KR20210053068A - Method and system for predicting colon cancer related information based on lifestyle information - Google Patents

Abstract

The present invention relates to a method and system for predicting colorectal cancer-related information based on lifestyle information. More specifically, by learning data for lifestyles of people obtained through health checkup results, and deriving and providing colorectal cancer-related information such as colorectal polyps and the possibility of colorectal cancer, a user can use the colorectal cancer-related information for a specific lifestyle as an index which can predict the onset of colorectal cancer according to the lifestyle, in the method and system for predicting colorectal cancer-related information based on lifestyle information.

Description

{Method and system for predicting colon cancer related information based on lifestyle information}

The present invention relates to a method and system for predicting colon cancer-related information based on lifestyle information, and more particularly, by learning data on lifestyles of people obtained through health examination results, colon cancer such as colon polyps and colon cancer potential. By deriving and providing relevant information, the user can use information related to colon cancer based on lifestyle information, which can be used as an index to predict the onset of colon cancer according to the corresponding lifestyle through information related to colon cancer for a specific lifestyle. It relates to a prediction method and system.

Colorectal cancer refers to a malignant tumor that occurs in the colon and rectum, and the incidence of colorectal cancer is rapidly increasing worldwide. Among them, the incidence rate of colon cancer in Korea was 51.7 cases per 100,000 people in 2012, ranking 3rd among all cancers. As the incidence of colon cancer in Korea has recently increased, interest in early colon cancer screening has increased, and colonoscopy and polypectomy are being actively performed. Adenomatous polyps occurring in the large intestine are known as precursor lesions of cancer, and it has been reported that by removing these polyps, the incidence of colon cancer can be reduced. The National Cancer Center currently performs more than 8,000 diagnosis and treatment colonoscopy every year, which is expected to increase further due to the demand of patients in the future. The incidence rate of colorectal cancer is low until the 30s, but the incidence rate starts to increase after the 40s, and the incidence rate increases significantly from the 50s. In addition, the incidence rate is higher in men than in women, and in the case of colorectal cancer, the risk factors for cancer incidence are relatively clear compared to other cancers, so many studies focusing on the prevention of cancer have been preceded.

Based on this, there is a need for a technology capable of providing an index for predicting colorectal cancer by deriving the potential for colorectal polyps and colorectal cancer according to individual characteristics and lifestyles, but such a conventional technology is absent.

The present invention provides information related to colon cancer such as the possibility of expression of colon polyps and the possibility of colon cancer by learning data on the lifestyles of people obtained through the results of health checkups, thereby diagnosing individuals according to the information related to colon cancer. The purpose of this study is to provide a method and system for predicting colorectal cancer-related information based on lifestyle information, which enables the direction of the examination to be presented.

In order to solve the above problems, the present invention is a method for predicting information related to colon cancer based on lifestyle information, performed by a server system, comprising lifestyle information for a plurality of items of a subject, colonoscopy result information, and A learning information receiving step of receiving learning information including tissue examination result information; Clustering colonoscopy result information and biopsy result information of one or more subjects with specific lifestyle information, and deriving polyp potential and colon cancer potential for groups with specific lifestyle information based on the clustered information. The step of finding the possibility; A prediction data set deriving step of deriving a prediction data set for the polyp possibility and the colorectal cancer possibility of the group having the plurality of specific lifestyle information; And, for the input lifestyle information, based on the prediction data set, a predicted result derivation step of deriving a result of the polyp possibility and colorectal cancer possibility of a person having the corresponding input lifestyle information; including, colon cancer-related It provides a method of predicting information.

In an embodiment of the present invention, in the step of deriving the likelihood, a keyword related to a colon polyp is extracted from the colonoscopy result information and the biopsy result information of the learning target, and the polyp location, polyp size, and polyp type of the learning target. Deriving polyp data including one or more of them; The specific lifestyle information is determined based on whether or not the learning target has polyps based on at least one of the polyp location, polyp size, and polyp type, and based on whether or not the polyps of two or more learning targets having the same specific lifestyle information have the polyp. Deriving the polyp possibility for; And deriving the likelihood of colon cancer for the specific lifestyle information according to information on the polyp size and polyp type of two or more learning targets having the same specific lifestyle information, and a preset mapping table. I can.

In an embodiment of the present invention, the prediction data set includes lifestyle information including a plurality of detailed category information; The polypability; And the likelihood of colon cancer; and the lifestyle information may include at least one of age, sex, BMI, exercise habit, drinking habit, smoking habit, family medical history, and personal medical history.

In one embodiment of the present invention, in the step of deriving the possibility, when there is no organizational examination result information in the learning information of the learning object, among learning information collected in the past, the learning object of the learning object received in the learning information receiving step Living habit information and lifestyle information are the same, the colonoscopy result information is similar within a preset criterion, and based on the previously collected learning information in which the tissue examination result information exists, the received in the learning information receiving step The possibility of colorectal cancer can be derived for learning information.

In an embodiment of the present invention, in the step of deriving the prediction result, the similarity is derived according to the matching degree of the input lifestyle information and the lifestyle information included in the prediction data set, and whether the similarity meets a preset criterion. Determining whether or not to derive similar group prediction data; And deriving a polyp possibility and a colorectal cancer possibility of a person having the input lifestyle information based on the similar group prediction data.

In order to solve the above problems, an embodiment of the present invention is a server system that performs a method for predicting information related to colon cancer based on lifestyle information,

A learning information receiving unit for receiving learning information including lifestyle information, colonoscopy result information, and tissue examination result information for a plurality of items of the learning subject; Clustering colonoscopy result information and biopsy result information of one or more subjects with specific lifestyle information, and deriving polyp potential and colon cancer potential for groups with specific lifestyle information based on the clustered information. Possibility-derived department; A prediction data set derivation unit for deriving a prediction data set for the polyp possibility and the colorectal cancer possibility of a group having a plurality of the specific lifestyle information; And a prediction result derivation unit for deriving a result of a polyp possibility and a colorectal cancer possibility of a person having the input lifestyle information based on the prediction data set with respect to the input lifestyle information. to provide.

