KR20190132290A - Method, server and program of learning a patient diagnosis - Google Patents

Abstract

The present invention relates to a patient diagnostic learning method. By constructing a disease information database and generating a virtual patient based on the database, a virtual patient who are more likely to exist in reality is generated. By receiving calibration data on the virtual patient from a specialist client and performing deep learning for the calibration data, and receiving feedback for virtual diagnostic information in an actual medical treatment process of a medical team and performing the deep learning for the feedback, the accuracy of the patient diagnosis can be improved.

Description

{Method, server and program of learning a patient diagnosis}

The present invention is directed to a method of learning a patient diagnosis by a computer.

In general, patients visited the hospital in person, explained their symptoms to the doctor, and received diagnosis and prescription accordingly.

However, as the Internet spreads and a lot of information is shared on the net, it is possible to search for symptoms on the Internet and obtain information on the symptoms, which are not provided by professional medical staff. Since most of them are rather wrong information is provided to patients often have a problem.

And, if the computer is to make a diagnosis virtually according to the symptoms, it is necessary to make a reliable diagnosis, but there is no method for learning the computer to make such a diagnosis.

In addition, when the computer virtually diagnoses according to a particular symptom, there is no method of securing reliability for the diagnosis.

The background art of the present invention is disclosed in Korean Patent Laid-Open Publication No. 10-2014-0148244 and the like, but there is no fundamental solution to the above-described problem.

The present invention for solving the above problems is to build a disease information database, create a virtual patient based on the diagnosis module after the virtual module to diagnose the virtual patient and the virtual diagnostic result from the expert client to receive the diagnostic module It can provide a patient diagnostic learning method of deep learning.

In addition, the present invention can provide a patient diagnosis learning method for the diagnostic module to virtually diagnose the patient through the patient information obtained when the medical staff actually consults the patient, and deep learning the diagnostic module through feedback received from the medical staff. have.

Problems to be solved by the present invention are not limited to the above-mentioned problems, and other problems not mentioned will be clearly understood by those skilled in the art from the following description.

The patient diagnosis learning method according to an embodiment of the present invention for solving the above problems is a method performed by a server, each of a plurality of diseases, at least of age, sex, symptoms, past history, physical examination results and vital signs Constructing a weighted disease information database representing a degree of relevance to a corresponding disease with respect to one element; After extracting two or more diseases including a specific chief complaint, extracting elements having a specific weight or more among the elements included in the extracted diseases, and randomly selecting the extracted elements, Generating; Inputting the virtual patient to a diagnosis module to provide a diagnosis result generated by the diagnosis to an expert client, and receiving calibration data on the diagnosis result; Storing and correcting the corrected contents in the disease information database, and deep learning the diagnosis module; Receiving patient information from a medical staff client or a patient client; Generating one or more virtual diagnosis information by inputting the patient information into the diagnosis module; Receiving feedback on the virtual diagnostic information from the medical staff client; And deep learning by storing feedback of the patient information and the virtual diagnosis information in the diagnosis module, wherein the patient information is information collected for diagnosis of the patient, and includes basic information and main appeal of the patient. At least one of symptoms, symptoms, past history, family history, surgical history, drug history, and physical examination.

In addition, the virtual patient generation step, the age selection step of randomly selecting from the normal distribution using the mean and standard deviation of the age information obtained by selecting the extracted disease as a whole; A gender selection step of randomly selecting the extracted disease in proportion to a distribution degree of gender information obtained by selecting all the diseases; And a vital sign selection step of randomly selecting from the normal distribution by using the mean and standard deviation of the vital signs obtained by selecting the extracted disease as a whole.

The virtual patient generation step may further include randomly selecting a questionnaire, a past history, and a physical examination for each system through a probability distribution proportional to the relation between the extracted elements and the major complaint symptoms.

The method may further include storing and updating the feedback received from the medical staff client in the disease information database, wherein the feedback is selected from the virtual diagnostic information or received new diagnostic information from the medical staff client. .

The receiving of the calibration data may further include deleting the virtual patient from the virtual patient record database when a specific virtual patient is deleted from the expert client.

