CN110853716A - Medical record template creating method and device - Google Patents
Medical record template creating method and device Download PDFInfo
- Publication number
- CN110853716A CN110853716A CN201910891498.8A CN201910891498A CN110853716A CN 110853716 A CN110853716 A CN 110853716A CN 201910891498 A CN201910891498 A CN 201910891498A CN 110853716 A CN110853716 A CN 110853716A
- Authority
- CN
- China
- Prior art keywords
- medical record
- clauses
- clause
- text
- category
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000012545 processing Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 201000010099 disease Diseases 0.000 description 4
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 230000007721 medicinal effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000035606 childbirth Effects 0.000 description 1
- 210000001072 colon Anatomy 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000005906 menstruation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- 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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention relates to a method and a device for creating a medical record template, wherein the method comprises the following steps: acquiring a text set corresponding to a medical record; for each text in the text set, identifying keywords in the text that are relevant to the medical record; and creating a medical record template corresponding to the medical record according to the keywords. Therefore, the time for creating the medical records can be shortened, the time and the energy of medical staff are saved, and meanwhile, the information is effectively prevented from being missed, so that the accurate and complete medical records with normativity are created.
Description
Technical Field
The embodiment of the invention relates to the technical field of template creation, in particular to a method and a device for creating a medical record template.
Background
The medical records are records of medical personnel on the processes of medical activities such as occurrence, development, outcome, examination, diagnosis, treatment and the like of diseases of patients, and have important functions in the aspects of medical treatment, prevention, teaching, scientific research, hospital management and the like.
Currently, medical records are written manually by medical personnel, and the method for creating the medical records has the following defects: first, manually writing medical records takes a great deal of time and effort on the part of medical personnel; secondly, information is inevitable to be missed when medical staff manually write medical records; thirdly, medical records written by different medical staff have different styles, and even under the same condition, descriptions in different medical records are often different, so that the existing medical records have no normalization and are difficult to support subsequent requirements, such as scenes related to artificial intelligence.
Disclosure of Invention
In view of this, to solve the above technical problem or some technical problems, embodiments of the present invention provide a method and an apparatus for creating a medical record template, so as to shorten the time for creating a medical record, save time and energy of medical staff, and effectively avoid missing and missing information, thereby creating an accurate and complete medical record with normativity.
In a first aspect, an embodiment of the present invention provides a method for creating a medical record template, including:
acquiring a text set corresponding to a medical record;
for each text in the text set, identifying keywords in the text that are relevant to the medical record;
and creating a medical record template corresponding to the medical record according to the keywords.
In a possible embodiment, the acquiring a text set corresponding to a medical record includes:
acquiring a plurality of electronic medical records;
extracting a target text from each electronic medical record;
and forming a text set corresponding to the medical record by all the extracted target texts.
In one possible embodiment, the identifying keywords in the text that are related to the medical record includes:
carrying out sentence splitting on the text to obtain a plurality of clauses;
clustering the plurality of clauses, wherein the editing distance similarity between different clauses in the same category is greater than a preset threshold value;
and aiming at each category, carrying out named entity identification on each clause in the category to obtain keywords related to the medical record.
In a possible embodiment, the sentence splitting the text into a plurality of clauses includes:
carrying out sentence splitting on the text to obtain a plurality of sentences, and determining the field to which each sentence belongs;
and splitting the sentence according to a heuristic rule corresponding to the field of the sentence to obtain a plurality of clauses, and adding a medical record id and a field name of the field of the sentence to each clause.
In one possible embodiment, the clustering the plurality of clauses includes:
classifying the clauses according to the field names to obtain a plurality of clause sets, wherein the clauses in the same clause set have the same field names;
for each clause set, selecting clauses which do not belong to any category from the clause sets as current clauses;
calculating the editing distance similarity between the current clause and other clauses which do not belong to any category, and if the editing distance similarity is larger than a preset threshold, classifying the other clauses and the current clause into the same category; and returning to the step of selecting clauses which do not belong to any category from the clause set as the current clause.