According to an embodiment of the present invention, by receiving the lifestyle information and providing the possibility of colon polyp and colon cancer derived from the lifestyle information, it is possible to exert the effect of presenting the colon cancer diagnostic screening criteria.

According to an embodiment of the present invention, by providing information related to colon cancer based on the result of learning lifestyle information, colonoscopy result information, and biopsy result information of various subjects, the user can It can exert the effect of being able to check the health status of the patient with an objective indicator.

According to an embodiment of the present invention, when there is no data similar to lifestyle information for predicting colorectal cancer-related information among the learned data, detailed category information of lifestyle information is excluded according to a preset criterion, and similar data is filtered. By doing so, it is possible to exert the effects that can be provided by deriving the possibility of colon polyps and colon cancer.

According to an embodiment of the present invention, the colorectal cancer potential of each learning object is derived based on the mapping table according to the polyp size and polyp type derived based on the learning information, and based on the colorectal cancer possibility of each learning object. Thus, by deriving the possibility of colorectal cancer for specific lifestyle information, it is possible to exert the effect of deriving and providing more analytically accurate possibilities.

According to an embodiment of the present invention, even when some data is not received, data is supplemented based on previously collected learning information, thereby improving the data reliability of colorectal cancer-related information derived from the data. Can be exerted.

1 schematically illustrates an operation of a server system according to a method for predicting information related to colon cancer based on lifestyle information according to an embodiment of the present invention.
2 schematically shows the internal configuration of a server system according to an embodiment of the present invention.
3 schematically shows a form of learning information processed by a possibility finding unit according to an embodiment of the present invention.
4 schematically shows the criteria for classifying lifestyle information according to an embodiment of the present invention.
5 schematically shows a process of processing information derived by a possibility derivation unit according to an embodiment of the present invention.
6 schematically shows a preset mapping table that is a basis for deriving the likelihood of colorectal cancer of a learning target by the likelihood derivation unit according to an embodiment of the present invention.
7 schematically shows the types of data derived by the possibility deriving unit and the predictive data set deriving unit according to an embodiment of the present invention.
8 schematically illustrates a step of performing a prediction result derivation unit according to an embodiment of the present invention.
9 schematically shows a criterion for excluding detailed category items of lifestyle information by a prediction result derivation unit according to an embodiment of the present invention.
10 schematically illustrates a process of processing derived information derived by a prediction result derivation unit according to an embodiment of the present invention.
11 schematically illustrates a configuration of a computing device according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement the present invention. However, the present invention may be implemented in various different forms and is not limited to the embodiments described herein. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is said to be "connected" with another part, this includes not only "directly connected" but also "electrically connected" with another element interposed therebetween. . In addition, when a part "includes" a certain component, it means that other components may be further included rather than excluding other components unless specifically stated to the contrary.

In addition, terms including ordinal numbers such as first and second may be used to describe various elements, but the elements are not limited by the terms. The above terms are used only for the purpose of distinguishing one component from another component. For example, without departing from the scope of the present invention, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element. The term and/or includes a combination of a plurality of related listed items or any of a plurality of related listed items.

In the present specification, the term "unit" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Further, one unit may be realized by using two or more hardware, or two or more units may be realized by one piece of hardware. Meanwhile,'~ unit' is not meant to be limited to software or hardware, and'~ unit' may be configured to be in an addressable storage medium or configured to reproduce one or more processors. Thus, as an example,'~ unit' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , Subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays and variables. Components and functions provided in the'~ units' may be combined into a smaller number of elements and'~ units', or may be further separated into additional elements and'~ units'. In addition, components and'~ units' may be implemented to play one or more CPUs in a device or a security multimedia card.

The "user terminal" mentioned below may be implemented as a computer or portable terminal that can access a server or other terminal through a network. Here, the computer includes, for example, a notebook equipped with a web browser, a desktop, a laptop, and the like, and the portable terminal is, for example, a wireless communication device that guarantees portability and mobility. , PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, etc. may include all kinds of handheld-based wireless communication devices. In addition, the "network" refers to a wired network such as a local area network (LAN), a wide area network (WAN), or a value added network (VAN), or a mobile radio communication network or satellite. It can be implemented with any type of wireless network such as a communication network.

1 schematically illustrates an operation of a server system according to a method for predicting information related to colon cancer based on lifestyle information according to an embodiment of the present invention.

In the server system 1000 shown in FIG. 1, by learning data on the lifestyles of people obtained through health examination results, by deriving and providing information related to colon cancer such as colon polyps and the likelihood of colon cancer according to the lifestyle. , The user can use it as an index to predict the onset of colorectal cancer according to the corresponding lifestyle through information related to colorectal cancer on a specific lifestyle. Preferably, the lifestyle information including a plurality of detailed category information includes at least one of age, sex, BMI, exercise habit, drinking habit, smoking habit, family medical history, and personal medical history. The lifestyle information is derived from the received health checkup information based on keywords related to the item of the detailed category information by receiving health checkup information such as the health checkup questionnaire, or inputting the item-specific information of the detailed category information intuitively. You can receive it. The server system 1000 of the present invention derives polyp potential and colorectal cancer potential by learning the learning information 1510 by receiving learning information 1510 including such lifestyle information and colonoscopy result information and tissue examination result information. And, it derives the possibility of polyp and colon cancer for specific lifestyle information. Thereafter, the result information related to colon cancer (1530) can be derived based on the derived polyp potential and the potential for colon cancer, and the derived colon cancer-related result of a person with the entered lifestyle information based on the entered lifestyle information. Information 1530 can be derived.

The server system 1000 illustrated in FIG. 1 includes a processor that receives the received learning information 1510 and derives colorectal cancer-related information, and one or more memories that store instructions executable by the processor. The processor includes a learning information receiving unit 1100, a possibility deriving unit 1200, a predicted data set deriving unit 1300, and a prediction result deriving unit 1400.

