowchart which shows the prediction method of a 1st onset risk. The flowchart which shows the measuring method of allergen amount. The flowchart which shows the prediction method of a 2nd onset risk.

  Embodiments of the present invention will be described below with reference to the drawings.

  First, the functional configuration of the allergy risk prediction device (hereinafter referred to as “prediction device”) will be described with reference to FIGS. FIG. 1 is a diagram illustrating a functional configuration of a prediction device according to an embodiment. As shown in FIG. 1, the prediction device includes a gene mutation DB 1, an antibody amount DB 2, an onset history DB 3, a prediction model construction unit 4, a prediction model storage unit 5, a first onset risk prediction unit 6, and an essential device. Attention allergen specifying unit 7, attention allergen storage unit 8, allergen amount measuring unit 9, allergen amount DB 10, indoor map DB 11, allergen amount calculating unit 12, second onset risk predicting unit 13, second An onset risk storage unit 14, an output unit 15, and a control unit 16 are provided.

  The gene mutation DB1 stores gene mutation data. The gene mutation data is data including a genotype for each single nucleotide polymorphism (SNP) (for example, IL-4, IL-13, PHF11, etc.) of a plurality of specimens. The genotype of each SNP of each specimen is obtained by analyzing a sample such as blood with a sequencer. In the gene mutation DB1, each sample is anonymized and specified by the sample ID.

  FIG. 2 is a diagram illustrating an example of gene mutation data stored in the gene mutation DB1. 2 includes the genotypes of SNPs 1 to 3 related to the allergy type i of the sample IDs 01 to 03 and the allergy onset odds ratio corresponding to the genotype. For example, in the example of FIG. 2, the genotype of SNP related to allergy i = 1 of specimen ID01 is BB, and the allergy onset odds ratio is 3.5.

  The gene mutation data may be stored for each allergy or for each allergen. When gene mutation data is stored for each allergy, allergy and SNP are associated with each other, and the gene mutation data for each allergy may include the SNP genotype associated with each allergy. In this case, a plurality of related SNPs can be assigned to each allergy. The same applies when storing gene mutation data for each allergen.

  The antibody amount DB2 stores antibody amount data. The antibody amount data is data including the antibody amount for each allergen of a plurality of specimens. The antibody amount is a measured value of an antibody such as IgE. The amount of antibody is measured by an allergic reaction test such as a blood biochemical test. In the antibody amount DB2, each sample is anonymized and is specified by the sample ID.

  FIG. 3 is a diagram illustrating an example of the latest antibody amount data level value stored in the antibody amount DB2. The antibody amount data in FIG. 3 includes antibody amount level values for allergen 1 of specimen IDs 01 to 03. For example, in the example of FIG. 3, the antibody amount level value for allergen 1 of specimen ID01 is 4. Here, the allergen antibody amount is set to a level of 1 to 4 based on a predetermined specific IgE threshold, but it may be changed to 0 to 6 by changing the threshold setting, for example. . The antibody amount DB 2 stores antibody amount level data as shown in FIG. 3 for each allergen.

  Hereinafter, the allergen i allergen is referred to as allergen i.

  The onset history DB 3 stores onset history data. The onset history data is data including the allergy onset history of a plurality of specimens every predetermined period (for example, every day or every month). The onset history is represented by two values, for example, onset and not onset. In the onset history DB 3, each sample is anonymized and specified by the sample ID.

  FIG. 4 is a diagram illustrating an example of onset history data stored in the onset history DB 3. The onset history data in FIG. 4 includes a daily onset history of allergy 1 with sample IDs 01 and 02. In FIG. 4, 1 indicates that the disease has developed, and 0 indicates that it has not developed. For example, in the example of FIG. 4, the sample ID 01 developed allergy 1 on March 2. The onset history DB 3 stores the onset history as shown in FIG. 4 for each allergy.

  The prediction model construction unit 4 (hereinafter referred to as “construction unit 4”) constructs a prediction model based on gene mutation data, antibody amount data, and onset history data. The prediction model is a model for predicting the risk of developing allergy according to the genotype and the amount of antibody. The construction unit 4 constructs a prediction model for each allergy. The method for constructing the prediction model will be described later in detail.

