WO2024043410A1

WO2024043410A1 - Examination data processing device, examination data processing method, and computer program for generating processed data by analyzing examination result data

Info

Publication number: WO2024043410A1
Application number: PCT/KR2022/019813
Authority: WO
Inventors: 강정규; 이미란; 윤남경; 장윤정; 안슬기
Original assignee: (의)삼성의료재단
Priority date: 2022-08-26
Filing date: 2022-12-07
Publication date: 2024-02-29
Also published as: KR20240029404A

Abstract

Embodiments of the present disclosure provide an examination data processing method comprising the steps in which: an examination data processing device receives examination result data for a first examinee; the examination data processing device analyzes the examination result data, and determines a first risk area for the first examinee and a first risk degree for the first risk area by using data stored in relation to a risk area and a risk degree; the examination data processing device determines a first risk level corresponding to the first risk area and the first risk degree in consideration of data on a group including the first examinee; the examination data processing device generates a first drawing for diagramming of the first risk area and the first risk degree, and generates a second drawing for diagramming of the first risk level; and the examination data processing device generates a report including the first drawing and the second drawing.

Description

Examination data processing device, examination data processing method, and computer program that analyzes examination result data and generates processed data

Embodiments of the present disclosure relate to a checkup data processing device, a checkup data processing device, and a computer program that analyzes checkup result data and generates processed data.

Today, modern people are very interested in health care as their life expectancy increases. By getting a health checkup every year, we want to know in advance about any health problems that may arise.

The result sheet notified as a result of a health checkup is written based on text and consists of medical and anatomical terms, making it difficult for the general public to understand.

In addition, there is a problem that it only provides uniform prevention guidelines and cannot provide information on individual risk levels.

Embodiments disclosed herein analyze health examination result data, extract risk areas of the examinee, determine the risk level for the risk area, and compare the risk area and risk level with data on the group including the examinee. Thus, a device and method for determining the risk level can be provided.

Additionally, an apparatus and method for generating a report based on risk level and blood vessel data obtained through health examination result data can be provided.

The examination data processing method according to embodiments of the present disclosure includes the steps of, by an examination data processing device, receiving examination result data for a first examinee; The examination data processing device analyzes the examination result data and determines a first risk area for the first examinee and a first risk level for the first risk area using data stored in relation to the risk area and risk level. steps; determining, by the examination data processing device, a first risk level corresponding to the first risk area and the first risk level by considering data about a group including the first examinee; generating, by the examination data processing device, a first drawing diagramming the first risk area and the first risk level, and generating a second drawing diagramming the first risk level; and generating, by the medical examination data processing device, a report including the first drawing and the second drawing.

The step of determining the first risk includes extracting a first text corresponding to a keyword related to the risk area and extracting a second text corresponding to a keyword related to the risk level; determining, by the examination data processing device, a first risk portion of the first examinee in consideration of the first text, and determining a first risk level of the first examinee in consideration of the second text; More may be included.

The data stored in relation to the risk area and risk level may include data on a plurality of past examination results, keywords for the risk area, and keywords for the risk level for the examination result data.

The first drawing may be a distribution diagram of arteriosclerosis including the external carotid artery, internal carotid artery, ampulla, distal common carotid artery, and middle common carotid artery.

The second drawing includes four levels of risk: normal, mild, moderate, and severe, and the risk level of each level can be expressed to have a size corresponding to the occurrence rate.

An examination data processing device according to embodiments of the present disclosure includes a computer-readable memory and one or more processors, wherein the processor receives examination result data for a first examinee, analyzes the examination result data, and , using the data stored in relation to the risk area and the risk level, the first risk area for the first examinee and the first risk level for the first risk area are determined, and data on the group in which the first examinee is included is determined. Considering the first risk area and the first risk level, a first risk level corresponding to the first risk level is determined, a first drawing diagramming the first risk part and the first risk level is generated, and the first risk level is schematized. A second drawing can be created, and a report including the first drawing and the second drawing can be generated.

