Disease risk analysis device, method and program

Abstract

To provide a disease risk analysis device, a disease risk analysis method and a disease risk analysis program which can properly analyze, time history data.SOLUTION: A disease risk analysis device of one embodiment comprises: a stratification data generation part; a first observation object data generation part; an origin data generation part; an observation object determination part; a second observation object data generation part; and an analysis part. The stratification data generation part executes stratification of genetic score data on the basis of a threshold, for generating stratification data. The first observation object data generation part generates first observation object data obtained by, extracting an inspection value and / or a state of seeing a doctor corresponding to reference, from the time history data. The origin data generation part generates origin data on the basis of the first observation object data and the reference. The observation object determination part determines an observation object from medical examination data and / or seeing a doctor data. The second observation object data generation part generates second observation object data, on the basis of the origin data and the observation object. The analysis part analyzes the second observation object data.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The embodiments relate to a disease risk analysis device, a disease risk analysis method, and a disease risk analysis program. [Background technology]

[0002] In recent years, it has become possible to estimate genetic differences for various diseases and predispositions using polygenic risk scores (PRS) calculated from individual genome data. PRS is a score that represents the genetic risk for various diseases and predispositions whose onset is related to multiple genes.

[0003] The PRS can be used to perform various analyses, such as correlation analysis between the PRS and the presence or absence of a medical history using cross-sectional data, and estimation of disease risk at a certain age when longitudinal data is stratified by the PRS. [Prior art documents] [Non-patent literature]

[0004] [Non-Patent Document 1] Khera, Amit V., et al. "Polygenic prediction of weight and obesity trajectories from birth to adulthood." Cell 177.3 (2019): 587-596. Summary of the Invention [Problem to be solved by the invention]

[0005] In order to reduce future diseases, it is important to implement appropriate preventive measures when a future disease risk is predicted to be high. To predict future disease risk, it is possible to use longitudinal data obtained by collecting health checkup results and medical examination results over time. Here, even among people who have the same test values ​​in their health checkup results, some people have a low risk of developing disease due to genetic differences, while others have a high risk. Also, even among people who develop a disease at the same time in their medical examination results, some people develop a disease quickly from the onset of the disease to developing complications, while others develop a long time due to genetic differences. Appropriate analysis of such longitudinal data may not be possible with simple stratification of PRS.

[0006] The embodiments provide a disease risk analysis device, a disease risk analysis method, and a disease risk analysis program capable of appropriately analyzing time-course data. [Means for solving the problem]