  The prediction model storage unit 5 stores the prediction model for each allergy constructed by the construction unit 4.

  The first onset risk prediction unit 6 (hereinafter referred to as “first prediction unit 6”) predicts the first onset risk for each allergy of the subject using the prediction model stored in the prediction model storage unit 5. The first risk of onset is predicted by applying the genotype and antibody amount of the subject to the prediction model. Therefore, the first onset risk is an onset risk corresponding to the genotype and antibody amount of the subject. That is, other environmental factors are not considered in the first onset risk. The method for predicting the first onset risk will be described in detail later.

  The caution allergen specifying unit 7 (hereinafter, referred to as “specifying unit 7”) specifies the caution allergen of the subject based on the first onset risk predicted by the first prediction unit 6. The allergens requiring attention are allergic antigens with a high risk of first onset for the subject. For example, the specifying unit 7 compares a preset threshold value with the first onset risk of each allergy, and specifies an allergic antigen whose first onset risk is equal to or higher than the threshold value as an allergen requiring attention. Details of the method for identifying allergens requiring attention will be described later.

  The caution allergen storage unit 8 stores the caution allergen of the subject specified by the specifying unit 7.

  The allergen amount measurement unit 9 (hereinafter referred to as “measurement unit 9”) measures the amount of indoor allergen for each allergen. The term “indoor” as used herein refers to the inside of a building that is a target for predicting the second onset risk of the subject's allergy. Details of the second onset risk will be described later.

  The function of the measuring unit 9 can be realized by, for example, a particle counter installed indoors. Specifically, the allergen amount for each allergen can be measured by setting the particle size for each allergen and counting the amount of fine particles of each particle size with a particle counter. The particle counter may be installed indoors independently, or may be installed so that the deposits of filters such as an air conditioner, an air cleaner, and a robot cleaner installed indoors can be observed.

  Moreover, the function of the measurement part 9 may be implement | achieved by imaging the deposit | attachment of filters, such as an air conditioner installed indoors, an air cleaner, and a robot cleaner, with a micro camera, and image-analyzing. Specifically, the allergen amount for each allergen can be measured by specifying the allergen by pattern matching from the shape of the fine particles contained in the image captured by the micro camera and counting the number of allergens specified. it can. In this case, the function of the measurement part 9 may be implement | achieved on the computer which comprises a prediction apparatus, and may be implement | achieved on the microcomputer mounted in the micro camera. A method for measuring the allergen amount using this method will be described in detail later.

  The method for measuring the allergen amount is not limited to the above method, and any method capable of measuring the allergen amount can be used. The measuring unit 9 measures the amount of allergen in a plurality of places in the room, and stores the measured amount of allergen in the allergen amount DB 10.

  The allergen amount DB 10 stores allergen amount data. The allergen amount data is data including the allergen amount for each allergen on each measurement date. Allergen amount data is stored for each measurement position. In the present embodiment, the allergen amount data is generated by storing the measurement result of the measuring unit 9, but can also be input from an external device. In this case, the prediction device may not include the measurement unit 9.

  FIG. 5 is a diagram illustrating an example of allergen amount data stored in the allergen amount DB 10. The allergen amount data in FIG. 5 includes, for example, allergen amounts of allergens 1, 2, and 3 measured in a room k = 4 from March 1 to March 2. For example, in the example of FIG. 5, the allergen level of allergen 1 on March 1 in room k = 4 is 0.8. Here, the maximum allergen amount in the history measured so far is set to 1, and the ratio to the maximum value is set as the allergen level. The allergen amount DB 10 stores allergen amount level data as shown in FIG. 5 for each room k.

  The position of the allergen amount level may be represented by indoor coordinates, may be represented by a device installed indoors, or may be represented by an area set indoors. In any case, it is only necessary that the allergen amount for each area described later can be calculated.

  The indoor map DB 11 stores indoor map data. In the present embodiment, a plurality of areas are set indoors, and the second onset risk for each area is predicted. Each area may be set for each room, may be set for each of a plurality of rooms, or may be set for each floor of a building. Indoor map data is data indicating the floor plan of an area set indoors.

