CN115392249B - Medical record structuring system and method - Google Patents
Medical record structuring system and method Download PDFInfo
- Publication number
- CN115392249B CN115392249B CN202210837076.4A CN202210837076A CN115392249B CN 115392249 B CN115392249 B CN 115392249B CN 202210837076 A CN202210837076 A CN 202210837076A CN 115392249 B CN115392249 B CN 115392249B
- Authority
- CN
- China
- Prior art keywords
- medical
- information
- module
- text
- entities
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 17
- 238000000605 extraction Methods 0.000 claims abstract description 51
- 230000002776 aggregation Effects 0.000 claims abstract description 41
- 238000004220 aggregation Methods 0.000 claims abstract description 41
- 230000004931 aggregating effect Effects 0.000 claims abstract description 38
- 235000019580 granularity Nutrition 0.000 claims abstract description 26
- 239000012634 fragment Substances 0.000 claims abstract description 23
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000012546 transfer Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 abstract description 10
- 238000010586 diagram Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000014509 gene expression Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000008929 regeneration Effects 0.000 description 2
- 238000011069 regeneration method Methods 0.000 description 2
- 230000009897 systematic effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Classifications
-
- 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
- G06F40/295—Named entity recognition
-
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
- 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)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a system and a method for structuring medical records. The system comprises a nested entity identification module, a relation extraction module, an event identification module and an event attribute and relation extraction module; wherein: the nested entity identification module is used for acquiring medical information entities with different granularities by adopting a SPAN model; the relation extraction module is used for determining the relation between the medical information entities; the event recognition module is used for extracting text fragments in the medical text information, aggregating the text fragments, extracting medical record text information and obtaining aggregation information; the event attribute and relation extraction module is used for aggregating the aggregation information to obtain an event map. Therefore, the events and the relationships among the events are obtained from unstructured medical record texts, layered processing is carried out, and medical entities, entity relationships and final events and event relationships are obtained step by step.
Description
Technical Field
The invention relates to the technical field of Internet, in particular to a method and a system for structuring medical records.
Background
Medical history is a data of great value that contains a true record of medical clinical practice. However, the clinical medical record is written in natural language, which is unfavorable for direct large-scale data statistics. The clinical history needs to be structured.
The structuring technology currently exists: and (5) completely and manually reading the medical record and filling in a report. Requiring a great deal of labor and time. Semi-artificial regular expressions and keywords. That is, for the fields of the required data report, rules are defined using regular expressions or keyword matching. The problem with this approach is the lack of versatility, requiring regeneration every field or different disease species. Named Entity Recognition (NER) technology is based, but lacks a subsequent systematic processing approach to the results of NER.
Disclosure of Invention
According to the invention, a system and a method for structuring medical records are provided to solve the existing structuring technology: and (5) completely and manually reading the medical record and filling in a report. Requiring a great deal of labor and time. Semi-artificial regular expressions and keyword methods lack versatility and require regeneration every field or different disease species. Named Entity Recognition (NER) based techniques lack the technical problem of a subsequent systematic processing method of the results of the NER.
According to a first aspect of the present invention, there is provided a system for structuring medical records, the system comprising a nested entity identification module, a relationship extraction module, an event identification module, and an event attribute and relationship extraction module; wherein:
the nested entity identification module is used for acquiring medical information entities with different granularities by adopting a SPAN model;
the relation extraction module is used for determining the relation between the medical information entities;
the event recognition module is used for extracting text fragments in the medical text information, aggregating the text fragments, extracting medical record text information and obtaining aggregation information;
the event attribute and relation extraction module is used for aggregating the aggregation information to obtain an event map.
Optionally, the nested entity identification module is configured to acquire medical information with different granularities by adopting a SPAN-based model, including:
the nested entity recognition module is used for vectorizing the medical record text and extracting the characteristics according to the encoding module, and constructing N according to the decoding module 2 The matrix is combined with a multi-classifier to obtain medical information entities with different granularities.
Optionally, the relationship extraction module is configured to determine a relationship between the medical information entities, including:
the relation extraction module comprises a dependency relation extraction module and a medical relation extraction module;
the dependency relation extraction module is used for acquiring the relation between the medical information entities directly expressed on the medical record text by adopting a transfer-based mode;
the medical relation extraction module is used for acquiring the relation between abstract medical information entities.
