KR20230116458A - Method and apparatus for processing health examination data - Google Patents

Abstract

According to an embodiment of the present disclosure, a method of processing health examination data performed by a computing device, the method relates to a change in health index over a period including at least one period for each user in a user group. generating health index history data; calculating a health index influence of one or more lifestyle items included in the lifestyle data based on the health index history data and the lifestyle data of users in the user group; , and generating health index prediction data according to a lifestyle of a target user corresponding to the user group, based on the health index influence.

Description

Health examination data processing method and device {METHOD AND APPARATUS FOR PROCESSING HEALTH EXAMINATION DATA}

The present disclosure relates to a method and apparatus for processing health examination data, and more specifically, to a method and apparatus for deriving a health index and a degree of influence on a health index for each lifestyle based on health examination data.

Most Koreans receive a health checkup once every two years or once a year through the National Health Insurance to which they are subscribed. Through such regular health examinations, it is possible to check one's own health condition as well as to detect or prevent diseases at an early stage.

However, the current health checkup results are simply notified to the subject of health checkup, and in most cases, the subject of health checkup proceeds with treatment or management only when certain items are out of the absolute standard set collectively. Accordingly, there is a problem in that the health examination results are less useful to individuals.

In other words, even if it does not deviate from the absolute standard value set collectively, for example, if a specific health checkup item shows a significantly different value compared to others of the same gender or age group, diagnosis and management of the corresponding health checkup item may be required.

Accordingly, there is a need for a technology that allows users to clearly recognize their own health status position within a group of users having similar characteristics such as gender or age, beyond simply being notified of the result of the health checkup.

Furthermore, by deriving not only the current health status location but also the degree of influence of the user's lifestyle such as drinking, smoking, and exercise on the health status, the future health status location is predicted in advance, and ultimately, health management plans and goals are easily established. There is a need in the art for a technique that allows setting.

An object to be solved is to provide a method for deriving the degree of influence of a user's lifestyle on a user's health index in a user group in order to predict the user's future health index. In addition to the above tasks, it may be used to achieve other tasks not specifically mentioned.

According to some embodiments of the present disclosure, a method of processing health examination data performed by a computing device, the method relates to a health index change over a period including at least one period for each user in a user group. generating health index history data; calculating a health index influence of one or more lifestyle items included in the lifestyle data based on the health index history data and the lifestyle data of users in the user group; , and generating health index prediction data according to a lifestyle of a target user corresponding to the user group, based on the health index influence.

The user group may include one or more users having a user attribute corresponding to the target user, and the user attribute may include at least one of a user's gender and a user's age.

The obtaining of health index history data may include calculating a health index of each user in the user group for each period included in the period from sample health checkup data for the user group, and in the user group The method may include generating the health index history data based on the health index calculated for each period for each user.

Calculating the health index may include collecting item attribute data including a decision criterion, direction, and category for each health examination item, and based on logic determined according to the item attribute data among a plurality of logics, Calculating the health index of each of the users in the user group using the sample health examination data.

The health index is a health index for each item calculated for each of the health checkup items included in the sample health checkup data, and each of the health checkup categories including at least one health checkup item based on the health index for each item. It may be at least one of a health index for each category calculated for , and a final health index calculated based on the health index for each category.

The health index for each item of each of the users in the user group for a specific health checkup item is normal when the item value of the specific health checkup item corresponds to the normal range of the specific health checkup item. It can be calculated to include the tendency of the health status of the user group for the range.

The health index for each item of each of the users in the user group for a specific health checkup item, when the item value of the specific health checkup item does not correspond to the normal range of the specific health checkup item, of the specific health checkup item According to the logic determined based on the directionality and the category value, the trend of the user group's health state for the normal range of the specific health checkup item and the health state of each user in the user group for the health state of the user group It can be calculated to include the tendency of

The calculating of the health index influence may include clustering the health index history data into one or more groups based on lifestyle data of users in the user group, and, for each of the one or more groups, the health index change. Calculating a representative value for each of the one or more groups, and based on the correlation between the lifestyle data corresponding to each of the one or more groups and the representative value for the change in health index, the influence of each of the one or more lifestyle items on the health index and calculating, and the one or more lifestyle items may include at least some of drinking, smoking, and exercise.

Each of the one or more groups may include the health index history data of at least some users having lifestyle data corresponding to each other among users in the user group.

According to some embodiments of the present disclosure, a method for processing health examination data performed by a computing device, the method comprising: sample health examination data collected over a period including at least one period for a user group, and health examination data Acquiring at least some of the item attribute data for each item, based on a logic determined according to the item attribute data among a plurality of logics, for each of the users in the user group using the sample health checkup data during the period generating health index history data, and generating health index prediction data according to lifestyles of target users corresponding to the user group based on the health index history data and the lifestyle data of users in the user group. steps may be included.

The generating of the health index history data may include calculating a health index of each of the users in the user group for each period included in the period, from the sample health examination data, and for each of the users in the user group. and generating the health index history data based on the health index calculated for each cycle.

The health index may have a smaller value as the health state of each of the users in the user group is better.

The health index is a health index for each item calculated for each of the health checkup items included in the sample health checkup data, and each of the health checkup categories including at least one health checkup item based on the health index for each item. It may be at least one of a health index for each category calculated for , and a final health index calculated based on the health index for each category.

The health index for each item of each of the users in the user group for a specific health checkup item, when the item value of the specific health checkup item corresponds to the normal range of the specific health checkup item, according to the first logic, the It can be calculated to include the tendency of the health status of the user group with respect to the normal range of a specific health examination item.

The first logic may calculate a health index for each item of the specific health checkup item by integerizing half a value of the cumulative probability of the normal range of the specific health checkup item.

The health index for each item of each of the users in the user group for a specific health checkup item, when the item value of the specific health checkup item does not correspond to the normal range of the specific health checkup item, of the specific health checkup item According to the second logic determined based on the directionality and the category value, the tendency of the health condition of the user group for the normal range of the specific health checkup item and each of the users in the user group for the health condition of the user group It can be calculated to include trends in health status.

The second logic, when the direction of the specific health checkup item has a first direction value and the value of the category of the specific health checkup item is 1, the numerical value of the specific health checkup item for the sample health checkup data. By integerizing the cumulative probability value, a health index for each item of the specific health checkup item may be calculated.

The second logic, when the direction of the specific health checkup item has a second directional value and the category value of the specific health checkup item is 1, accumulates the values of the specific health checkup item with respect to the sample health checkup data. A value obtained by subtracting a probability value from 1 may be integerized to calculate a health index for each item of the specific health examination item.