The processor extracts a first text corresponding to a keyword related to a risk area, extracts a second text corresponding to a keyword related to a risk level, and, considering the first text, selects a first risk area of the first examinee. , and considering the second text, the first risk of the first examinee can be determined.

A computer program according to an embodiment of the present invention may be stored in a medium to execute any one of the methods according to an embodiment of the present invention using a computer.

In addition to this, another method for implementing the present invention, another system, and a computer-readable recording medium for recording a computer program for executing the method are further provided.

Other aspects, features and advantages in addition to those described above will become apparent from the following drawings, claims and detailed description of the invention.

According to one of the means for solving the above-mentioned problem, data on health examination results is analyzed, the patient's risk area is extracted, the risk level for the risk area is determined, the risk area and the risk level are calculated, and data on the group including the examinee are provided. A device and method for determining the risk level can be presented by comparing it with

In addition, a device and method for generating a report based on risk level and blood vessel data obtained through health examination result data can be presented.

1 is a block diagram of an examination data processing device 100 according to embodiments of the present disclosure.

Figure 2 is a block diagram of the examination data processing unit.

Figure 3 is a flowchart of a method for determining a patient's risk area and risk level according to embodiments of the present disclosure.

Figure 4 is a flowchart of a method for determining a risk level according to embodiments of the present disclosure.

Figure 5 is an example diagram of an arteriosclerosis distribution map generated according to embodiments of the present disclosure.

Figure 6 is an example diagram of the distribution of arteriosclerosis by age and sex generated according to embodiments of the present disclosure.

Figure 7 is an example diagram of an image of a patient's blood vessels generated according to embodiments of the present disclosure.

Figure 8 is an example diagram of risk factors of a patient according to embodiments of the present disclosure.

Hereinafter, the configuration and operation of the present invention will be described in detail with reference to embodiments of the present invention shown in the attached drawings.

Since the present invention can be modified in various ways and can have various embodiments, specific embodiments will be illustrated in the drawings and described in detail in the detailed description. The effects and features of the present invention and methods for achieving them will become clear by referring to the embodiments described in detail below along with the drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various forms.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. When describing with reference to the drawings, identical or corresponding components will be assigned the same reference numerals and redundant description thereof will be omitted. .

In this specification, terms such as “learning” and “learning” are not intended to refer to mental operations such as human educational activities, but are terms that refer to performing machine learning through procedural computing. interpret.

In the following embodiments, terms such as first and second are used not in a limiting sense but for the purpose of distinguishing one component from another component.

In the following examples, singular terms include plural terms unless the context clearly dictates otherwise.

In the following embodiments, terms such as include or have mean that the features or components described in the specification exist, and do not exclude in advance the possibility of adding one or more other features or components.

In the drawings, the sizes of components may be exaggerated or reduced for convenience of explanation. For example, the size and thickness of each component shown in the drawings are shown arbitrarily for convenience of explanation, so the present invention is not necessarily limited to what is shown.

In cases where an embodiment can be implemented differently, a specific process sequence may be performed differently from the described sequence. For example, two processes described in succession may be performed substantially at the same time, or may be performed in an order opposite to that in which they are described.

The checkup data processing device 100 can convert and generate checkup result data performed on a user into processed data. Examination result data refers to data obtained as a result of performing a comprehensive examination service and includes image data such as endoscopy, ultrasound, CT, MRI, judgment data on image data, blood test data, urine test data, etc. . Processed data refers to data that has been intuitively processed so that users without medical knowledge can understand it. The examination data processing device 100 may generate at least one of processed data for image data, processed data for decision data for image data, blood test data, or processed data for urine test data. The processed data may additionally include improvement information about the patient's condition information obtained through at least one of image data, judgment data for the image data, blood test data, and urine test data.

The examination data processing device 100 may be implemented including a processor 110, a memory 120, a communication unit 130, and an examination data processing unit 140.