Optionally, the event recognition module is configured to extract text segments in the medical text information and aggregate the text segments, and extract medical record text information, so as to obtain aggregate information, where the event recognition module includes:
the event recognition module is used for extracting text fragments in medical text information and aggregating according to a preset expert rule and a DNN text classification-based model, extracting medical record text information and obtaining aggregation information.
Optionally, the event attribute and relationship extraction module is configured to aggregate the aggregation information to obtain an event map, including:
the event attribute and relation extraction module is used for aggregating the aggregation information through a rule engine and an extracted document model to obtain an event map.
According to another aspect of the present invention, there is also provided an event map extraction method, including:
acquiring medical information entities with different granularities by adopting a SPAN model;
determining a relationship between the medical information entities;
according to the relation between the medical information entities, extracting text fragments in medical text information, aggregating, extracting medical record text information and obtaining aggregation information;
and aggregating the aggregation information to obtain an event map.
Optionally, obtaining medical information entities with different granularities by adopting a SPAN-based model includes:
and carrying out vectorization and feature extraction on the medical record text according to the coding module, constructing an N2 matrix according to the decoding module, and integrating a multi-classifier to obtain medical information entities with different granularities.
Optionally, determining the relationship between the medical information entities comprises:
acquiring the relationship between medical information entities directly expressed on a medical record text by adopting a transfer-based mode;
relationships between abstract medical information entities are obtained.
Optionally, according to the relationship between the medical information entities, extracting text segments in the medical text information and aggregating, and extracting medical record text information to obtain aggregated information, including:
and extracting text fragments in the medical text information and aggregating according to a preset expert rule and a DNN text classification-based model, and extracting medical record text information to obtain aggregation information.
Optionally, aggregating the aggregation information to obtain an event map, including:
and aggregating the aggregation information through a rule engine and a removable document model to obtain an event map.
Thereby, medical information entities with different granularities are acquired by adopting a SPAN model; determining a relationship between the medical information entities; according to the relation between the medical information entities, extracting text fragments in medical text information, aggregating, extracting medical record text information and obtaining aggregation information; and aggregating the aggregation information to obtain an event map. Therefore, the events and the relationships among the events are obtained from unstructured medical record texts, layered processing is carried out, and medical entities, entity relationships and final events and event relationships are obtained step by step.
Drawings
Exemplary embodiments of the present invention may be more completely understood in consideration of the following drawings:
FIG. 1 is a schematic diagram of a system framework for medical record structuring according to the present embodiment;
fig. 2 is a flow chart of a method for structuring medical records according to the present embodiment.
Detailed Description
The exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, however, the present invention may be embodied in many different forms and is not limited to the examples described herein, which are provided to fully and completely disclose the present invention and fully convey the scope of the invention to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the accompanying drawings is not intended to be limiting of the invention. In the drawings, like elements/components are referred to by like reference numerals.
Unless otherwise indicated, terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art. In addition, it will be understood that terms defined in commonly used dictionaries should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense.
According to a first aspect of the present invention, there is provided a system for structuring medical records, the system comprising a nested entity identification module, a relationship extraction module, an event identification module, and an event attribute and relationship extraction module; wherein:
the nested entity identification module is used for acquiring medical information entities with different granularities by adopting a SPAN model;
the relation extraction module is used for determining the relation between the medical information entities;
the event recognition module is used for extracting text fragments in the medical text information, aggregating the text fragments, extracting medical record text information and obtaining aggregation information;
the event attribute and relation extraction module is used for aggregating the aggregation information to obtain an event map.
Specifically, an "event map" is used as a generic layer. The medical record describes the complete passage of a patient visit, including complaints, medical history, admission and discharge records, calendar records, surgical records, diagnoses, inspection reports, orders, and the like, which are essentially a stream of events. There is a logical relationship between events. For example, a "diagnostic" event results in a "medication" event. The invention recovers the event stream and the relationship between the events in a structuring way.