[0007] A disease risk analysis device according to one embodiment includes an acquisition unit, a threshold determination unit, a stratified data generation unit, a criterion setting unit, a first observation target data generation unit, a starting point data generation unit, an observation target determination unit, a second observation target data generation unit, and an analysis unit. The acquisition unit acquires healthcare data including genetic score data that holds a genetic score for each user, and time-course data including at least one of health checkup data and medical examination data for each user collected over time. The threshold determination unit determines a threshold for stratifying the genetic score. The stratified data generation unit generates stratified data by stratifying the genetic score data based on the threshold. The criterion setting unit sets a criterion for at least one test value of the health checkup data and / or at least one medical examination situation of the medical examination data. The first observation target data generation unit generates first observation target data by extracting test values ​​and / or medical examination situations corresponding to the criterion from the time-course data. The starting point data generation unit generates starting point data based on the first observation target data and the criterion. The observation target determination unit determines an observation target from at least one test value in the health checkup data and / or at least one medical examination status in the medical examination data. The second observation target data generation unit generates second observation target data by extracting the test value and / or medical examination status determined by the observation target determination unit from the time-series data using the starting point data as a starting point. The analysis unit analyzes the second observation target data by stratifying the second observation target data based on the stratification data. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of a configuration of a disease risk analysis device according to an embodiment. [Diagram 2] FIG. 2 is a diagram showing an example of the PRS data. [Diagram 3] FIG. 3 is a diagram showing an example of medical checkup data. [Figure 4] Figure 4 is an example of medical examination data. [Diagram 5] FIG. 5 is a diagram illustrating an example of a hardware configuration of the disease risk analysis apparatus. [Figure 6] FIG. 6 is a flowchart showing the operation of the disease risk analysis device. [Figure 7] FIG. 7 shows stratified data stratified by diabetes PRS thresholds. [Figure 8] FIG. 8 is a diagram illustrating an example of the first observation target data. [Figure 9] FIG. 9 is a diagram illustrating an example of starting point data. [Figure 10] FIG. 10 is a diagram showing an example of the second observation target data. [Figure 11A] FIG. 11A is a graph obtained by selecting HbA1c as the second observation data and stratifying HbA1c by the PRS of BMI. [Figure 11B] FIG. 11B is a graph obtained by selecting systolic blood pressure as the second observation data and stratifying the systolic blood pressure by the PRS of BMI. [Figure 11C] FIG. 11C is a graph obtained by selecting LDL as the second observation data and stratifying LDL by the PRS of BMI. [Figure 11D] FIG. 11D is a graph obtained by selecting HDL as the second observation data and stratifying HDL by the PRS of BMI. [Figure 11E] FIG. 11E is a graph obtained by selecting TG as the second observation data and stratifying the TG by PRS of BMI. [Figure 11F] FIG. 11F is a graph obtained by selecting BMI as the second observation data and stratifying the BMI by the PRS of BMI. [Figure 11G] FIG. 11G is a graph obtained by selecting body weight as the second observation data and stratifying body weight by the PRS of BMI. [Figure 11H] FIG. 11H is a graph obtained by selecting GOT as the second observation data and stratifying GOT by the PRS of BMI. [Figure 11I] FIG. 11I is a graph obtained by selecting GPT as the second observation data and stratifying GPT by PRS of BMI. [Figure 11J] FIG. 11J is a graph obtained by selecting γGPT as the second observation data and stratifying γGPT by the PRS of BMI. [Figure 12A] FIG. 12A is a graph obtained by selecting the prevalence of diabetes as the second observation data and stratifying the prevalence of diabetes by PRS of systolic blood pressure. [Figure 12B] FIG. 12B is a graph obtained by selecting the prevalence of hypertension as the second observation data and stratifying the prevalence of hypertension by PRS of systolic blood pressure. [Figure 12C] FIG. 12C is a graph obtained by selecting the prevalence of dyslipidemia as the second observation data and stratifying the prevalence of dyslipidemia by PRS of systolic blood pressure. [Figure 12D] FIG. 12D is a graph obtained by selecting the prevalence of obesity as the second observation data and stratifying the prevalence of obesity by PRS of systolic blood pressure. [Figure 12E] FIG. 12E is a graph obtained by selecting the prevalence of liver dysfunction as the second observation data and stratifying the prevalence of liver dysfunction by PRS of systolic blood pressure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an embodiment will be described with reference to the drawings. Fig. 1 is a diagram showing an example of a configuration of a disease risk analysis device according to an embodiment. The disease risk analysis device 1 has an acquisition unit 11, a threshold determination unit 12, a stratified data generation unit 13, a standard setting unit 14, a first observation target data generation unit 15, a starting point data generation unit 16, a second observation target data determination unit 17, a second observation target data generation unit 18, and an analysis unit 19.

[0010] The acquisition unit 11 acquires healthcare data. The healthcare data is data for each individual user related to prediction of the user's disease risk. The healthcare data includes PRS data. The healthcare data also includes time-course data. The healthcare data can be input by any method, such as an operation of the disease risk analysis device 1 by a disease risk analyst such as a doctor.

[0011] PRS data is data that holds a PRS value as a genetic score for each user who is the subject of disease risk analysis. FIG. 2 is a diagram showing an example of PRS data. As shown in FIG. 2, PRS data has an ID and a PRS value. The ID is a character string that is uniquely assigned to each user. The PRS is a score that represents genetic differences in various diseases and constitutions whose onset involves a large number of genes. The PRS data is associated with each disease and constitution. FIG. 2 shows a diabetes PRS and a hypertension PRS as examples. The diabetes PRS is a score that represents the genetic susceptibility to diabetes. On the other hand, the hypertension PRS is a score that represents the genetic susceptibility to hypertension. In an embodiment, the PRS may be a PRS that is correlated with the risk of developing obesity, hypertension, diabetes, dyslipidemia, and liver dysfunction, and a PRS that is correlated with test values ​​such as BMI (body mass index), HbA1c (hemoglobin A1c), systolic blood pressure, LDL (low density lipoprotein), HDL (high density lipoprotein), TG (triglyceride), body weight, GOT (glutamic oxaloaxetic transaminase), GPT (glutamic pyruvic transaminase), and γGPT.