  FIG. 6 is a diagram schematically illustrating an example of a floor plan of an area set indoors. In FIG. 6, six areas 1 to 6 are set indoors. FIG. 7 is a diagram showing indoor map data corresponding to the floor plan of FIG. In FIG. 7, each room (area) k is shown as a range of xy coordinates shown in FIG. For example, in the example of FIG. 7, the coordinate value defined by the distance from the reference point in the southwest on the drawing is described in mm, and the room k = 1 is x = 1000 mm to 3000 mm and y = 3000 mm. It is the range of -9000mm.

  The allergen amount level calculation unit 12 (hereinafter referred to as “calculation unit 12”) calculates the allergen amount level of allergens requiring attention in each area based on the allergen amount level data and the indoor map data. Specifically, the calculation unit 12 acquires a caution allergen from the caution allergen storage unit 8 and acquires an allergen amount level for each measurement position of the caution allergen from the allergen amount DB 10. And the calculation part 12 matches a measurement position and an area based on indoor map data, and calculates the allergen amount level of the allergen requiring attention of each area.

  For example, when the measurement position is represented by coordinates, the measurement position can be associated with the area by comparing the coordinates of the measurement position with the coordinates of each area included in the indoor map data. When the measurement position is represented by a device, the indoor map DB 11 may store the correspondence between the area and the device. Note that when the measurement position is represented by an area, the prediction device may not include the calculation unit 12.

  The second onset risk prediction unit 13 (hereinafter referred to as “second prediction unit 13”) calculates the second onset risk for each allergy of the subject based on the allergen amount of the allergens requiring attention and the first onset risk for each area. Predict. The second onset risk is predicted to multiply the first onset risk by a value corresponding to the amount of allergen and increase as the allergen amount increases. Therefore, the second onset risk is an onset risk considering not only the genotype and antibody amount of the subject but also environmental factors such as the allergen amount for each area. The method for predicting the second onset risk will be described later in detail.

  The second onset risk storage unit 14 stores the second onset risk for each area predicted by the second onset risk prediction unit 13. When there are a plurality of allergens requiring attention, the second onset risk is stored for each allergen requiring attention.

  FIG. 8 is a diagram illustrating an example of the second onset risk stored in the second onset risk storage unit 14. In FIG. 8, the allergens requiring attention are allergies 1 and 2, and the second risk of onset in areas 4 and 6 is stored. For example, in the example of FIG. 8, the second onset risk of allergy 2 in the subject's area 6 is 18.7.

  The output unit 15 outputs a prediction result of the second onset risk. The output here includes displaying a prediction result on a display device and transmitting the prediction result to an external device. The output unit 15 may output predetermined information according to the prediction result together with the prediction result.

  FIG. 9 is a diagram illustrating an example of a prediction result that the output unit 15 displays on the display device. In FIG. 9, the second onset risk of FIG. 8 is displayed in the corresponding area on the indoor map. Moreover, the corresponding allergen is displayed with the 2nd onset risk. For example, in the example of FIG. 9, the second risk of onset in area 6 is the risk of developing mite allergy. Further, below the indoor map, advice to the target person according to the prediction result is displayed.

  In this way, by feeding back the prediction result of the second onset risk to the subject, the subject can recognize the risk of developing allergy and take preventive measures. Therefore, the onset of allergy can be suppressed.

  In addition, in FIG. 9, although it displays only about the 2nd onset risk more than a threshold value (= 4.5), a threshold value is not restricted to this, All the 2nd onset risks may be displayed. The output unit 15 may not only display the prediction result on the display device but also notify the target person of the prediction result by e-mail.

  The control part 16 controls the household appliance installed indoors so that a 2nd onset risk may fall according to a 2nd onset risk. The household appliances controlled by the control unit 16 include any household appliances having a function of removing allergens, such as an air conditioner, an air cleaner, and a robot cleaner.

  Specifically, the control unit 16 turns on or enhances the allergen removal function of the air conditioner or the air cleaner in an area where the second risk of occurrence is high (for example, areas 4 and 6 in FIG. 9). Can be considered. Moreover, the control part 16 may make a robot cleaner clean an area with a high 2nd onset risk, or may improve the frequency with which a robot cleaner cleans an area with a high 2nd onset risk.

