CN112349367B - Method, device, electronic equipment and storage medium for generating simulated medical record - Google Patents

Method, device, electronic equipment and storage medium for generating simulated medical record Download PDF

Info

Publication number
CN112349367B
CN112349367B CN202011253477.2A CN202011253477A CN112349367B CN 112349367 B CN112349367 B CN 112349367B CN 202011253477 A CN202011253477 A CN 202011253477A CN 112349367 B CN112349367 B CN 112349367B
Authority
CN
China
Prior art keywords
diagnosis
treatment
target
medical record
historical
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202011253477.2A
Other languages
Chinese (zh)
Other versions
CN112349367A (en
Inventor
张盼盼
任彩红
胡可云
陈联忠
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Jiahesen Health Technology Co ltd
Original Assignee
Beijing Jiahesen Health Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Jiahesen Health Technology Co ltd filed Critical Beijing Jiahesen Health Technology Co ltd
Priority to CN202011253477.2A priority Critical patent/CN112349367B/en
Publication of CN112349367A publication Critical patent/CN112349367A/en
Application granted granted Critical
Publication of CN112349367B publication Critical patent/CN112349367B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/21—Design, administration or maintenance of databases
    • G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/31—Indexing; Data structures therefor; Storage structures
    • G06F16/313—Selection or weighting of terms for indexing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • G06F16/355—Class or cluster creation or modification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/205—Parsing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/284—Lexical analysis, e.g. tokenisation or collocates
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Primary Health Care (AREA)
  • Epidemiology (AREA)
  • Artificial Intelligence (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • Pathology (AREA)
  • Biomedical Technology (AREA)
  • Quality & Reliability (AREA)
  • Software Systems (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

The application discloses a method, a device, electronic equipment and a storage medium for generating a simulated medical record. The method comprises the following steps: obtaining a reference medical record; obtaining a diagnosis and treatment problem request, wherein the diagnosis and treatment problem request carries the identification of a target department and a target disease; obtaining a target diagnosis and treatment problem set corresponding to the target department and the target disease, and outputting the target diagnosis and treatment problem set, wherein each diagnosis and treatment problem in the diagnosis and treatment problem set is pre-constructed with a mapping relation with fields in a structured medical record; taking the selected diagnosis and treatment problem in the target diagnosis and treatment problem set as a target diagnosis and treatment problem; acquiring an answer corresponding to the target diagnosis and treatment problem from the reference medical record based on the mapping relation between the target diagnosis and treatment problem and the fields in the structured medical record; and writing the target diagnosis and treatment questions and the corresponding answers into corresponding fields in the template medical record to obtain the simulated medical record. Based on the scheme disclosed by the application, the simulation medical record meeting the teaching requirement can be generated rapidly.