[0012] The time-series data includes at least one of medical checkup data and medical examination data for each user collected over time. The medical checkup data is data on the results of medical examinations of each user. The medical examination data is data on the medical examination status of each user at a medical institution.

[0013] FIG. 3 is a diagram showing an example of health check data. The health check data can be generated from the results of a health check performed annually for each user. As shown in FIG. 3, the health check data includes an ID, a medical examination year, an age, and a test value. The ID is a character string uniquely assigned to each user. The ID in the PRS data and the ID in the health check data are common. The medical examination year is the year in which the user of the corresponding ID underwent a health check. The age is the age of the user of the corresponding ID at the time of the health check. The test value is various test values ​​that can be a criterion for determining the onset of obesity, hypertension, diabetes, dyslipidemia, and liver dysfunction. Here, the health check data may include information other than the test value. For example, the health check data may include information obtained by a medical history interview or the like.

[0014] FIG. 4 is an example of medical examination data. The medical examination data is generated from information included in, for example, a medical receipt. The medical receipt includes various information on medical examination status, such as the name of the injury or illness for which each user visited a medical institution, the medical procedure, and the medicine prescribed. The medical examination data in FIG. 4 includes the medical examination status of whether or not the user of each ID received a prescription for medicine related to the corresponding disease in each year. The medical examination status is various medical examination status that can be a criterion for determining the onset of obesity, hypertension, diabetes, dyslipidemia, and liver dysfunction. In FIG. 4, "1" is recorded when a prescription for medicine is received, and "0" is recorded when it is not received. The medicine may be a specific medicine, or may be a collection of multiple medicines. The medical examination data may also include the medical examination status of whether or not a specific medical procedure is received.

[0015] The threshold determination unit 12 determines the PRS used for stratification of the time-course data and the threshold of the PRS used for stratification. The PRS used for stratification and its threshold can be determined, for example, in response to an operation of the disease risk analysis device 1 by a disease risk analyst such as a doctor. The threshold is determined to divide users into, for example, top 10%, middle 80%, and bottom 10%. Not limited to this, the threshold may be arbitrarily determined, such as dividing users into top 33%, middle 34%, and bottom 33%. Furthermore, the threshold is not necessarily set to divide users into three groups, but may be set to divide users into two groups, or may be set to divide users into four or more groups. Furthermore, the threshold may be set for a plurality of PRS. Furthermore, the threshold may be a fixed value, or may be a variable value set by an operation of the disease risk analysis device 1 by a disease risk analyst such as a doctor.

[0016] The stratified data generating unit 13 generates stratified data by stratifying the PRS data based on the PRS threshold determined by the threshold determining unit 12. The stratified data is data in which a label representing each stratum is associated with each ID of the PRS data stratified by the threshold.

[0017] The standard setting unit 14 sets a standard for the first observation target data for determining the starting point of a change in the time-course data. The first observation target data is selected from at least one test value of the health checkup data and / or at least one medical examination situation of the medical examination data. The first observation target data and its standard can be set by any method, such as an operation of the disease risk analysis device 1 by a disease risk analyst such as a doctor.

[0018] The first observation target data generating unit 15 generates first observation target data from the time-course data based on the criteria set by the criteria setting unit 14. The first observation target data is generated by extracting test values ​​and / or medical examination conditions corresponding to the criteria from the health checkup data and / or medical examination data. When multiple criteria are set, first observation target data for test values ​​and / or medical examination conditions corresponding to each criterion can be generated.

[0019] The starting point data generating unit 16 generates starting point data based on the first observation target data. The starting point data is data in which the medical examination year in which the test value for a certain ID of the first observation target data reached the standard is set as the starting point, that is, year 0, and other medical examination years of the same ID are held as the relative years from year 0. The starting point data may be data that holds only the relative years before in time from year 0, or may be data that holds only the relative years after in time from year 0, or may be data that holds the relative years before and after in time from year 0. The starting point data may be data that holds only the most recent relative years from year 0. The setting of the data held as starting point data may be set by any method, such as setting by a disease risk analyst such as a doctor operating the disease risk analysis device 1.

[0020] The second observation target data determination unit 17 determines second observation target data from the time-course data. The second observation target data is determined from at least one test value of the health checkup data and / or at least one medical examination situation of the medical examination data. The second observation target data can be selected by any method, such as being set by a disease risk analyst, such as a doctor, operating the disease risk analysis device 1.