The virtual diagnostic information may include at least one of a clinical examination list, a possibility of coincidence of the virtual diagnosis, and medical information about the diagnosis.

The method may further include generating one or more virtual diagnosis information by inputting symptom information received from a patient client into the diagnosis module; And analyzing the generated virtual diagnostic information to select a medical subject to be visited by a corresponding patient, and providing the virtual diagnostic information and information about the medical subject to the patient client.

Patient diagnosis learning server according to an embodiment of the present invention for solving the above problems, at least one element of age, sex, symptoms, past history, physical examination results and vital signs for each of a plurality of diseases and the corresponding disease and A disease information database constructed by being weighted to mean a degree of relevance; A generator for extracting two or more diseases including a particular major complaint symptom, extracting elements having a specific weight or more among the elements included in the extracted diseases, and randomly selecting the extracted elements to generate virtual patients ; And a diagnostic module for diagnosing the virtual patient by inputting the virtual patient, wherein the server inputs the virtual patient to the diagnosis module, provides a diagnosis result generated by diagnosis to an expert client, and corrects data of the diagnosis result. Receive the information, store the updated correction information in the disease information database, update the diagnostic module, deepen the diagnosis module, and input patient information received from a medical staff client or a patient client into the diagnostic module to provide one or more virtual diagnostic information. And generating the virtual diagnosis information to the medical staff client and receiving the feedback on the virtual diagnostic information from the medical staff client, storing the feedback on the patient information and the virtual diagnostic information in the diagnostic module to perform the diagnosis. Deep learning the module, the patient information The information collected by the party to diagnose, contain the basic information, the main complaints of the patients, symptoms, medical history, family history, surgical history, medication history, and at least one of the figures of Science examination.

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 may be further provided.

According to the present invention as described above, by building a disease information database, and based on this to create a virtual patient, there is an effect of creating a virtual patient that is likely to exist in reality.

According to the present invention, the diagnostic module diagnoses the virtual patient and corrects the virtual diagnosis result from the expert client, thereby updating the disease information database and the virtual patient record database, and deeply running the diagnostic module to improve the diagnostic capability of the diagnostic module. It is effective to improve.

In addition, the present invention is based on the actual case by the diagnostic module to diagnose the patient virtually through the patient information obtained when the medical staff actually consults the patient, and deep learning the diagnostic module by receiving feedback on the virtual diagnosis from the medical staff It is effective to improve the diagnostic capability of the diagnostic module.

Effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 and 2 are schematic diagrams of a patient diagnosis learning method according to an embodiment of the present invention.
3 is a flow chart of a patient diagnosis learning method according to an embodiment of the present invention.
4 is a diagram illustrating the construction of a disease information database according to an embodiment of the present invention.
5 is a diagram illustrating the creation of a virtual patient according to an embodiment of the present invention.
6 is a diagram illustrating a result of a virtual diagnosis of the virtual patient by the diagnostic module.
FIG. 7 is a diagram illustrating a diagnosis module generating virtual diagnosis information based on patient information received from a medical staff client.
8 is a diagram illustrating receiving feedback on virtual diagnostic information from a medical staff client.
9 is a block diagram of a patient diagnosis learning server according to an embodiment of the present invention.

Advantages and features of the present invention and methods for achieving them will be apparent with reference to the embodiments described below in detail with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but can be embodied in various different forms, and the present embodiments only make the disclosure of the present invention complete, and those of ordinary skill in the art to which the present invention belongs. It is provided to fully inform the skilled worker of the scope of the invention, which is defined only by the scope of the claims.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. In this specification, the singular also includes the plural unless specifically stated otherwise in the phrase. As used herein, "comprises" and / or "comprising" does not exclude the presence or addition of one or more other components in addition to the mentioned components. Like reference numerals refer to like elements throughout, and "and / or" includes each and all combinations of one or more of the mentioned components. Although "first", "second", etc. are used to describe various components, these components are of course not limited by these terms. These terms are only used to distinguish one component from another. Therefore, of course, the first component mentioned below may be a second component within the technical spirit of the present invention.