In a possible embodiment, the creating a medical record template corresponding to the medical record according to the keyword includes:
labeling the keywords in each clause in the category to obtain a plurality of initial templates;
carrying out duplicate removal processing on the plurality of initial templates;
and creating a medical record template according to the initial template subjected to the duplicate removal processing.
In a second aspect, an embodiment of the present invention provides an apparatus for creating a medical record template, including:
the acquisition module is used for acquiring a text set corresponding to the medical record;
the identification module is used for identifying keywords related to the medical record in the text aiming at each text in the text set;
and the creating module is used for creating a medical record template corresponding to the medical record according to the keywords.
In one possible embodiment, the obtaining module includes:
the medical record acquisition sub-module is used for acquiring a plurality of electronic medical records;
the text extraction sub-module is used for extracting a target text from the electronic medical records aiming at each electronic medical record;
and the set composition module is used for composing all the extracted target texts into a text set corresponding to the medical record.
In one possible embodiment, the identification module comprises:
the first splitting submodule is used for carrying out sentence splitting on the text to obtain a plurality of clauses;
the clustering submodule is used for clustering the plurality of clauses, wherein the editing distance similarity between different clauses in the same category is greater than a preset threshold value;
and the named entity identification submodule is used for carrying out named entity identification on each clause in each category according to each category to obtain keywords related to the medical record.
In one possible embodiment, the first splitting sub-module includes:
the second splitting submodule is used for carrying out sentence splitting on the text to obtain a plurality of sentences and determining the field to which each sentence belongs;
and the third splitting submodule is used for splitting each sentence according to a heuristic rule corresponding to the field to which the sentence belongs to obtain a plurality of clauses, and adding a medical record id and the field name of the field to which the sentence belongs to each clause.
In one possible embodiment, the clustering submodule includes:
the classification submodule is used for classifying the clauses according to the field names to obtain a plurality of clause sets, wherein the clauses in the same clause set have the same field names;
the selection submodule is used for selecting clauses which do not belong to any category from the clause sets as current clauses aiming at each clause set;
the calculation submodule is used for calculating the editing distance similarity between the current clause and other clauses which do not belong to any category, and if the editing distance similarity is larger than a preset threshold value, the other clauses and the current clause are classified into the same category; and returning to execute the step of selecting clauses which do not belong to any category from the clause set and are executed by the selection submodule as the current clause.
In one possible embodiment, the creating a template includes:
the marking submodule is used for marking the keywords in each clause in the category to obtain a plurality of initial templates;
the duplication removing submodule is used for carrying out duplication removing processing on the plurality of initial templates;
and the template creating submodule is used for creating a medical record template according to the initial template after the duplication removing processing.
According to the method for creating the medical record template, the text set corresponding to the medical record is obtained, the keywords related to the medical record in the text are identified aiming at each text in the text set, and the medical record template corresponding to the medical record is created according to the keywords, so that the medical record can be generated according to the medical record template in a plurality of scenes, the medical record creating time can be shortened, the time and the energy of medical staff can be saved, meanwhile, the information is effectively prevented from being missed, and the medical record with accuracy, completeness and standardization can be created.
Drawings
Fig. 1 is a flowchart of an embodiment of a method for creating a medical record template according to an exemplary embodiment of the present invention;
FIG. 2 is an example of an electronic medical record;
FIG. 3 is an example of a medical record template;
fig. 4 is a flowchart of an embodiment of a medical record template creation method according to another exemplary embodiment of the present invention;
FIG. 5 is an example of a sentence resulting from sentence splitting a text;
FIG. 6 is an example of a clause resulting from splitting the sentence illustrated in FIG. 5;
FIG. 7 is an example of a clustering result of the clause illustrated in FIG. 6;
FIG. 8 is an example of an initial template;
FIG. 9 is an example of the initial template illustrated in FIG. 8 after deduplication processing;
fig. 10 is a block diagram of an embodiment of a medical record template creation apparatus according to an exemplary embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
For the convenience of understanding of the embodiments of the present invention, the following description will be further explained with reference to specific embodiments, which are not to be construed as limiting the embodiments of the present invention.