[0021] The second observation target data generating unit 18 generates second observation target data based on the time-course data acquired by the acquiring unit 11, the starting point data generated by the starting point data generating unit 16, and the result determined by the second observation target data determining unit 17. The second observation target data is data obtained by extracting the test values ​​and / or medical examination conditions determined as the second observation target data from the time-course data by aligning the relative years based on the starting point data.

[0022] The analysis unit 19 performs processing for performing analysis using the second observation target data. For example, the analysis unit 19 stratifies the second observation target data using the stratification data. Then, the analysis unit 19 displays a graph based on the stratified second observation target data on the display device. In addition, the analysis unit 19 may perform various processing for analysis, such as having a learning model learn the relationship between the test value and / or medical examination situation of the stratified second observation target data and the risk of developing a specific disease.

[0023] 5 is a diagram showing an example of a hardware configuration of the disease risk analysis device 1. The disease risk analysis device 1 may be a computer having, for example, a processor 101, a memory 102, a storage 103, an input device 104, a display device 105, and a communication device 106 as hardware. The processor 101, the memory 102, the storage 103, the input device 104, the display device 105, and the communication device 106 are connected to a bus 107. The disease risk analysis device 1 may be mounted on a terminal device such as a personal computer (PC), a smartphone, or a tablet terminal.

[0024] The processor 101 is a processor that controls the overall operation of the disease risk analysis device 1. The processor 101 operates as an acquisition unit 11, a threshold determination unit 12, a stratification data generation unit 13, a standard setting unit 14, a first observation target data generation unit 15, a starting point data generation unit 16, a second observation target data determination unit 17, a second observation target data generation unit 18, and an analysis unit 19, by executing a disease risk analysis program stored in the storage 103, for example. The processor 101 is, for example, a CPU. The processor 101 may be an MPU, a GPU, an ASIC, an FPGA, or the like. The processor 101 may be a single CPU, or may be multiple CPUs, or the like.

[0025] The memory 102 includes a ROM and a RAM. The ROM is a non-volatile memory. The ROM stores a startup program for the disease risk analysis device 1 and the like. The RAM is a volatile memory. The RAM is used as a working memory during processing in the processor 101, for example.

[0026] The storage 103 is, for example, a storage such as a flash memory, a hard disk drive, or a solid state drive. The storage 103 stores various programs executed by the processor 101, such as a disease risk analysis program 1031. The storage 103 may also store healthcare data 1032, stratified data 1033, first observation target data 1034, starting point data 1035, and second observation target data 1036. The healthcare data 1032, stratified data 1033, first observation target data 1034, starting point data 1035, and second observation target data 1036 do not necessarily need to be stored in the storage 103. For example, the healthcare data 1032, stratified data 1033, first observation target data 1034, starting point data 1035, and second observation target data 1036 may be stored in a server outside the disease risk analysis device 1. In this case, the disease risk analysis device 1 acquires necessary information by accessing the server using the communication device 106.

[0027] The input device 104 is an input device such as a touch panel, a keyboard, a mouse, etc. When the input device 104 is operated, a signal corresponding to the operation is input to the processor 101 via the bus 107. The processor 101 performs various processes according to the signal. The input device 104 can be used, for example, to input health care data, determine a threshold for generating stratified data, set a criterion for judging a starting point, and determine second observation target data.

[0028] The display device 105 is a display device such as a liquid crystal display, an organic EL display, etc. The display device 105 displays various images.

[0029] The communication device 106 is a communication device for communicating with an external device by the disease risk analysis device 1. The communication device 106 may be a communication device for wired communication, or may be a communication device for wireless communication.

[0030] Next, the operation of the disease risk analysis device 1 of the embodiment will be described with a concrete example. Fig. 6 is a flowchart showing the operation of the disease risk analysis device 1. The processing of Fig. 6 is executed by the processor 101. Furthermore, prior to the following description, it is assumed that the threshold determination unit 12 has determined a threshold, the standard setting unit 14 has set a standard, and the second observation target data determination unit 17 has determined the second observation target data.