Description

Method, device, electronic equipment and storage medium for generating simulated medical record
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method, an apparatus, an electronic device, and a storage medium for generating a simulated medical record.
Background
Medical science is a highly intellectual and specialized discipline. How to improve the diagnosis and treatment level of teaching objects (including medical students and primary doctors) is an important part of teaching tasks. At present, medical records are commonly used for teaching a teaching object. For example, for a certain disease in a certain department, a high-quality medical record is constructed, and according to diagnosis and treatment questions and corresponding answers in the medical record, a simulation question and answer is conducted on the teaching object, so that the purpose of improving the diagnosis and treatment level of the teaching object is achieved.
Currently, medical records for teaching are written by experienced doctors based on real historical medical records, and the written medical records are called simulated medical records or simulated medical records. However, the existing scheme for generating the simulated medical record has the defects of low efficiency and long time consumption.
Disclosure of Invention
In view of the foregoing, an object of the present application is to provide a method, an apparatus, an electronic device, and a storage medium for generating a simulated medical record, so as to quickly generate a simulated medical record that meets teaching requirements.
In order to achieve the above purpose, the present application provides the following technical solutions:
the application provides a method for generating a simulated medical record, which comprises the following steps:
obtaining a reference medical record;
Obtaining a diagnosis and treatment problem request, wherein the diagnosis and treatment problem request carries identification of a target department and a target disease;
obtaining a target diagnosis and treatment problem set corresponding to the target department and the target disease in a diagnosis and treatment problem set pre-constructed for each disease in each department, and outputting the target diagnosis and treatment problem set; each diagnosis and treatment problem in the diagnosis and treatment problem set is pre-established with a mapping relation with fields in the structured medical record;
taking the selected diagnosis and treatment problem in the target diagnosis and treatment problem set as a target diagnosis and treatment problem;
acquiring an answer corresponding to the target diagnosis and treatment problem from the reference medical record based on the mapping relation between the target diagnosis and treatment problem and the fields in the structured medical record;
and writing the target diagnosis and treatment questions and the corresponding answers into corresponding fields in the template medical record to obtain the simulated medical record.
Optionally, in the above method, a solution for diagnosing and treating a set of questions is pre-built, including:
acquiring historical diagnosis and treatment data;
cleaning the historical diagnosis and treatment data;
classifying the cleaned historical diagnosis and treatment data, wherein the types of the historical diagnosis and treatment data comprise inquiry and examination;
Performing similarity normalization processing on the cleaned historical diagnosis and treatment data to obtain standardized historical diagnosis and treatment data;
determining a field corresponding to the standardized historical diagnosis and treatment data in the structured medical record, and establishing a mapping relation between diagnosis and treatment problems in the standardized historical diagnosis and treatment data and the field;
determining departments and diseases corresponding to diagnosis and treatment problems in the standardized historical diagnosis and treatment data;
and adding the diagnosis and treatment problems into a diagnosis and treatment problem set constructed by corresponding departments and diseases.
Optionally, in the above method, the cleaning the historical diagnosis and treatment data includes:
performing word segmentation processing on the historical diagnosis and treatment data to obtain a first word segmentation result;
if at least one word in the first word segmentation result belongs to a medical knowledge base, a synonym dictionary of the medical knowledge base or a preset high-frequency medical vocabulary, the historical diagnosis and treatment data are reserved, and otherwise, the historical diagnosis and treatment data are deleted.
Optionally, in the above method, the classifying the cleaned historical diagnosis and treatment data includes:
if the cleaned historical diagnosis and treatment data comprises words or inquiry keywords corresponding to symptom bodies, determining that the cleaned historical diagnosis and treatment data is of an inquiry type;
And if the cleaned historical diagnosis and treatment data comprises words corresponding to the part body, determining that the cleaned historical diagnosis and treatment data is of a query type.
Optionally, in the above method, the performing similarity normalization processing on the cleaned historical diagnosis and treatment data to obtain standardized historical diagnosis and treatment data includes:
determining the similarity between the historical diagnosis and treatment data belonging to the same type in the cleaned historical diagnosis and treatment data;
and carrying out normalization processing on a plurality of pieces of washed historical diagnosis and treatment data with the similarity reaching a preset similarity threshold value, and generating a piece of standardized historical diagnosis and treatment data.
Optionally, in the above method, the determining a field corresponding to the standardized historical diagnosis and treatment data in the structured medical record includes:
respectively determining the association weights between the standardized historical diagnosis and treatment data and each field in the structured medical record;
and determining the field with the highest association weight as the field corresponding to the standardized historical diagnosis and treatment data in the structured medical record.
Optionally, in the above method, the determining departments and diseases corresponding to diagnosis and treatment problems in the standardized historical diagnosis and treatment data includes:
Determining a department corresponding to the diagnosis and treatment problem in the standardized historical diagnosis and treatment data according to a field corresponding to the standardized historical diagnosis and treatment data in the structured medical record;
and performing word segmentation processing on the standardized historical diagnosis and treatment data to obtain a second word segmentation result, determining the similarity between the second word segmentation result and medical keywords of each disease in the department, and determining the disease with the highest similarity as the disease corresponding to the diagnosis and treatment problem in the standardized historical diagnosis and treatment data.
The application also provides a device for generating the simulated medical record, which comprises:
a reference medical record acquisition unit for acquiring a reference medical record;
the request acquisition unit is used for acquiring a diagnosis and treatment problem request, wherein the diagnosis and treatment problem request carries the identification of a target department and a target disease;
a target diagnosis and treatment problem set acquisition unit, configured to obtain a target diagnosis and treatment problem set corresponding to the target department and the target disease from diagnosis and treatment problem sets pre-constructed for each disease in each department, and output the target diagnosis and treatment problem set; each diagnosis and treatment problem in the diagnosis and treatment problem set is pre-established with a mapping relation with fields in the structured medical record;
The target diagnosis and treatment problem acquisition unit is used for taking the selected diagnosis and treatment problem in the target diagnosis and treatment problem set as a target diagnosis and treatment problem;
a diagnosis and treatment answer obtaining unit, configured to obtain an answer corresponding to the target diagnosis and treatment question in the reference medical record based on a mapping relationship between the target diagnosis and treatment question and a field in the structured medical record;
and the data processing unit is used for writing the target diagnosis and treatment questions and the corresponding answers into corresponding fields in the template medical record to obtain the simulated medical record.
The application also provides an electronic device comprising a processor, a memory and a communication interface;
the memory is used for storing programs;
the processor is configured to execute the program to implement the steps of the method for generating a simulated medical record as any one of the above.
The present application also provides a readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of a method of generating a simulated medical record as any of the above. It can be seen from this:
according to the method, the device, the electronic equipment and the storage medium for generating the simulated medical record, diagnosis and treatment problem sets are constructed in advance for all diseases in all departments, and mapping relations between each diagnosis and treatment problem in the diagnosis and treatment problem sets and fields in the structured medical record are constructed in advance; after obtaining a diagnosis and treatment problem request carrying identification of a target department and a target disease, obtaining a target diagnosis and treatment problem set corresponding to the target department and the target disease from a pre-constructed diagnosis and treatment problem set, outputting the target diagnosis and treatment problem set, then taking the selected diagnosis and treatment problem in the diagnosis and treatment problem set as a target diagnosis and treatment problem, obtaining an answer corresponding to the target diagnosis and treatment problem from a reference medical record based on a mapping relation between the target diagnosis and treatment problem and a field in a structured medical record, and writing the target diagnosis and treatment problem and the corresponding answer into corresponding fields in a template medical record to obtain a simulated medical record.
It can be seen that, based on the scheme disclosed in the application, the user only needs to determine the target department and the target disease according to the teaching requirement, and select the target diagnosis and treatment problem in the target diagnosis and treatment problem set corresponding to the target department and the target disease, and the electronic device can quickly generate the simulation model meeting the teaching requirement based on the reference medical record and the mapping relation between the diagnosis and treatment problem and the fields in the structured medical record.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method of generating a simulated medical record disclosed herein;
FIG. 2 is a flow chart of a method of pre-building a problem set as disclosed herein;
FIG. 3 is a schematic diagram of a set of medical questions disclosed herein and a mapping relationship between each medical question in the set of medical questions and fields in a structured medical record;
FIG. 4-1 is a schematic diagram of historical diagnostic data disclosed herein;