Referring to fig. 1, a flowchart of an embodiment of a method for creating a medical record template according to an exemplary embodiment of the present invention is provided, where the method includes the following steps:
step 101: and acquiring a text set corresponding to the medical record.
In the embodiment of the present invention, a plurality of electronic medical records can be acquired from an existing medical record management system, for example, as shown in fig. 2, which is an example of an electronic medical record. And subsequently, aiming at each electronic medical record, extracting target texts from the electronic medical record, and forming a text set corresponding to the medical record by all the extracted target texts.
As an example, the electronic medical record can be divided into a structured portion and an unstructured portion, for example, as shown in FIG. 2, wherein the portion illustrated by numeral 21 is a structured portion and the portion illustrated by numeral 22 is an unstructured portion. As can be understood by those skilled in the art, in the electronic medical record, the unstructured part describes the process of medical activities such as occurrence, development, regression, examination, diagnosis, treatment and the like of a disease of a patient, and the unstructured part is difficult to write, occupies a great deal of time and energy of medical staff, so that the unstructured part can be determined as a target text.
Step 102: for each text in the text collection, keywords in the text that are relevant to the medical record are identified.
In the embodiment of the present invention, keywords related to medical records in each text in the text set can be identified based on the medical knowledge graph, and the keywords related to medical records may include: diseases, causes, disorders, parts, drugs, examinations, treatment procedures, etc., while time-type keywords, as well as numeric-type keywords, may also be identified in each text in the text collection based on regular expressions.
In the embodiment of the present invention, the keywords related to the medical record, the keywords of the time type, and the keywords of the number type may be collectively regarded as the keywords related to the medical record.
How to identify the keywords related to the medical record in each text in the text set is described below, and will not be described in detail here.
Step 103: and creating a medical record template corresponding to the medical record according to the keywords.
In an embodiment of the present invention, a medical record template corresponding to the medical record can be created according to the keywords related to the medical record identified in step 102, for example, as shown in fig. 3, which is an example of the medical record template.
According to the embodiment, the text set corresponding to the medical records is obtained, the keywords related to the medical records in the text are identified for each text in the text set, the medical record template corresponding to the medical records is created according to the keywords, and the medical records can be generated according to the medical record templates in a plurality of scenes, so that the medical record creation time can be shortened, the time and the energy of medical staff are saved, meanwhile, the information can be effectively prevented from being missed, and the accurate and complete medical records are created.
So far, the description about the flowchart shown in fig. 1 is completed.
Next, a flowchart illustrated in fig. 4 is shown, and step 102 and step 103 in the flowchart illustrated in fig. 1 are described in detail, where the flowchart illustrated in fig. 4 includes the following steps:
step 401: and carrying out sentence splitting on the text to obtain a plurality of clauses.
In this step, firstly, a sentence is split into a plurality of sentences, and a field to which each sentence belongs is determined.
As an example, as shown in fig. 2, the above-mentioned belonging field may be one of the following: chief complaints, current medical history, past history, personal history, menstruation, marriage and childbirth history and family history.
As an example, the medical record id and the field name of the field to which it belongs may also be added in each sentence. For example, as shown in fig. 5, an example of a sentence obtained by sentence splitting a text is shown.
Next, aiming at each sentence, splitting the sentence according to a heuristic rule corresponding to the field of the sentence to obtain a plurality of clauses, and adding a medical record id and the field name of the field of the sentence to each clause. For example, if the field of the sentence is "present medical history", the sentence can be split using comma, colon, and semicolon to obtain a plurality of clauses; if the field of the sentence is "past history", the sentence can be split by using commas to obtain a plurality of clauses. For example, as shown in fig. 6, an example of a clause obtained by splitting the sentence illustrated in fig. 5 is shown.