The second logic is that the direction of the specific health checkup item has a first direction value, the value of the category of the specific health checkup item is 2, and the numerical value of the specific health checkup item is within the normal range of the specific health checkup item. If greater than the highest value of , it is possible to calculate an item-specific health index for the specific health checkup item by integerizing the cumulative probability value of the value of the specific health checkup item for the sample health checkup data.

The second logic is that the direction of the specific health checkup item has a first direction value, the value of the category of the specific health checkup item is 2, and the numerical value of the specific health checkup item is within the normal range of the specific health checkup item. If it is smaller than the minimum value, the cumulative probability value between the value of the specific health checkup item for the sample health checkup data and the minimum value of the normal range of the specific health checkup item, and the specific health checkup for the sample health checkup data A health index for each item of the specific health checkup item may be calculated by integerizing the sum of the cumulative probability values of the normal range of the item.

According to some embodiments of the present disclosure, based on health checkup data, a health index capable of intuitively confirming a relative position of a user's health status within a user group may be derived.

According to some embodiments of the present disclosure, a more meaningful and detailed health index can be calculated by comprehensively using not only health examination data of a user group, but also attributes such as normal range, direction, and/or category for each health examination item. there is.

According to some embodiments of the present disclosure, it is possible to accurately predict the user's future health index by deriving the degree of influence on the health index for each lifestyle in a user group corresponding to the user.

According to some embodiments of the present disclosure, by deriving the user's future health index as a value dependent on the user's lifestyle, the user can accurately and systematically set a health management plan in association with his/her lifestyle.

1 is a block diagram illustrating a health examination data processing apparatus according to some embodiments of the present disclosure.
Figure 2 is a schematic diagram for explaining a health examination data processing method according to some embodiments of the present disclosure.
3 is a flowchart illustrating a health examination data processing method according to some embodiments of the present disclosure.
4 is a flowchart illustrating a health examination data processing method according to some embodiments of the present disclosure.
5 is a diagram exemplarily illustrating item attribute data for one or more health checkup items according to some embodiments of the present disclosure.
6 is a diagram exemplarily illustrating a method of calculating a health index according to some embodiments of the present disclosure.
7 is a diagram illustrating a method of calculating a health index for each item, a health index for each category, and a final health index according to some embodiments of the present disclosure.
8 is a diagram illustrating an example of a health examination data processing method according to some embodiments of the present disclosure.
9 is a block diagram illustrating a computing device for providing a health examination data processing method according to some embodiments of the present disclosure.

Hereinafter, with reference to the accompanying drawings, embodiments of the present disclosure will be described in detail so that those skilled in the art can easily carry out the present disclosure. However, the present disclosure may be embodied in many different forms and is not limited to the embodiments described herein. And in order to clearly describe the present disclosure in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

In the present disclosure, when a part "includes" a certain component, it means that it may further include other components without excluding other components unless otherwise stated. Devices constituting the network may be implemented as hardware, software, or a combination of hardware and software.

In the present disclosure, the term “target user” may be used as a term meaning a user who wants to receive his or her health index. Specifically, the target user provides or agrees to provide data on his/her own health examination results to the health examination data processing device of the present disclosure, and predicts his or her own health index data calculated according to the health examination data processing method of the present disclosure. may be a user who is provided with.

In the present disclosure, “user attribute” may be used as a term meaning demographic information about each user including a target user. For example, the user attributes may be each user's gender, age, occupation, or region of residence. In particular, in the present disclosure, user attributes may be used to identify a user group corresponding to a target user and to generate sample health examination data from large-scale health examination data. Specifically, users having the same or similar user attributes as the target user can be identified as a user group, and among the large-scale health checkup data collected on a large number of unspecified users, at least some of the health checkup data corresponding to the user attributes of the target user Data can be extracted to generate sample health checkup data for user groups.

In the present disclosure, the term "logic" may be used as a term meaning a calculation algorithm applied to one or more health examination data to calculate a health index according to the present disclosure. Specifically, the logic in the present disclosure may include one or more calculation algorithms applied to sample health examination data of a user group to calculate a health index of each user in the user group. In particular, the logic in the present disclosure may be at least one logic determined from among a plurality of logics based on item attribute data for each of the health checkup items. Since the health index according to the present disclosure is calculated by comprehensively considering the attributes of each health checkup item as well as the sample health checkup data, it is possible to calculate an intuitive health index while containing more diverse information.

1 is a block diagram illustrating a health examination data processing apparatus according to some embodiments of the present disclosure.

Referring to FIG. 1, the health examination data processing apparatus 100 according to the present disclosure includes a data collection unit 110 including a large-scale data collection unit 111 and a target user data collection unit 112, and a sample data generation unit. 121, health index calculation unit 122, health index history data generation unit 123, health index influence degree calculation unit 124, and health index prediction data generation unit 125 including a data analysis unit 120 can include

However, the above configuration is not essential to implement the health examination data processing apparatus 100 according to the present disclosure, and thus the health examination data processing apparatus 100 may be implemented with more or less configurations than the listed configurations. For example, the health examination data processing device 100 does not include the data collection unit 110 and may receive necessary data from an external database or a cloud database through a network.

The data collection unit 110 of the health checkup data processing apparatus 100 according to the present disclosure includes large-scale health checkup data for an unspecified number of users, and item attribute data including criterion, direction, and category for each health checkup item. At least some of them can be collected.

Specifically, the large-scale data collection unit 111 of the data collection unit 110 may collect large-scale health checkup data for an unspecified number of users. The large-scale health checkup data may include item values for each of the health checkup items of a number of unspecified users and user properties for each of the plurality of unspecified users.

Large-scale health examination data can be collected from related organizations (National Health Insurance Corporation, etc.). For example, the large-scale data collection unit 111 may collect large-scale health checkup data by scraping a server or web of a related institution, or may receive large-scale health checkup data from a related institution according to prior approval.

In particular, the large-scale health examination data collected by the large-scale data collection unit 111 may include large-scale health examination data collected during a period including at least one cycle. For example, if one year is a daily cycle, large-scale health checkup data may include health checkup data collected at least twice at an interval of one year (for example, health checkup data with 2014 and 2015 as checkup years, respectively). can

The large-scale data collection unit 111 may collectively collect large-scale health checkup data for a period including at least one cycle, or continuously collect large-scale health checkup data through a related institution or the like. For example, the large-scale data collection unit 111 collects and accumulates large-scale health checkup data through related institutions at predetermined intervals, and obtains large-scale health checkup data for a period including at least one cycle.