The processor 110 may be implemented with one or more processors and configured to process instructions of a computer program by performing basic arithmetic, logic, and input/output operations. Commands may be provided to the processor 110 by a storage medium or the communication unit 130. For example, the processor 110 may be configured to execute commands received according to program codes stored in the examination data processing unit 140 or a recording device such as a storage medium.

Memory 120 may be a non-permanent mass storage device, such as random access memory (RAM), read only memory (ROM), and a disk drive. The examination data processing unit 140 may be a computer-readable recording medium such as a floppy drive, disk, tape, DVD/CD-ROM drive, or memory card.

The communication unit 130 may provide a function for communicating with an external device through a network. The communication unit 130 may acquire image data, judgment data for the image data, blood test data, urine test data, etc. according to instructions of the examination data processing unit 140, and transmit the generated processed data. .

The examination data processing device 10 may further include a non-permanent mass storage device such as computer-readable recording media such as random access memory (RAM), read only memory (ROM), and a disk drive. However, it is not limited to this.

The examination data processing unit 140 may include a data receiving unit 141, a risk generating unit 142, a risk level determining unit 143, a blood vessel imaging unit 144, and a report generating unit 145.

The data receiving unit 141 may receive data generated as services such as checkups, medical tests, and treatment progress. The data receiving unit 141 may receive image data such as endoscopy, ultrasound, CT, MRI, judgment data for the image data, blood test data, urine test data, etc.

At this time, the image data may further include information about the device through which the image is acquired, such as an endoscope, ultrasound, CT, or MRI, and information about the medical staff who took the image. Judgment data for image data may be generated by a medical staff based on the results of reading the image data, or may be automatically generated using a predetermined algorithm. Decision data for image data may further include information about the creator (generation device). Information about the creator may include the medical department, name of the medical staff, affiliated organization, etc. Blood test data and urine test data include numerical values obtained through a blood test or urine test, and may further include whether the numerical value is within a normal range.

The risk generation unit 142 may generate a risk level indicating the risk area extracted from the examinee's data on the stored anatomy drawing in response to the examination result data. The anatomical drawing may be determined as a drawing to be provided to the examiner. The risk generator 142 may analyze the examination result data, extract text about the risk part, and convert the text about the risk part into a corresponding risk level. The risk generator 142 may extract text from the examination result data and extract text about the risk area from the texts. Risk refers to the risk of developing a disease in a dangerous area. For example, it may be about cardiovascular disease, brain-related disease, risk of developing cancer, risk of developing dementia, etc. Text about risk areas refers to text about parts of the subject's body that frequently occur as risk areas. Text about the risk area may include text related to the risk area and text related to the degree of risk. The risk generator 142 may generate an anatomy diagram that displays one or more risk areas and one or more risks extracted through the above process on the anatomy diagram. Among the plurality of pre-stored anatomical drawings, a first anatomical drawing related to a risk area is determined, and in the first anatomical drawing, an area corresponding to the risk area is marked with a separate color or outline, and the risk level for the risk area is written in text. Alternatively, you can create images, drawings, etc. displayed with separate marks, separate colors, etc.

In an optional embodiment, the risk generator 142 may extract keywords related to the examinee's risk parts or risk levels from the examination result data using keywords related to the risk parts. The risk generation unit 142 may determine the examinee's risk area and risk level using keywords related to the risk area or keywords related to the risk level. The risk generator 142 can generate the examinee's risk area and risk by converting it into an anatomy diagram. The anatomical diagram, including the risk area and risk level, may be a schematic diagram of the carotid artery condition or an arteriosclerosis distribution diagram, but is not limited thereto and may be a variety of diagrams.

Here, keywords related to risk areas or keywords related to risk are pre-stored and may be stored as results learned by inputting a plurality of examination result data. Keywords related to risk areas or risk levels may be stored differently depending on the examination center. By dividing examination centers or pathologists, keywords related to risk areas or keywords related to risk can be extracted and managed.