Unless otherwise defined, all terms used in the present specification (including technical and scientific terms) may be used in a sense that can be commonly understood by those skilled in the art. In addition, terms that are defined in a commonly used dictionary are not ideally or excessively interpreted unless they are specifically defined clearly.

Hereinafter, with reference to the accompanying drawings will be described an embodiment of the present invention;

Prior to the description, the meaning of terms used in the present specification will be briefly described. However, it is to be noted that the description of the terms is intended to help the understanding of the present specification, and thus, the terms are not used to limit the technical spirit of the present invention unless explicitly stated as limiting the present invention.

Expert: A specialist, such as a physician, who is authorized or qualified to make a diagnosis to a patient.

Medical staff: Supporting personnel, such as doctors who work with patients and nurses who work with them.

Science test data: refers to data measured through blood pressure, blood sugar, pulse rate, electrocardiogram, heart rate, body temperature, body fat, respiratory rate, blood oxygen level and screening, palpation, percussion, and auscultation.

Clinical test data: Refers to clinical test data of patients such as blood test, urine test, fecal test, sputum test, electrocardiogram test, EEG test, ultrasound test, allergy test, x-ray, endoscope, MRI, vitamin level, inflammation do.

Vital Signs: Measures vital information such as body temperature, respiration, pulse rate, and blood pressure.

In the embodiment of the present invention, the client means a device such as a computer and a terminal. For example, the expert client 300 is a client device used by an expert, and the medical staff client 500 refers to a client device such as a computer or a terminal used by a medical staff in a hospital.

In addition, the patient client 700 refers to a device such as a smartphone or tablet used by the patient, in the embodiment of the present invention to receive information from the patient client 700 and to provide information to the patient client 700 It means to be performed through the installed service application.

1 and 2 are schematic diagrams of a patient diagnostic learning method according to an embodiment of the present invention.

1 and 2 to briefly describe the patient diagnosis learning method according to an embodiment of the present invention.

The server 100 generates a virtual patient using the information stored in the disease information database 120 and the virtual patient generation algorithm, and diagnoses the virtual patient through the diagnosis module 150 to transmit the diagnosis result to the expert client 300. to provide.

In addition, the expert client 300 directly diagnoses the received virtual patient, matches the diagnosis result, and corrects the diagnosis result. The server 100 receives calibration data from the expert client 300.

The server 100 first trains the diagnostic module 150 through the corrected contents from the expert client 300.

In addition, the patient information received from the medical staff client 500 is input to the diagnostic module 150 to generate virtual diagnostic information and provide the medical staff client 500.

For example, as shown in FIG. 8, when the medical team client 500 inputs patient information and transmits the patient information to the server as shown in area 710, the server inputs the patient information received from the client in question to the diagnosis module 150. The virtual diagnostic information is generated as described above and provided to the medical staff client 500.

The medical team checks whether the virtual diagnosis information received from the server 100 matches the actual diagnosis result and checks whether the medical diagnosis is matched, and generates a feedback for this to provide the server 100.

The server 100 stores the feedback in the diagnostic module to second learn the diagnostic module 150.

Through the above-described configuration and processes, the server 100 performs the deep learning of the diagnostic module 150 while undergoing a number of primary learning and secondary learning processes, and finally, as the deep learning progresses, an artificial intelligence physician builds up. This makes it possible for the artificial intelligence doctor to diagnose the patient.

In addition, it is not a random diagnosis and learning, but by learning and diagnosing a virtual patient of an expert, and since the second clinician conducts a second study in the process of treating a patient, the reliability is higher than that of an existing AI doctor. There is a guaranteed effect.

It is possible to build a learning model at a low cost, collect feedback from incumbent medical staff to build a learning model, and update the disease information database 120 and the virtual patient record database 120. It is effective to reflect medical trends in real time.

In the medical field, diagnosis guides for diseases presented at conferences are often changed, diseases unknown to the medical field may be added, diseases unknown in research may be studied, and treatment methods for diseases without treatment may be published.

Due to these matters, when building a learning model and applying it as an artificial intelligence doctor, a problem may occur in that it cannot keep up with the latest technology trend. However, the present invention continuously collects feedback from medical staff working in the field and continuously learns. It is possible to reflect the latest technology trends in real time.