Step 402: and clustering a plurality of clauses, wherein the editing distance similarity between different clauses in the same category is greater than a preset threshold value.
In this step, a plurality of clauses are first classified according to field names to obtain a plurality of clause sets, wherein the clauses in the same clause set have the same field names.
And secondly, classifying the clauses in the clause set according to the editing distance similarity aiming at each clause set. As an example, the classification process may be: selecting clauses which do not belong to any category from the clause set as current clauses, calculating the editing distance similarity between the current clauses and other clauses which do not belong to any category, and if the editing distance similarity is larger than a preset threshold, classifying the other clauses and the current clauses into the same category; and returning to the step of selecting clauses which do not belong to any category from the clause set as the current clause until each clause in the clause set is classified.
As an example, a classification label may be added to a clause in each classification, for example, the initial value of the classification label is "1", after the other clauses and the current clause are classified into the same classification, the current classification label is added with 1, and a classification label of the next classification is obtained, for example, as shown in fig. 7, the classification label is an example of the clustering result of the clause illustrated in fig. 6;
it will be appreciated by those skilled in the art that through the above processing, the semantics of clauses in the same category can be made more similar.
Step 403: and aiming at each category, carrying out named entity identification on each clause in the category to obtain keywords related to the medical record.
As an example, a named entity vocabulary may be derived based on a medical knowledge graph, which may include 7 concepts of disease, etiology, disorder, location, drug, examination, and treatment. And for each clause, marking out the named entities in the clause, namely keywords related to medical records, by inquiring the word list of the named entities, and meanwhile, marking out the named entities of the numeric class and the time class in the clause based on a pre-compiled regular expression, wherein the named entities of the numeric class and the time class can also be regarded as the keywords related to the medical records.
Step 404: and creating a medical record template corresponding to the medical record according to the keywords.
In this step, terms are replaced for the keywords in each clause, so that an initial template can be obtained, for example, as shown in fig. 8, which is an example of the initial template.
Next, a plurality of the initial templates obtained in the foregoing are subjected to a deduplication process, that is, duplicate initial templates are removed, for example, the first row and the second row in fig. 8 are duplicated, and then one of the duplicate initial templates is removed, for example, as shown in fig. 9, which is an example of the original template illustrated in fig. 8 after being subjected to the deduplication process.
Finally, a medical record template, such as the medical record template illustrated in fig. 3, can be created according to the initial template after the deduplication process.
So far, the description about the flowchart shown in fig. 4 is completed.
Corresponding to the method for creating the medical record template, the invention also provides a device for creating the medical record template.
As shown in fig. 10, a block diagram of an embodiment of an apparatus for creating a medical record template according to an exemplary embodiment of the present invention includes: an acquisition module 101, a recognition module 102, and a creation module 103.
The acquiring module 101 is configured to acquire a text set corresponding to a medical record;
the identification module 102 is configured to identify, for each text in the text set, a keyword in the text that is related to the medical record;
and the creating module 103 is configured to create a medical record template corresponding to the medical record according to the keyword.
In an embodiment, the acquisition module 101 comprises (not shown in fig. 10):
the medical record acquisition sub-module is used for acquiring a plurality of electronic medical records;
the text extraction sub-module is used for extracting a target text from the electronic medical records aiming at each electronic medical record;
and the set composition module is used for composing all the extracted target texts into a text set corresponding to the medical record.
In one embodiment, the identification module 102 includes (not shown in fig. 10):
the first splitting submodule is used for carrying out sentence splitting on the text to obtain a plurality of clauses;
the clustering submodule is used for clustering the plurality of clauses, wherein the editing distance similarity between different clauses in the same category is greater than a preset threshold value;
and the named entity identification submodule is used for carrying out named entity identification on each clause in each category according to each category to obtain keywords related to the medical record.