In order to acquire the events and the relationships among the events from unstructured medical record texts, the system adopts a pipline mode to conduct layering processing, and medical entities, entity relationships and final events and event relationships are acquired gradually. Overall system frame diagram referring to fig. 1:
the specific explanation of each submodule is as follows:
the nested entity identification is realized by adopting a SPAN-based model for acquiring medical information with different granularities, and the model is mainly divided into two modules, namely an ENCODER module and a DECODER module. The encoding module realizes vectorization and feature extraction of the medical record text and mainly adopts a combined structure of Transform-encoding and CNN. By construction N in the DECODER stage 2 The matrix union integrates a multi-classifier to obtain entities with different granularities.
The dependency relation extraction module is used for obtaining the relation between the medical entities of the shallower layers directly expressed on the text, and is mainly realized by referring to the dependency syntax analysis task in the NLP and adopting a transfer-based mode. The model not only comprises a DNN-based classification module, but also comprises a stack and a list for supporting entity scheduling.
The medical relationship extraction module is similar to the dependency relationship extraction module, but is primarily used to obtain more abstract medical relationships. The algorithm in the module is mainly modified by PCNN model.
The event recognition module is used for finding and acquiring more specific and rich text fragments of information in the medical text, so that aggregation of the information and extraction of important information of medical record text are realized. The module is mainly implemented by adopting expert rules and a DNN text classification-based model.
And extracting the event attribute and the relationship, wherein the attribute and the relationship are extracted by further realizing information aggregation on the basis of event extraction, so as to obtain a final event map. The module is mainly implemented by a rule engine and a removable document model. Thereby, medical information entities with different granularities are acquired by adopting a SPAN model; determining a relationship between the medical information entities; according to the relation between the medical information entities, extracting text fragments in medical text information, aggregating, extracting medical record text information and obtaining aggregation information; and aggregating the aggregation information to obtain an event map. Therefore, the events and the relationships among the events are obtained from unstructured medical record texts, layered processing is carried out, and medical entities, entity relationships and final events and event relationships are obtained step by step.
Optionally, the nested entity identification module is configured to acquire medical information with different granularities by adopting a SPAN-based model, including:
the nested entity recognition module is used for vectorizing the medical record text and extracting the characteristics according to the encoding module, and constructing N according to the decoding module 2 The matrix is combined with a multi-classifier to obtain medical information entities with different granularities.
Optionally, the relationship extraction module is configured to determine a relationship between the medical information entities, including:
the relation extraction module comprises a dependency relation extraction module and a medical relation extraction module;
the dependency relation extraction module is used for acquiring the relation between the medical information entities directly expressed on the medical record text by adopting a transfer-based mode;
the medical relation extraction module is used for acquiring the relation between abstract medical information entities.
Optionally, the event recognition module is configured to extract text segments in the medical text information and aggregate the text segments, and extract medical record text information, so as to obtain aggregate information, where the event recognition module includes:
the event recognition module is used for extracting text fragments in medical text information and aggregating according to a preset expert rule and a DNN text classification-based model, extracting medical record text information and obtaining aggregation information.
Optionally, the event attribute and relationship extraction module is configured to aggregate the aggregation information to obtain an event map, including:
the event attribute and relation extraction module is used for aggregating the aggregation information through a rule engine and an extracted document model to obtain an event map.
Event maps are data models of results produced by on-demand production subsystems that aim to express medical record information to the greatest extent through structured form "maps". The main protection point is the schema design of the event map.
Thereby, medical information entities with different granularities are acquired by adopting a SPAN model; determining a relationship between the medical information entities; according to the relation between the medical information entities, extracting text fragments in medical text information, aggregating, extracting medical record text information and obtaining aggregation information; and aggregating the aggregation information to obtain an event map. Therefore, the events and the relationships among the events are obtained from unstructured medical record texts, layered processing is carried out, and medical entities, entity relationships and final events and event relationships are obtained step by step.
According to another aspect of the present invention, there is also provided a method 200 of structuring medical records, as shown with reference to fig. 2, the method 200 comprising:
s201, acquiring medical information entities with different granularities by adopting a SPAN model;
s202, determining the relation between the medical information entities;
s203, extracting text fragments in medical text information and aggregating according to the relation between the medical information entities, and extracting medical record text information to obtain aggregation information;
and S204, aggregating the aggregation information to obtain an event map.
Optionally, obtaining medical information entities with different granularities by adopting a SPAN-based model includes:
and carrying out vectorization and feature extraction on the medical record text according to the coding module, constructing an N2 matrix according to the decoding module, and integrating a multi-classifier to obtain medical information entities with different granularities.