In addition, since the diagnostic doctor 150 learns the diagnosis module 150 according to the flow of the process performed by the actual doctor, the diagnosis may be similar to the actual doctor when the artificial intelligence doctor is constructed.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to other drawings.

3 is a flow chart of a patient diagnosis learning method according to an embodiment of the present invention, Figure 4 is a diagram illustrating the construction of a disease information database 120 according to an embodiment of the present invention, Figure 5 is an embodiment of the present invention FIG. 6 is a diagram illustrating an example of generating a virtual patient. FIG. 6 is a diagram illustrating a result of a virtual diagnosis of the virtual patient by the diagnosis module 150. FIG. 7 is a diagram illustrating patient information received from a medical staff client 500. FIG. 8 is a diagram illustrating the generation of virtual diagnostic information by the diagnosis module 150, and FIG. 8 is a diagram illustrating receiving feedback on the virtual diagnosis information from the medical staff client 500.

3 to 8, a patient diagnosis learning method according to an embodiment of the present invention will be described.

Patient diagnosis learning method according to an embodiment of the present invention is performed by the server 100, a computer.

First, the server 100 provides a disease information database to which each of the plurality of diseases is assigned a weight indicating at least one element of age, sex, symptoms, past history, physical examination results, vital signs, and the likeness of the disease. 120). (Step S510)

For example, suppose that there are three types of weights: 1st level, 2nd level, and 3rd level. Level 1 is not related to the element, the disease is related, level 2 is usually related, level 3 is very related Means high.

On the other hand, in FIG. 4, it is illustrated that weights of respective elements of Wilson disease are set in the disease information database 120.

Among them, abdominal swelling, drooling, leg swelling, and aphasia are highly related to Wilson's disease and can be a major complaint of Wilson's disease (a major complaint when the patient has the disease).

The database 120 according to an embodiment of the present invention includes a disease information database 120 and a virtual patient record database 120.

Next, in step S510, the generation unit 110 of the server 100 extracts two or more diseases including a particular major complaint symptom, extracts elements having a specific weight or more among the elements included in the extracted diseases, and then extracts them. Randomized elements are selected at random to create a virtual patient. (Step S520)

In more detail, the generation unit 110 of the server 100 selects a specific major appeal symptom using a virtual patient generation algorithm. Then, two or more diseases including the corresponding major complaint symptoms are extracted.

Next, the generation unit 110 extracts elements having a specific weight or more from the elements included in the extracted two or more diseases, and randomly selects the extracted elements to generate a virtual patient.

Preferably, the generation unit 110 extracts 1 or 2 elements by randomly weighting three or more levels among the elements included in the extracted two or more diseases, and randomly selects the extracted whole elements to select virtual patients. Will be created.

In this case, the virtual patient generation step (S520), the generation unit 110, the age selection step to randomly select from the normal distribution using the mean and standard deviation of the age information obtained by selecting the entire disease extracted, generation unit 110 ) Is a gender selection step of randomly selecting proportional to the distribution of gender information obtained by selecting all the extracted diseases, and using the mean and the standard deviation of the vital signs obtained by selecting all the extracted diseases from the generator 110. In the vital sign selection step of randomly selecting at step, the generation unit 110 further comprises the step of randomly selecting the questionnaire, past history, physical examination by system through the probability distribution proportional to the relationship between the extracted element and the major complaint symptoms can do.

In this case, the reason why the server 100 selects from a probability distribution proportional to the relevance is that the higher the relevance is, the more often it appears together.

One of the big challenges in deep learning AI doctors is to get patient cases for learning.

Since the server 100 is generated using the constructed disease information database 120 and the virtual patient generation algorithm as described above, it is possible to create a large number of virtual patients, as well as to create a virtual patient that is likely to exist. Will be used.

At this time, the generation unit 110 may further give at least one or more of the past history, family history, social history and the value of the science test to the virtual patient. In addition, the server 100 may give a detailed physical condition such as height, weight, waist circumference, and the like to the case in some cases.