The risk level determination unit 143 may analyze the examination result data, convert it into the examinee's risk level, and output the risk level. The risk level can be determined based on the risk area and risk level determined through the risk generation unit 142. The risk level may take into account the condition of the risk area depending on the examinee's age, gender, etc. Risk areas and risk levels can be converted into risk grades by comparing them with groups of the same age and gender. Based on the examinee’s age and gender, the ‘male 35-39 age group’ can be determined, and the risk of arteriosclerosis in the ‘male 35-39 age group’ can be compared with the conditions of the risk area and converted into a relative risk. It may be a group designated by gender and age, such as women in their 70s, men in their 60s, or a group designated by region, gender, and age, such as women in their 40s in Seoul and men in their 50s in Busan.

The risk level can be set to one of four levels: normal, mild, severe, and very severe. A diagram displaying risk levels can be schematized to have a size equal to the proportion of people belonging to each level.

The blood vessel imaging unit 144 can analyze the captured image and extract the thickness of the blood vessel wall and the blood vessel passage included in the image. The blood vessel imaging unit 144 can calculate the thickness of the blood vessel wall and the width of the blood vessel passage. Specifically, the blood vessel imaging unit 144 can designate a blood vessel passage from an image of a blood vessel among image data. At this time, a vascular passage extraction model learned using training data including images of blood vessels and vascular passages can be used. The blood vessel imaging unit 144 can use a blood vessel passage extraction model to designate a blood vessel passage for an image taken of blood vessels of an examinee. When a blood vessel passage is designated, the blood vessel imaging unit 144 can calculate the width of the blood vessel passage by considering the resolution of the blood vessel image.

The blood vessel imaging unit 144 may generate an image of the examinee's blood vessel showing the designated blood vessel wall and blood vessel passage for a portion of the image taken of the examinee's blood vessel.

The report generator 145 may generate a report including a drawing indicating the risk area and risk level, information on the risk level, and a blood vessel image showing the blood vessel wall and blood vessel passage.

The report generator 145 may generate a report that includes a first drawing diagramming the examinee's risk portion and risk level and a second drawing schematizing the examinee's risk level.

The report generation unit 145 may determine risk factors related to the risk level in relation to the examinee's risk level and generate a report that further includes data on the risk factors. Data on risk factors may further include data obtained through blood tests, physical examinations, urine tests, and interview data, in addition to data on risk areas and risk levels. For example, drinking-related data (whether you drink, how often you drink, how much you drink, etc.), smoking-related data (whether you smoke, how much you smoke, how often you smoke, how long you smoke, etc.), whether you are obese, whether there is a need for improvement in cholesterol levels, etc., and how much improvement is needed. , methods for improvement, etc. may be included in data on risk factors.

Through the first drawing that visually schematizes the examinee's risk area and risk level generated by the examination data processing server 100, the examinee can more accurately recognize his/her risk area and risk level.

Through the second drawing that visually depicts the risk level generated by the examination data processing server 100, the examinee can accurately recognize what level of risk level he or she has among people of the same age and gender. .

Through data on risk factors generated by the examination data processing server 100, the examinee can accurately recognize ways to lower his or her risk and improve his or her health.

Through the report generated by the examination data processing server 100, it is possible to make it easier for the examinee to understand the risks to the examinee's health condition without taking extra effort and effort to explain the examination result data.

In S110, the examination data processing device 100 may extract the first text related to the risk area and the second text related to the risk level from the examination result data of the first examinee. At this time, the examination data processing device 100 extracts the first text related to the risk area and the second text related to the risk by considering the keywords related to the risk area and the keywords related to the risk, respectively, obtained by inputting the examination result data. You can.

In S120, the examination data processing server 100 determines the first risk part corresponding to the first texts and the first risk degree corresponding to the second text using an algorithm learned with data from the first examination institution. You can.

The first examination institution may be an institution where the first examinee provided the examination service. If the quality of the algorithm learned from the examination result data of the first examination institution is good, the algorithm learned from the examination result data of the first examination institution can be used, and if the quality is not good, the algorithm learned from the examination result data of the first examination institution can be used, and if the quality is not good, the algorithm learned from the examination result data of the first examination institution can be used. You can use the algorithm learned with the resulting data.