  Thereby, the allergen of an area with a high 2nd onset risk can be removed, and a 2nd onset risk can be reduced. Therefore, the onset of the subject's allergy can be suppressed.

  Next, the hardware configuration of the prediction apparatus according to the present embodiment will be described with reference to FIG. The prediction apparatus according to the present embodiment is configured by a computer 100 as shown in FIG. The computer 100 includes a CPU (central processing unit) 101, an input device 102, a display device 103, a communication device 104, and a storage device 105, which are connected to each other via a bus 106.

  The CPU 101 is a control device and a calculation device of the computer 100. The CPU 101 performs arithmetic processing based on data or a program input from each device (for example, the input device 102, the communication device 104, and the storage device 105) connected via the bus 106, and outputs the calculation result and the control signal. The data is output to each device (for example, the display device 103, the communication device 104, and the storage device 105) connected via the bus 106.

  Specifically, the CPU 101 executes an OS (operating system) of the computer 100, an allergy risk prediction program (hereinafter referred to as “prediction program”), and the like, and controls each device constituting the computer 100. The prediction program is a program that causes the computer 100 to realize the above-described functional configurations of the prediction device. When the CPU 101 executes the prediction program, the computer 100 functions as a prediction device.

  The input device 102 is a device for inputting information to the computer 100. The input device 102 is, for example, a keyboard, a mouse, and a touch panel, but is not limited thereto. By using the input device 102, the user of the prediction device can input information such as the subject's genotype and antibody amount.

  The display device 103 is a device for displaying images and videos. The display device 103 is, for example, an LCD (liquid crystal display), a CRT (CRT), and a PDP (plasma display), but is not limited thereto. The output unit 15 can cause the display device 103 to display a prediction result as shown in FIG.

  The communication device 104 is a device for the computer 100 to communicate with an external device wirelessly or by wire. The communication device 104 is, for example, a modem, a hub, and a router, but is not limited thereto. The output unit 15 and the control unit 16 may communicate with an external device via the communication device 104. Further, the allergen amount measuring unit 9 may be configured by an indoor air conditioner or the like, and the measurement result may be stored in the allergen amount DB 10 via the communication device 104.

  The storage device 105 is a storage medium that stores the OS of the computer 100, a prediction program, data necessary for execution of the prediction program, data generated by execution of the prediction program, and the like. The storage device 105 includes a main storage device and an external storage device. The main storage device is, for example, a RAM, a DRAM, or an SRAM, but is not limited thereto. The external storage device is a hard disk, an optical disk, a flash memory, and a magnetic tape, but is not limited thereto. The gene mutation DB1, the antibody amount DB2, the onset history DB3, the prediction model storage unit 5, the cautionary allergen storage unit 8, the allergen amount DB10, the indoor map DB11, and the second onset risk storage unit 14 are configured using the storage device 105. can do.

  The computer 100 may include one or more CPUs 101, input devices 102, display devices 103, communication devices 104, and storage devices 105, or may be connected to peripheral devices such as printers and scanners. .

  In addition, the prediction device may be configured by a single computer 100 or may be configured as a system including a plurality of computers 100 connected to each other.

  Furthermore, the prediction program may be stored in advance in the storage device 105 of the computer 100, may be stored in a storage medium such as a CD-ROM, or may be uploaded on the Internet. In either case, the prediction apparatus can be configured by installing the prediction program in the computer 100 and executing it.

  Next, the operation of the prediction apparatus according to this embodiment will be described with reference to FIG.

  FIG. 11 is a flowchart illustrating a prediction model construction method by the construction unit 4.

  In step S1, the construction unit 4 selects an allergy i for constructing a prediction model.

  In step S2, the construction unit 4 acquires gene mutation data, antibody amount data, and onset history data related to allergy i. Specifically, the construction unit 4 acquires all the gene mutation data from the gene mutation DB1, acquires the antibody amount data of allergen 1 from the antibody amount DB2, and acquires the onset history data of allergy i from the onset history DB3. .

  In addition, when the gene variation data is stored for each allergy or for each allergen, the construction unit 4 may acquire allergen i or allergy i gene variation data.

  In step S3, the construction unit 4 divides the data acquired in step S2 into learning data and verification data. Data division is performed on a sample basis. For example, of all the samples, 2/3 sample data is used as learning data, and 1/3 sample data is used as verification data.