Hereinafter, more specific operations of the learning information receiving unit 1100, the probability deriving unit 1200, the predicted data set deriving unit 1300, and the predicted result deriving unit 1400 will be described in detail.

2 schematically shows the internal configuration of the server system 1000 according to an embodiment of the present invention.

The server system 1000 of the present invention may perform a method of predicting information related to colon cancer based on lifestyle information. Briefly, by learning data on people's lifestyles obtained through health checkup results, information related to colon cancer such as colon polyps and the likelihood of colon cancer according to lifestyle are derived and provided. The server system 1000 may include a learning information receiving unit 1100, a possibility deriving unit 1200, a predictive data set deriving unit 1300, and a predicting result deriving unit 1400.

The learning information receiving unit 1100 receives lifestyle information, colonoscopy result information, and tissue examination result information for a plurality of items of a learning subject. Specifically, the living habit information of the learning subject may be received from information including information on the living habits of the learning subject, such as health checkup information. Preferably, the lifestyle information may include at least one of age, gender, BMI, exercise habit, drinking habit, smoking habit, family medical history, and personal medical history. The colonoscopy result information refers to information on a colonoscopy result of a learning subject who performs a diagnosis through a colonoscopy such as a colonoscopy certificate and holds the diagnosis result. The biopsy result information means information on the biopsy result of a learning subject who has performed a biopsy and holds the biopsy result, for example, a biopsy result report.

The possibility derivation unit 1200 clusters colonoscopy result information and tissue examination result information of one or more learning subjects having specific lifestyle information, and polyps for a group having specific lifestyle information based on the clustered information. The likelihood, and the likelihood of colorectal cancer, are derived. Specifically, first, colonoscopy result information and tissue examination result information of one or more subjects having the same specific lifestyle information among a plurality of subjects are clustered. Thereafter, based on the clustered information, it is determined whether or not polyps of the learning subject have polyps, and based on the polyps of a plurality of learning subjects having the same specific lifestyle information, the polyp possibility for a group with specific lifestyle information is derived. . Also, based on the clustered information and a preset mapping table, the possibility of colon cancer is derived for a group having specific lifestyle information. The likelihood derivation unit 1200 repeats the above-described process for a plurality of specific lifestyle information to derive polyp potential and colorectal cancer potential for each group having specific lifestyle information for each of the subjects to be studied.

The predicted data set deriving unit 1300 derives a predicted data set 1520 for polyp potential and colorectal cancer probability of a group having a plurality of specific lifestyle information. After the likelihood of polyp and colorectal cancer for each group having specific lifestyle information is derived by the likelihood extraction unit 1200, the prediction data set extraction unit 1300 includes the lifestyle information including a plurality of detailed category information, A predicted data set 1520 including the polyp potential and the colon cancer potential is derived. Preferably, the lifestyle information includes at least one of age, sex, BMI, exercise habit, drinking habit, smoking habit, family medical history, and personal medical history.

Thereafter, the prediction result derivation unit 1400, based on the predicted data set 1520 derived by the predicted data set derivation unit 1300, with respect to the input lifestyle information, the polyp of a person having the input lifestyle information. It derives the results for the likelihood and the likelihood of colon cancer. Specifically, the prediction result derivation unit 1400 matches the received input lifestyle information and the lifestyle information included in the prediction data set 1520, and matches the detailed category information of each lifestyle information to the matching degree. Accordingly, it is possible to derive the possibility of polyp and colorectal cancer of a person with input lifestyle information based on the detailed prediction data set with high matching accuracy.

On the other hand, in the DB 1500 of the server system 1000, learning information 1510 including lifestyle information, colonoscopy result information, and tissue examination result information for a plurality of items to be studied, age, gender, BMI, Lifestyle information including at least one of exercise habits, drinking habits, smoking habits, family medical history, and personal medical history, predicted data set (1520) including the possibility of polyp and colorectal cancer, polyp of a person with input lifestyle information Colon cancer-related result information 1530 including the likelihood and the likelihood of colon cancer may be stored.

The server system 1000 illustrated in FIG. 2 may further include elements other than the illustrated elements, but for convenience, only elements related to the method for predicting colorectal cancer-related information based on lifestyle information according to embodiments of the present invention Is indicated.

3 schematically shows the form of the learning information 1510 processed by the likelihood derivation unit 1200 according to an embodiment of the present invention.

The learning information 1510 received by the learning information receiving unit 1100 included in the server system 1000 of the present invention includes lifestyle information, colonoscopy result information, and tissue examination result information for a plurality of items to be studied. . Thereafter, the received learning information 1510 may be processed by the possibility derivation unit 1200. Specifically, FIG. 3 (a) schematically shows lifestyle information, FIG. 3 (b) shows colonoscopy result information, and FIG. 3 (c) schematically shows tissue examination result information. When the lifestyle information is received, for example, health checkup information such as the health checkup questionnaire of the learning target as shown in Fig. 3(a), the possibility derivation unit 1200 may determine health based on the received health checkup questionnaire. It is possible to derive lifestyle information included in the examination questionnaire image. Alternatively, it is possible to directly receive lifestyle information for a plurality of detailed category information that has already been pre-processed from the outside through a health checkup questionnaire. On the other hand, the colonoscopy result information means information on a colonoscopy result of a learning subject who performs a diagnosis through a colonoscopy such as a colonoscopy certificate and holds the diagnosis result. The colonoscopy result information is clustered by the possibility guide unit 1200 to determine the polyp location (pericolica area in FIG. 3) and the polyp size (3 cm in FIG. 3) from the colonoscopy result information as shown in FIG. 3(b). Can be derived. In addition, the biopsy result information refers to information on the result of a biopsy of a learning subject that has the test result of the tissue in the large intestine by performing a biopsy, such as a biopsy result report. In addition, the type of polyp (adenoma in FIG. 3) may be derived from the biopsy result information by the possibility derivation unit 1200 as shown in FIG. 3(c). In this way, when the learning information 1510 is received, the possibility deriving unit 1200 extracts keywords related to the colon polyp from the learning information 1510 and includes the polyp size, the polyp location, and the polyp type of the learning target. Perform the step of deriving polyp data.