The large-scale health examination data collected by the large-scale data collection unit 111 may be transmitted to the sample data generation unit 121 to be described later and used to generate sample health examination data. In addition, the collected large-scale health examination data may be stored and managed in a storage unit (not shown) of the health examination data processing device 100 or a separate database.

Meanwhile, the target user data collection unit 112 of the data collection unit 110 may collect data about the target user. Specifically, the target user data collection unit 112 may collect health examination data of the target user and/or data related to user attributes such as gender or age of the target user.

The user attribute data of the target user collected by the target user data collection unit 112 is transmitted to the sample data generator 121 to be described later, and data of a user group corresponding to the target user is extracted from large-scale health examination data and sampled. It can be used to generate health examination data. In addition, the health checkup data of the target user collected by the target user data collection unit 112 may be transferred to the health index prediction data generator 125 to be described later and used to calculate the future health index of the target user.

In addition, the data collection unit 110 may collect item attribute data including criterion, direction, and category for each health examination item. Here, the criterion may be information including at least one critical value for determining a normal range for a specific health examination item. Here, the category may be a value corresponding to the number of threshold values included in the determination criterion. Here, the direction may be a value related to a correlation type between a numerical value of a specific health examination item and a health risk. Specifically, the directionality may have a positive directional value when the numerical value of the health checkup items and the health risk have a positive correlation, and a negative directional value when the numerical value of the health checkup items and the health risk have a negative correlation. can have

Meanwhile, item attribute data may be continuously collected and updated through related organizations. For example, the data collection unit 110 collects item attribute data for each of the health checkup items through a related institution whenever preset conditions are satisfied (cycle, item property data change in a related institution, user request, etc.) can However, it is not limited thereto.

Item attribute data acquired by the data collection unit 110 may be used to determine logic to be used to calculate a health index for a health examination item. For example, when the directions and category values of two or more health checkup items included in the sample health checkup data are different from each other, different logics may be used for each item.

The data analysis unit 120 of the health checkup data processing apparatus 100 according to the present disclosure extracts health checkup data on a user group corresponding to a target user from among large-scale health checkup data, and in a period including at least one cycle. Sample health checkup data for each user group may be generated, and a health index for each period of each user in the user group may be calculated using the sample health checkup data based on logic determined according to item attribute data.

Specifically, the sample data generation unit 121 of the data analysis unit 120 extracts at least some of the health examination data related to the user group of the target user from among the large-scale health examination data collected by the large-scale data collection unit 111. Thus, sample health examination data can be generated. Here, the user group may include one or more users having user properties corresponding to the target user among a plurality of users related to the large-scale health examination data. That is, sample health examination data may be generated by extracting only health examination data for users corresponding to at least one of the target user and gender or age (a specific age or age group) from large-scale health examination data.

On the other hand, the sample data generation unit 121, prior to generating the sample health examination data, with respect to the extracted health examination data for each health examination item to detect data outliers and these data outliers can be removed. For example, the Z-Score (standard score) is calculated for each of the numerical values for a specific health checkup item in the extracted health checkup data, and the values with the absolute value of the Z value within 3 are 99.73% of the total. , values with an absolute value of 3 or more of the Z value can be viewed as data outliers and removed from the extracted health checkup data.

Alternatively, the sample data generation unit 121 calculates values for new health checkup items using values for each of at least some health checkup items included in the extracted health checkup data, and calculates values for the calculated health checkup items. It is also possible to generate sample health examination data that further includes data on the subject. For example, when a BMI item is missing from the extracted health checkup data but a height item and a weight item are included, the sample data generation unit 121 uses values of each of the height item and the weight item to determine the BMI item. A numerical value is newly calculated, and sample health examination data may be generated to further include data on the calculated BMI item.

The sample health examination data generated by the sample data generation unit 121 is transmitted to the health index calculation unit 122 of the data analysis unit 120 and used to calculate the health index for each period of users in the user group. can

The health index calculation unit 122 of the data analysis unit 120 may calculate the health index for each period of each user in the user group, based at least on logic determined according to item attribute data. That is, the health index calculation unit 122 considers not only the sample health examination data for the user group, but also the characteristics of each item (ie, item attribute data) of the health examination items included in them together, so that each health A health index representing the health status of each user for the checkup item may be calculated.

Here, the health index may be a value that includes at least one of information about the tendency of the user group's health state for the normal range of each health checkup item, and information about the tendency of the health state of each user with respect to the health state of the user group. . A detailed description of the logic for each case for calculating the health index will be described later with reference to FIGS. 4 and 6 .

Meanwhile, in the present disclosure, the health index may be calculated to have a smaller value as the user's health condition is better. For example, if user A's health index is 46 and user B's health index is 66, user A's health condition may be interpreted as being better than user B's health condition. However, it is not limited thereto, and the health index may be calculated to have a larger value as the user's health condition is better.

Meanwhile, the health index calculator 122 may calculate, in addition to the health index for each item described above, a health index for each category of health checkup categories including at least one health checkup item, and a final health index for each user. there is. Here, the health index for each category may be calculated based on the health index for each item for each of one or more health checkup items included in the corresponding health checkup category. Likewise, the final health index may be calculated based on the health index for each category for one or more health examination categories. An example of calculating the health index for each item, the health index for each category, and the final health index will be described later with reference to FIG. 7 .

On the other hand, the data analysis unit 120 according to the present disclosure, based on the above-mentioned health index, the health index history data about the health index change, the health index influence for each lifestyle item, and the target user's lifestyle Health index prediction data may be sequentially generated.

Specifically, the health index history data generation unit 123 of the data analysis unit 120 generates health index history data related to changes in the health index of each user in the user group based on the health index calculated from the sample health examination data. can do. The health index influence calculation unit of the data analysis unit 120 may calculate the health index influence of each of one or more lifestyle items based on health index history data and lifestyle data of users in the user group. Further, the health index prediction data generation unit of the data analysis unit 120 may generate health index prediction data according to the lifestyle of the target user based on the health index influence. In this regard, it will be described in more detail through FIGS. 2 and 3 below.

Figure 2 is a schematic diagram for explaining a health examination data processing method according to some embodiments of the present disclosure.

The health index history data generation unit 123 according to the present disclosure may generate health index history data related to changes in health index based on the health index calculated for each user in the user group for each period. That is, the health index history data may be generated for each user in the user group, and may be data capable of tracking changes in the health index of each user for each period.