Physical examination includes blood pressure, blood sugar, pulse rate, electrocardiogram, heart rate, body temperature, body fat, respiratory rate, blood oxygen level, etc. Social history means smoking, drinking, patient occupation, and the like.

In operation S520, the server 100 provides a diagnosis result generated by inputting a virtual patient to the diagnosis module 150 to the expert client 300, and the receiver 130 receives calibration data about the diagnosis result. do. (Step S530)

In more detail, the server 100 diagnoses the virtual patient generated through the operation S520 to the diagnosis module 150 and provides the generated diagnosis result to the expert client 300.

The expert client 300 checks the virtual patient and the diagnosis result received from the server 100 and directly rediagnoses the diagnosis result. At this time, the expert client 300 performs calibration on the diagnosis result of the diagnosis module 150 and provides the calibration data to the server 100.

In this case, step S530 may further include deleting the virtual patient from the virtual patient record database 120 when a specific virtual patient is deleted from the expert client 300.

For example, although the virtual patient is generated by using the disease information database 120 and the virtual patient generation algorithm, the virtual patient is generated with a low probability, and thus, the expert client 300 may be generated. When the patient deletes the patient, it is determined that the virtual patient cannot exist and is deleted from the virtual patient record database 120.

In addition, the virtual patient generation algorithm can be updated by learning the deleted patient's information to the virtual patient generation algorithm.

In operation S530, the server 100 stores and updates correction data received from the expert client 300 in the disease information database 120, and deeply runs the diagnosis module 150. (Step S540)

For example, when the calibration data is different from the disease name in which the expert client 300 diagnoses the virtual patient and the weight of the elements included in the virtual patient is different from the information previously stored in the disease information database 120, the calibration of the expert client 300 is performed. The data is input to the disease information database 120 to update the database 120. (Diagnosis module 150 primary learning)

At this time, a good diagnosis can be recommended to the doctor by the database 120 search technology, but as time goes by, the amount of data in the patient record database 120 will be enormous, and in particular, the hospital data can be directly received through the EMR business. Since problems may occur when processing, deep learning is useful in the patient learning method according to the embodiment of the present invention.

Through the configuration and processes of steps S510 to S540 described above, the server 100 deeply runs the diagnostic module 150 and the diagnostic accuracy of the diagnostic module 150 is increased.

In operation S540, the receiving unit 130 of the server 100 receives patient information from the medical staff client 500 or the patient client 700. (Step S550)

At this time, the patient information is the information collected by the medical staff for the diagnosis of the patient, and includes the patient's basic information, major complaint symptoms, symptoms, past history, family history, surgery, medication taking, physical examination.

The server 100 receiving the patient information from the medical staff client 500 or the patient client is illustrated in FIG.

As such, the medical team client 500 does not input special data for the virtual diagnosis, but when the various types of information collected for the diagnosis are input as usual, the medical staff client 500 is transferred to the server 100 to perform a virtual diagnosis. There is an effect that no load occurs.

More specifically, the server is a clinician client or patient client, which includes the patient's age, sex, major complaints, vital signs (biosignal), ROS (Review of System), history, physical examination, and corresponding symptoms. Request information input for the initial diagnosis disease information, etc., and receive and receive the corresponding information from the medical staff or the patient.

In operation S550, the server 100 inputs patient information to the diagnosis module 150 to generate one or more virtual diagnosis information, and provides the virtual diagnosis information to the medical staff client 500. (Step S560)

More specifically, the server 100 inputs information received from the medical team client 500 or the patient client 700 into the diagnostic module, and the diagnostic module virtualizes the patient using a learning model built up to the present time. Diagnosis generates one or more virtual diagnostic information.

In addition, when the server 100 receives the patient's information from the medical staff client 500 in step S550, the server 100 provides virtual diagnosis information to the medical staff client 500, and the patient 100 receives the patient's information from the patient client 700. The virtual diagnosis information may be provided to the client 700 or the medical staff client 500 of the patient's medical staff.

The virtual diagnosis information includes the diagnosis name of the patient, a list of clinical tests necessary for the diagnosis, the likelihood of matching the diagnosis, and medical information about the diagnosis.