  In step S4, the construction unit 4 constructs a prediction model for allergy i from the learning data. Specifically, the construction unit 4 uses the onset history data as teacher data to learn a model for determining whether or not it is the day when allergy i has occurred from the genotype and the amount of antibody. The construction unit 4 may construct a prediction model using a known machine learning technique such as a multiple regression model, a logistic regression model, or SVM (Support Vector Machine).

  In step S5, the construction unit 4 evaluates the performance of the constructed allergy i prediction model. Specifically, the construction unit 4 inputs the genotype and antibody amount included in the verification data into the prediction model constructed in step S4 and outputs the onset, and the onset history included in the verification data. And the performances such as the correct answer rate, false positive rate, and false negative rate are calculated.

  When the performance of allergy i is equal to or higher than a predetermined lower limit (for example, a correct answer rate of 90% or higher, a false positive rate of 80% or higher, a false negative rate of 70% or higher, etc.), the construction unit 4 The prediction model constructed in S4 is stored in the prediction model storage unit 5 as a prediction model for allergy i (step S7).

  On the other hand, when the performance of allergy i is less than the predetermined lower limit (NO in step S6), the construction unit 4 discards the prediction model constructed in step S4. In this case, a prediction model for allergy i is not constructed. Thereafter, the process proceeds to step S8.

  In step S8, the construction unit 4 determines whether the prediction model construction processing has been completed for all allergies. If there is an allergy that has not yet been subjected to the prediction model construction process (YES in step S8), the construction unit 4 selects the next allergy i (step S9). Thereafter, the process returns to Step 2.

  On the other hand, when the prediction model construction process is completed for all allergies (NO in step S8), the prediction model construction process ends.

  The following formula is an example of a prediction model constructed by the construction unit 4.

In formula (1), allergy_risk_i is the first risk of allergy i, IgE_Level _i is the antibody amount level calculated according to the IgE antibody amount, J is the number of SNPs included in the gene mutation data, A _{snp_ij} Is the value of the onset odds ratio corresponding to the genotype of SNPj (1 ≦ j ≦ J) included in the gene variation data of allergy i. When constructing the prediction model of Expression (1), the construction unit 4 may use haplotype data prepared in advance.

  FIG. 12 is a flowchart showing a method for predicting the first onset risk by the first predicting unit 6 and a method for specifying the allergen requiring attention by the specifying unit 7. Below, the 1st onset risk of allergies 1-I shall be estimated.

  In step S10, the first prediction unit 6 selects an allergy i that predicts the first risk of onset.

  In step S <b> 11, the first prediction unit 6 acquires the subject's genotype and antibody amount related to allergy i. As described above, the genotype and antibody amount of the subject may be input using the input device 102, or may be stored in the gene mutation DB1 and the antibody amount DB2.

  In step S <b> 12, the first prediction unit 6 acquires a prediction model of allergy i as expressed by Equation (1) from the prediction model storage unit 5.

  In step S <b> 13, the first prediction unit 6 inputs the subject's genotype and antibody amount to the allergy i prediction model, and predicts the first onset risk of allergy i. The first prediction unit 6 inputs the calculated first onset risk to the specifying unit 7.

  In step S14, the specifying unit 7 compares the first onset risk of allergy i with a threshold value. When the first onset risk is equal to or higher than the threshold (YES in Step S14), the specifying unit 7 stores the allergen i as the subject's caution allergen in the caution allergen storage unit 8 (Step S15).

  On the other hand, when the first onset risk is less than the threshold (NO in step S14), the specifying unit 7 does not store the allergen i as the subject's caution allergen in the caution allergen storage unit 8, and the process proceeds to step S16. Proceed to

  In step S <b> 16, the first prediction unit 6 determines whether the first onset risk prediction process has been completed for all allergies. If there is an allergy for which the first risk of onset is not yet predicted (YES in step S16), the first prediction unit 6 selects the next allergy i (step S17). Thereafter, the process returns to Step 11.

  On the other hand, when the first onset risk is predicted for all allergies (NO in step S16), the first onset risk prediction process ends.