Figure 2 shows that the sample health checkup data includes health checkup data (200, 210) over a total of two times in the year Y-1 and year Y, and the health of each user from the sample health checkup data in the year Y-1 and the year Y, respectively. Indexes 201 and 211 are calculated, and accordingly, an example in which health index history data 220 is generated to indicate a change in health index of each user over a period between year Y-1 and year Y is shown.

In this case, the health index for each period may be the health index for each item, the health index for each category, or the final health index. That is, the health index history data is, for each user, health index change information for each period for a specific health checkup item, health index change information for each cycle for a specific health checkup category, and/or final health for each period of the user. It may be generated to include at least some of index change information.

Meanwhile, the health index influence calculation unit 124 according to the present disclosure, based on the health index history data 220 and the lifestyle data 230 of users in the user group, the health index influence of each of one or more lifestyle items ( 240) can be calculated.

Here, the lifestyle data 230 is data about the lifestyle of each user, and may include one or more lifestyle items and values for each item. For example, one or more lifestyle items may be drinking, smoking, exercise, and the like. In addition, the value of each lifestyle item may be whether each user has a corresponding lifestyle and/or detailed information about the lifestyle. For example, in the case of an exercise lifestyle item, values of the lifestyle item may include average exercise time, exercise frequency, and type of exercise.

The health index influence calculation unit 124 according to the present disclosure clusters the health index history data 220 generated for each user into one or more groups based on the lifestyle data 230 of users in the user group. can

Here, each of one or more groups may be composed of health index history data about at least some users having lifestyle data corresponding to each other among users in the user group. In other words, health index history data belonging to the same group may be health index history data of users having the same lifestyle.

Next, the health index influence calculation unit 124 according to the present disclosure may calculate a representative value (eg, average value, mode value, maximum value, median value, etc.) of the change in health index for each of one or more groups. there is. In addition, the health index influence calculation unit 124 calculates the health index influence of each of one or more lifestyle items (240 ) can be calculated. That is, the degree of influence on the health index may be a value quantitatively indicating the effect of a specific lifestyle item on the health index.

Meanwhile, the health index prediction data generator 125 according to the present disclosure may generate health index prediction data 260 according to the lifestyle of the target user based on the health index influence 240 .

Specifically, the health index prediction data generation unit 125 may match the health index influence 240 calculated for each lifestyle item for a user group corresponding to the target user with the lifestyle data 250 of the target user. . The health index prediction data generation unit 125 may generate health index prediction data 260 according to the lifestyle of the target user.

For example, if the target user maintains a lifestyle, it is possible to predict in which direction and by how much the target user's health index will change in the future. Alternatively, when at least a part of the lifestyle of the target user is changed, it is possible to predict how the target user's health index will change in the future, compared to a case where it is not.

As described above, according to the health examination data processing method of the present disclosure, the future health index of the target user can be accurately predicted by using the health index influence derived for each lifestyle within the user group of the target user, and furthermore, the future health index By deriving the value dependent on the lifestyle, it is possible for the target user to accurately and systematically set up a health care plan in association with his/her lifestyle.

3 is a flowchart illustrating a health examination data processing method according to some embodiments of the present disclosure.

Referring to FIG. 3 , the health checkup data processing apparatus 100 according to the present disclosure first generates health index history data about changes in health index over a period including at least one period for each user in the user group. It can be done (S110).

Specifically, the health index history data generation unit 123 of the health examination data processing device 100, based on the health index calculated by the health index calculation unit 122 for each user in the user group for each user group, Health index history data about changes in health index of each of my users may be generated.

Next, the health examination data processing apparatus 100 according to the present disclosure affects the health index of each of one or more lifestyle items included in the lifestyle information based on the health index history data and the lifestyle data of users in the user group. A diagram can be calculated (S120).

Specifically, the health index influence calculation unit 124 of the health examination data processing apparatus 100 clusters the health index history data generated for each user into one or more groups based on the lifestyle data of users in the user group. can do. In other words, health index history data belonging to the same group may be health index history data of users having the same lifestyle.

For each of one or more groups, the health index influence calculation unit 124 may calculate a representative value (eg, average value, mode value, maximum value, median value, etc.) of change in health index. And the health index influence calculation unit 124 calculates the health index influence of each of one or more lifestyle items based on the correlation between the lifestyle data corresponding to each of the one or more groups and the representative value of the change in health index. can do.

Next, the health examination data processing apparatus 100 according to the present disclosure may generate health index prediction data according to the lifestyle of a target user corresponding to a user group based on the health index influence (S130).

Specifically, the health index prediction data generation unit 125 of the health examination data processing device 100 matches the calculated health index influence for each lifestyle item for a user group corresponding to the target user with the lifestyle data of the target user. can do. In addition, the health index prediction data generation unit 125 may generate health index prediction data according to the lifestyle of the target user.

4 is a flowchart illustrating a health examination data processing method according to some embodiments of the present disclosure.

Specifically, FIG. 4 illustrates a method in which the health index calculation unit 122 according to the present disclosure calculates a health index for each period for each user using sample health examination data.

Referring to FIG. 4 , the health checkup data processing apparatus 100 according to the present disclosure first includes sample health checkup data collected over a period including at least one period for a user group and item attribute data for each health checkup item. At least a part may be acquired (S210).

Here, the item attribute data for each health checkup item may include a criterion for each health checkup item, a direction, and a category. The decision criterion may be information including at least one critical value for determining a normal range for a specific health examination item. The category may be a value corresponding to the number of threshold values included in the decision criterion. The directionality may be a value related to a correlation type between a numerical value of a specific health examination item and a health risk. Specifically, the directionality may have a positive directional value when the numerical value of the health checkup items and the health risk have a positive correlation, and a negative directional value when the numerical value of the health checkup items and the health risk have a negative correlation. can have

Item attribute data acquired by the data collection unit 110 may be used to determine logic to be used to calculate a health index for a health examination item. For example, when the directions and category values of two or more health checkup items included in the sample health checkup data are different from each other, different logics may be used for each item.

Next, the health examination data processing apparatus 100 according to the present disclosure relates to a change in health index during the period for each user in the user group based on logic determined according to item attribute data among a plurality of logics. Health index history data may be generated (S220).

Specifically, the health index history data generation unit 123 of the health examination data processing device 100, based on the health index calculated by the health index calculator 122 for each user in the user group for each user group, Health index history data about changes in health index of each user in the group may be generated.

In order to calculate the health index, the health index calculation unit 122 may first determine whether the value of each user's specific health checkup item included in the sample health checkup data corresponds to the normal range of the health checkup item. .