In an embodiment, the first split sub-module comprises (not shown in fig. 10):
the second splitting submodule is used for carrying out sentence splitting on the text to obtain a plurality of sentences and determining the field to which each sentence belongs;
and the third splitting submodule is used for splitting each sentence according to a heuristic rule corresponding to the field to which the sentence belongs to obtain a plurality of clauses, and adding a medical record id and the field name of the field to which the sentence belongs to each clause.
In an embodiment, the clustering submodule comprises (not shown in fig. 10):
the classification submodule is used for classifying the clauses according to the field names to obtain a plurality of clause sets, wherein the clauses in the same clause set have the same field names;
the selection submodule is used for selecting clauses which do not belong to any category from the clause sets as current clauses aiming at each clause set;
the calculation submodule is used for calculating the editing distance similarity between the current clause and other clauses which do not belong to any category, and if the editing distance similarity is larger than a preset threshold value, the other clauses and the current clause are classified into the same category; and returning to execute the step of selecting clauses which do not belong to any category from the clause set and are executed by the selection submodule as the current clause.
In one embodiment, the creation template 103 includes (not shown in fig. 10):
the marking submodule is used for marking the keywords in each clause in the category to obtain a plurality of initial templates;
the duplication removing submodule is used for carrying out duplication removing processing on the plurality of initial templates;
and the template creating submodule is used for creating a medical record template according to the initial template after the duplication removing processing.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, a software module executed by a processor, or a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (12)
1. A method for creating a medical record template is characterized by comprising the following steps:
acquiring a text set corresponding to a medical record;
for each text in the text set, identifying keywords in the text that are relevant to the medical record;
and creating a medical record template corresponding to the medical record according to the keywords.
2. The method of claim 1, wherein the obtaining a text set corresponding to the medical record comprises:
acquiring a plurality of electronic medical records;
extracting a target text from each electronic medical record;
and forming a text set corresponding to the medical record by all the extracted target texts.
3. The method of claim 1, wherein the identifying keywords in the text that are relevant to the medical record comprises:
carrying out sentence splitting on the text to obtain a plurality of clauses;
clustering the plurality of clauses, wherein the editing distance similarity between different clauses in the same category is greater than a preset threshold value;
and aiming at each category, carrying out named entity identification on each clause in the category to obtain keywords related to the medical record.
4. The method of claim 3, wherein the sentence splitting of the text into a plurality of clauses comprises:
carrying out sentence splitting on the text to obtain a plurality of sentences, and determining the field to which each sentence belongs;
and splitting the sentence according to a heuristic rule corresponding to the field of the sentence to obtain a plurality of clauses, and adding a medical record id and a field name of the field of the sentence to each clause.
5. The method of claim 3, wherein clustering the plurality of clauses comprises:
classifying the clauses according to the field names to obtain a plurality of clause sets, wherein the clauses in the same clause set have the same field names;
for each clause set, selecting clauses which do not belong to any category from the clause sets as current clauses;
calculating the editing distance similarity between the current clause and other clauses which do not belong to any category, and if the editing distance similarity is larger than a preset threshold, classifying the other clauses and the current clause into the same category; and returning to the step of selecting clauses which do not belong to any category from the clause set as the current clause.
6. The method according to claim 3, wherein the creating a medical record template corresponding to the medical record according to the keyword comprises:
labeling the keywords in each clause in the category to obtain a plurality of initial templates;
carrying out duplicate removal processing on the plurality of initial templates;
and creating a medical record template according to the initial template subjected to the duplicate removal processing.
7. An apparatus for creating a medical record template, comprising:
the acquisition module is used for acquiring a text set corresponding to the medical record;
the identification module is used for identifying keywords related to the medical record in the text aiming at each text in the text set;
and the creating module is used for creating a medical record template corresponding to the medical record according to the keywords.