  Through the above processing, the first risk of onset for each allergy of the subject can be predicted, and the allergens requiring attention of the subject can be identified.

  FIG. 13 is a flowchart illustrating a method for measuring the allergen amount by the measurement unit 9. Below, the case where the amount of allergen is measured from the image of the filter of an air conditioner using pattern matching is demonstrated. It is assumed that the function of the measurement unit 9 is realized on the computer 100.

  In step S18, the measuring unit 9 selects the allergen i.

  In step S <b> 19, the measurement unit 9 acquires template data for allergen i. The template data is data serving as a reference for the shape of allergen i. For example, the template data may be stored in the prediction device in advance or may be acquired from an external device.

  In step S20, the measurement unit 9 acquires a filter image. The image of the filter can be acquired from the micro camera via the communication device 104.

  In step S21, the measurement unit 9 detects the contour shape of the fine particles in the image. A well-known detection method such as an edge detection algorithm can be used as a method for detecting the contour shape of the fine particles.

  In step S22, the measurement unit 9 calculates the similarity between the detected shape of the fine particles and the template of the allergen i by pattern matching. The similarity can be calculated using the Euclidean distance or the wavelet distance. Further, the measurement unit 9 may calculate the similarity by absorbing a local contour shift by dynamic time warping. Furthermore, the measurement unit 9 may calculate the similarity for a plurality of fine particles, and output the average value or the like as the similarity to the template for allergy i.

  In step S23, the measurement unit 9 determines whether the similarity calculation has been completed for all allergens. When there is an allergen whose similarity is not calculated (NO in step S23), the measurement unit 9 selects the next allergen i (step S24). Thereafter, the process returns to step S19.

  On the other hand, when the calculation of the similarity is completed for all allergens (YES in step S23), the process proceeds to step S25.

  In step S25, the measurement unit 9 measures the amount of fine particles in the image.

  In step S26, the measuring unit 9 stores the measured amount of fine particles in the allergen amount DB 10 as the allergen amount of the allergen i having the highest similarity. Moreover, the measurement part 9 stores measurement positions, such as ID and a coordinate of an air conditioning machine, with allergen amount in allergen amount DB10.

  When there are a plurality of measurement positions, the measurement unit 9 may perform the above processing for each measurement position. The measurement unit 9 repeats the above processing every predetermined time, thereby storing allergen amount data of each date and time indoors.

  FIG. 14 is a flowchart showing a method for calculating the allergen amount for each area by the calculation unit 12 and a method for predicting the second onset risk by the second prediction unit 13.

  In step S <b> 27, the calculation unit 12 acquires the subject's caution allergen from the caution allergen storage unit 8.

  In step S28, the calculation unit 12 selects the allergen i requiring attention.

  In step S <b> 29, the second prediction unit 13 acquires the first onset risk of the subject's attention allergen i from the first prediction unit 6.

  In step S30, the calculation unit 12 acquires the indoor allergen data of the subject from the allergen DB 10, and acquires the indoor map data of the subject from the indoor map DB.

  In step S31, the calculation unit 12 selects an area k set indoors.

  In step S32, the calculation unit 12 calculates the allergen amount of the allergen i requiring attention in the area k. Specifically, the measurement unit 12 associates the allergen amount of the allergen i of interest included in the allergen amount data with each area based on the measurement position and the indoor map data, and the allergen associated with the area k. Calculate the total amount. The calculation unit 12 inputs the allergen amount of the area k to the second prediction unit 13.

  In step S33, the second prediction unit 13 predicts the second risk of onset of allergen i requiring attention in area k based on the allergen amount of allergen i requiring attention in area k and the first onset risk of allergen i. To do. The second onset risk is calculated by the following formula, for example.

In the above formula (2), position_risk _ik is the second onset risk of allergen i requiring attention in area k, allergy_risk _i is the first risk of allergen i requiring attention, and parlevel ik is allergen i requiring attention in area k. It is a level according to the amount of allergen.

  In step S34, the second predicting unit 13 stores the second onset risk calculated in step S33 in the second onset risk storage unit 14.