FIG. 4-2 is a schematic diagram of the word segmentation result of the historic diagnosis and treatment data shown in FIG. 4-1;
FIG. 4-3 is a schematic diagram of the results of screening the historic diagnosis and treatment data of FIG. 4-1 based on a medical knowledge base and a synonym dictionary of the medical knowledge base;
fig. 4-4 is a schematic diagram of a result of screening the historical diagnosis and treatment data shown in fig. 4-1 based on a preset high-frequency medical vocabulary;
FIGS. 4-5 are graphs showing the results of cleaning the historic diagnostic data of FIG. 4-1;
FIG. 5 is a sample illustration of the site body disclosed herein;
FIG. 6 is a sample illustration of the symptom ontology disclosed herein;
FIG. 7 is a schematic diagram of a partial classification result obtained by classifying the cleaned historic diagnosis and treatment data shown in FIGS. 4 to 5;
FIG. 8 is a schematic illustration of the cleaned question and answer and normalization results disclosed herein;
FIG. 9 is a schematic diagram of the result of normalization processing of the cleaned volume data according to the present disclosure;
FIG. 10 is a schematic diagram of word segmentation results of diagnosis and treatment problems in standardized historical diagnosis and treatment data and keywords in a Chinese name path of a structured field;
FIG. 11 is a schematic structural diagram of an apparatus for generating a simulated medical record disclosed in the present application;
fig. 12 is a schematic structural diagram of an electronic device disclosed in the present application.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
Technical terms appearing in the present application will be first described.
Medical classification word stock: the word stock commonly used in the medical field is composed of six major categories, such as diseases, symptoms, surgery, medicines, inspection, examination, and the like. For example, the disease word stock includes coronary atherosclerotic heart disease, hypertension, etc., the symptom word stock includes fever, headache, etc., the operation word stock includes heart intervention operation, thoracoscopic operation, etc., the medicine word stock includes aspirin, atorvastatin calcium, etc., the examination word stock includes erythrocytes, leukocytes, etc., and the examination word stock includes electrocardiogram, ultrasound, etc.
Diagnosis and treatment data: in diagnosing diseases, questions of doctors and answers of patients (i.e., answers of patients) can be subdivided into inquiry questions and corresponding answers, and physical examination questions and corresponding answers.
Natural language processing: natural Language Processing (NLP) is an important direction in the fields of computer science and artificial intelligence. It is studying various theories and methods that enable effective communication between a person and a computer in natural language. Natural language processing is a science that integrates linguistics, computer science, and mathematics. That is to say let the computing mechanism solve the language we are using daily.
Structured data: the current data is divided into structured data, semi-structured data, and unstructured data. Structured data refers to data that can be represented and stored using a relational database, represented in two dimensions. Unstructured data is data that has no fixed structure, such as pictures, documents, etc. Semi-structured data is a form of structured data that does not conform to a data model structure associated with a relational database or other data table form, but contains associated tags that separate semantic elements and hierarchy records and fields. Therefore, it is also called a self-describing structure.
Text similarity: a method of examining whether two texts are similar and determining a degree of similarity between the two texts.
The application discloses a method for generating a simulated medical record, which can quickly generate diagnosis and treatment questions and corresponding answers according to teaching requirements, so that the simulated medical record meeting the teaching requirements is quickly generated.
The method for generating the simulated medical record is applied to the electronic equipment, wherein the electronic equipment can be terminal equipment such as a mobile phone and a personal computer, and can also be a server or a server cluster for providing the service for generating the simulated medical record.
Referring to fig. 1, fig. 1 is a flowchart of a method of generating a simulated medical record disclosed in the present application. The method comprises the following steps:
step S101: obtaining a reference medical record.
The reference medical record is a real historical medical record and is reference data for generating the simulation medical record.
In implementation, after determining that a simulated medical record is to be generated for a disease under a certain department, one or more historical medical records of the disease under the department are obtained as reference medical records. For example, to generate a simulated medical record for hypertension in a cardiovascular setting, one or more historical medical records for hypertension in a cardiovascular setting are obtained as reference medical records.
Step S102: obtaining a diagnosis and treatment problem request.
The diagnosis and treatment problem request carries identification of a target department and a target disease.
In one possible implementation, the user directly inputs a diagnosis and treatment question request at the graphical interface, the diagnosis and treatment question request carrying the identification of the target department and the target disease. The graphical interface is a front page that enables man-machine interaction.
In another possible implementation manner, the departments and the diseases under the departments are displayed on a graphical interface, the user selects a department and the diseases under the departments, and when clicking a confirmation control, a diagnosis and treatment problem request is generated, wherein the diagnosis and treatment problem request carries the identification of the target department and the target disease.
Step S103: and obtaining a target diagnosis and treatment problem set corresponding to the target department and the target disease in a diagnosis and treatment problem set pre-constructed for each disease in each department, and outputting the target diagnosis and treatment problem set. Each diagnosis and treatment problem in the diagnosis and treatment problem set is pre-constructed with a mapping relation with fields in the structured medical record.
A diagnosis and treatment problem set is pre-built for each disease in each department, each diagnosis and treatment problem set generally comprises a plurality of diagnosis and treatment problems, and each diagnosis and treatment problem in the diagnosis and treatment problem set is pre-built with a mapping relation with fields in a structured medical record.
Taking cardiovascular medicine as an example, diagnosis and treatment problem sets are respectively constructed in advance aiming at hypertension and coronary atherosclerotic heart disease. Referring to fig. 3, fig. 3 shows a diagnosis and treatment problem set pre-constructed for a disease in a department, and a mapping relationship between each diagnosis and treatment problem in the diagnosis and treatment problem set and fields in a structured medical record.
After obtaining the diagnosis and treatment problem request, determining the identification of a target department and a target disease carried by the diagnosis and treatment problem request, and obtaining a target diagnosis and treatment problem set corresponding to the target department and the target disease in a diagnosis and treatment problem set which is pre-built for each disease under each department in advance.
It should be noted that the diagnosis and treatment problems include inquiry problems and physical examination problems.
Step S104: and taking the selected diagnosis and treatment problem in the target diagnosis and treatment problem set as a target diagnosis and treatment problem.
After the target diagnosis and treatment problem set is obtained, the target diagnosis and treatment problem set is displayed, one or more diagnosis and treatment problems in the target diagnosis and treatment problem set are selected by a user, and the selected diagnosis and treatment problems are used as target diagnosis and treatment problems. That is, the number of targeted medical questions may be one or more.
Step S105: based on the mapping relation between the target diagnosis and treatment problem and the fields in the structured medical record, obtaining an answer corresponding to the target diagnosis and treatment problem from the reference medical record.
Step S106: and writing the target diagnosis and treatment questions and the corresponding answers into corresponding fields in the template medical record to obtain the simulated medical record.
The mapping relation between the target diagnosis and treatment questions and the fields in the structured medical record is known, and the answers corresponding to the target diagnosis and treatment questions are obtained in the reference medical record based on the mapping relation between the target diagnosis and treatment questions and the fields in the structured medical record. And writing the target diagnosis and treatment questions and the corresponding answers into corresponding fields in the template medical record, thereby obtaining the simulated medical record.
Here, the diagnosis and treatment problem set shown in fig. 3 is taken as an example:
if a target diagnosis and treatment question is "whether other diseases exist before", the target diagnosis and treatment question and an admission record, a past history, a disease and a disease name "field in the structured medical record have a mapping relationship. Therefore, the data of the field of the admission record, the past history, the disease and the disease name in the reference medical record is obtained, the data comprises the diagnosis and treatment questions and corresponding answers, and the answers in the data are further obtained, namely the answers corresponding to the target diagnosis and treatment questions. And writing the target diagnosis and treatment question whether other diseases exist before and the corresponding answers into an admission record, a past history, a disease and a disease name field in the template medical record.
If a plurality of target diagnosis and treatment questions exist, answers corresponding to the target diagnosis and treatment questions are sequentially obtained from the reference medical records, and the target diagnosis and treatment questions and the corresponding answers are written into corresponding fields in the template medical records to obtain the simulated medical records.
It should be noted that, the simulated medical record generated based on the method disclosed by the application is mainly used for carrying out inquiry and teaching in the aspect of physical examination on the teaching object, so that the simulated medical record contains diagnosis and treatment questions and corresponding answers.
In addition, considering that a real medical record often includes inquiry data, examination data and diagnosis data, optionally, on the basis of the obtained simulated medical record, the following steps may be set: one or more of the test data, the inspection data, and the diagnostic data are obtained, and the obtained data are written into the simulated medical record.