[0031] In step S1, the acquisition unit 11 acquires healthcare data. The healthcare data may be input to the disease risk analysis device 1 in response to an operation of the disease risk analysis device 1 by a disease risk analyst such as a doctor. Here, in the following example, it is assumed that healthcare data including the PRS data shown in Fig. 2, the medical checkup data shown in Fig. 3, and the medical examination data shown in Fig. 4 have been acquired.

[0032] In step S2, the stratified data generating unit 13 generates stratified data by stratifying the PRS data by the threshold determined by the threshold determining unit 12. FIG. 7 is a diagram showing an example of stratified data. FIG. 7 shows stratified data stratified by the diabetic PRS threshold. As shown in FIG. 7, each ID included in the PRS data is classified into one of layers, for example, "upper", "middle", and "lower", according to the comparison result between the diabetic PRS value and the threshold. The "upper" is a layer with a higher diabetic PRS and is considered to be genetically prone to diabetes. The "lower" is a layer with a lower diabetic PRS and is considered to be genetically unlikely to develop diabetes. Although not shown in FIG. 7, the "middle" is a layer that is not included in either the "upper" or "lower" and is considered to be moderately prone to diabetes.

[0033] In step S3, the first observation target data generating unit 15 generates the first observation target data from the time-course data based on the criteria set by the criteria setting unit 14. FIG. 8 is a diagram showing an example of the first observation target data. FIG. 8 shows the first observation target data when the criteria are set with HbA1c as the observation target. In this case, the first observation target data includes an ID, a medical examination year, and a value of HbA1c as the test value of the observation target, as shown in FIG. 8. The first observation target data may further include age. In addition, when multiple criteria are set, such as HbA1c and the presence or absence of a prescription for oral diabetes drug A, the first observation target data may include data on multiple test values ​​and / or medical examination conditions.

[0034] In step S4, the starting point data generating unit 16 refers to the first observation target data and judges whether the test value and / or medical examination situation as the first observation target data meets the standard. For example, if the observation target is HbA1c, when there is a medical examination year in which the HbA1c value meets the preset standard, the observation target is judged to meet the standard. In addition, if the standard is receiving a prescription for any oral diabetes drug, when there is a medical examination year in which any oral diabetes drug is prescribed, the observation target is judged to meet the standard. Here, when multiple test values ​​and / or medical examination situations are observation targets, the first observation target data may be judged to meet the standard when one of the first observation target data meets the standard, or the first observation target data may be judged to meet the standard when all of the first observation target data meet the standard. When it is judged in step S4 that the first observation target data does not meet the standard, the process of FIG. 6 ends. When it is judged in step S4 that the first observation target data meets the standard, the process proceeds to step S5.

[0035] In step S5, the starting point data generating unit 16 generates starting point data from the first observation target data. FIG. 9 is a diagram showing an example of starting point data. The starting point data is data in which the year in which the first observation target data first reached the standard is set as year 0, and the years before and after that are expressed as relative years from year 0. That is, the starting point data includes an ID, a medical examination year, and a relative number of years. For example, the user with ID "A001" in FIG. 9 has a value of "0" in 2021. This indicates that the HbA1c value of the user with ID "A001" reached the standard in 2021 and developed diabetes. Since 2021 is set to "0", 2019 is set to "-2", 2020 is set to "-1", and 2022 is set to "1". Here, the starting point data in FIG. 9 includes both the relative number of years before and the relative number of years after the starting point 2021. As previously mentioned, the origin data may include only one of the data before or after the origin in time.

[0036] In step S6, the second observation target data generating unit 18 generates the second observation target data based on the time-course data and the starting point data. FIG. 10 is a diagram showing an example of the second observation target data. The second observation target data is data extracted from the time-course data by associating the relative years with the observation target determined as the second observation target data. FIG. 10 shows the second observation target data when BMI is determined as the observation target. In this case, the second observation target data includes an ID, a relative years, and a BMI value as a test value, as shown in FIG. 10. The second observation target data may further include age. In addition, when multiple test values ​​and / or medical examination situations are selected, the second observation target data may include data on multiple test values ​​and / or medical examination situations.

[0037] In step S7, the analysis unit 19 performs an analysis of the second observation target data. After that, the process of Fig. 6 ends. For example, the analysis unit 19 stratifies the second observation target data by PRS using the stratified data generated in step S2. Then, the analysis unit 19 displays a graph of the stratified second observation target data on the display device.