The algorithm that determines the risk area and risk level can be said to have been learned using examination result data and learning data including the risk area and risk level.

In S130, the examination data processing server 100 may display the first risk part in the anatomical diagram of the examination area and generate an anatomical diagram of the examinee that displays the first risk part by the first risk level.

The examination data processing server 100 may provide drawings D51 and D52 as shown in FIG. 5 . D51 is a diagram schematically depicting areas related to arteriosclerosis, and D52 is a diagram showing the risk areas of the first examinee in the drawing D51. D51 may be schematic pre-stored data. As with D51 and D52, an arteriosclerosis distribution map including the external carotid artery, internal carotid artery, ampullary artery, distal common carotid artery, and middle common carotid artery can be generated. As in D52, for the first patient, the internal carotid artery, ampulla, distal common carotid artery, and middle common carotid artery can be determined and displayed as risk areas.

In S210, the examination data processing server 100 may receive the first risk area and the first risk level with respect to the examination result data of the first examinee.

In S220, the examination data processing server 100 may determine the first risk level of the first examinee by comparing the first risk area and the first risk level with information on the group including the first examinee.

The examination data processing server 100 may determine the first risk level of the first examinee by considering the risk area and risk level of the group having the same age and gender as the first examinee. Even if the patient has the same risk area and risk level, the patient's risk level may be determined differently if the patient is in his 40s or in his 70s.

In S230, the examination data processing server 100 may probabilistically determine the highest risk level and the lowest risk level among the first risk levels.

In S240, the examination data processing server 100 may generate risk level data indicating a range between the highest risk level and the lowest risk level.

As shown in FIG. 6, the examination data processing server 100 may display and provide the examinee's risk level. In a diagram including four levels of risk, a drawing 61 including a mark D62 indicating the risk level of the examinee may be created.

Figure 7 is an example diagram of an image of a patient's blood vessels created according to an embodiment of the present disclosure.

The examinee's blood vessel image (D71) may include a marking (D72) indicating a narrowed passage in the examinee's blood vessel wall.

Figure 8 is an example diagram of a report generated according to an embodiment of the present disclosure.

The examination data processing server 100 may generate data representing the risk level for arteriosclerosis risk factors related to the examinee.

The examination data processing server 100 may obtain pre-stored factors for arteriosclerosis risk factors and extract test values of the examinee corresponding to each factor. As shown in the drawing, the examination data processing server 100 collects smoking status, weight, obesity-related information, blood sugar levels, blood pressure values, cholesterol levels, etc. measured by blood tests in order to generate data on risk factors for arteriosclerosis. It can be extracted.

The examination data processing server 100 may generate data on cardiovascular risk factors, stroke risk factors, cancer risk factors, dementia risk factors, etc. in addition to arteriosclerosis risk factors. For example, from the examinee's blood test, urine test values, obesity-related values, smoking status, drinking-related data, imaging data (ultrasound, endoscopy, etc.), cardiovascular risk factors, stroke risk factors, cancer risk factors, and dementia risk. It can be generated by extracting data about factors, etc.

The examination data processing device 100 may generate risk factor data by extracting risk factors for colon cancer, stomach cancer, etc. from decision data for colonoscopy, decision data for gastroscopy, etc.

The device described above may be implemented with hardware components, software components, and/or a combination of hardware components and software components. For example, devices and components described in embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), etc. , may be implemented using one or more general-purpose or special-purpose computers, such as a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. Additionally, a processing device may access, store, manipulate, process, and generate data in response to the execution of software. For ease of understanding, a single processing device may be described as being used; however, those skilled in the art will understand that a processing device includes multiple processing elements and/or multiple types of processing elements. It can be seen that it may include. For example, a processing device may include a plurality of processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are possible.