In implementation, the test data, the inspection data and the diagnosis data in the reference medical record can be acquired, and the acquired data is written into the simulation medical record.
According to the method for generating the simulated medical record, a diagnosis and treatment problem set is constructed in advance for each disease in each department, and each diagnosis and treatment problem in the diagnosis and treatment problem set is pre-constructed with a mapping relation with fields in the structured medical record; after obtaining a diagnosis and treatment problem request carrying identification of a target department and a target disease, obtaining a target diagnosis and treatment problem set corresponding to the target department and the target disease from a pre-constructed diagnosis and treatment problem set, outputting the target diagnosis and treatment problem set, then taking the selected diagnosis and treatment problem in the diagnosis and treatment problem set as a target diagnosis and treatment problem, obtaining an answer corresponding to the target diagnosis and treatment problem from a reference medical record based on a mapping relation between the target diagnosis and treatment problem and a field in a structured medical record, and writing the target diagnosis and treatment problem and the corresponding answer into corresponding fields in a template medical record to obtain a simulated medical record.
It can be seen that, based on the method disclosed in the application, the user only needs to determine the target department and the target disease according to the teaching requirement, and select the target diagnosis and treatment problem in the target diagnosis and treatment problem set corresponding to the target department and the target disease, and the electronic device can quickly generate the simulation model meeting the teaching requirement based on the reference medical record and the mapping relation between the diagnosis and treatment problem and the fields in the structured medical record.
In the technical scheme disclosed in the application, diagnosis and treatment problem sets are built in advance for a plurality of diseases in a plurality of departments in a hospital. The following describes a scheme for constructing a diagnosis and treatment problem set in advance.
Referring to fig. 2, fig. 2 is a flow chart of a method of pre-building a problem set as disclosed herein. The method comprises the following steps:
step S201: and acquiring historical diagnosis and treatment data.
And acquiring diagnosis and treatment data (namely historical diagnosis and treatment data) generated in the actual diagnosis and treatment process by a doctor from the existing actual diagnosis and treatment case. The diagnosis and treatment data comprise diagnosis and treatment questions and corresponding answers, and in addition, the diagnosis and treatment data can be divided into inquiry type and investigation type.
In practice, the historical diagnosis and treatment data can be acquired by adopting a web crawler technology. Referring to fig. 4-1, fig. 4-1 shows a portion of historical diagnostic data.
Step S202: and cleaning the historical diagnosis and treatment data.
In one possible implementation, the cleaning of the historical diagnosis and treatment data includes:
a1: performing word segmentation processing on the historical diagnosis and treatment data to obtain a first word segmentation result;
a2: if at least one word in the first word segmentation result belongs to a medical knowledge base, a synonym dictionary of the medical knowledge base or a preset high-frequency medical vocabulary, the historical diagnosis and treatment data are reserved, and otherwise, the historical diagnosis and treatment data are deleted.
That is, the whole of the history diagnosis and treatment data is washed one by one. The method comprises the steps of performing word segmentation on a piece of historical diagnosis and treatment data to obtain word segmentation results, and marking the word segmentation results as first word segmentation results for convenience in description; and then judging whether at least one word in the first word segmentation result belongs to a medical knowledge base, a synonym dictionary of the medical knowledge base or a preset high-frequency medical vocabulary, if one or more words in the first word segmentation result belong to the medical knowledge base, the synonym dictionary of the medical knowledge base or the preset high-frequency medical vocabulary, retaining the historical diagnosis and treatment data, and if the words in the first word segmentation result do not belong to the medical knowledge base, the synonym dictionary of the medical knowledge base or the preset high-frequency medical vocabulary, deleting the historical diagnosis and treatment data.
This is described in connection with fig. 4-1 to 4-5.
The acquired historical diagnosis and treatment data are shown in the figure 4-1. The historical diagnosis and treatment data shown in fig. 4-1 are subjected to word segmentation, and the obtained word segmentation result is shown in fig. 4-2. Comparing the word segmentation result of the historical diagnosis and treatment data shown in fig. 4-2 with the medical knowledge base and the synonym dictionary of the medical knowledge base, and if any one or more word segments in the word segmentation result of the historical diagnosis and treatment data belong to the medical knowledge base or the synonym dictionary of the medical knowledge base, reserving the historical diagnosis and treatment data, as shown in fig. 4-3. Comparing the word segmentation result of the historical diagnosis and treatment data shown in fig. 4-2 with a preset high-frequency medical vocabulary, and if any one or more word segments in the word segmentation result of the historical diagnosis and treatment data belong to the preset high-frequency medical vocabulary, reserving the historical diagnosis and treatment data. The result of cleaning the historical diagnosis and treatment data shown in fig. 4-1 is obtained by combining fig. 4-3 and fig. 4-4, as shown in fig. 4-5.
Of course, other schemes can be adopted to clean the historical diagnosis and treatment data, so long as the cleaned historical diagnosis and treatment data is guaranteed to be directly related to the diagnosis and treatment process.
Step S203: and classifying the cleaned historical diagnosis and treatment data. The type of the historical diagnosis and treatment data comprises inquiry and physical examination.
In one possible implementation, classifying the washed historical diagnostic data includes:
b1: if the cleaned historical diagnosis and treatment data comprises words or inquiry keywords corresponding to the symptom ontology, determining that the cleaned historical diagnosis and treatment data is of an inquiry type;
b2: if the cleaned historical diagnosis and treatment data comprises words corresponding to the part body, determining that the cleaned historical diagnosis and treatment data is of a check type.
Referring to fig. 5 and 6, fig. 5 shows a sample of a partial body, and fig. 6 shows a sample of a partial body. The inquiry keywords are words which are obtained by counting a large amount of inquiry data and have higher use frequency in the inquiry process. For example, the query keywords include, but are not limited to: age, sex, etc. It should be noted that if the diagnosis and treatment question does not have a corresponding answer, the diagnosis and treatment question is not of the inquiry type. The partial results of classifying the washed historic diagnosis and treatment data shown in fig. 4 to 5 are shown in fig. 7.
Step S204: and performing similarity normalization processing on the cleaned historical diagnosis and treatment data to obtain standardized historical diagnosis and treatment data.
Similar historical diagnosis and treatment data may exist in the cleaned historical diagnosis and treatment data, and if a plurality of similar historical diagnosis and treatment data are reserved, data redundancy is caused, so that similarity normalization processing is performed on the cleaned historical diagnosis and treatment data, and the purpose of the similarity normalization processing is to process the similar historical diagnosis and treatment data into one piece of standardized historical diagnosis and treatment data.
The diagnosis and treatment data includes a consultation type and a physical examination type, and correspondingly, the history diagnosis and treatment data after cleaning also includes a consultation type and a physical examination type. The similarity normalization processing is required to be performed on the data belonging to the inquiry type in the cleaned historical diagnosis and treatment data, and the similarity normalization processing is required to be performed on the data belonging to the query type in the cleaned historical diagnosis and treatment data.
In one possible implementation manner, the similarity normalization processing is performed on the cleaned historical diagnosis and treatment data, and includes:
c1: and determining the similarity between the historical diagnosis and treatment data belonging to the same type in the cleaned historical diagnosis and treatment data.
In implementation, word segmentation processing is respectively carried out on a plurality of pieces of history diagnosis and treatment data belonging to the same type in the cleaned history diagnosis and treatment data to obtain word segmentation results of each piece of history diagnosis and treatment data, similarity characteristic values of all the words in the word segmentation results are determined, and then similarity among the history diagnosis and treatment data is determined by utilizing the similarity characteristic values of all the words in the word segmentation results based on a cosine similarity principle.
Optionally, the similarity feature value of the word segmentation is word frequency (TF). The TF of a word is: the number of times the word appears in the document divided by the total number of words in the document. Alternatively, the TF of a word is: the number of occurrences of the word in the document divided by the number of occurrences of the word having the greatest number of occurrences in the document.
Optionally, the similarity feature value of the segmentation is TF minus IDF. If a word appears in N documents, the greater the value of N, the smaller the weight of the word, and correspondingly, the smaller the value of N, the greater the weight of the word. Inverse Document Frequency (IDF) for a word=log (total number of documents of corpus/total number of documents containing the word+1).
C2: and carrying out normalization processing on a plurality of pieces of washed historical diagnosis and treatment data with the similarity reaching a preset similarity threshold value, and generating a piece of standardized historical diagnosis and treatment data.
If the similarity between the plurality of pieces of washed historical diagnosis and treatment data reaches a preset similarity threshold (for example, 70%), normalization processing is required to be performed on the plurality of pieces of historical diagnosis and treatment data, and a piece of standardized historical diagnosis and treatment data is generated.
In implementation, if the plurality of pieces of cleaned historical diagnosis and treatment data to be subjected to normalization processing are of a consultation type, the historical diagnosis and treatment data are segmented, synonym conversion is performed on segmentation results, and an adverb dictionary and a synonym dictionary are used for conversion, so that standardized historical diagnosis and treatment data are obtained. Referring to fig. 8, fig. 8 shows the question and answer after washing and the result of normalization processing.