[0038] 11A, 11B, 11C, 11D, 11E, 11F, 11G, 11H, 11I, and 11J are graphs obtained by selecting HbA1c, systolic blood pressure, LDL, HDL, TG, BMI, weight, GOT, GPT, and γGPT as the second observation data, and stratifying each selected test value by PRS of BMI. In the graphs of FIG. 11A-FIG. 11J, the year when diabetes developed is set as year 0, and test values ​​from before that are extracted as the second observation data. The year when diabetes developed is determined from the fact that HbA1c, which is the first observation data, reached the reference value and the prescription of oral diabetes medication.

[0039] Here, the test values ​​as the second observation target data shown in Figures 11A-11J indicate the average values ​​of the test values ​​of the IDs included in the upper, middle, and lower groups of the BMI PRS. Here, the legend of the graph shown in Figure 11F can be applied to other graphs.

[0040] The graphs in Figures 11A-11J show the trends in each test value before the onset of diabetes, stratified by BMI PRS. For example, looking at the trends in BMI in Figure 11F, there is a large difference in BMI values ​​between the lower and higher BMI PRS groups by the year diabetes developed. This shows that people with a high BMI PRS have a long time to develop diabetes even if their BMI test value is high, and people with a low BMI PRS have a short time to develop diabetes even if their BMI test value is low. In this way, by aligning the years when a specific disease developed and stratifying by genetic differences, it is possible to analyze whether the disease risk differs even with the same test value.

[0041] Figures 12A, 12B, 12C, 12D, and 12E are graphs obtained by selecting the prevalence of diabetes, the prevalence of hypertension, the prevalence of dyslipidemia, the prevalence of obesity, and the prevalence of liver dysfunction as the second observation data, and stratifying each selected prevalence by PRS of systolic blood pressure.

[0042] In the graphs of Figures 12A to 12E, the year in which the BMI reached the standard, which is the first observation data, is set as year 0, and the prevalence rate later in time is extracted as the second observation data.

[0043] Here, the prevalence as the second observation target data shown in Figures 12A-12E indicates the prevalence among IDs included in each of the upper, middle, and lower groups of BMI PRS. Here, the legend of the graph shown in Figure 12B can be applied to other graphs.

[0044] The graphs in Figures 12A, 12B, 12C, and 12E show the transition of the prevalence of other diseases after a person is suspected of having a high BMI, i.e., obesity, stratified by PRS of systolic blood pressure. It is generally known that obesity increases the risk of hypertension, but it can be seen that there is a difference due to genetic differences between the time from becoming obese to the onset of hypertension. In this way, by aligning the year in which a specific disease was developed and stratifying by genetic differences, it is possible to analyze whether the risk of complications after developing a specific disease differs. Here, in Figures 12A-12E, the prevalence of other complications after developing obesity is analyzed. In contrast, the incidence rate of other complications after developing obesity may be analyzed by the Kaplan-Meier method, with each test value after developing obesity as the second observation data as the explanatory variable and the incidence rate of each complication as the objective variable.

[0045] As described above, according to this embodiment, a standard is set for any of the user's test values ​​and / or medical examination conditions, and second observation target data is generated from the time-course data and stratified data, based on the year in which the test value and / or medical examination condition reached the standard. This makes it possible to perform various analyses that cannot be performed by simple stratification using PRS.

[0046] Here, it goes without saying that the analysis in the analysis unit 19 is not limited to the method of calculating the average test value in Figures 11A to 11J and the method of calculating the prevalence rate shown in Figures 12A to 12E. Various analyses can be performed depending on which factors are selected as the PRS data, the first observation target data, and the second observation target data.

[0047] Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope of the invention and its equivalents described in the claims, as well as in the scope and spirit of the invention. [Explanation of symbols]

[0048] 1 disease risk analysis device, 11 acquisition unit, 12 threshold determination unit, 13 stratified data generation unit, 14 standard setting unit, 15 first observation target data generation unit, 16 starting point data generation unit, 17 second observation target data determination unit, 18 second observation target data generation unit, 19 analysis unit, 101 processor, 102 memory, 103 storage, 104 input device, 105 display device, 106 communication device, 107 bus, 1031 disease risk analysis program, 1032 healthcare data, 1033 stratified data, 1034 first observation target data, 1035 starting point data, 1036 second observation target data.