4 schematically shows the criteria for classifying lifestyle information according to an embodiment of the present invention.

The server system 1000 of the present invention may classify the received lifestyle information according to a preset criterion of each detailed category information. The criteria by which the lifestyle information is classified may be classified as shown in FIG. 4. Lifestyle information including at least one of age, sex, BMI, exercise habit, drinking habit, smoking habit, family medical history, and personal medical history is classified according to preset criteria as shown in Fig. 4 according to each subcategory. It can be recognized by giving a separate index. For example, in the case of gender among subcategories, a gender item index of 00 may be assigned to a woman, and a gender item index of 01 may be assigned to a male. In addition, as shown in FIG. 4, for the subcategory items in which the degree of individual habits such as drinking habits or smoking habits may be large, as shown in FIG. 4, for example, smoking period * average daily smoking amount and The item-specific index can be derived by converting the degree of subcategory items into numerical values based on the same criteria and assigning the smoking item index according to whether the numerical value meets the preset criteria. It is possible to recognize lifestyle information according to the derived item-specific index, and based on the item-specific index derived for each subcategory, the lifestyle information can be identified with one ID (for example, 30-01-00-00-10- 10-01-01) can also be derived. By classifying the lifestyle information in this way, it is possible to achieve the effect of objectively classifying the information of a plurality of learning subjects.

5 schematically shows a process of processing information derived by the likelihood extraction unit 1200 according to an embodiment of the present invention, and FIG. 6 schematically shows the possibility of colorectal cancer of a subject to be learned by the likelihood extraction unit 1200 It schematically shows a preset mapping table that is the basis for this.

The possibility derivation unit 1200 of the present invention extracts a keyword related to a colon polyp from the colonoscopy result information and the biopsy result information of the learning target, and one of the polyp size, polyp location, and polyp type of the learning target. Deriving polyp data including the above (S100); The specific lifestyle information is determined based on whether or not the learning target has a polyp based on at least one of the polyp size, the location of the polyp, and the type of the polyp, and based on whether or not the polyp is held by two or more learning targets having the same specific lifestyle information. Deriving the polyp possibility for (S110); And deriving the likelihood of colon cancer for the specific lifestyle information according to information on the polyp size and type of polyp of two or more learning targets having the same specific lifestyle information, and a preset mapping table; (S120) To do.

Specifically, in step S100, the possibility derivation unit 1200 extracts keywords related to the colon polyp from the colonoscopy result information and the biopsy result information of the learning target, and determines at least one of the polyp size, the polyp location, and the polyp type of the learning target. It is possible to derive the polyp data to be included. As described above in the description of FIG. 3, the possibility deriving unit 1200 derives polyp data including at least one of a polyp location, a polyp size, and a polyp type. FIG. 5A shows learning information 1510 of one or more learning targets having specific lifestyle information from which polyp data is derived by the possibility derivation unit 1200. According to the standard of FIG. 4, lifestyle information including a plurality of detailed category information is indicated by an item-specific index, and the polyp location, polyp size, and polyp type according to the colonoscopy result information and tissue examination result information of each learning subject are shown. Has been. In the case of learning information #1 and learning information #4, it indicates that keywords related to colon polyps were not extracted from the colonoscopy results and biopsy results information of the subject. This indicates that no polyps were found in the large intestine of the subject. It means you didn't.

Thereafter, in step S110, the likelihood extraction unit 1200 determines whether or not the learning target has a polyp based on at least one of the polyp location, the polyp size, and the polyp type. As shown in (b) of FIG. 5, in the case of learning object #1 and learning object #4, colon polyps in the colonoscopy result and tissue examination result information in the learning information 1510 of the learning object as described above. It is shown that polyp data was not derived based on that the keyword related to was not extracted. In this way, it is possible to determine whether or not the polyp of the learning target has a polyp according to whether or not polyp data including at least one of the polyp location, the size of the polyp, and the type of the polyp is derived. If at least one of the polyp location, polyp size, and polyp type is derived, it is determined that the polyp is possessed, and if at least one of the polyp location, polyp size, and polyp type is not derived, the polyp is not possessed. Discriminate.

After determining whether a plurality of learning targets having the same specific lifestyle information have polyps, the possibility derivation unit 1200 determines whether or not the polyps of two or more learning targets having the specific lifestyle information have the specific living habits information. Polypability for habit information can be derived. In an embodiment of the present invention, as shown in (b) of FIG. 5, the lifestyle information indicating age-gender-BMI-exercise habits-drinking habits-smoking habits-family medical history-personal medical history is 30-01- As 00-00-10-10-01-01, five subjects with the same specific living information are shown. Among them, it is shown that two subjects #1 and #4 do not have polyps, and three subjects #2, subjects #3, and #5 have polyps. Based on this, the polyp possibility may be derived according to the following derivation equation 1.

[Draw Expression 1]

Number of learning subjects with specific lifestyle information with polyps / Total number of learning subjects with specific lifestyle information *100 (%)

If the example shown in (b) of FIG. 5 is applied to the derivation equation 1, the polypability of the derivation equation 1 = 3/5 *100 = 60% is derived. Therefore, the polypability of the learning subject having the lifestyle information 30-01-00-00-10-10-01-01 is derived as 60% as shown in (c) of FIG. 5.

In this way, the possibility derivation unit 1200 may derive a polyp possibility for specific lifestyle information.

Thereafter, the step (S120) of deriving the likelihood of colon cancer for the specific lifestyle information performed by the likelihood extraction unit 1200 (S120) includes information on the polyp size and polyp type of two or more learning targets having specific lifestyle information. And deriving the likelihood of colorectal cancer for each learning target according to a preset mapping table (S120-1). And deriving a colorectal cancer possibility for the specific lifestyle information based on the colorectal cancer possibility for each learning target; (S120-2).