In this case, the server 100 may further include a filtering step in which the server 100 confirms the sex of the patient and deletes the virtual diagnosis information that cannot occur in the patient from the virtual diagnosis information.

For example, if the patient is a female and includes virtual diagnostic information that cannot occur to the female, the virtual diagnostic information irrelevant to the patient is not included through the filtering step of deleting the virtual diagnostic information.

In addition, the virtual diagnostic information generated by the diagnostic module of the server 100 may be displayed together with the possibility of diagnosis of each virtual diagnostic information, and additional checklists necessary to help the medical staff make an accurate diagnosis of the patient. And medical information about the diagnosis.

In this case, the medical information may include medical knowledge related to symptoms such as basic information of symptoms, causes, test methods, treatment, prevention, symptoms over time, complications, food for improving symptoms, nutrition information, and the like.

In operation S560, the receiving unit 130 of the server 100 receives the feedback on the virtual diagnostic information from the medical staff client 500. (Step S570)

In this case, the feedback may be selected from the virtual diagnosis information from the medical staff client 500 or received new diagnostic information, and may include a specific clinical test value of the patient.

For example, cold, sore throat, tonsillitis and reflux esophagitis are output as virtual diagnostic information, and the medical staff client 500 selects a sore throat from four virtual diagnostic information and provides feedback to the server 100. It is.

At this time, the medical staff client 500 diagnosed the actual patient, the symptom findings of the sore throat was brought down, and therefore, the sore throat was checked for the sore throat from the virtual diagnosis information provided from the server 100, so the server 100 was checked. Provided feedback.

The server 100 is selected if there is a match in the virtual diagnosis information from the medical staff client 500, and if there is no match in the virtual diagnostic information is received from the medical staff client 500 directly receives the new diagnostic information.

In addition, when the feedback received from the medical staff client 500 includes the specific clinical result value of the patient, the diagnostic module 150 of the server 100 may learn the actual clinical result value together.

At this time, the diagnostic module 150 may be trained by receiving input values such as electrocardiogram, hemoglobin, electrolyte, and inflammation, and receive image data of test results such as ultrasound, x-ray, and endoscope. You can also learn about images.

For example, it may be learned to determine that there is an abnormality when a heterogeneous image is detected at a specific point in comparison with the X-ray, ultrasound, and endoscope photograph of a normal and healthy person.

In operation S570, the server 100 stores the feedback based on the patient information and the virtual diagnosis information in the diagnosis module 150 to deep run the diagnosis module 150. (Step S580)

More specifically, the server 100 stores the patient information and the feedback received from the medical staff client 500 in the diagnostic module 150 to deep learning the diagnostic module 150.

In operation S580, the server 100 may further include storing the feedback received from the medical staff client 500 in the disease information database 120 to update the disease information database 120. Since medical information and disease information may be added or changed according to the development of medical technology and information, even if the information stored in the disease information database 120 a year ago was correct at that time, it may be updated now.

Therefore, since the diagnostic module 150 performs the second learning based on the diagnosis result obtained by meeting the actual patient and the doctor, the reliability of the data to be learned is secured and the diagnosis accuracy is further increased.

In addition, without the hassle of the medical staff of the affiliated hospital to separately enter the information on the patient, when the patient information is naturally input in the process of proceeding with the patient as in the past, the diagnostic module 150 in the server 100 Since the virtual diagnostic information is generated and provided to the medical staff client 500, and the feedback of the virtual diagnostic information is received from the medical staff client 500, the medical staff and the patient can collect the information without any objection.

In addition, since the server 100 learns the diagnostic module 150 through the collected information, the diagnostic module 150 receives the diagnosis of the actual symptom and has a deep learning effect.

For example, when receiving feedback from medical staff clients 500 of 100 affiliated hospitals that diagnose 100 patients per day, the diagnosis module 150 may be trained for more than 3 million medical cases per year. Will be.

In an embodiment, when the analysis unit 170 of the server 100 receives and receives symptom information from the patient client 700, the analysis unit 170 may input one symptom information into the diagnosis module 150 to generate one or more virtual diagnosis information.