8. The apparatus of claim 7, wherein the obtaining module comprises:
the medical record acquisition sub-module is used for acquiring a plurality of electronic medical records;
the text extraction sub-module is used for extracting a target text from the electronic medical records aiming at each electronic medical record;
and the set composition module is used for composing all the extracted target texts into a text set corresponding to the medical record.
9. The apparatus of claim 7, wherein the identification module comprises:
the first splitting submodule is used for carrying out sentence splitting on the text to obtain a plurality of clauses;
the clustering submodule is used for clustering the plurality of clauses, wherein the editing distance similarity between different clauses in the same category is greater than a preset threshold value;
and the named entity identification submodule is used for carrying out named entity identification on each clause in each category according to each category to obtain keywords related to the medical record.
10. The apparatus of claim 9, wherein the first split sub-module comprises:
the second splitting submodule is used for carrying out sentence splitting on the text to obtain a plurality of sentences and determining the field to which each sentence belongs;
and the third splitting submodule is used for splitting each sentence according to a heuristic rule corresponding to the field to which the sentence belongs to obtain a plurality of clauses, and adding a medical record id and the field name of the field to which the sentence belongs to each clause.
11. The apparatus of claim 9, wherein the clustering submodule comprises:
the classification submodule is used for classifying the clauses according to the field names to obtain a plurality of clause sets, wherein the clauses in the same clause set have the same field names;
the selection submodule is used for selecting clauses which do not belong to any category from the clause sets as current clauses aiming at each clause set;
the calculation submodule is used for calculating the editing distance similarity between the current clause and other clauses which do not belong to any category, and if the editing distance similarity is larger than a preset threshold value, the other clauses and the current clause are classified into the same category; and returning to execute the step of selecting clauses which do not belong to any category from the clause set and are executed by the selection submodule as the current clause.
12. The apparatus of claim 9, wherein the creating a template comprises:
the marking submodule is used for marking the keywords in each clause in the category to obtain a plurality of initial templates;
the duplication removing submodule is used for carrying out duplication removing processing on the plurality of initial templates;
and the template creating submodule is used for creating a medical record template according to the initial template after the duplication removing processing.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910891498.8A CN110853716B (en) | 2019-09-19 | 2019-09-19 | Medical record template creation method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910891498.8A CN110853716B (en) | 2019-09-19 | 2019-09-19 | Medical record template creation method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110853716A true CN110853716A (en) | 2020-02-28 |
CN110853716B CN110853716B (en) | 2024-06-11 |
Family
ID=69594857
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910891498.8A Active CN110853716B (en) | 2019-09-19 | 2019-09-19 | Medical record template creation method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110853716B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111967238A (en) * | 2020-09-03 | 2020-11-20 | 卫宁健康科技集团股份有限公司 | Medical record template knowledge base and construction method and construction device thereof |
CN113377928A (en) * | 2021-08-11 | 2021-09-10 | 明品云(北京)数据科技有限公司 | Text recommendation method, system, device and medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103020453A (en) * | 2012-12-15 | 2013-04-03 | 中国科学院深圳先进技术研究院 | Generation method of structured electronic medical record based on ontology technology |
CN103365912A (en) * | 2012-04-06 | 2013-10-23 | 富士通株式会社 | Method and device for clustering and extracting entity relationship modes |
CN108153734A (en) * | 2017-12-26 | 2018-06-12 | 北京嘉和美康信息技术有限公司 | A kind of text handling method and device |
CN109192255A (en) * | 2018-07-03 | 2019-01-11 | 北京康夫子科技有限公司 | Case history structural method |
CN109522338A (en) * | 2018-11-09 | 2019-03-26 | 天津开心生活科技有限公司 | Clinical term method for digging, device, electronic equipment and computer-readable medium |