Specifically, in step S120-1, the possibility derivation unit 1200 derives the possibility of colon cancer for each learning information 1510 having specific lifestyle information through a preset mapping table as shown in FIG. 6. As shown in FIGS. 5 and 6, the mapping table serves as a criterion for deriving the possibility of colon cancer according to the size of the polyp and the type of the polyp. According to (b) of FIG. 5, the polyp size of the learning information #2 is 4, and the polyp type is shown as chorionic adenoma. Based on this, the polyp type in the standard of the mapping table of FIG. 6 is chorionic adenoma and corresponds to a polyp size of less than 3 to 6 cm, so that the likelihood of colon cancer is derived as 25% as shown in FIG. I can. Similarly, in the case of learning information #3 and learning information 1510 and #5, it is shown that the possibility of colon cancer for each learning information 1510 is derived according to the mapping table of FIG. 6. In this way, the likelihood derivation unit 1200 derives the possibility of colon cancer for each learning object according to the information on the polyp size and type of the polyp and a preset mapping table of two or more learning targets having specific lifestyle information.

Thereafter, in step S120-2, the likelihood of colon cancer for the specific lifestyle information is derived based on the likelihood of colon cancer for each learning target. The likelihood derivation unit 1200 may derive the likelihood of colon cancer for specific lifestyle information according to Equation 2 below based on the likelihood of colon cancer by two or more learning targets having specific lifestyle information.

[Draw Expression 2]

In the derivation equation 2, N denotes the total number of learning subjects having specific lifestyle information.

If the example shown in (b) of FIG. 5 is applied to the derivation equation 2, the likelihood of colon cancer for the specific life information of the derivation equation 2 = ((25 + 80 + 2)/5) = 21.4% is derived. Accordingly, the likelihood of colon cancer for the lifestyle information 30-01-00-00-10-10-01-01 is derived as 21.4% as shown in (c) of FIG. 5.

In this way, the likelihood extraction unit 1200 may derive the possibility of colon cancer for specific lifestyle information.

7 schematically shows the types of data derived by the possibility deriving unit 1200 and the predictive data set deriving unit 1300 according to an embodiment of the present invention.

As described above, the possibility derivation unit 1200 derives polyp data including at least one of the polyp location, the size of the polyp, and the type of the polyp based on the lifestyle information, the colonoscopy result information, and the biopsy result information, It derives the possibility of polyp and colon cancer for specific lifestyle information. FIG. 7A shows an example form of learning information 1510 including polyp data including at least one of the polyp location, polyp size, and polyp type by the possibility derivation unit 1200. If there is a value for the polyp data, the learning target with the corresponding learning information 1510 has the polyp, and if there is no value for the polyp data, the learning target with the corresponding learning information 1510 does not have the polyp. It can be determined as.

On the other hand, the possibility derivation unit 1200, if there is no organizational examination result information in the learning information 1510 of the learning target, among the learning information 1510 collected in the past, the learning information received from the learning information receiving unit 1100 Based on the collected learning information 1510 in the past in which the living habit information and the lifestyle information of the learning subject are the same, the colonoscopy result information is similar within a preset criterion, and the tissue examination result information exists, The possibility of colon cancer is derived for the learning information 1510 received from the learning information receiving unit 1100. Specifically, as shown in (a) of FIG. 7, the learning information 1510 #1 shows that values for the polyp location and the polyp size exist, but no values for the polyp type exist. This means that the biopsy result information was not received. As described above, in an embodiment of the present invention, there may be a case where there is no tissue test result information in the learning information 1510 of the learning object received by the server system 1000. In such a case, the possibility derivation unit 1200 includes the learning information 1510 having the same lifestyle information as the learning information 1510 of the learning subject without the received tissue test result information among the learning information 1510 collected in the past. To filter. Thereafter, the polyp location and the polyp size included in the received learning information 1510 are compared with the polyp location and size of one or more learning information 1510 having the same lifestyle information, and similar learning information (1510) within a preset criterion. ) To filter. According to (a) and (b) of FIG. 7, a plurality of learning targets having the same lifestyle information 40-00-00-00-10-10-01-01 as learning information #1 without a value for the type of polyp The learning information 1510 is shown, and when the polyp location and the polyp size of each of the learning information 1510 are compared, the polyp location and the polyp size of the learning information #1 and the learning information #5 are the same as R and 4. Is shown. Accordingly, the possibility derivation unit 1200 derives the polyp type of the learning information #1 as the polyp type type 4 identical to that of the learning information #5. Preferably, if the learning information 1510 with the same polyp location and polyp size derived from the colonoscopy result information exists among the learning information 1510 of one or more subjects having the same lifestyle information collected in the past, When the polyp type of the learning information 1510 is derived as the polyp type of the learning information 1510 received from the learning information receiving unit 1100, and the learning information 1510 having the same polyp location and polyp size does not exist, It is possible to derive the polyp type of the learning information 1510 received from the learning information receiving unit 1100 that has the same polyp location and the polyp type of the learning information 1510 corresponding to the polyp size within a preset range.

In this way, the possibility derivation unit 1200 derives all information on the tissue test result information based on the learning information 1510 collected in the past when there is no tissue test result information, Thereafter, the likelihood of colon cancer is derived for the learning information 1510 received in the learning information 1510 receiving step through the method described in FIGS. 5 and 6, and the likelihood of colon cancer is derived for the corresponding specific lifestyle information. .

In this way, even if all the learning information 1510 is not received, the possibility derivation unit 1200 supplements the learning information 1510 based on some of the learning information 1510 to improve data reliability. Can exert.