When a numerical value of a specific health checkup item of a user corresponds to the normal range of the corresponding health checkup item, the health index calculator 122 uses the first logic to determine the health index for each item of the user's specific health checkup item. can be calculated. In this case, the health index for each item of a specific health checkup item may be calculated to include the tendency of the health state of the user group for the normal range of the specific health checkup item.

Specifically, the first logic may be to calculate a health index for each item of a specific health checkup item by using a logic that integerizes a half value of a cumulative probability of a normal range of a specific health checkup item for sample health checkup data.

In this case, even if the numerical value of the user's item falls within the normal range for any two health checkup items, according to the tendency of the health state of the user group for the normal range of each health checkup item, The user's health index may be calculated differently.

For example, in the case of any one of the two health checkup items, the majority of users within the normal range may be present in the user group. In this case, since it will not be difficult to maintain the normal range value for the corresponding health checkup item, even if the value of a certain user's item is also in the normal range, the health index of the corresponding user has a relatively high value (ie, the health condition is very good). values that cannot be seen).

On the other hand, in the case of the other health checkup item among the two health checkup items, there may be few users within the normal range in the user group. In this case, since it would be difficult to maintain the normal range value for the corresponding health checkup item, if a user's item value is in the normal range, the health index of the user has a relatively low value (ie, the health condition is considered to be very good) value) can be calculated.

That is, according to the health checkup data processing method of the present disclosure, even when the values of each user's health checkup items in the user group are within the absolute normal range, the tendency of the user group's health condition for the normal range of the health checkup items The health index can be calculated differently depending on the Ultimately, the health index according to the present disclosure can be calculated to include more three-dimensional and accurate information about each user.

On the other hand, when the numerical value of a specific health checkup item of a user does not correspond to the normal range of the corresponding health checkup item, the health index calculation unit 122 uses a second logic determined according to the direction and category value of the specific health checkup item. By using, it is possible to calculate a health index for each item for a specific health checkup item of the corresponding user. In this case, the health index for each item of a specific health checkup item includes the tendency of the user group's health state for the normal range of the specific health checkup item and the user's health state tendency for the user group's health state. can be derived.

Specifically, when the directionality of a specific health checkup item has a positive direction value and the category value is 1, the second logic integerizes the cumulative probability value of the numerical value of the specific health checkup item for the sample health checkup data. It may be to calculate the health index for each item of the checkup item.

Alternatively, when the directionality of a specific health checkup item has a negative direction value and the category value is 1, the second logic subtracts the cumulative probability value of the numerical value of the specific health checkup item from 1 for the sample health checkup data. Integerization may be performed to calculate a health index for each item of a specific health checkup item.

Alternatively, if the directionality of a specific health checkup item has a positive direction value, the value of the category is 2, and the item value of the specific health checkup item is greater than the highest value of the normal range of the corresponding health checkup item, the second logic is The health index for each item of the specific health checkup item may be calculated by integerizing the cumulative probability value of the numerical value of the specific health checkup item for the health checkup data.

Alternatively, if the directionality of a specific health checkup item has a positive direction value, the value of the category is 2, and the item value of the specific health checkup item is less than the minimum value of the specific health checkup item, the second logic is, sample health checkup data After summing the cumulative probability value between the value of a specific health checkup item and the minimum value in the normal range of a specific health checkup item for the sample health checkup data, and the cumulative probability value of the normal range of the specific health checkup item for the sample health checkup data, it is integerized to obtain a specific health It may be to calculate the health index for each item of the checkup item.

In this case, even if the item values for any two health checkup items of any user are out of the absolute normal range, each health checkup item is determined according to the tendency of the user group's health condition for the normal range of each health checkup item. The user's health index for ? may be calculated differently.

For example, in the case of any one health checkup item among the two health checkup items, the majority of users in the user group deviate from the normal range in the same direction as the corresponding user. In this case, it can be interpreted that it is relatively difficult for the user group to fall within the normal range for the corresponding health checkup item. can be calculated as a value that cannot be regarded as very bad).

On the other hand, in the case of the other health checkup item among the two health checkup items, there may be few users who deviate from the normal range in the same direction as the corresponding user in the user group. In this case, it can be interpreted that it is relatively easy for the user group to fall within the normal range for the corresponding health checkup item. If the user's item value is outside the normal range, the health index has a relatively high value (ie, health can be calculated as a value that can be regarded as very bad).

Furthermore, even if the values of each of the two users for any health examination item are out of the absolute normal range, according to the tendency of the health status of each of the two users with respect to the health status of the user group, Health indices can be calculated differently.

For example, if the item value of one of the two users is the lowest among the item values of users in the user group, the health index for that user is a relatively high value (that is, the user's health condition can be regarded as very bad). value) can be calculated. On the other hand, if the item value of one of the two users is in the middle or lower rank among the item values of users in the user group, the health index for that user is a relatively low value (that is, the user's health condition is not considered to be very bad). value) can be calculated.

That is, according to the health checkup data processing method of the present disclosure, if the item value of the user's health checkup item is outside the absolute normal range, in addition to the information that is simply out of the normal range, the user group for the normal range of the health checkup item It is possible to calculate a health index further including trend information of the health state of each user and trend information of the health state of each user group with respect to the health state of the user group. Ultimately, the health index according to the present disclosure can be calculated to include more three-dimensional and accurate information about each user.

Meanwhile, in the above-described health index calculation method, each cumulative probability value may be calculated by substituting the Z value calculated for the sample health examination data into a cumulative distribution function (CDF). For example, the normal range cumulative probability value is calculated by calculating the Z value of each of the minimum and maximum values of the normal range for the sample health examination data, substituting the corresponding Z values into the cumulative distribution function to obtain each cumulative probability, and then , it can be calculated as the value obtained by subtracting the cumulative probability of the lowest value in the normal range from the cumulative probability of the highest value in the normal range.

In addition, in the above-described health index calculation method, integerization may mean multiplying values of greater than 0 and less than 1 calculated by the method by a preset constant and/or removing a decimal part from a value multiplied by the preset constant. . For example, the normal range cumulative probability for the waist circumference item of a female user aged 30 to 34 can be calculated as 0.918301, and the integerization for the value is 0.918301 multiplied by a preset single constant (eg, 10), It may be a process of calculating a value obtained by removing the decimal part from a value multiplied by a preset single constant (ie, 9.18301) (ie, 9). In this example, a preset constant is 10, and an example in which decimal places are discarded to remove a decimal part has been given, but is not limited thereto. For example, the preset single constant may be variously set to 100, 35, 5, etc. in addition to 10, and any method such as rounding up, rounding down, or rounding down may be used to remove the decimal part.