  In step S <b> 35, the second prediction unit 13 determines whether the prediction process of the second onset risk has been completed for the area included indoors. When there is an area where the prediction process is not performed (NO in step S35), the calculation unit 12 selects the next area k (step S36). Thereafter, the process returns to step S32. On the other hand, when the prediction process is completed for all areas (YES in step S35), the process proceeds to step S36.

  In step S <b> 37, the second prediction unit 13 determines whether the second onset risk prediction process has been completed for all the allergens requiring attention of the subject. When there is a caution allergen that has not been predicted (NO in step S37), the calculation unit 12 selects the next caution allergen i (step S38). On the other hand, when the prediction process is completed for all the allergens requiring attention (YES in step S37), the prediction process of the second onset risk is terminated.

  With the above processing, it is possible to predict the second onset risk for each caution allergen in each area of the subject.

  As described above, the prediction device according to the present embodiment can predict the risk of developing allergy for each area according to the amount of allergen. By taking into account the environmental factor of the allergen amount, the risk of onset can be accurately predicted.

  The subject can reduce or eliminate allergens with reference to the predicted onset risk and advice, thereby reducing the risk of developing allergy or suppressing the allergy from becoming serious.

  Note that the present invention is not limited to the above-described embodiments as they are, and can be embodied by modifying the components without departing from the scope of the invention in the implementation stage. Moreover, various inventions can be formed by appropriately combining a plurality of constituent elements disclosed in the above embodiments. Further, for example, a configuration in which some components are deleted from all the components shown in each embodiment is also conceivable. Furthermore, you may combine suitably the component described in different embodiment.

1: gene mutation DB, 2: antibody amount DB, 3: onset history DB, 4: prediction model construction unit, 5: prediction model storage unit, 6: first onset risk prediction unit, 7: caution allergen identification unit, 8 : Allergen storage unit requiring attention, 9: allergen amount measurement unit, 10: allergen amount DB, 11: indoor map DB, 12: allergen amount calculation unit, 13: second onset risk prediction unit, 14: second onset risk storage unit , 15: output unit, 16: control unit

Claims (14)

A first prediction unit that predicts a first risk of developing allergy based on data indicating a subject's genotype and antibody amount;
A second predicting unit that predicts the second onset risk for each area based on the first onset risk and data indicating the amount of allergen for each of a plurality of areas set indoors;
An allergy risk prediction device comprising: The allergy onset risk prediction apparatus according to claim 1, further comprising an output unit that outputs a prediction result of the second onset risk. The allergy onset risk prediction device according to claim 2, wherein the output unit displays the second onset risk for each room on the indoor map. The said output part is the allergy onset risk prediction apparatus of Claim 2 or Claim 3 which displays the advice according to the said 2nd onset risk. The allergy onset risk prediction apparatus according to any one of claims 1 to 4, further comprising a control unit that controls the indoor home appliance according to the second onset risk for each area. The said control part is an allergy onset risk prediction apparatus of Claim 5 which controls the said household appliance so that the said 2nd onset risk for every said area may fall. The allergy risk prediction apparatus according to claim 5 or 6, wherein the home appliance includes an air cleaner, an air conditioner, a cleaner, and a robot cleaner. The allergy onset risk prediction apparatus according to claim 1, further comprising a measurement unit that measures the amount of the allergen in the indoor. The allergy onset risk prediction apparatus according to claim 8, wherein the measurement unit specifies an allergen by pattern matching. The allergy onset risk prediction apparatus according to any one of claims 1 to 9, further comprising a construction unit that constructs a prediction model of the first onset risk according to the genotype and the amount of the antibody. The allergy onset risk prediction apparatus according to claim 1, further comprising a specifying unit that specifies an allergen having a high first onset risk of the subject. The allergy risk prediction device according to any one of claims 1 to 11, wherein the area is set for each indoor room. Predicting the first risk of allergy based on the data indicating the subject's genotype and antibody amount;
Predicting the second onset risk for each area based on the first onset risk and data indicating the amount of allergen for each of a plurality of areas set indoors;
Allergy risk prediction method including. Predicting the first risk of allergy based on the data indicating the subject's genotype and antibody amount;
Predicting the second onset risk for each area based on the first onset risk and data indicating the amount of allergen for each of a plurality of areas set indoors;
Is a program for predicting the risk of developing allergies.

Images