On the other hand, the predicted data set derivation unit 1300 is, based on the polyp probability and colorectal cancer probability for the specific lifestyle information derived by the probability derivation unit 1200, the polyp probability of a group having a plurality of the specific lifestyle information. And a predicted data set 1520 for the likelihood of colon cancer. The prediction data set 1520 includes lifestyle information including a plurality of subcategories, the polyp potential, and the colon cancer potential, and the lifestyle information includes age, sex, BMI, exercise habits, drinking habits, smoking Includes habits, family medical history, and personal medical history. As shown in Fig. 7(c), the polyp potential and the colon cancer potential for the specific lifestyle information derived by the possibility finding unit 1200 are lifestyle information 40-00-00-00-10-10-01- 01 derives polyp potential A1 and colon cancer potential B1, and the predicted data set derivation unit 1300 converts the entire learning information 1510 into a plurality of the specific lifestyle habits, as shown in FIG. 7(d). A predicted data set (1520) including lifestyle information for each group with information, polyp potential for lifestyle information, and colon cancer potential is derived. On the basis of the predicted data set 1520 thus derived, the prediction result derivation unit 1400 to be described later may predict the polyp potential and the colon cancer potential for the input lifestyle information.

8 schematically shows the steps of performing the prediction result derivation unit 1400 according to an embodiment of the present invention, and Fig. 9 is a lifestyle information by the prediction result derivation unit 1400 according to an embodiment of the present invention. The criteria for excluding subcategory items of are schematically shown.

The prediction result deriving unit 1400 of the present invention is a person who has the input lifestyle information based on the predicted data set 1520 derived from the predicted data set deriving unit 1300 with respect to the input lifestyle information. It is possible to derive the results for the polyp potential of and colon cancer potential. Specifically, the prediction result derivation unit 1400 derives a similarity according to the matching degree of the input lifestyle information and the lifestyle information included in the prediction data set 1520, and the similarity meets a preset criterion. Determining whether or not to derive similar group prediction data (S1000 to S1300); And deriving a polyp possibility and a colorectal cancer possibility of a person having the input lifestyle information based on the similar group prediction data (S1400).

In step S1000, the degree of similarity is derived according to the matching degree of the inputted lifestyle information and lifestyle information included in the prediction data set 1520. The inputted lifestyle information is matched with the lifestyle information of the predicted dataset 1520 derived in the step of deriving the predicted dataset 1520 to determine whether to match according to the detailed category of the lifestyle information. Similarity can be derived. After discriminating whether each category is matched with age, gender, BMI, exercise habit, drinking habit, smoking habit, family medical history and personal medical history included in the lifestyle information, similarity is derived according to the matching status. The equation for deriving the degree of similarity is shown in the following derivation equation 3.

[Draw Expression 3]

(Number of subcategory items in matched lifestyle information / Total subcategory items)*100

An example in which the prediction result deriving unit 1400 derives the degree of similarity is as follows.

[Example 1]

Input lifestyle information: 30-01-00-00-10-10-01-01

Detailed prediction data set lifestyle information: 50-00-01-00-12-10-01-01

Matching :X-X-X-O-X-O-O-O

If the above example is applied to the derivation equation 3, a similarity of (4/8) * 100 = 40% can be derived. In this way, the prediction result derivation unit 1400 derives the similarity between the input lifestyle information and the prediction data set 1520.

Thereafter, in step S1100, it is determined whether the degree of similarity derived in step S1000 meets a preset criterion. For example, assuming that the similarity from which the predetermined criterion is derived is 80% or more, in an embodiment of the present invention, the number of detailed category items of the lifestyle information is 8, so that the lifestyle information of the 7 or more items is In the same case, a similarity of 80% or more can be derived. Accordingly, the prediction result derivation unit 1400 determines a detailed prediction data set from which a similarity of 80% or more is derived among the prediction data set 1520. Thereafter, when there is a detailed prediction data set with a similarity that meets a preset criterion, step S1200 is performed, and when there is no detailed prediction data set with a similarity that meets the preset criterion, step S1300 is performed.

Step S1200 is a step performed by the prediction result derivation unit 1400 when there is a detailed prediction data set that satisfies a preset criterion of the similarity. In step S1200, a criterion with a preset similarity of the prediction data set 1520 At least one detailed prediction data set that meets is derived as similar group prediction data.

On the other hand, step S1300 is a step performed by the prediction result derivation unit 1400 when there is no detailed prediction data set that meets the predetermined criterion with the degree of similarity. In step S1300, a plurality of detailed category information of the input lifestyle information A part of is excluded according to the preset criteria. As shown in FIG. 9, the degree of similarity derived according to the matching degree of items of eight detailed category information according to age, gender, BMI, exercise habit, drinking habit, smoking habit, family medical history, and personal medical history is based on a preset criterion. If there is no matching detailed prediction data set, 6 detailed category information according to BMI, exercise habit, drinking habit, smoking habit, family medical history and personal medical history, excluding age and gender among the multiple detailed category information of lifestyle information. It is a standard. In this way, the prediction result derivation unit 1400 may exclude some of the plurality of detailed category information according to a preset criterion as illustrated in FIG. 9. Preferably, the input lifestyle information includes at least one of age, gender, BMI, exercise habit, drinking habit, smoking habit, family medical history and personal medical history, and the step of deriving the similar group prediction data includes age , Gender, BMI, exercise habit, drinking habit, smoking habit, family medical history and personal medical history to determine whether the first similarity meets a preset criterion, and if the first similarity does not meet the preset criteria, Determine whether the second similarity for BMI, exercise habits, drinking habits, smoking habits, family medical history and personal medical history meets the preset criteria, and if the second similarity does not meet the preset criteria, BMI, smoking It is determined whether the third similarity degree for habit, drinking habit, and personal medical history meets a preset criterion to derive the similar group prediction data.

After excluding some of the plurality of detailed category information matching the input lifestyle information and the prediction data set 1520 as described above, the prediction result derivation unit 1400 performs the steps S1000 to S1200 again, and the similarity is determined. One or more detailed prediction data sets meeting the set criteria can be derived as similar group prediction data.

In step S1400, the prediction result derivation unit 1400 derived from the similar group prediction data through the execution of the steps S1000 to S1300, the polyp possibility and colorectal cancer of a person with input lifestyle information based on the similar group prediction data. Derive the possibility.