Software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing unit to operate as desired, or may be processed independently or collectively. You can command the device. Software and/or data may be used on any type of machine, component, physical device, virtual equipment, computer storage medium or device to be interpreted by or to provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed over networked computer systems and 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 on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on the medium may be specially designed and configured for the embodiment or may be known and available to those skilled in the art of 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. -Includes optical media (magneto-optical media) and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include machine language code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described with limited examples and drawings, various modifications and variations can be made by those skilled in the art from the above description. For example, the described techniques are performed in a different order than the described method, and/or components of the described system, structure, device, circuit, etc. are combined or combined in a different form than the described method, or other components are used. Alternatively, appropriate results may be achieved even if substituted or substituted by an equivalent.

Therefore, other implementations, other embodiments, and equivalents of the claims also fall within the scope of the claims described below.

100: Examination data processing device

110: processor

120: memory

130: Department of Communications

140: Examination data processing unit

Claims

A step of receiving, by an examination data processing device, examination result data for a first examinee;

The examination data processing device analyzes the examination result data and determines a first risk area for the first examinee and a first risk level for the first risk area using data stored in relation to the risk area and risk level. steps;

determining, by the examination data processing device, a first risk level corresponding to the first risk area and the first risk level by considering data about a group including the first examinee;

generating, by the examination data processing device, a first drawing diagramming the first risk area and the first risk level, and generating a second drawing diagramming the first risk level; and

A method of processing medical examination data comprising the step of generating, by the medical examination data processing device, a report including the first drawing and the second drawing.
According to paragraph 1,

The step of determining the first risk is

Extracting first text corresponding to keywords related to the risk area and extracting second text corresponding to keywords related to the risk level;

determining, by the examination data processing device, a first risk portion of the first examinee in consideration of the first text, and determining a first risk level of the first examinee in consideration of the second text; Methods for processing examination data, including further.
According to paragraph 1,

Data stored in relation to the above-mentioned risk areas and risk levels are

A method of processing examination data, including data on multiple past examination results, keywords for risk areas for the examination result data, and keywords for risk.
According to paragraph 1,

The first drawing is,

Method for processing screening data, a distribution map of arteriosclerosis including the external carotid artery, internal carotid artery, ampullary artery, distal common carotid artery, and middle common carotid artery.
According to paragraph 1,

The second drawing is,

It includes four risk levels: normal, mild, moderate, and severe.

A screening data processing method in which the risk level of each stage is expressed to have a size corresponding to the occurrence rate.
Comprising a computer-readable memory and one or more processors,

The processor,

Receive examination result data for the first examinee,

Analyzing the examination result data, determining a first risk area for the first examinee and a first risk level for the first risk area using stored data related to the risk area and risk level,

Determining a first risk level corresponding to the first risk area and the first risk level by considering data on the group including the first examinee,

Generating a first drawing schematizing the first risk area and the first risk level, and generating a second drawing diagramming the first risk level,

An examination data processing device that generates a report including the first drawing and the second drawing.
According to clause 6,

The processor,

Extracting first text corresponding to keywords related to the risk area, extracting second text corresponding to keywords related to risk,

An examination data processing device that determines a first risk portion of the first examinee in consideration of the first text, and determines a first risk level of the first examinee in consideration of the second text.
According to clause 6,

Data stored in relation to the above-mentioned risk areas and risk levels are

An examination data processing device including data on a plurality of past examination results, keywords for risk areas for the examination result data, and keywords for the degree of risk.
According to clause 6,

The first drawing is,

A screening data processing device, which is a distribution map of arteriosclerosis including the external carotid artery, internal carotid artery, ampullary artery, distal common carotid artery, and middle common carotid artery.
According to clause 6,

The second drawing is,

It includes four risk levels: normal, mild, moderate, and severe.

A screening data processing device in which the risk level of each stage is expressed to have a size corresponding to the occurrence rate.
A computer program stored in a computer-readable storage medium to execute the method of any one of claims 1 to 5 using a computer.