Claims

1. An acquisition unit that acquires healthcare data including genetic score data that holds a genetic score for each user and time-series data that includes at least one of health checkup data and medical examination data for each user collected over time; A threshold determination unit that determines a threshold for stratifying the genetic score; a stratification data generation unit that generates stratification data by stratifying the genetic score data based on the threshold value; a standard setting unit that sets a standard for at least one test value of the health checkup data and / or at least one medical examination situation of the medical examination data; a first observation data generating unit that generates first observation data by extracting test values ​​and / or medical examination conditions corresponding to the criteria from the time-course data; a starting point data generating unit that generates starting point data based on the first observation target data and the criterion; an observation target determination unit that determines an observation target based on at least one test value of the health checkup data and / or at least one medical examination situation of the medical examination data; a second observation target data generating unit that generates second observation target data by extracting the test value and / or the medical examination situation determined by the observation target determining unit from the time-course data with the starting point data as a starting point; an analysis unit for analyzing the second observation target data by stratifying the second observation target data based on the stratification data; A disease risk analysis device comprising:

2. The starting point data is data of the relative number of years starting from the year in which the first observation target data reached the standard, The second observation target data generation unit extracts from the time-course data test values ​​and / or medical examination statuses for a relative number of years before the origin, test values ​​and / or medical examination statuses for a relative number of years after the origin, or test values ​​and / or medical examination statuses for a relative number of years before and after the origin. The disease risk analysis device according to claim 1 .

3. The genetic score is a PRS. The disease risk analysis device according to claim 1 .

4. The PRS includes at least one of a PRS correlated with the risk of developing obesity, hypertension, diabetes, dyslipidemia, and liver dysfunction, a PRS correlated with BMI, systolic blood pressure, HbA1c, LDC, HDL, TG, GOT, GPT, and γGPT; The disease risk analysis device according to claim 3 .

5. The analysis unit calculates an average value of the test value for each stratum from the second observation target data stratified by the stratification data. The disease risk analysis device according to claim 1 .

6. The analysis unit calculates a prevalence rate for each stratum from the second observation target data stratified by the stratification data. The disease risk analysis device according to claim 1 .

7. the analysis unit performs an analysis using the Kaplan-Meier method with each test value in the second observation data as an explanatory variable and an incidence rate of a specific disease as an objective variable. The disease risk analysis device according to claim 1 .

8. The first observation target data is health checkup data and / or medical examination data that serve as a criterion for determining the onset of obesity, hypertension, diabetes, dyslipidemia, and liver dysfunction, The disease risk analysis device according to claim 1 .

9. The second observation target data is health checkup data and / or medical examination data that serve as a criterion for determining the onset of obesity, hypertension, diabetes, dyslipidemia, and liver dysfunction. The disease risk analysis device according to claim 1 .

10. Acquiring healthcare data including genetic score data that holds a genetic score for each user and time-series data that includes at least one of health checkup data and medical examination data for each user collected over time; determining a threshold for stratifying said genetic score; stratifying the genetic score data based on the threshold to generate stratified data; Setting a standard for at least one test value of the health checkup data and / or at least one medical examination status of the medical examination data; generating first observation target data by extracting test values ​​and / or medical examination conditions corresponding to the criteria from the time-course data; generating origin data based on the first observation target data and the criterion; determining an observation target based on at least one test value of the health checkup data and / or at least one medical examination situation of the medical examination data; generating second observation target data by extracting the determined test value and / or medical examination situation from the time-course data with the origin data as a starting point; analyzing the second observed data by stratifying the second observed data based on the stratification data; A disease risk analysis method comprising:

11. Acquiring healthcare data including genetic score data that holds a genetic score for each user and time-series data that includes at least one of health checkup data and medical examination data for each user collected over time; determining a threshold for stratifying said genetic score; stratifying the genetic score data based on the threshold to generate stratified data; Setting a standard for at least one test value of the health checkup data and / or at least one medical examination status of the medical examination data; generating first observation target data by extracting test values ​​and / or medical examination conditions corresponding to the criteria from the time-course data; generating origin data based on the first observation target data and the criterion; determining an observation target based on at least one test value of the health checkup data and / or at least one medical examination situation of the medical examination data; generating second observation target data by extracting the determined test value and / or medical examination situation from the time-course data with the origin data as a starting point; analyzing the second observed data by stratifying the second observed data based on the stratification data; A disease risk analysis program for causing a processor to execute the above.

Images