In an embodiment of the present invention, when the inputted lifestyle information is input as shown in FIG. 10A, the prediction result derivation unit 1400 performs the steps S1000 to S1300. The detailed prediction data set as shown in b) can be derived as similar group prediction data. It is shown that the lifestyle information of the detailed prediction data set shown in (b) of FIG. 10 includes the same 20-00-00-00-10-10-01-01 as the input lifestyle information. The prediction result derivation unit 1400 derives the similar group prediction data, and then based on the similar group prediction data for specific lifestyle information corresponding to 20-00-00-00-10-10-01-01. It derives the polyp potential and colorectal cancer potential of a person with input lifestyle information corresponding to 20-00-00-00-10-10-01-01. Accordingly, (c) of FIG. 10 shows that A1 and colorectal cancer probability B2, which is the polyp probability value of the similar group prediction data for the specific lifestyle information corresponding to 20-00-00-00-10-10-01-01, are 20. It is shown that the polyp potential value of a person with the input lifestyle information corresponding to -00-00-00-10-10-01-01 is derived as A1 and the colorectal cancer probability value is derived as B2.

10B illustrates the case where all the detailed category information items of the lifestyle information match the input lifestyle information as described above, but in an embodiment of the present invention, the input lifestyle information and prediction There may be a case where all items of the detailed category information of the lifestyle information of the dataset 1520 do not match. FIG. 10C shows similar group prediction data derived according to a preset criterion when there is no detailed prediction data set in which all items of the detailed category information match. As shown in (c) of FIG. 10, five detailed prediction datasets are similar group prediction data that meets a predetermined standard of similarity according to the degree of matching with 20-00-00-00-10-10-01-01. Was derived. In the case of detailed prediction data set #1, the items of category information excluding gender are the same, and in the case of detailed prediction data set #2, the items of category information excluding age are the same, and the remaining detailed prediction data set #3, In the case of #4 and #5, it is shown that the items of category information except for drinking habits, smoking habits, and BMI are the same, respectively. In this case, the prediction result derivation unit 1400, based on the similar group prediction data for the specific lifestyle information corresponding to 20-00-00-00-10-10-01-01, 20-00-00-00 It derives the possibility of polyp and colorectal cancer of a person with the input lifestyle information corresponding to -10-10-01-01. Accordingly, (e) of FIG. 10 shows the polypability of the five detailed prediction datasets, which are similar group prediction data for specific lifestyle information corresponding to 20-00-00-00-10-10-01-01, and Input life where A1+A2+A3+A4+A5/5 and B1+B2+B3+B4+B5/5, which are average values of cancer likelihood, are 20-00-00-00-10-10-01-01 It is shown that the polyp likelihood value of a person with habit information is A1+A2+A3+A4+A5/5 and the colorectal cancer likelihood value is B1+B2+B3+B4+B5/5.

Preferably, the polyp possibility and colon cancer possibility of a person with the input lifestyle information can be derived based on the following derivation equation 4 and derivation equation 5.

[Draw Expression 4]

[Draw Expression 5]

Preferably, the step of deriving similar group prediction data performed by the prediction result derivation unit 1400 includes all items of a plurality of detailed category information of the input lifestyle information while meeting a predetermined criterion with the degree of similarity. When there is a matching detailed prediction data set, only the detailed prediction data set is derived as the similar group prediction data, and while the similarity meets a preset criterion, items of a plurality of detailed category information of the input lifestyle information are When there is no detailed prediction data set that all match, one or more derived detailed prediction data sets are derived as the similar group prediction data.

In this way, the prediction result derivation unit 1400 can derive the polyp potential and colorectal cancer potential of a person having the input lifestyle information based on the predicted data set 1520 derived by learning the learning information 1510. have.

11 schematically illustrates an internal configuration of a computing device according to an embodiment of the present invention.

The server system 1000 that performs the method of predicting colorectal cancer-related information according to FIG. 1 may include one or more modules of the computing device illustrated in FIG. 13.

11, the computing device 11000 includes at least one processor 11100, a memory 11200, a peripheral interface 11300, and an input/output subsystem ( I/Osubsystem) 11400, a power circuit 11500, and a communication circuit 11600 may be included at least. In this case, the computing device 11000 may include a system 1000 for deriving the asymmetry characteristic information of the face, or may be connected to the server system 1000 by the input/output subsystem 11400.

The memory 11200 may include, for example, high-speed random access memory, magnetic disk, SRAM, DRAM, ROM, flash memory, or nonvolatile memory. have. The memory 11200 may include a software module, an instruction set, or other various data necessary for the operation of the computing device 11000.

In this case, access to the memory 11200 from another component such as the processor 11100 or the peripheral device interface 11300 may be controlled by the processor 11100. The processor 11100 may be configured as a single unit or a plurality of units, and may include a processor in the form of a GPU and a TPU in order to improve operation processing speed.

The peripheral device interface 11300 may couple input and/or output peripheral devices of the computing device 11000 to the processor 11100 and the memory 11200. The processor 11100 may execute various functions for the computing device 11000 and process data by executing a software module or instruction set stored in the memory 11200.

The input/output subsystem 11400 may couple various input/output peripherals to the peripherals interface 11300. For example, the input/output subsystem 11400 may include a monitor, a keyboard, a mouse, a printer, or a controller for coupling a peripheral device such as a touch screen or a sensor to the peripheral device interface 11300 as needed. According to another aspect, the input/output peripheral devices may be coupled to the peripheral device interface 11300 without going through the input/output subsystem 11400.

The power circuit 11500 may supply power to all or part of the components of the terminal. For example, the power circuit 11500 may include a power management system, one or more power sources such as batteries or alternating current (AC), a charging system, a power failure detection circuit, a power converter or inverter, a power status indicator or power. It may contain any other components for creation, management, and distribution.

The communication circuit 11600 may enable communication with another computing device using at least one external port.

Alternatively, as described above, if necessary, the communication circuit 11600 may enable communication with other computing devices by transmitting and receiving an RF signal, also known as an electromagnetic signal, including an RF circuit.