Optionally, determining the relationship between the medical information entities comprises:
acquiring the relationship between medical information entities directly expressed on a medical record text by adopting a transfer-based mode;
relationships between abstract medical information entities are obtained.
Optionally, according to the relationship between the medical information entities, extracting text segments in the medical text information and aggregating, and extracting medical record text information to obtain aggregated information, including:
and extracting text fragments in the medical text information and aggregating according to a preset expert rule and a DNN text classification-based model, and extracting medical record text information to obtain aggregation information.
Optionally, aggregating the aggregation information to obtain an event map, including:
and aggregating the aggregation information through a rule engine and a removable document model to obtain an event map.
A method for structuring medical records according to an embodiment of the present invention corresponds to a system for structuring medical records according to another embodiment of the present invention, and is not described herein.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The solutions in the embodiments of the present application may be implemented in various computer languages, for example, object-oriented programming language Java, and an transliterated scripting language JavaScript, etc.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the spirit or scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims and the equivalents thereof, the present application is intended to cover such modifications and variations.
Claims (2)
1. A system for structuring medical records, which is characterized by comprising a nested entity identification module, a relation extraction module, an event identification module and an event attribute and relation extraction module; the method is characterized in that:
the nested entity identification module is used for acquiring medical information entities with different granularities by adopting a SPAN model;
the relation extraction module is used for determining the relation between the medical information entities;
the event recognition module is used for extracting text fragments in the medical text information, aggregating the text fragments, extracting medical record text information and obtaining aggregation information;
the event attribute and relation extraction module is used for aggregating the aggregation information to obtain an event map;
the nested entity identification module is used for acquiring medical information with different granularities by adopting a SPAN model, and comprises the following steps:
the nested entity recognition module is used for vectorizing the medical record text and extracting the characteristics according to the encoding module, and constructing N according to the decoding module 2 The matrix is combined with a multi-classifier to obtain medical information entities with different granularities;
the relationship extraction module is configured to determine a relationship between the medical information entities, and includes:
the relation extraction module comprises a dependency relation extraction module and a medical relation extraction module;
the dependency relation extraction module is used for acquiring the relation between the medical information entities directly expressed on the medical record text by adopting a transfer-based mode;
the medical relation extraction module is used for acquiring the relation between abstract medical information entities;
the event recognition module is used for extracting text fragments in medical text information and aggregating, extracting medical record text information and obtaining aggregated information, and comprises the following steps:
the event recognition module is used for extracting text fragments in medical text information and aggregating according to a preset expert rule and a DNN text classification-based model, extracting medical record text information and obtaining aggregation information;
the event attribute and relationship extraction module is configured to aggregate the aggregation information to obtain an event map, and includes:
the event attribute and relation extraction module is used for aggregating the aggregation information through a rule engine and an extracted document model to obtain an event map;
the SPAN model is divided into two modules, namely an ENCODER module and a DECODER module, the ENCODER module realizes vectorization and feature extraction of medical record texts, a Transform-encoding and CNN combined structure is adopted, and entities with different granularities are obtained simultaneously by constructing an N2 matrix and integrating a multi-classifier in the DECODER stage.