If the plurality of pieces of washed historical diagnosis and treatment data to be subjected to normalization processing are of a check type, the historical diagnosis and treatment data are converted according to the synonym dictionary of the body part, and standardized historical diagnosis and treatment data are obtained. Referring to fig. 9, fig. 9 shows the result of the normalization processing of the volume data after washing.
Step S205: determining corresponding fields of the standardized historical diagnosis and treatment data in the structured medical record, and establishing a mapping relation between diagnosis and treatment problems and the fields in the standardized historical diagnosis and treatment data.
In one possible implementation, determining a field corresponding to standardized historical medical data in a structured medical record includes:
d1: and respectively determining the association weights between the standardized historical diagnosis and treatment data and each field in the structured medical record.
D2: and determining the field with the highest association weight as the field corresponding to the standardized historical diagnosis and treatment data in the structured medical record.
And (3) representing the association weight between each field in the standardized historical diagnosis and treatment data and the structured medical record: the correlation between the standardized historical diagnosis and treatment data and the fields in the structured medical record is high or low. And determining the association weight between each field in the standardized historical diagnosis and treatment data and the structured medical record according to each standardized historical diagnosis and treatment data, and then determining the field with the highest association weight as the field corresponding to the standardized historical diagnosis and treatment data in the structured medical record.
It should be noted that the structured medical record includes a structured field and an unstructured field.
Optionally, determining the association weight between the standardized historical diagnosis and treatment data and the structured fields in the structured medical record, and adopting the following scheme:
Extracting keywords in a Chinese name path of the structured field; performing word segmentation on diagnosis and treatment problems in the standardized historical diagnosis and treatment data to obtain word segmentation results; and matching the keyword and the word segmentation result to obtain a matching result, and generating an association weight according to the matching result.
The number of the keywords and the matched words in the word segmentation result and the value of the association weight form a positive correlation relation. That is, the more words that match in the keyword and the word segmentation result, the greater the association weight between the standardized historical diagnosis and treatment data and the structured field.
Referring to fig. 10, fig. 10 shows the word segmentation result of the diagnosis and treatment problem in the standardized historical diagnosis and treatment data and the keywords in the chinese name path of the structured field.
Optionally, if the standardized historical diagnosis and treatment data is of a consultation type, determining an association weight between the standardized historical diagnosis and treatment data and a structured field in the structured medical record, and adopting the following scheme:
extracting keywords in a Chinese name path of the structured field; the diagnosis and treatment problems (particularly, inquiry problems) in the standardized historical diagnosis and treatment data are segmented to obtain a segmentation result; matching the keyword and the word segmentation result to obtain a first matching result, and generating a first association weight according to the first matching result;
Counting the value domain of the structured field, matching the distribution condition of the value domain with the word distribution condition of the word segmentation result of the diagnosis and treatment problem in the standardized historical diagnosis and treatment data to obtain a second matching result, and generating a second association weight according to the second matching result;
and taking the sum of the first association weight and the second association weight as the association weight between the standardized historical diagnosis and treatment data and the structured fields in the structured medical record.
And the matching degree of the second matching result and the value of the second association weight form a positive correlation relation. That is, the higher the matching degree between the value domain distribution condition of the structured field and the word distribution condition of the word segmentation result of the diagnosis and treatment problem, the larger the value of the second association weight.
Optionally, determining the association weight between the standardized historical diagnosis and treatment data and the unstructured field in the structured medical record adopts the following scheme:
performing word segmentation on one complaint and five histories in the admission record of the history medical record, performing normalization on the word segmentation result, and counting the distribution situation of high-frequency words in the word segmentation result after normalization; performing word segmentation processing on the standardized historical diagnosis and treatment data, and counting the word distribution condition of word segmentation results; and matching the two distribution conditions to obtain a matching result, and generating an association weight according to the matching result. The matching degree of the distribution condition of the high-frequency words and the distribution condition of the words of the word segmentation result and the association weight form a positive correlation relation.
Step S206: and determining departments and diseases corresponding to the diagnosis and treatment problems in the standardized historical diagnosis and treatment data.
In one possible implementation, determining departments and diseases corresponding to diagnosis and treatment problems in standardized historical diagnosis and treatment data includes:
e1: and determining a department corresponding to the diagnosis and treatment problem in the standardized historical diagnosis and treatment data according to the field corresponding to the standardized historical diagnosis and treatment data in the structured medical record.
The corresponding relation between the fields in the structured medical record and the departments is determined, and the departments corresponding to the diagnosis and treatment problems in the standardized historical diagnosis and treatment data can be determined according to the corresponding fields and the corresponding relation of the standardized historical diagnosis and treatment data in the structured medical record.
It should be noted that, some fields in the structured medical record are set as common fields, such as fields related to age and gender are set as common fields. If the standardized historical medical data corresponds to a common field in the structured medical record, the standardized historical medical data is common data for each department, that is, the medical questions in the standardized historical medical data correspond to all departments.
E2: performing word segmentation processing on the standardized historical diagnosis and treatment data to obtain a second word segmentation result, determining the similarity between the second word segmentation result and medical keywords of each disease in a department, and determining the disease with the highest similarity as the disease corresponding to the diagnosis and treatment problem in the standardized historical diagnosis and treatment data.
A plurality of diseases are arranged under each department, and after the department corresponding to the diagnosis and treatment problem in the standardized historical diagnosis and treatment data is determined, the diseases corresponding to the diagnosis and treatment problem also need to be further determined. Each disease has the characteristics, and the medical keywords are different, so that according to the word segmentation result of the standardized historical diagnosis and treatment data and the similarity of the medical keywords of a plurality of diseases in the department, the diagnosis and treatment problem in the standardized historical diagnosis and treatment data can be determined to correspond to which disease in the department.
Step S207: and adding the diagnosis and treatment problems into a diagnosis and treatment problem set constructed by the corresponding departments and diseases.
After the department and the diseases corresponding to the diagnosis and treatment problems are determined, the diagnosis and treatment problems are added into a diagnosis and treatment problem set corresponding to the department and the diseases.
According to the scheme shown in fig. 2, after the electronic equipment acquires the historical diagnosis and treatment data, the electronic equipment cleans the historical diagnosis and treatment data after cleaning, classifies the historical diagnosis and treatment data after cleaning, and performs similarity normalization processing on the historical diagnosis and treatment data after cleaning, so that the similar historical diagnosis and treatment data in the same class are processed into standardized historical diagnosis and treatment data, then corresponding fields of the standardized historical diagnosis and treatment data in the structured medical record are determined, mapping relations between diagnosis and treatment problems in the standardized historical diagnosis and treatment data and the fields are established, departments and diseases corresponding to the diagnosis and treatment problems in the standardized historical diagnosis and treatment data are determined, diagnosis and treatment problems are added into diagnosis and treatment problem sets corresponding to the corresponding departments and diseases, and accordingly construction of diagnosis and treatment problem sets corresponding to the diseases in each department is completed.
The application discloses a method for generating the simulated medical record and correspondingly, a device for generating the simulated medical record. The descriptions of the two in the specification can be referred to each other.
Referring to fig. 11, fig. 11 is a schematic structural diagram of an apparatus for generating a simulated medical record disclosed in the present application. The device comprises:
a reference medical record obtaining unit 1101 is configured to obtain a reference medical record.
The request obtaining unit 1102 is configured to obtain a diagnosis and treatment question request, where the diagnosis and treatment question request carries an identifier of a target department and a target disease.
The target diagnosis and treatment problem set obtaining unit 1103 is configured to obtain a target diagnosis and treatment problem set corresponding to the target department and the target disease from diagnosis and treatment problem sets pre-constructed for each disease in each department, and output the target diagnosis and treatment problem set. Each diagnosis and treatment problem in the diagnosis and treatment problem set is pre-constructed with a mapping relation with fields in the structured medical record.
The target diagnosis and treatment problem obtaining unit 1104 is configured to take the selected diagnosis and treatment problem in the target diagnosis and treatment problem set as a target diagnosis and treatment problem.