In addition, the analysis unit 170 analyzes the generated virtual diagnosis information, selects a treatment subject to be visited by the corresponding patient, and provides the virtual diagnosis information and information about the treatment subject to the patient client 700.

9 is a block diagram of a patient diagnosis learning server 100 according to an embodiment of the present invention.

9, the patient diagnosis learning server 100 according to an embodiment of the present invention includes a generation unit 110, a reception unit 130, a diagnosis module 150, an analysis unit 170, a filtering module 190, Database 120.

However, in some embodiments, the server 100 may include fewer components or more components than the components shown in FIG. 9.

The disease information database 120 is constructed by assigning weights to at least one of age, sex, symptoms, past history, scientific test results, and vital signs to each of the plurality of diseases, indicating the degree of relevance to the disease.

The generation unit 110 extracts two or more diseases including a specific major complaint symptom, extracts elements having a specific weight or more among the elements included in the extracted diseases, and then randomly selects extracted elements. Create a patient.

The diagnosis module 150 diagnoses the input virtual patient and generates diagnostic information.

The server 100 provides a diagnosis result generated by the server 100 by inputting a virtual patient to the diagnosis module 150 to diagnose the expert client 300, and the receiver 130 receives calibration data about the diagnosis result. do.

In addition, the server 100 stores and updates correction data received from the expert client 300 in the disease information database 120, updates the diagnosis module 150, and updates the patient information received from the medical staff client 500. Input to the diagnostic module 150 generates one or more virtual diagnostic information, and provides the virtual diagnostic information to the medical staff client 500.

In addition, when the receiver 130 receives the feedback on the virtual diagnosis information from the medical staff client 500, the server 100 stores the feedback on the patient information and the virtual diagnosis information in the diagnosis module 150 to diagnose the diagnosis module ( Deep learning 150).

In this case, the patient information is information collected for the diagnosis of the patient, and includes at least one of basic information of the patient, major complaint symptoms, symptoms, past history, family history, surgical history, drug taking history, and physical examination.

The patient diagnosis learning server 100 according to the embodiment of the present invention described above is different only from the categories of the patient diagnosis learning method and the invention described with reference to FIGS. 1 to 8, and thus overlapping descriptions and examples will be omitted. .

The method according to an embodiment of the present invention described above may be implemented as a program (or an application) and stored in a medium to be executed in combination with a server which is hardware.

The above-described program includes C, C ++, JAVA, machine language, etc. which can be read by the computer's processor (CPU) through the computer's device interface so that the computer reads the program and executes the methods implemented as the program. Code may be coded in the computer language of. Such code may include functional code associated with a function or the like that defines the necessary functions for executing the methods, and includes control procedures related to execution procedures necessary for the computer's processor to execute the functions according to a predetermined procedure. can do. In addition, the code may further include memory reference code for additional information or media required for the computer's processor to execute the functions at which location (address address) of the computer's internal or external memory should be referenced. have. Also, if the processor of the computer needs to communicate with any other computer or server remotely in order to execute the functions, the code may be used to communicate with any other computer or server remotely using the communication module of the computer. It may further include a communication related code for whether to communicate, what information or media should be transmitted and received during communication.

The stored medium is not a medium for storing data for a short time such as a register, a cache, a memory, but semi-permanently, and means a medium that can be read by the device. Specifically, examples of the storage medium include, but are not limited to, a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like. That is, the program may be stored in various recording media on various servers to which the computer can access or various recording media on the computer of the user. The media may also be distributed over network coupled computer systems so that the computer readable code is stored in a distributed fashion.

The steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, in a software module executed by hardware, or by a combination thereof. The software module may be a random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or It may reside in any form of computer readable recording medium well known in the art.

In the above, embodiments of the present invention have been described with reference to the accompanying drawings, but those skilled in the art to which the present invention pertains may realize the present invention in other specific forms without changing the technical spirit or essential features thereof. I can understand that. Therefore, it should be understood that the embodiments described above are exemplary in all respects and not restrictive.