Next, the health examination data processing apparatus 100 according to the present disclosure, based on the health index history data generated using the above-described health index and the lifestyle data of users in the user group, the target user corresponding to the user group Health index prediction data according to the lifestyle of the person may be generated (S230).

5 is a diagram exemplarily illustrating item attribute data for one or more health checkup items according to some embodiments of the present disclosure.

Referring to FIG. 5 , for example, the waist circumference item among the health checkup items is determined to be within the normal range when the value is less than 90 (for males), and within the risk range where the disease is suspected when the value is greater than or equal to 90 (ie, judgment standard). In this case, since the critical value included in the determination criterion is 1 (ie, 90), the category value of the waist circumference item may be 1. Meanwhile, the waist circumference item may have a positive directional value because the greater the value, the greater the health risk.

As another example, total cholesterol among health checkup items is determined as a normal range if less than 200, a boundary range if 200 or more and less than 239, and a risk range if 240 or more (ie, judgment standard). In this case, since the critical values included in the criterion are 2 (ie, 200 and 239), the category value of the total cholesterol item may be 2. Meanwhile, since the total cholesterol item also has a higher value, the health risk increases, so the directionality of the total cholesterol item may have a positive direction value.

Health examination items as shown in FIG. 5 and item attribute data related to each item may be continuously collected and updated through related institutions and the like. For example, the data collection unit 110 according to the present disclosure, when a preset condition is satisfied (cycle, change of item attribute data in a related institution, user request, etc.), items for each of the health checkup items through a related institution, etc. Attribute data can be collected. However, it is not limited thereto.

The health examination data processing method according to the present disclosure may determine a logic for calculating a health index of each health examination item from a plurality of logics based on the item attribute data for each health examination item described above. For example, when the direction and category values of two or more items included in the user health examination data are different from each other, different logic may be used for each item.

As such, the health checkup data processing method according to the present disclosure calculates a health index for each health checkup item by considering not only the user's health checkup data and sample health checkup data, but also the characteristics of individual health checkup items included in them. Therefore, it is possible to provide users with intuitive health index information while containing more diverse information.

6 is a diagram exemplarily illustrating a method of calculating a health index according to some embodiments of the present disclosure.

Specifically, FIG. 6 illustrates a method of calculating a health index for each health checkup item and an example of the calculated health index for a user who is female and is 33 years old.

Referring to FIG. 6 , when the HDL cholesterol level of a female user aged 30 to 34 is 59, the value does not fall within the normal range of the HDL cholesterol level. The directionality of the HDL cholesterol item has a negative directionality value, and the category value of the HDL cholesterol item is 1. The value (59) of the HDL item of the target user for the sample health examination data is calculated as 0.312756, and the value obtained by subtracting the cumulative probability value from 1 is 0.687244. Accordingly, the health index for the HDL cholesterol item of the corresponding user may be calculated as 68 (100 is used as a preset single constant for integerization).

Alternatively, referring to FIG. 6 , when the value of the BMI item of a female user aged 30 to 34 is 25.39, the value does not fall within the normal range of the BMI item. The directionality of the BMI item has a positive direction value, the category value of the BMI item is 2, and the BMI item value of the target user corresponds to a value greater than 24.9, the highest value of the normal range of the BMI item. Accordingly, if the cumulative probability of the user's BMI item value for the sample health examination data is calculated, it is 0.857457, and 85 (100 is used as a preset single constant for integerization), which is an integer number, is the user's BMI item value. It can be calculated as a health index.

Alternatively, referring to FIG. 6 , when the value of the fasting blood sugar item of a female user aged 30 to 34 is 68, the value does not fall within the normal range of the fasting blood sugar item. The directionality of the fasting blood glucose item has a positive direction value, the category value of the fasting blood sugar item is 2, and the value of the fasting blood sugar item of the target user has a value less than 70, which is the minimum value of the normal range of the fasting blood sugar item. Accordingly, the cumulative probability of the value of the fasting blood sugar item of the corresponding target user for the sample health checkup data is calculated as 0.0083895, and the sum of this with the normal range cumulative probability of the fasting blood sugar item is 0.8274875, which is integerized to 82 (preset for integerization) 100 is used as a single constant) may be calculated as a health index for the fasting blood sugar item of the corresponding user.

As such, the health checkup data processing method according to the present disclosure calculates the health index for each health checkup item by considering not only the sample health checkup data, but also the characteristics of individual health checkup items included in them, so that more diverse information is obtained. It can provide users with intuitive health index information while containing

7 is a diagram illustrating a method of calculating a health index for each item, a health index for each category, and a final health index according to some embodiments of the present disclosure.

Specifically, FIG. 7 shows an example in which the health index for each item, the health index for each category, and the final health index are calculated for each of the different users (User A and User B).

If the health index for each health checkup item is used as it is, for example, a relatively high weight is given to the 'regional' health checkup category that includes four health checkup items, whereas a 'blood sugar level' that includes one health checkup item In the case of the 'index' health checkup category, a relatively low weight is given.

Since each health checkup category has a parallel relationship with each other, it is necessary to adjust so that the same weight is given to each health checkup category when calculating the final health index for the target user. Accordingly, as described above, there is a need to calculate a health index for each category corresponding to each health examination category based on the health index for each item. However, it is not limited thereto, and each health examination category may be adjusted to have different weights according to the purpose of using the health index.

For example, the health index calculator 122 may calculate the health index for each category for a health checkup category including only one health checkup item as the same value as the health index for each item for the one health checkup item. there is.

Referring to FIG. 7 , since each of the blood sugar categories and the anemia categories includes one health checkup item, the health index for each item of the corresponding health checkup item can be directly used as the health index for each category.

Alternatively, if the health checkup category includes a plurality of health checkup items and the values of each of the plurality of health checkup items are all within the normal range, the representative values of the health indices for each item of the plurality of health checkup items are corresponding. It can be calculated as a health index for each category of health checkup category.

Referring to FIG. 7 , since the blood pressure category includes two health checkup items (a systolic blood pressure item and a diastolic blood pressure item), when the values of the systolic blood pressure item and the diastolic blood pressure item are both in the normal range, the systolic blood pressure item and the diastolic blood pressure item The average value of the health index for each diastolic blood pressure item may be calculated as the health index for each category of the blood pressure category.

Alternatively, if the health checkup category includes a plurality of health checkup items, but at least one value of the plurality of health checkup items is out of the normal range, the health index of each item for each of the plurality of health checkup items is the highest. A large value can be calculated as a category-specific health index for the corresponding health examination category.