US20190243841A1 (en) * | 2018-02-06 | 2019-08-08 | Thomson Reuters (Professional) UK Ltd. | Systems and method for generating a structured report from unstructured data |
-
2019
- 2019-09-19 CN CN201910891498.8A patent/CN110853716B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103365912A (en) * | 2012-04-06 | 2013-10-23 | 富士通株式会社 | Method and device for clustering and extracting entity relationship modes |
CN103020453A (en) * | 2012-12-15 | 2013-04-03 | 中国科学院深圳先进技术研究院 | Generation method of structured electronic medical record based on ontology technology |
CN108153734A (en) * | 2017-12-26 | 2018-06-12 | 北京嘉和美康信息技术有限公司 | A kind of text handling method and device |
US20190243841A1 (en) * | 2018-02-06 | 2019-08-08 | Thomson Reuters (Professional) UK Ltd. | Systems and method for generating a structured report from unstructured data |
CN109192255A (en) * | 2018-07-03 | 2019-01-11 | 北京康夫子科技有限公司 | Case history structural method |
CN109522338A (en) * | 2018-11-09 | 2019-03-26 | 天津开心生活科技有限公司 | Clinical term method for digging, device, electronic equipment and computer-readable medium |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111967238A (en) * | 2020-09-03 | 2020-11-20 | 卫宁健康科技集团股份有限公司 | Medical record template knowledge base and construction method and construction device thereof |
CN111967238B (en) * | 2020-09-03 | 2023-11-14 | 卫宁健康科技集团股份有限公司 | Medical record template knowledge base construction method, medical system and construction device thereof |
CN113377928A (en) * | 2021-08-11 | 2021-09-10 | 明品云(北京)数据科技有限公司 | Text recommendation method, system, device and medium |
CN113377928B (en) * | 2021-08-11 | 2022-05-27 | 明品云(北京)数据科技有限公司 | Text recommendation method, system, device and medium |
Also Published As
Publication number | Publication date |
---|---|
CN110853716B (en) | 2024-06-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107562732B (en) | Method and system for processing electronic medical record | |
CN106407443B (en) | Method and device for generating structured medical data | |
CN109344250B (en) | Rapid structuring method of single disease diagnosis information based on medical insurance data | |
CN110931128B (en) | Method, system and device for automatically identifying unsupervised symptoms of unstructured medical texts | |
JP2022546593A (en) | Automated information extraction and refinement within pathology reports using natural language processing | |
US10157176B2 (en) | Information processing apparatus and display method | |
CN110853716B (en) | Medical record template creation method and device | |
CN110851506B (en) | Clinical big data searching method and device, storage medium and server | |
CN114065756A (en) | Method and device for extracting positive symptoms of electronic medical record | |
CN111177309A (en) | Medical record data processing method and device | |
CN114021563A (en) | Method, device, equipment and storage medium for extracting data in medical information | |
CN112071431B (en) | Clinical path automatic generation method and system based on deep learning and knowledge graph | |
CN110069614A (en) | A kind of question and answer exchange method and device | |
US20170220550A1 (en) | Information processing apparatus and registration method | |
CN113111660A (en) | Data processing method, device, equipment and storage medium | |
US20230377697A1 (en) | System and a way to automatically monitor clinical trials - virtual monitor (vm) and a way to record medical history | |
CN112053760B (en) | Medication guide method, medication guide device, and computer-readable storage medium | |
US11899692B2 (en) | Database reduction based on geographically clustered data to provide record selection for clinical trials | |
Baghal et al. | Agile natural language processing model for pathology knowledge extraction and integration with clinical enterprise data warehouse | |
CN112101034A (en) | Method and device for distinguishing attribute of medical entity and related product | |
CN111326262B (en) | Entity relation extraction method, device and system in electronic medical record data | |
CN114154502B (en) | Word segmentation method and device for medical text, computer equipment and storage medium | |
CN111415751B (en) | Topic segmentation method, device and system for electronic medical record data | |
CN111079420B (en) | Text recognition method and device, computer readable medium and electronic equipment | |
AU2021106441A4 (en) | Method, System and Device for Extracting Compound Words of Pathological location in Medical Texts Based on Word-Formation |
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 |