The diagnosis and treatment answer obtaining unit 1105 is configured to obtain an answer corresponding to the target diagnosis and treatment question in the reference medical record based on the mapping relationship between the target diagnosis and treatment question and the fields in the structured medical record.
The data processing unit 1106 is configured to write the target diagnosis and treatment question and the corresponding answer into the corresponding field in the template medical record, so as to obtain a simulated medical record.
According to the device for generating the simulated medical record, a diagnosis and treatment problem set is constructed in advance for each disease in each department, and each diagnosis and treatment problem in the diagnosis and treatment problem set is pre-constructed with a mapping relation with fields in the structured medical record; after obtaining a diagnosis and treatment problem request carrying identification of a target department and a target disease, obtaining a target diagnosis and treatment problem set corresponding to the target department and the target disease from a pre-constructed diagnosis and treatment problem set, outputting the target diagnosis and treatment problem set, then taking the selected diagnosis and treatment problem in the diagnosis and treatment problem set as a target diagnosis and treatment problem, obtaining an answer corresponding to the target diagnosis and treatment problem from a reference medical record based on a mapping relation between the target diagnosis and treatment problem and a field in a structured medical record, and writing the target diagnosis and treatment problem and the corresponding answer into corresponding fields in a template medical record to obtain a simulated medical record.
It can be seen that, based on the device for generating a simulated medical record disclosed by the application, a user only needs to determine a target department and a target disease according to teaching requirements and select a target diagnosis and treatment problem in a target diagnosis and treatment problem set corresponding to the target department and the target disease, and the device can quickly generate a simulation model meeting the teaching requirements based on a mapping relation between a reference medical record, a pre-constructed diagnosis and treatment problem and fields in a structured medical record.
In another embodiment, on the basis of the apparatus shown in fig. 11, a preprocessing unit is further provided, where the preprocessing unit is configured to pre-construct a diagnosis and treatment problem set for each disease under each department.
Optionally, the preprocessing unit includes:
the historical diagnosis and treatment data acquisition subunit is used for acquiring historical diagnosis and treatment data;
the data cleaning subunit is used for cleaning the historical diagnosis and treatment data;
the diagnosis and treatment data classification subunit is used for classifying the cleaned historical diagnosis and treatment data, and the types of the historical diagnosis and treatment data comprise inquiry and examination;
the normalization processing subunit is used for performing similarity normalization processing on the cleaned historical diagnosis and treatment data to obtain standardized historical diagnosis and treatment data;
the mapping relation processing subunit is used for determining the corresponding field of the standardized historical diagnosis and treatment data in the structured medical record and establishing the mapping relation between the diagnosis and treatment problems in the standardized historical diagnosis and treatment data and the field;
the department and disease determination subunit is used for determining departments and diseases corresponding to the diagnosis and treatment problems in the standardized historical diagnosis and treatment data;
the diagnosis and treatment problem processing subunit is used for adding the diagnosis and treatment problems into a diagnosis and treatment problem set constructed by a corresponding department and a disease.
Optionally, the data cleaning subunit cleans the historical diagnosis and treatment data, specifically:
performing word segmentation processing on the historical diagnosis and treatment data to obtain a first word segmentation result;
if at least one word in the first word segmentation result belongs to a medical knowledge base, a synonym dictionary of the medical knowledge base or a preset high-frequency medical vocabulary, the historical diagnosis and treatment data are reserved, and otherwise, the historical diagnosis and treatment data are deleted.
Optionally, the diagnosis and treatment data classification subunit classifies the cleaned historical diagnosis and treatment data, specifically:
if the cleaned historical diagnosis and treatment data comprises words or inquiry keywords corresponding to the symptom ontology, determining that the cleaned historical diagnosis and treatment data is of an inquiry type;
if the cleaned historical diagnosis and treatment data comprises words corresponding to the part body, determining that the cleaned historical diagnosis and treatment data is of a check type.
Optionally, the normalization processing subunit performs similarity normalization processing on the cleaned historical diagnosis and treatment data to obtain standardized historical diagnosis and treatment data, which specifically includes:
determining the similarity between the historical diagnosis and treatment data belonging to the same type in the cleaned historical diagnosis and treatment data;
and carrying out normalization processing on a plurality of pieces of washed historical diagnosis and treatment data with the similarity reaching a preset similarity threshold value, and generating a piece of standardized historical diagnosis and treatment data.
Optionally, the mapping relation processing subunit determines a field corresponding to the standardized historical diagnosis and treatment data in the structured medical record, specifically:
respectively determining the association weights between the standardized historical diagnosis and treatment data and each field in the structured medical record;
and determining the field with the highest association weight as the field corresponding to the standardized historical diagnosis and treatment data in the structured medical record.
Optionally, the department and disease determining subunit determines a department and a disease corresponding to the diagnosis and treatment problem in the standardized historical diagnosis and treatment data, specifically:
determining a department corresponding to the diagnosis and treatment problem in the standardized historical diagnosis and treatment data according to the corresponding field of the standardized historical diagnosis and treatment data in the structured medical record;
performing word segmentation processing on the standardized historical diagnosis and treatment data to obtain a second word segmentation result, determining the similarity between the second word segmentation result and medical keywords of each disease in a department, and determining the disease with the highest similarity as the disease corresponding to the diagnosis and treatment problem in the standardized historical diagnosis and treatment data.
The application also provides electronic equipment. Referring to fig. 12, fig. 12 shows a hardware structure of an electronic device, which may include: at least one processor 1201, at least one communication interface 1202, at least one memory 1203, and at least one communication bus 1204.
In the embodiment of the present application, the number of the processor 1201, the communication interface 1202, the memory 1203, and the communication bus 1204 is at least one, and the processor 1201, the communication interface 1202, and the memory 1203 complete communication with each other through the communication bus 1204.
The processor 1201 may be a Central Processing Unit (CPU), or a specific integrated circuit (asic) ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention, or the like.
The memory 1203 may include a high speed RAM memory, and may also include a non-volatile memory (non-volatile memory) or the like, such as at least one disk memory.
Wherein the memory stores a program, the processor is operable to invoke the program stored in the memory, the program operable to:
obtaining a reference medical record;
obtaining a diagnosis and treatment problem request, wherein the diagnosis and treatment problem request carries identification of a target department and a target disease;
obtaining a target diagnosis and treatment problem set corresponding to the target department and the target disease in a diagnosis and treatment problem set pre-constructed for each disease in each department, and outputting the target diagnosis and treatment problem set; each diagnosis and treatment problem in the diagnosis and treatment problem set is pre-established with a mapping relation with fields in the structured medical record;
Taking the selected diagnosis and treatment problem in the target diagnosis and treatment problem set as a target diagnosis and treatment problem;
acquiring an answer corresponding to the target diagnosis and treatment problem from the reference medical record based on the mapping relation between the target diagnosis and treatment problem and the fields in the structured medical record;
and writing the target diagnosis and treatment questions and the corresponding answers into corresponding fields in the template medical record to obtain the simulated medical record.
Alternatively, the refinement function and the extension function of the program may be described with reference to the above.
The present application also provides a readable storage medium storing a program adapted to be executed by a processor, the program being configured to:
obtaining a reference medical record;
obtaining a diagnosis and treatment problem request, wherein the diagnosis and treatment problem request carries identification of a target department and a target disease;
obtaining a target diagnosis and treatment problem set corresponding to the target department and the target disease in a diagnosis and treatment problem set pre-constructed for each disease in each department, and outputting the target diagnosis and treatment problem set; each diagnosis and treatment problem in the diagnosis and treatment problem set is pre-established with a mapping relation with fields in the structured medical record;
taking the selected diagnosis and treatment problem in the target diagnosis and treatment problem set as a target diagnosis and treatment problem;
Acquiring an answer corresponding to the target diagnosis and treatment problem from the reference medical record based on the mapping relation between the target diagnosis and treatment problem and the fields in the structured medical record;
and writing the target diagnosis and treatment questions and the corresponding answers into corresponding fields in the template medical record to obtain the simulated medical record.
Alternatively, the refinement function and the extension function of the program may be described with reference to the above.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. The apparatus, the electronic device, the server and the storage medium disclosed in the embodiments correspond to the method disclosed in the embodiments, so that the description is simpler, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing is merely a preferred embodiment of the present application and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present application and are intended to be comprehended within the scope of the present application.