Referring to Figure 7, since the fat category includes four health checkup items (total cholesterol, triglyceride, HDL cholesterol, and LDL cholesterol), at least one of these items does not fall within the normal range. If it exists, the largest value among the health index values for each item of the four health examination items can be calculated as the health index for each category of the fat category.

Meanwhile, the health index calculation unit 122 may calculate a representative value of health indexes for each category for one or more health examination categories as a final health index. 7 illustrates an example in which the average value of influence indices for each category calculated for each user is calculated as the final health index of each user. However, it is not limited thereto, and a mode value, a maximum value, a median value, and the like other than an average value may be calculated as the final health index.

According to the health examination data processing method of the present disclosure, the health index may be calculated to have a smaller value as the user's health condition is better. Referring to FIG. 7 , since the health index of user A and that of user B are 66, it can be interpreted that the health status of user A is better than that of user B. However, it is not limited thereto, and the health index may be calculated to have a larger value as the user's health condition is better.

8 is a diagram illustrating an example of a health examination data processing method according to some embodiments of the present disclosure.

Specifically, FIG. 8 (a) shows an example of health checkup history data 220, and FIG. 8 (b) shows an example of clustering the health checkup history data 220 based on lifestyle data 230 of users. shows

First, referring to (a) of FIG. 8, the health index history data 220 is calculated for the year Y-1 and the year Y, respectively, based on the sample health checkup data over a total of two times in the year Y-1 and year Y. health index for each user. Here, the health index may be a health index for each health examination item, a health index for each health examination category, or a final health index for each user.

For example, referring to the health index history data of user ID 111000, the health index of the user was calculated as 45 in year Y and 40 in year Y-1, respectively, that is, the health index increased by 5 for one year, and then again. In other words, it indicates that the health condition has deteriorated by 5 points in the health index in one year.

As another example, referring to the health index history data of user ID 111002, the health index of the user was calculated as 40 in year Y and 52 in year Y-1, respectively, that is, the health index decreased by 12 for one year, and then again. In other words, it indicates that the health status has improved by 12 in the health index for one year.

Next, referring to FIG. 8 (b), the health index influence calculation unit 124 converts one or more health index history data 220 generated for each user based on the lifestyle data 230 of the users. Clustering may be performed into groups, and representative values related to changes in the health index may be calculated for each of one or more groups.

In (b) of FIG. 8, the health index influence calculation unit 124 calculates drinking and smoking based on three lifestyle items (ie, drinking, smoking, and exercise) constituting the lifestyle data 230 of users. , Group A, which is a group that does not exercise, and Group B, which is a group that does not drink or smoke but exercise, shows an example of clustering health index history data 220. In addition, (b) of FIG. 8 shows an example in which the average change in the health index for each group for one year is calculated as a representative value for the change in the health index.

The health index influence calculation unit 124 according to the present disclosure determines the health of each of one or more lifestyle items based on the correlation between the lifestyle data corresponding to each of the one or more groups and the representative value related to the change in health index. An exponential impact 240 can be calculated.

Referring to (b) of FIG. 8, in the case of group A who did not drink, smoke, or exercise, the health index decreased by 1 on average for one year, whereas in contrast, in the case of group B who did not drink or smoke, but did exercise, 1 It can be seen that the average health index decreased by 10 per year. That is, it can be seen that the exercise lifestyle item has an effect of reducing the health index by 9 for the corresponding user group. Accordingly, the health index influence calculation unit 124 may calculate the health index influence 240 of the exercise lifestyle item as -9. However, it is not limited thereto.

As in the above example, the health index influence calculation unit 124 may calculate the health index influence 240 for each of one or more lifestyle items, and the health index prediction data generator 125 may calculate the health index influence Based on step 240, health index prediction data 260 according to the lifestyle of the target user may be generated.

For example, if the target user has a lifestyle of not drinking, smoking, or exercising, health index prediction data 260 that indicates that the target user's health index will decrease by 1 after one year if the lifestyle is maintained can be generated. there is. Alternatively, health index prediction data 260 indicating that the target user's health index may further decrease by 9 after one year may be generated when the target user changes his/her lifestyle by exercising.

As described above, according to the health examination data processing method of the present disclosure, the future health index of the target user can be accurately predicted by using the health index influence derived for each lifestyle within the user group of the target user, and furthermore, the future health index By deriving the value dependent on the lifestyle, it is possible for the target user to accurately and systematically set up a health care plan in association with his/her lifestyle.

9 is a block diagram illustrating a computing device for providing a health examination data processing method according to some embodiments of the present disclosure.

Here, the computing device 10 providing the health checkup data processing method is the above-described health checkup data processing device 100, or a user communicatively connected to the health checkup data processing device 100 to obtain health index information. It may be a terminal (not shown). However, it is not limited thereto.

Referring to FIG. 9 , a computing device 10 according to the present disclosure includes one or more processors 11, a memory 12 for loading programs executed by the processors 11, and a storage 13 for storing programs and various data. ), and a communication interface 14. However, since the above-described components are not essential to implement the computing device 10 according to the present disclosure, the computing device 10 may have more or fewer components than the components listed above. For example, the computing device 10 may further include an output unit and/or an input unit (not shown), or the storage 13 may be omitted.

The program may include instructions that, when loaded into memory 12, cause processor 11 to perform methods/operations in accordance with various embodiments of the present disclosure. That is, the processor 11 may perform methods/operations according to various embodiments of the present disclosure by executing instructions. A program consists of a series of computer readable instructions grouped together on a functional basis and is executed by a processor.

The processor 11 controls the overall operation of each component of the computing device 10 . The processor 11 may include at least one of a Central Processing Unit (CPU), a Micro Processor Unit (MPU), a Micro Controller Unit (MCU), a Graphic Processing Unit (GPU), or any type of processor well known in the art of the present disclosure. can be configured to include Also, the processor 11 may perform an operation for at least one application or program for executing a method/operation according to various embodiments of the present disclosure.

Memory 12 stores various data, commands and/or information. Memory 12 may load one or more programs from storage 13 to execute methods/operations according to various embodiments of the present disclosure. The memory 12 may be implemented with volatile memory such as RAM, but the technical scope of the present disclosure is not limited thereto.

The storage 13 may store programs non-temporarily. The storage 13 is a non-volatile memory such as read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, or the like, a hard disk, a removable disk, or well known in the art. It may be configured to include any known type of computer-readable recording medium. The communication interface 14 may be a wired/wireless communication module.