100: server
110: generator
120: database
130: receiver
150: diagnostic module
170: analysis unit
190: filtering module
300: professional client
500: medical staff client
700: patient client

Claims (9)

In the way performed by the server,
Constructing a weighted disease information database for each of the plurality of diseases, the weight of each of the at least one of age, sex, symptoms, past history, physical examination results, and vital signs indicating a relationship with the disease;
After extracting two or more diseases including a specific chief complaint, extracting elements having a specific weight or more among the elements included in the extracted diseases, and randomly selecting the extracted elements, Generating;
Inputting the virtual patient to a diagnosis module to provide a diagnosis result generated by the diagnosis to an expert client, and receiving calibration data on the diagnosis result;
Storing and correcting the corrected contents in the disease information database, and deep learning the diagnosis module;
Receiving patient information from a medical staff client or a patient client;
Generating one or more virtual diagnosis information by inputting the patient information into the diagnosis module;
Receiving feedback on the virtual diagnostic information from the medical staff client; And
And deep learning by storing feedback of the patient information and the virtual diagnosis information in the diagnosis module.
The patient information is information collected for the diagnosis of the patient, and includes the patient's basic information, major complaint symptoms, symptoms, past history, family history, surgical history, medication history, and a physical examination. Diagnostic learning method.
The method of claim 1,
The virtual patient generation step,
An age selection step of randomly selecting from a normal distribution using an average and a standard deviation of age information obtained by selecting all the extracted diseases;
A gender selection step of randomly selecting the extracted disease in proportion to a distribution degree of gender information obtained by selecting all the diseases; And
And a vital sign selection step of randomly selecting from the normal distribution by using the mean and standard deviation of the vital signs obtained by selecting the extracted disease as a whole.
The method of claim 1,
The virtual patient generation step,
And randomly selecting a questionnaire, a past history, and a physical examination for each system through a probability distribution proportional to the relation between the extracted elements and the major complaint symptoms.
The method of claim 1,
And storing and updating the feedback received from the medical staff client in the disease information database.
The feedback is,
Is selected from the virtual diagnostic information from the medical staff client or received new diagnostic information, patient diagnosis learning method.
The method of claim 1,
The calibration data receiving step,
And deleting the virtual patient from the virtual patient record database when a specific virtual patient is deleted from the expert client.
The method of claim 1,
The virtual diagnostic information,
And at least one of a list of clinical tests necessary for diagnosis of the patient, possibility of coincidence of virtual diagnosis, and medical information about the diagnosis.
The method of claim 1,
Generating at least one virtual diagnosis information by inputting symptom information received from a patient client into the diagnosis module;
And analyzing the generated virtual diagnosis information to select a medical subject to be visited by the patient, and providing the virtual diagnostic information and information about the medical subject to the patient client.
Regarding the patient diagnosis learning server,
A disease information database constructed with weights representing a degree of relevance to the disease for at least one of age, sex, symptoms, past history, physical examination results, and vital signs;
A generator for extracting two or more diseases including a particular major complaint symptom, extracting elements having a specific weight or more among the elements included in the extracted diseases, and randomly selecting the extracted elements to generate virtual patients ;
And a diagnostic module for diagnosing by inputting the virtual patient.
The server inputs the virtual patient to the diagnosis module, provides a diagnosis result generated by diagnosis to an expert client, receives calibration data on the diagnosis result,
Storing and updating the corrected information in the disease information database, and deep learning the diagnosis module,
Inputting patient information received from a medical staff client or a patient client into the diagnostic module to generate one or more virtual diagnostic information, and providing the virtual diagnostic information to the medical staff client,
When receiving the feedback on the virtual diagnostic information from the medical staff client, by storing the feedback on the patient information and the virtual diagnostic information in the diagnostic module to deep learning the diagnostic module,
The patient information is information collected for the diagnosis of the patient, and includes the patient's basic information, major complaint symptoms, symptoms, past history, family history, surgical history, medication history, physical examination, at least one of the numerical values, patient diagnosis Learning server.
A patient diagnostic learning program, coupled to a computer that is hardware and stored on a medium for carrying out the method of any one of claims 1 to 7.

Images