Claims (10)

1. A method of generating a simulated medical record, comprising:
obtaining a reference medical record;
obtaining a diagnosis and treatment problem request, wherein the diagnosis and treatment problem request carries identification of a target department and a target disease;
obtaining a target diagnosis and treatment problem set corresponding to the target department and the target disease in a diagnosis and treatment problem set pre-constructed for each disease in each department, and outputting the target diagnosis and treatment problem set; each diagnosis and treatment problem in the diagnosis and treatment problem set is pre-established with a mapping relation with fields in the structured medical record;
taking the selected diagnosis and treatment problem in the target diagnosis and treatment problem set as a target diagnosis and treatment problem;
acquiring an answer corresponding to the target diagnosis and treatment problem from the reference medical record based on the mapping relation between the target diagnosis and treatment problem and the fields in the structured medical record;
and writing the target diagnosis and treatment questions and the corresponding answers into corresponding fields in the template medical record to obtain the simulated medical record.
2. The method of claim 1, wherein pre-constructing a solution to the set of medical problems comprises:
acquiring historical diagnosis and treatment data;
cleaning the historical diagnosis and treatment data;
Classifying the cleaned historical diagnosis and treatment data, wherein the types of the historical diagnosis and treatment data comprise inquiry and examination;
performing similarity normalization processing on the cleaned historical diagnosis and treatment data to obtain standardized historical diagnosis and treatment data;
determining a field corresponding to the standardized historical diagnosis and treatment data in the structured medical record, and establishing a mapping relation between diagnosis and treatment problems in the standardized historical diagnosis and treatment data and the field;
determining departments and diseases corresponding to diagnosis and treatment problems in the standardized historical diagnosis and treatment data;
and adding the diagnosis and treatment problems into a diagnosis and treatment problem set constructed by corresponding departments and diseases.
3. The method of claim 2, wherein the cleaning the historical diagnostic data comprises:
performing word segmentation processing on the historical diagnosis and treatment data to obtain a first word segmentation result;
if at least one word in the first word segmentation result belongs to a medical knowledge base, a synonym dictionary of the medical knowledge base or a preset high-frequency medical vocabulary, the historical diagnosis and treatment data are reserved, and otherwise, the historical diagnosis and treatment data are deleted.
4. The method of claim 2, wherein classifying the post-cleaning historical diagnostic data comprises:
If the cleaned historical diagnosis and treatment data comprises words or inquiry keywords corresponding to symptom bodies, determining that the cleaned historical diagnosis and treatment data is of an inquiry type;
and if the cleaned historical diagnosis and treatment data comprises words corresponding to the part body, determining that the cleaned historical diagnosis and treatment data is of a query type.
5. The method according to claim 2, wherein the performing similarity normalization processing on the cleaned historical diagnosis and treatment data to obtain standardized historical diagnosis and treatment data includes:
determining the similarity between the historical diagnosis and treatment data belonging to the same type in the cleaned historical diagnosis and treatment data;
and carrying out normalization processing on a plurality of pieces of washed historical diagnosis and treatment data with the similarity reaching a preset similarity threshold value, and generating a piece of standardized historical diagnosis and treatment data.
6. The method of claim 2, wherein the determining a corresponding field of the standardized historical diagnostic data in the structured medical record comprises:
respectively determining the association weights between the standardized historical diagnosis and treatment data and each field in the structured medical record;
and determining the field with the highest association weight as the field corresponding to the standardized historical diagnosis and treatment data in the structured medical record.
7. The method of claim 2, wherein the determining departments and diseases corresponding to the diagnosis and treatment questions in the standardized historical diagnosis and treatment data comprises:
determining a department corresponding to the diagnosis and treatment problem in the standardized historical diagnosis and treatment data according to a field corresponding to the standardized historical diagnosis and treatment data in the structured medical record;
and performing word segmentation processing on the standardized historical diagnosis and treatment data to obtain a second word segmentation result, determining the similarity between the second word segmentation result and medical keywords of each disease in the department, and determining the disease with the highest similarity as the disease corresponding to the diagnosis and treatment problem in the standardized historical diagnosis and treatment data.
8. An apparatus for generating a simulated medical record, comprising:
a reference medical record acquisition unit for acquiring a reference medical record;
the request acquisition unit is used for acquiring a diagnosis and treatment problem request, wherein the diagnosis and treatment problem request carries the identification of a target department and a target disease;
a target diagnosis and treatment problem set acquisition unit, configured to obtain a target diagnosis and treatment problem set corresponding to the target department and the target disease from diagnosis and treatment problem sets pre-constructed for each disease in each department, and output the target diagnosis and treatment problem set; each diagnosis and treatment problem in the diagnosis and treatment problem set is pre-established with a mapping relation with fields in the structured medical record;
The target diagnosis and treatment problem acquisition unit is used for taking the selected diagnosis and treatment problem in the target diagnosis and treatment problem set as a target diagnosis and treatment problem;
a diagnosis and treatment answer obtaining unit, configured to obtain an answer corresponding to the target diagnosis and treatment question in the reference medical record based on a mapping relationship between the target diagnosis and treatment question and a field in the structured medical record;
and the data processing unit is used for writing the target diagnosis and treatment questions and the corresponding answers into corresponding fields in the template medical record to obtain the simulated medical record.
9. An electronic device comprising a processor, a memory, and a communication interface;
the memory is used for storing programs;
the processor being configured to execute the program to perform the steps of the method of generating a simulated medical record as claimed in any one of claims 1 to 7.
10. A readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of generating a simulated medical record according to any of claims 1 to 7.
CN202011253477.2A 2020-11-11 2020-11-11 Method, device, electronic equipment and storage medium for generating simulated medical record Active CN112349367B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011253477.2A CN112349367B (en) 2020-11-11 2020-11-11 Method, device, electronic equipment and storage medium for generating simulated medical record