The embodiments of the present disclosure described above are not implemented only through devices and methods, and may be implemented through a program that realizes functions corresponding to the configuration of the embodiments of the present disclosure or a recording medium on which the program is recorded.

Although the embodiments of the present disclosure have been described in detail above, the scope of the present disclosure is not limited thereto, and various modifications and improvements of those skilled in the art using the basic concepts of the present disclosure defined in the following claims are also included in the present disclosure. that fall within the scope of the right.

Claims (20)

A health examination data processing method performed by a computing device,
For each of the users in the user group, generating health index history data about a change in health index over a period including at least one period;
Calculating a health index influence of each of one or more lifestyle items included in the lifestyle data based on the health index history data and the lifestyle data of users in the user group, and
Based on the health index influence, generating health index prediction data according to the lifestyle of a target user corresponding to the user group,
How to process health checkup data.
In claim 1,
The user group,
Including one or more users having user attributes corresponding to the target user;
The user properties are
Including at least one of the user's gender and the user's age,
How to process health checkup data.
In claim 1,
Obtaining the health index history data,
Calculating a health index of each user in the user group for each period included in the period from sample health checkup data for the user group, and
Generating the health index history data based on the health index calculated for each period for each user in the user group,
How to process health checkup data.
In paragraph 3,
The step of calculating the health index,
Collecting item attribute data including criterion, direction, and category for each health checkup item, and
Calculating the health index of each of the users in the user group using the sample health examination data based on logic determined according to the item attribute data among a plurality of logics,
How to process health checkup data.
In paragraph 3,
The health index is
A health index for each item calculated for each of the health checkup items included in the sample health checkup data, and a category calculated for each of the health checkup categories including at least one health checkup item based on the health index for each item. At least one of a health index for each category and a final health index calculated based on the health index for each category,
How to process health checkup data.
In paragraph 5,
The health index for each item of each user in the user group for a specific health checkup item,
When the item value of the specific health checkup item corresponds to the normal range of the specific health checkup item, calculated to include the tendency of the health state of the user group for the normal range of the specific health checkup item,
How to process health checkup data.
In paragraph 5,
The health index for each item of each user in the user group for a specific health checkup item,
If the item value of the specific health checkup item does not correspond to the normal range of the specific health checkup item, according to the logic determined based on the direction and category value of the specific health checkup item, the normal range of the specific health checkup item Calculated to include the tendency of the health state of the user group and the tendency of the health state of each user in the user group with respect to the health state of the user group for
How to process health checkup data.
In claim 1,
In the step of calculating the health index influence,
Clustering the health index history data into one or more groups based on lifestyle data of users in the user group;
For each of the one or more groups, calculating a representative value for change in health index; and
Calculating a health index influence of each of the one or more lifestyle items based on a correlation between the lifestyle data corresponding to each of the one or more groups and the representative value of the change in health index,
The one or more lifestyle items,
including at least some of drinking, smoking, and exercise,
How to process health checkup data.
In paragraph 8,
Each of the one or more groups,
Among the users in the user group, including the health index history data for at least some users having lifestyle data corresponding to each other,
How to process health checkup data.
A health examination data processing method performed by a computing device,
Obtaining at least a portion of sample health examination data collected over a period including at least one cycle for a user group and item attribute data for each health examination item;
Generating health index history data according to the period for each user in the user group using the sample health examination data based on logic determined according to the item attribute data among a plurality of logics; and
Based on the health index history data and the lifestyle data of users in the user group, generating health index prediction data according to the lifestyle of a target user corresponding to the user group,
How to process health checkup data.
In claim 10,
The step of generating the health index history data,
Calculating a health index of each user in the user group for each period included in the period from the sample health checkup data; and
Generating the health index history data based on the health index calculated for each period for each user in the user group,
How to process health checkup data.
In claim 11,
The health index is
Having a smaller value as the health status of each of the users in the user group is better,
How to process health checkup data.
In claim 11,
The health index is
A health index for each item calculated for each of the health checkup items included in the sample health checkup data, and a category calculated for each of the health checkup categories including at least one health checkup item based on the health index for each item. At least one of a health index for each category and a final health index calculated based on the health index for each category,
How to process health checkup data.
In paragraph 13,
The health index for each item of each user in the user group for a specific health checkup item,
When the item value of the specific health checkup item corresponds to the normal range of the specific health checkup item, according to the first logic, it is calculated to include the tendency of the health state of the user group for the normal range of the specific health checkup item. felled,
How to process health checkup data.
In claim 14,
The first logic is,
Calculating the health index for each item for the specific health checkup item by integerizing the half value of the cumulative probability of the normal range of the specific health checkup item,
How to process health checkup data.
In paragraph 13,
The health index for each item of each user in the user group for a specific health checkup item,
If the item value of the specific health checkup item does not correspond to the normal range of the specific health checkup item, according to the second logic determined based on the direction and category value of the specific health checkup item, Calculated to include the tendency of the health state of the user group for the normal range and the tendency of the health state of each user in the user group with respect to the health state of the user group,
How to process health checkup data.
In claim 16,
The second logic,
When the directionality of the specific health checkup item has a first direction value and the value of the category of the specific health checkup item is 1, the cumulative probability value of the numerical value of the specific health checkup item for the sample health checkup data is integerized , Calculating the health index for each item for the specific health checkup item,
How to process health checkup data.
In claim 16,
The second logic,
When the directionality of the specific health checkup item has a second directional value and the category value of the specific health checkup item is 1, the cumulative probability value of the numerical value of the specific health checkup item for the sample health checkup data is subtracted from 1 By integerizing the value, calculating the health index for each item for the specific health checkup item,
How to process health checkup data.
In claim 16,
The second logic,
When the directionality of the specific health checkup item has a first direction value, the value of the category of the specific health checkup item is 2, and the numerical value of the specific health checkup item is greater than the highest value of the normal range of the specific health checkup item. , Calculating the item-specific health index for the specific health checkup item by integerizing the cumulative probability value of the numerical value of the specific health checkup item for the sample health checkup data,
How to process health checkup data.
In claim 16,
The second logic is,
When the directionality of the specific health checkup item has a first direction value, the value of the category of the specific health checkup item is 2, and the value of the specific health checkup item is smaller than the minimum value of the normal range of the specific health checkup item. , the cumulative probability value between the value of the specific health checkup item for the sample health checkup data and the minimum value of the normal range of the specific health checkup item, and the normal range of the specific health checkup item for the sample health checkup data Calculating the health index for each item in the specific health checkup item by integerizing the sum of the cumulative probability values,
How to process health checkup data.