2. A method of structuring medical records, comprising:
acquiring medical information entities with different granularities by adopting a SPAN model;
determining a relationship between the medical information entities;
according to the relation between the medical information entities, extracting text fragments in medical text information, aggregating, extracting medical record text information and obtaining aggregation information;
the aggregation information is aggregated to obtain an event map;
obtaining medical information entities with different granularities by adopting a SPAN model, comprising:
vectorizing the medical record text and extracting features according to the coding module, constructing an N2 matrix according to the decoding module, and integrating a multi-classifier to obtain medical information entities with different granularities;
determining a relationship between the medical information entities, comprising:
acquiring the relationship between medical information entities directly expressed on a medical record text by adopting a transfer-based mode;
acquiring the relation between abstract medical information entities;
according to the relation between the medical information entities, extracting text fragments in medical text information, aggregating, extracting medical record text information, and obtaining aggregation information, wherein the method comprises the following steps:
according to a preset expert rule and a DNN text classification-based model, extracting text fragments in medical text information, aggregating, extracting medical record text information, and obtaining aggregation information;
aggregating the aggregation information to obtain an event map, including:
aggregating the aggregation information through a rule engine and a removable document model to obtain an event map;
the SPAN model is divided into two modules, namely an ENCODER module and a DECODER module, the ENCODER module realizes vectorization and feature extraction of medical record texts, a Transform-encoding and CNN combined structure is adopted, and entities with different granularities are obtained simultaneously by constructing an N2 matrix and integrating a multi-classifier in the DECODER stage.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210837076.4A CN115392249B (en) | 2022-07-15 | 2022-07-15 | Medical record structuring system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210837076.4A CN115392249B (en) | 2022-07-15 | 2022-07-15 | Medical record structuring system and method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115392249A CN115392249A (en) | 2022-11-25 |
CN115392249B true CN115392249B (en) | 2024-01-30 |
Family
ID=84115895
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210837076.4A Active CN115392249B (en) | 2022-07-15 | 2022-07-15 | Medical record structuring system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115392249B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106951438A (en) * | 2017-02-13 | 2017-07-14 | 北京航空航天大学 | A kind of event extraction system and method towards open field |
CN110990579A (en) * | 2019-10-30 | 2020-04-10 | 清华大学 | Cross-language medical knowledge graph construction method and device and electronic equipment |
CN113505244A (en) * | 2021-09-10 | 2021-10-15 | 中国人民解放军总医院 | Knowledge graph construction method, system, equipment and medium based on deep learning |
-
2022
- 2022-07-15 CN CN202210837076.4A patent/CN115392249B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106951438A (en) * | 2017-02-13 | 2017-07-14 | 北京航空航天大学 | A kind of event extraction system and method towards open field |
CN110990579A (en) * | 2019-10-30 | 2020-04-10 | 清华大学 | Cross-language medical knowledge graph construction method and device and electronic equipment |
CN113505244A (en) * | 2021-09-10 | 2021-10-15 | 中国人民解放军总医院 | Knowledge graph construction method, system, equipment and medium based on deep learning |
Non-Patent Citations (1)
Title |
---|
整合BiLSTM-CRF网络和词典资源的中文电子病历实体识别;李纲;潘荣清;毛进;操玉杰;;现代情报(第04期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN115392249A (en) | 2022-11-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107622103B (en) | Managing data queries | |
US8375061B2 (en) | Graphical models for representing text documents for computer analysis | |
US8065326B2 (en) | System and method for building decision trees in a database | |
US10339465B2 (en) | Optimized decision tree based models | |
US11861462B2 (en) | Preparing structured data sets for machine learning | |
Chung et al. | JackHare: a framework for SQL to NoSQL translation using MapReduce | |
US20150142821A1 (en) | Database system for analysis of longitudinal data sets | |
JP6416770B2 (en) | Interoperable case series system | |
Pita et al. | A Spark-based Workflow for Probabilistic Record Linkage of Healthcare Data. | |
CN111028952B (en) | Method and device for constructing Chinese medical implication knowledge graph | |
CN110945559B (en) | Method and system for optimizing visual summaries of a sequence of time event data | |
GB2507095A (en) | Generating synthetic data from a decision tree model of a dataset | |
CN112329857A (en) | Image classification method based on improved residual error network | |
CN112786215A (en) | Method and system for generating DIP comprehensive disease category catalog based on big data clustering | |
Győrödi et al. | A comparative study of MongoDB and document-based MySQL for big data application data management | |
Brahim et al. | Model Driven Extraction of NoSQL Databases Schema: Case of MongoDB. | |
Imam et al. | Dsp: Schema design for non-relational applications | |
CN115392249B (en) | Medical record structuring system and method | |
CN110321556A (en) | A kind of method and its system of doctor's diagnosis and treatment medical insurance control expense intelligent recommendation scheme | |
US20160004968A1 (en) | Correlation rule analysis apparatus and correlation rule analysis method | |
Satti et al. | Unsupervised semantic mapping for healthcare data storage schema | |
Hussain et al. | Semantic transformation model for clinical documents in big data to support healthcare analytics | |
US20070239794A1 (en) | Method and system for updating logical information in databases | |
Horita et al. | Analysis and identification of possible automation approaches for embedded systems design flows | |
Akulich et al. | Multiset-Trie Data Structure |
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 |