The embodiment of FIG. 11 is only an example of the computing device 11000, and the computing device 11000 omits some of the components shown in FIG. 11, further includes additional components not shown in FIG. 11, or 2 It can have a configuration or arrangement that combines two or more components. For example, a computing device for a communication terminal in a mobile environment may further include a touch screen or a sensor in addition to the components shown in FIG. 11, and various communication methods (WiFi, 3G, LTE) are included in the communication circuit 1160. , Bluetooth, NFC, Zigbee, etc.) may include a circuit for RF communication. Components that may be included in the computing device 11000 may be implemented as hardware, software, or a combination of hardware and software including one or more signal processing or application-specific integrated circuits.

Methods according to an embodiment of the present invention may be implemented in the form of program instructions that can be executed through various computing devices and recorded in a computer-readable medium. In particular, the program according to the present embodiment may be configured as a PC-based program or an application dedicated to a mobile terminal. An application to which the present invention is applied may be installed in a user terminal through a file provided by the file distribution system. As an example, the file distribution system may include a file transmission unit (not shown) that transmits the file according to the request of the user terminal.

The apparatus described above may be implemented as a hardware component, a software component, and/or a combination of a hardware component and a software component. For example, the devices and components described in the embodiments are, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA). , A programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions, such as one or more general purpose computers or special purpose computers. The processing device may execute an operating system (OS) and one or more software applications executed on the operating system. Further, the processing device may access, store, manipulate, process, and generate data in response to the execution of software. For the convenience of understanding, although it is sometimes described that one processing device is used, one of ordinary skill in the art, the processing device is a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it may include. For example, the processing device may include a plurality of processors or one processor and one controller. In addition, other processing configurations are possible, such as a parallel processor.

The software may include a computer program, code, instruction, or a combination of one or more of these, configuring the processing unit to operate as desired or processed independently or collectively. You can command the device. Software and/or data may be interpreted by a processing device or to provide instructions or data to a processing device, of any type of machine, component, physical device, virtual equipment, computer storage medium or device. , Or may be permanently or temporarily embodyed in a transmitted signal wave. The software may be distributed over networked computing devices, and may be stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -A hardware device specially configured to store and execute program instructions such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those produced by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware device described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

Although the methods and systems of the present invention have been described in connection with specific embodiments, some or all of their components or operations may be implemented using a computer system having a general-purpose hardware architecture.

The above description of the present invention is for illustrative purposes only, and those of ordinary skill in the art to which the present invention pertains will be able to understand that other specific forms can be easily modified without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and are not limiting. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as being distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims to be described later rather than the detailed description, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. do.

Claims (6)

As a method for predicting information related to colon cancer based on lifestyle information, performed by a server system,
A learning information receiving step of receiving learning information including lifestyle information, colonoscopy result information, and tissue examination result information for a plurality of items of the learning subject;
Clustering colonoscopy result information and biopsy result information of one or more subjects with specific lifestyle information, and deriving polyp potential and colon cancer potential for groups with specific lifestyle information based on the clustered information. The step of finding the possibility;
A prediction data set deriving step of deriving a prediction data set for the polyp possibility and the colorectal cancer possibility of the group having the plurality of specific lifestyle information; And
Regarding the input lifestyle information, a prediction result derivation step of deriving a result of the polyp possibility and colon cancer possibility of a person having the input lifestyle information based on the prediction data set; including, colon cancer-related information Prediction method.
The method according to claim 1,
The step of deriving the possibility,
Extracting a keyword related to a colon polyp from the colonoscopy result information and the biopsy result information of the learning target to derive polyp data including at least one of the polyp location, the polyp size, and the polyp type of the learning target;
The specific lifestyle information is determined based on whether or not the learning target has polyps based on one or more of the polyp location, polyp size, and polyp type, and based on whether or not the polyps of two or more learning targets having the same specific lifestyle information have the polyps. Deriving the polyp possibility for; And
The large intestine comprising: deriving the likelihood of colon cancer for the specific lifestyle information according to information on the polyp size and polyp type of two or more learning targets having the same specific lifestyle information, and a preset mapping table. How to predict cancer-related information.
The method according to claim 2,
The prediction data set,
Lifestyle information including a plurality of detailed category information; The polypability; And the colon cancer possibility; Including,
The lifestyle information includes at least one of age, sex, BMI, exercise habit, drinking habit, smoking habit, family medical history and personal medical history, colon cancer-related information prediction method.
The method according to claim 2,
The step of deriving the possibility,
If there is no organizational examination result information in the learning information of the learning subject,
Among the learning information collected in the past, the lifestyle information and the lifestyle information of the learning subject received in the learning information receiving step are the same, the colonoscopy result information is similar within a preset criterion, and the tissue examination result information is A method for predicting colorectal cancer-related information for deriving the possibility of colorectal cancer for the learning information received in the learning information receiving step, based on the existing collected learning information in the past.
The method according to claim 1,
The step of deriving the prediction result,
Deriving similarity group prediction data by deriving a similarity according to the matching degree of the input lifestyle information and the lifestyle information included in the predicted data set, and determining whether the similarity level meets a preset criterion; And
A method for predicting colorectal cancer-related information comprising; deriving a polyp possibility and a colorectal cancer possibility of a person having the input lifestyle information based on the similar group prediction data.
As a server system that performs a method of predicting information related to colon cancer based on lifestyle information,
A learning information receiving unit for receiving learning information including lifestyle information, colonoscopy result information, and tissue examination result information for a plurality of items of the learning subject;
Clustering colonoscopy result information and biopsy result information of one or more subjects with specific lifestyle information, and deriving polyp potential and colon cancer potential for groups with specific lifestyle information based on the clustered information. Possibility-derived department;
A prediction data set deriving unit for deriving a prediction data set for the polyp possibility and the colorectal cancer possibility of a group having a plurality of the specific lifestyle information; And
Containing, a server system comprising; for the input lifestyle information input, a prediction result derivation unit for deriving a result of the polyp possibility and colorectal cancer possibility of a person having the input lifestyle information on the basis of the prediction data set.

Images