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011253477.2A CN112349367B (en) 2020-11-11 2020-11-11 Method, device, electronic equipment and storage medium for generating simulated medical record

Publications (2)

Publication Number Publication Date
CN112349367A CN112349367A (en) 2021-02-09
CN112349367B true CN112349367B (en) 2023-08-08

Family

ID=74363332

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011253477.2A Active CN112349367B (en) 2020-11-11 2020-11-11 Method, device, electronic equipment and storage medium for generating simulated medical record

Country Status (1)

Country Link
CN (1) CN112349367B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113571167B (en) * 2021-07-28 2024-04-19 重庆橡树信息科技有限公司 Rapid triage system based on configuration type grading knowledge model
CN113792129B (en) * 2021-09-16 2024-06-14 联通在线信息科技有限公司 Intelligent session method, device, computer equipment and medium

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101236579A (en) * 2008-02-20 2008-08-06 杭州创业软件股份有限公司 Dynamic structured electronic patient history
WO2016101351A1 (en) * 2014-12-26 2016-06-30 深圳市前海安测信息技术有限公司 Network hospital based general practitioner auxiliary diagnosis and treatment system and method
CN109710670A (en) * 2018-12-11 2019-05-03 河南通域医疗科技有限公司 A method of case history text is converted into structural metadata from natural language
CN111292817A (en) * 2018-12-07 2020-06-16 深圳坐标软件集团有限公司 Electronic medical record generation method and device
CN111429989A (en) * 2020-04-21 2020-07-17 北京嘉和海森健康科技有限公司 Method and device for generating pre-diagnosis medical record
CN111696640A (en) * 2020-06-12 2020-09-22 上海联影医疗科技有限公司 Method, device and storage medium for automatically acquiring medical record template
CN111739599A (en) * 2020-06-19 2020-10-02 北京嘉和海森健康科技有限公司 Method and device for generating teaching medical record
CN111755109A (en) * 2020-05-14 2020-10-09 中山大学孙逸仙纪念医院 Diagnosis and treatment follow-up system
CN111833977A (en) * 2020-07-17 2020-10-27 成都市妇女儿童中心医院 Intelligent hospital digitalized electronic medical record and scientific research and teaching integrated system

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8900141B2 (en) * 2006-02-17 2014-12-02 Medred, Llc Integrated method and system for diagnosis determination

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101236579A (en) * 2008-02-20 2008-08-06 杭州创业软件股份有限公司 Dynamic structured electronic patient history
WO2016101351A1 (en) * 2014-12-26 2016-06-30 深圳市前海安测信息技术有限公司 Network hospital based general practitioner auxiliary diagnosis and treatment system and method
CN111292817A (en) * 2018-12-07 2020-06-16 深圳坐标软件集团有限公司 Electronic medical record generation method and device
CN109710670A (en) * 2018-12-11 2019-05-03 河南通域医疗科技有限公司 A method of case history text is converted into structural metadata from natural language
CN111429989A (en) * 2020-04-21 2020-07-17 北京嘉和海森健康科技有限公司 Method and device for generating pre-diagnosis medical record
CN111755109A (en) * 2020-05-14 2020-10-09 中山大学孙逸仙纪念医院 Diagnosis and treatment follow-up system
CN111696640A (en) * 2020-06-12 2020-09-22 上海联影医疗科技有限公司 Method, device and storage medium for automatically acquiring medical record template
CN111739599A (en) * 2020-06-19 2020-10-02 北京嘉和海森健康科技有限公司 Method and device for generating teaching medical record
CN111833977A (en) * 2020-07-17 2020-10-27 成都市妇女儿童中心医院 Intelligent hospital digitalized electronic medical record and scientific research and teaching integrated system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
李昆.基于电子病历的深度神经网络预测模型研究与应用.《中国优秀硕士学位论文全文数据库 (医药卫生科技辑)》.2017,(第11期),E053-34. *

Also Published As

Publication number Publication date
CN112349367A (en) 2021-02-09

Similar Documents

Publication Publication Date Title
Moradi et al. Deep contextualized embeddings for quantifying the informative content in biomedical text summarization
CN106874643B (en) Method and system for automatically constructing knowledge base to realize auxiliary diagnosis and treatment based on word vectors
Shin et al. Classification of radiology reports using neural attention models
JP7357614B2 (en) Machine-assisted dialogue system, medical condition interview device, and method thereof
CN111429989B (en) Method and device for generating pre-diagnosis medical record
CN112349367B (en) Method, device, electronic equipment and storage medium for generating simulated medical record
US11170895B2 (en) Olfactory cognitive diagnosis
CN112201350A (en) Intelligent triage method and device and electronic equipment
Liu et al. Knowledge-aware deep dual networks for text-based mortality prediction
Athira et al. Annotating and detecting topics in social media forum and modelling the annotation to derive directions-a case study
Banerjee et al. A scalable machine learning approach for inferring probabilistic US-LI-RADS categorization
CN110199354B (en) Biological system information retrieval system and method
CN114300127A (en) Method, device, equipment and storage medium for inquiry processing
Zhou et al. Converting semi-structured clinical medical records into information and knowledge
Wang et al. Research on named entity recognition of doctor-patient question answering community based on bilstm-crf model
Batool et al. Automatic extraction and mapping of discharge summary’s concepts into SNOMED CT
Hao et al. A substring replacement approach for identifying missing IS-A relations in SNOMED CT
Saba et al. Question-Answering Based Summarization of Electronic Health Records using Retrieval Augmented Generation
CN106354715A (en) Method and device for medical word processing
Sabra et al. Performance evaluation for semantic-based risk factors extraction from clinical narratives
Ghoulam et al. Using local grammar for entity extraction from clinical reports
Zhang et al. Medical Q&A statement NER based on ECA attention mechanism and lexical enhancement
CN113314236A (en) Intelligent question-answering system for hypertension
Yu et al. Identifying causal effects of the clinical sentiment of patients' nursing notes on anticipated fall risk stratification
Bagheri Text mining in healthcare: bringing structure to electronic health records

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant