CN110277149A - Processing method, device and the equipment of electronic health record - Google Patents
Processing method, device and the equipment of electronic health record Download PDFInfo
- Publication number
- CN110277149A CN110277149A CN201910579541.7A CN201910579541A CN110277149A CN 110277149 A CN110277149 A CN 110277149A CN 201910579541 A CN201910579541 A CN 201910579541A CN 110277149 A CN110277149 A CN 110277149A
- Authority
- CN
- China
- Prior art keywords
- case history
- text
- medicine entity
- entity
- candidate
- 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.)
- Pending
Links
Classifications
-
- 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
- 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
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
Abstract
The invention proposes a kind of processing method of electronic health record, device and equipment, wherein method includes: to obtain case history text to be processed；Identify medicine entity and the attribute information in case history text；Determine the corresponding relationship between medicine entity and the attribute information；Structured patient record is generated according to corresponding relationship.As a result, by the attribute information of medical bodies and description medical bodies in identification electronic health record, and structured patient record is generated, meets the structuring demand to case history, improve efficiency, reduce costs.
Description
Technical field
The present invention relates to medical text-processing technical field more particularly to a kind of processing method of electronic health record, device and
Equipment.
Background technique
Case history as medical worker to the generation of patient disease, develop, lapse to, checked, diagnosed, being treated etc. that medical treatment is living
The record of dynamic process contains the information of a large amount of preciousnesses, and doctor can be helped to study occurrence regularity, improve treatment method, can be with
Help medicine enterprise research and development new drug, it might even be possible to help how medical treatment AI study diagnoses the illness.
With the development of hospital information, most of hospital is provided with HIS (management information system for hospitals) system, so that
The record of case history realizes electronization substantially.But since the writing style of different doctors, word mode have very big difference, no
It is constantly alternated using the version of different HIS system and HIS also with the time with hospital, causes electronic health record to be difficult wide
General utilization.Case history structuring is by analyzing and identifying the important information in case history, the weight of building description case history from many levels
Feature is wanted, finally by structureless case history natural language text, is converted into convenient for computer understanding (while also people being facilitated to understand)
Structured message.
In the related technology, it is usually extracted by important information of the healthcare givers to case history and structuring, efficiency is lower, people
Power is at high cost.
Summary of the invention
The present invention is directed to solve at least some of the technical problems in related technologies.
For this purpose, the first purpose of this invention is to propose a kind of processing method of electronic health record, pass through identification electronics disease
The attribute information of medical bodies and description medical bodies in going through, and structured patient record is generated, meet the structuring need to case history
It asks, improves efficiency, reduce costs.
Second object of the present invention is to propose a kind of processing unit of electronic health record.
Third object of the present invention is to propose a kind of computer equipment.
Fourth object of the present invention is to propose a kind of computer readable storage medium.
First aspect present invention embodiment proposes a kind of processing method of electronic health record, comprising:
Obtain case history text to be processed；
Identify the medicine entity and attribute information in the case history text；
Determine the corresponding relationship between the medicine entity and the attribute information；
Structured patient record is generated according to the corresponding relationship.
The processing method of the electronic health record of the embodiment of the present invention by obtaining case history text to be processed, and then identifies
Medicine entity and attribute information in case history text.Further determine that the corresponding pass between medicine entity and the attribute information
System generates structured patient record according to corresponding relationship.Thereby, it is possible to identify medical bodies and description medical bodies in electronic health record
Attribute information, and the expression of structuring improves efficiency, reduces costs, meet the structuring demand in practical application.It provides
The general understanding to electronic health record is as a result, cover the information such as most important medical bodies and attribute, Ke Yibang in case history
It helps the systems such as auxiliary diagnosis, case history retrieval to understand case history from semantic level, constructs the semantic feature of case history.
In addition, the processing method of electronic health record according to the above embodiment of the present invention can also have following supplementary technology special
Sign:
Optionally, the medicine entity identified in the case history text includes: to obtain preset medical vocabulary,
In, it include candidate medicine entity in the medical vocabulary；The candidate medicine entity is matched with the case history text, really
Medicine entity in the fixed case history text.
Optionally, the medicine entity identified in the case history text includes: by the case history text input in advance
It is first handled in trained sequence labelling model, obtains the entity markup information of the case history text；According to the entity mark
Note information determines the medicine entity in the case history text.
Optionally, the attribute information identified in the case history text includes: to obtain preset attribute vocabulary,
In, it include candidate attribute in the attribute vocabulary；The candidate attribute is matched with the case history text, determines the disease
Go through the attribute information in text.
Optionally, after determining the corresponding relationship between the medicine entity and the attribute information, further includes: obtain
The candidate categories of the medicine entity extract the medicine entity attributes for each candidate categories, by what is extracted respectively
Classification of the largest number of candidate categories of attribute as the medicine entity；And/or according to the medicine entity in the case history
Contextual information in text determines the classification of the medicine entity.
Optionally, acquisition case history text to be processed includes: to obtain plain text case history；According to preset field noun
Allusion quotation is matched with the plain text case history, determines the field name in the plain text case history；According to the field name from described
Field contents corresponding with the field name are determined in plain text case history, according to the field name and the field contents to described
Plain text case history carries out cutting.
Optionally, after determining the field name in the plain text case history, further includes: based on keyword match and/or
The field name is mapped as the field name of standard by semantic similarity model.
Optionally, after carrying out cutting to the plain text case history according to the field name and the field contents, also
Include: in the plain text case history after judging cutting whether absent field content；If so, being based on keyword match and/or text
Disaggregated model obtains the field contents of missing from the plain text case history；After the field contents of missing are added to the cutting
Plain text case history in aiming field name position.
Optionally, the method further include: subordinate sentence is carried out to the case history text, and according to preset rules from the disease
It goes through and determines candidate sentence in text；Output content corresponding with preset output title is extracted from the candidate sentence, according to described
It exports title and the output content generates the structured message of customization.
Second aspect of the present invention embodiment proposes a kind of processing unit of electronic health record, comprising:
Module is obtained, for obtaining case history text to be processed；
Identification module, for identification the medicine entity and attribute information in the case history text out；
Determining module, for determining the corresponding relationship between the medicine entity and the attribute information；
Generation module, for generating structured patient record according to the corresponding relationship.
The processing unit of the electronic health record of the embodiment of the present invention can identify the medical bodies in electronic health record and description doctor
Entity attributes information, and the expression of structuring are treated, improves efficiency, reduces costs, meet the structuring need in practical application
It asks.The general understanding to electronic health record is provided as a result, covering the information such as most important medical bodies and attribute in case history,
The systems such as auxiliary diagnosis, case history retrieval can be helped to understand case history from semantic level, construct the semantic feature of case history.
In addition, the processing unit of electronic health record according to the above embodiment of the present invention can also have following supplementary technology special
Sign:
Optionally, the identification module is specifically used for: obtaining preset medical vocabulary, wherein wraps in the medical vocabulary
Include candidate medicine entity；The candidate medicine entity is matched with the case history text, is determined in the case history text
Medicine entity.
Optionally, the identification module is specifically used for: by the case history text input to sequence labelling mould trained in advance
It is handled in type, obtains the entity markup information of the case history text；The case history is determined according to the entity markup information
Medicine entity in text.
Optionally, the identification module is specifically used for: obtaining preset attribute vocabulary, wherein wraps in the attribute vocabulary
Include candidate attribute；The candidate attribute is matched with the case history text, determines the attribute information in the case history text.
Optionally, the device further include: categorization module, for obtaining the candidate categories of the medicine entity, for
Each candidate categories extract the medicine entity attributes respectively, using the largest number of candidate categories of the attribute extracted as institute
State the classification of medicine entity；And/or the contextual information according to the medicine entity in the case history text, determine described in
The classification of medicine entity.
Optionally, the acquisition module includes: acquiring unit, for obtaining plain text case history；Matching unit is used for basis
Preset field name dictionary is matched with the plain text case history, determines the field name in the plain text case history；Cutting list
Member, for determining field contents corresponding with the field name from the plain text case history according to the field name, according to institute
It states field name and the field contents and cutting is carried out to the plain text case history.
Optionally, the acquisition module further include: map unit, for being based on keyword match and/or semantic similarity
The field name is mapped as the field name of standard by model.
Optionally, the acquisition module further include: judging unit, for judging whether lack in the plain text case history after cutting
Lose field contents；If so, missing is obtained from the plain text case history based on keyword match and/or textual classification model
Field contents；The field contents of missing are added to the position of aiming field name in the plain text case history after the cutting.
Optionally, the device further include: processing module, for carrying out subordinate sentence to the case history text, and according to pre-
If rule determines candidate sentence from the case history text；Output corresponding with preset output title is extracted from the candidate sentence
Content generates the structured message of customization according to the output title and the output content.
Third aspect present invention embodiment proposes a kind of computer equipment, including processor and memory；Wherein, described
Processor is corresponding with the executable program code to run by reading the executable program code stored in the memory
Program, with the processing method for realizing the electronic health record as described in first aspect embodiment.
Fourth aspect present invention embodiment proposes a kind of computer readable storage medium, is stored thereon with computer journey
Sequence realizes the processing method of the electronic health record as described in first aspect embodiment when the program is executed by processor.
The additional aspect of the present invention and advantage will be set forth in part in the description, and will partially become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of the processing method of electronic health record provided by the embodiment of the present invention；
Fig. 2 is the flow diagram of the processing method of another kind electronic health record provided by the embodiment of the present invention；
Fig. 3 is the flow diagram of the processing method of another kind electronic health record provided by the embodiment of the present invention；
Fig. 4 is a kind of structural schematic diagram of the processing unit of electronic health record provided by the embodiment of the present invention；
Fig. 5 is the structural schematic diagram of the processing unit of another kind electronic health record provided by the embodiment of the present invention；
Fig. 6 shows the block diagram for being suitable for the exemplary computer device for being used to realize the embodiment of the present invention.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to is used to explain the present invention, and is not considered as limiting the invention.
Below with reference to the accompanying drawings processing method, device and the equipment of the electronic health record of the embodiment of the present invention are described.
Fig. 1 is a kind of flow diagram of the processing method of electronic health record provided by the embodiment of the present invention, such as Fig. 1 institute
Show, this method comprises:
Step 101, case history text to be processed is obtained.
In the present embodiment, in order to meet the structuring demand of case history, case history text to be processed can be first obtained.For example,
Electronic health record text in available management information system for hospitals (HIS) is as case history text to be processed.Wherein, structuring
Demand refers to the medical bodies in identification case history, and description, modification, the attribute information for limiting medical bodies, to extract
The feature of case history semanteme is described.
Step 102, medicine entity and the attribute information in case history text are identified.
In the present embodiment, medicine entity and description medicine entity attributes information can be first identified from case history text.
Wherein, medicine entity includes but is not limited to generate heat, cough etc., and the classification of medicine entity includes but is not limited to symptom, sign, disease
Disease, drug, operation, inspection, inspection, allergies, history of life etc..Attribute information is for describing medicine entity, such as attribute information
Including yin and yang attribute, time of origin, duration, degree, frequency, inducement, drug dose, the result, the anaphylactogen that check inspection etc..
Wherein, there are many implementations that the medicine entity in identification acquisition case history text is carried out to case history text.
In one embodiment of the invention, medical vocabulary can be preset, and stores candidate doctor in medical vocabulary
Entity is learned, it is alternatively possible to medical vocabulary be excavated from case history, internet, medical book, to match medicine in case history text
Candidate's medicine entity present in vocabulary.In turn, available preset medical vocabulary, by candidate medicine entity and case history text
It is matched, determines the medicine entity in case history text.
As an example, can be known from case history text by the matched mode of canonical according to preset medical vocabulary
It Chu not medicine entity.
In one embodiment of the invention, can training sequence marking model in advance, and by case history text input in advance
It is first handled in trained sequence labelling model, obtains the entity markup information of case history text, believed to be marked according to entity
Cease the medicine entity determined in case history text.
As an example, case history text can be collected in advance and marks the medicine entity in case history text, and then basis
The processing parameter of the text training neural network of mark, formation sequence marking model make sequence labelling mode input text, defeated
It is out the text after mark.Further, case history text to be processed is obtained, and by case history text input to the sequence labelling model
In handled, obtain the text of mark, and the medicine entity in case history text is determined according to the text of mark.
Optionally, sequence labelling model can be based on two-way length memory network-condition random field (Bi-LSTM-CRF) in short-term
It realizes.In training sequence marking model, the nerve net of pre-training can be utilized based on the small-sample learning engine of domain-oriented
Network language model reduces the artificial mark sample size that model needs, and the effect manually marked is improved using Active Learning mechanism
Rate.
It should be noted that the implementation that above-mentioned identification obtains the medicine entity in case history text is only exemplary
, it can according to need selection one or more of them and identified, herein with no restriction.
The implementation for obtaining attribute information below for identification case history text is illustrated.
In one embodiment of the invention, attribute vocabulary can be preset, and stores candidate belong in attribute vocabulary
Property.In turn, preset attribute vocabulary is obtained, the candidate attribute in default vocabulary is matched with case history text, determines case history
Attribute information in text.It is alternatively possible to by the matched mode of canonical, according to preset attribute vocabulary from case history text
Identify attribute information.As an example, when in case history text including " no cough ", "None" is matched to according to vocabulary, in turn
Determine that attribute information includes negative (i.e. measurement symptom and sign disease is not occurring with patient).
Step 103, the corresponding relationship between medicine entity and attribute information is determined.
In the present embodiment, after obtaining the medicine entity and attribute information in case history text, medicine may further determine that
Corresponding relationship between entity and attribute information, to determine attribute information for which medicine entity to be described.
In one embodiment of the invention, in available case history text with target property information apart from nearest medicine
Entity, so according to default vocabulary match in the context of target property information and medicine entity whether include special characteristic word or
Mode, if being matched to special characteristic word or mode, it is determined that there are corresponding relationships with medicine entity for the target property information；If not
It is matched to, then further chooses other medicine entities and matched with target property information.
In one embodiment of the invention, relationship disaggregated model can also be trained.In turn, attribute information and medicine is real
The combination of body is input in relationship disaggregated model and is handled, and obtains classification results.Wherein, classification results include the presence of corresponding close
It is and corresponding relationship is not present.
As an example, can collecting be labeled with corresponding relationship and mark, there is no the medicine of corresponding relationship is real
The sample of body and attribute information, according to the processing parameter of sample training CNN convolutional neural networks, production Methods disaggregated model.Into
And classified according to the medicine entity, the attribute information that identify by relationship disaggregated model, to judge medicine entity and attribute
Information whether there is relationship.
In one embodiment of the invention, the classification of case history text traditional Chinese medicine entity can also be determined, such as can root
The classification of medicine entity is obtained according to the mapping table of preset medicine entity and classification.In practical applications, due to same table
The medicine entity stated may correspond to multiple classifications, therefore also need to carry out classification disambiguation processing to medicine entity.
As a kind of possible implementation, due to same statement medicine entity different classes of corresponding attribute not
Together, therefore it is also different for the attribute number of different classes of extraction.The candidate categories of available medicine entity, for each time
Classification is selected to extract medicine entity attributes respectively, using the largest number of candidate categories of the attribute extracted as the class of medicine entity
Not.For example, medicine entity " LDH " possible classification is disease and inspection, for " a large amount of pleural effusions in right side of example 1.Serum
LDH:628U/L." for classification inspection can extract inspection by attributes end value: 628U/L, do not extracted for classification disease
Attribute, it is determined that the classification of medicine entity " LDH " is to examine.
It, can be according to contextual information of the medicine entity in case history text, really as alternatively possible implementation
Determine the classification of medicine entity.For example, medicine entity " LDH " possible classification be disease and inspection, for example 2 " tentative diagnosis:
LDH".Obtaining contextual information of the LDH in case history text includes field tentative diagnosis, it is determined that the class of medicine entity " LDH "
It Wei not disease.
Optionally, processing can also be replaced to the statement of medicine entity according to the classification of entity, for example basis prestores
LDH examine with the corresponding relationship of title, the title lactic dehydrogenase that obtains that treated obtains waist after handling according to LDH disease
The protrusion of the intervertebral disc.
It should be noted that can choose one or more of them combination according to actual needs carries out entity class disambiguation,
Herein with no restriction.
In one embodiment of the invention, place can also be standardized to the medicine entity and attribute information identified
Reason, is normalized to standard or more common synonymous expression for the title of medicine entity and attribute information, or will be in attribute information
Numerical value and the time carry out unit standardization.It is alternatively possible to be believed based on preset synonym table medicine entity and attribute
The title that breath title is matched, and will match to maps to preset title.
As an example, it is also based on the normalization that attribute realizes medicine entity, by disassembling each medicine entity
For corresponding attribute, and the attribute attribute corresponding with default medicine entity name by disassembling out compares, if consistent
Number of attributes is greater than preset threshold, it is determined that the medicine entity is synonymous, and the title of medicine entity is normalized.
As another example, be also based on skip-thoughts semantic similarity model calculate medicine entity with
Similarity between default entity, if similarity is greater than preset threshold, it is determined that medicine entity is similar, by medicine entity name normalizing
Change.
Step 104, structured patient record is generated according to corresponding relationship.
In the present embodiment, after determining the corresponding relationship of medicine entity and attribute information, medicine entity and right can be determined
It should describe the medicine entity attributes information and construct the semantic feature of case history to generate structured patient record.
As an example, case history text to be processed is " paroxysmal upper abdomen occur without obvious inducement before patient's private prosecution 2 days
Portion's severe pain, occur together 38.7 degree of heat, no cough and expectoration etc. ", the structured patient record ultimately generated is as shown in the table,
The processing method of the electronic health record of the embodiment of the present invention by obtaining case history text to be processed, and then identifies
Medicine entity and attribute information in case history text.Further determine that the corresponding pass between medicine entity and the attribute information
System generates structured patient record according to corresponding relationship.Thereby, it is possible to identify medical bodies and description medical bodies in electronic health record
Attribute information, and the expression of structuring improves efficiency, reduces costs, meet the structuring demand in practical application.It provides
The general understanding to electronic health record is as a result, cover the information such as most important medical bodies and attribute, Ke Yibang in case history
It helps the systems such as auxiliary diagnosis, case history retrieval to understand case history from semantic level, constructs the semantic feature of case history.
Based on the above embodiment, further, when obtaining electronic health record to be processed, electronic health record can also be carried out
Standardization processing.The electronic health record of specification includes preset field, for example, tell including five histories one (main suit, present illness history, past medical history,
Personal history, obsterical history, family history) etc. fields.
Fig. 2 is the flow diagram of the processing method of another kind electronic health record provided by the embodiment of the present invention, such as Fig. 2 institute
Show, this method comprises:
Step 201, plain text case history is obtained.
In practical applications, lack of standardization due to record, it is understood that there may be not by each field in electronic health record (as main
Tell, present illness history etc.) it is stored separately in the form of field name-field contents, but stored with a text-only file pure
Text case history, in the present embodiment, available plain text case history, further to carry out standardization processing to plain text case history.
Step 202, it is matched according to preset field name dictionary with plain text case history, determines the word in plain text case history
Section name.
In the present embodiment, field name dictionary can be preset, includes field name such as main suit, existing disease in field name dictionary
History etc. and signal language corresponding with field name.
It as an example, include that corresponding signal language " main suit: " " main suit " is " [main in dictionary for field name " main suit "
Tell] " etc..Signal language in dictionary can be matched with plain text case history, determine the signal language in case history.Optionally, may be used
By by canonical it is matched in a manner of, signal language is identified from case history text according to preset field name dictionary.In turn, according to knowledge
Not Chu signal language determine the field name in plain text case history.
In one embodiment of the invention, due to the case where there may be field name misregisters, such as " existing disease
History " is recorded as " medical history ", and hence it is also possible to which field name to be mapped as to the field name of standard.It as an example, can be based on pass
Key word matches the field name that field name is mapped as to standard.For example, by " medical history " of the keyword match into case history text, into
And " medical history " is revised as " present illness history ".
As another example, field name can be mapped as to the field name of standard based on semantic similarity model.It is based on
Semantic similarity model calculates the similarity of the field name recognized in preset criteria field name and text, most according to similarity
Big criteria field name replaces the field name in corresponding text.
Step 203, field contents corresponding with field name are determined from plain text case history according to field name, according to field name
Cutting is carried out to plain text case history with field contents.
In the present embodiment, after identifying field name, it may further determine that the corresponding field contents of each field name.Example
It such as, can be by aiming field name to the content between next field name, as the corresponding field contents of aiming field name.Example again
It such as, can be by aiming field name to the content between paragraph end mark, as the corresponding field contents of aiming field name.
Optionally, for the above method can not cutting paragraph, can based on convolutional neural networks training text classify mould
Remaining paragraph input text disjunctive model is handled, exports corresponding field name by type, thus realize according to field name and
Field contents carry out cutting to plain text case history.
Step 204, in the plain text case history after judging cutting whether absent field content.
Step 205, if so, obtaining missing from plain text case history based on keyword match and/or textual classification model
Field contents.
Step 206, the field contents of missing are added to the position of aiming field name in the plain text case history after cutting.
In practical applications, it is understood that there may be medical history record is lack of standardization, and certain field merging is caused to be recorded in other fields
In, for example main suit may be recorded in present illness history, obsterical history is recorded in personal history.
In the present embodiment, plain text case history after can first judging cutting whether absent field content, if so, further
It attempts to extract the field contents lacked from existing field contents.
As an example, keyword match can be based on from plain text case history for each field name preset keyword
The middle field contents for obtaining missing.Such as the mode of " because * * * is admitted to hospital " is matched in the field contents of present illness history, extract missing
Main suit, then the model such as matching " married " or " unmarried " in personal history extract corresponding sentence filling obsterical history.
As another example, the field contents of missing are obtained from plain text case history based on textual classification model.It is based on
Convolutional neural networks training text disaggregated model, and each sentence in preset part field is predicted, determine each sentence
The corresponding field name of son, to judge whether each sentence can insert absent field.
In one embodiment of the invention, if case history is semi-structured case history lack of standardization, i.e. case history includes field name-
The structure of field contents form, but the case where there are field name misregisters, it can be based on keyword match and/or semantic phase
Field name is mapped as to the field name of standard like degree model.In turn, it carries out absent field to case history text to fill up, to obtain specification
Electronic health record, be further processed convenient for subsequent, improve accuracy.
The processing method of the electronic health record of the embodiment of the present invention, by carrying out content cutting classification to case history text and lacking
It loses field to fill up, realizes electronic health record standardization, utilize the case history of different editions HIS by more effective unification.And
The significant field lacked in case history can be supplemented, the electronic health record for helping hospital's building more to standardize achieves.
Based on the above embodiment, further, the important information in extraction case history that can also be customized.
Fig. 3 is the flow diagram of the processing method of another kind electronic health record provided by the embodiment of the present invention, such as Fig. 3 institute
Show, this method comprises:
Step 301, subordinate sentence is carried out to case history text, and determines candidate sentence from case history text according to preset rules.
In the present embodiment, data to be extracted can be pre-defined, wherein data to be extracted can according to need progress
Setting, including but not limited to different diseases, document types or demand of subscriber etc..
It is alternatively possible to pre-process to case history text, medicine entity and the attribute information in case history text are identified.
As an example, candidate sentence locating rule can be preset according to data to be extracted, determines candidate sentence
Antistop list.In turn, subordinate sentence is carried out to case history text, according to the candidate sentence locating rule of setting, if matching in a certain sentence
The content in antistop list is arrived, it is determined that the sentence is candidate sentence.
Step 302, corresponding with preset output title output content is extracted from candidate sentence, according to exporting title and defeated
Content generates the structured message of customization out.
In the present embodiment, data to be extracted can be output title-output content form.
As an example, output contents extraction rule can be preset according to data to be extracted, determined in output
The antistop list of appearance.For example, for export title " lesion type ", can in vocabulary predetermined keyword " gland cancer " etc. it is a series of
Lesion type, and then corresponding keyword is matched from candidate sentence, if being matched to " gland cancer ", using the word as with output title
" lesion type " corresponding output content.
Optionally, semantic similarity model is also based on to be extended to the vocabulary in above-mentioned matching rule, is improved
The generalization of rule.
For example, case history text are as follows: " case history details: (the right upper lung part lobe of the lung) part lobe of the lung tissue, size
12x11x4cm.Away from the visible tubera cinereum of the bronchus broken ends of fractured bone about 0.2cm, diameter 4cm, matter is crisp, and boundary is clear, and ash is red, in matter.
Conclusion: ice is remaining to organize right upper lung) gland cancer, in-differentiated, based on the growth of adherent sample (adherent type 60%+ acinus type 40%)."
The structured message of customization is as follows:
" sample position: superior lobe of right lung
Lesion type: gland cancer
Lesion hypotype: [attached wall-like gland cancer, acinar adenocarcinoma]
Sample size: num:[12,11,4], unit:cm }
Tumor size: { num:4, unit:cm } "
Optionally, the customization of rule for convenience can introduce medical practitioner and complete above-mentioned rule configuration and number
The general of algorithm is improved using the deep learning model of text structure based on the data of platform mark according to mark work
Change ability.
It is alternatively possible to tell field for five histories one, general case history structured data sets are constructed centered on patient.It should
Data set includes the time shaft of patient, and each time point includes the sings and symptoms and other patient's condition, the inspection done that patient occurs
Check test, the disease that diagnose, treatment (perform the operation or drug), curative effect and the prognosis of progress etc..Thereby, it is possible to integrate patient it is multiple when
The medical record information of phase, and relevant personnel are clearly presented to according to the time.
The processing method of the electronic health record of the embodiment of the present invention can extract in the slave case history according to user demand customization
Specific important feature information, thus complete to the deeper understanding of case history, it is effective that doctor is helped to construct patient data
Library or scientific data collection.
In order to realize above-described embodiment, the present invention also proposes a kind of processing unit of electronic health record.
Fig. 4 is a kind of structural schematic diagram of the processing unit of electronic health record provided by the embodiment of the present invention, such as Fig. 4 institute
Show, which includes: to obtain module 100, identification module 200, determining module 300, generation module 400.
Wherein, module 100 is obtained, for obtaining case history text to be processed.
Identification module 200, for identification the medicine entity and attribute information in case history text out.
Determining module 300, for determining the corresponding relationship between medicine entity and attribute information.
Generation module 400, for generating structured patient record according to corresponding relationship.
In one embodiment of the invention, identification module 200 is specifically used for: obtaining preset medical vocabulary, wherein doctor
Learning in vocabulary includes candidate medicine entity；Candidate medicine entity is matched with case history text, determines the doctor in case history text
Learn entity.
In one embodiment of the invention, identification module 200 is specifically used for: by case history text input to training in advance
It is handled in sequence labelling model, obtains the entity markup information of case history text；Case history text is determined according to entity markup information
Medicine entity in this.
In one embodiment of the invention, identification module 200 is specifically used for: obtaining preset attribute vocabulary, wherein belongs to
Property vocabulary in include candidate attribute；Candidate attribute is matched with case history text, determines the attribute information in case history text.
On the basis of fig. 4, device shown in fig. 5 further include: categorization module 500, processing module 600.
Wherein, each candidate categories are extracted respectively for obtaining the candidate categories of medicine entity categorization module 500
Medicine entity attributes, using the largest number of candidate categories of the attribute extracted as the classification of medicine entity；And/or according to
Contextual information of the medicine entity in case history text, determines the classification of medicine entity.
Processing module 600 for carrying out subordinate sentence to case history text, and determines candidate according to preset rules from case history text
Sentence；Output content corresponding with preset output title is extracted from candidate sentence, it is fixed to generate according to output title and output content
The structured message of system.
In one embodiment of the invention, obtaining module 100 includes: acquiring unit, for obtaining plain text case history；?
The field name in plain text case history is determined for being matched according to preset field name dictionary with plain text case history with unit；
Cutting unit, for determining corresponding with field name field contents from plain text case history according to field name, according to field name with
Field contents carry out cutting to plain text case history.
Optionally, module 100 is obtained further include: map unit, for being based on keyword match and/or semantic similarity mould
Field name is mapped as the field name of standard by type.
Optionally, module 100 is obtained further include: judging unit, for judging whether lack in the plain text case history after cutting
Lose field contents；If so, the field of missing is obtained from plain text case history based on keyword match and/or textual classification model
Content；The field contents of missing are added to the position of aiming field name in the plain text case history after cutting.
It should be noted that previous embodiment is equally applicable to this implementation to the explanation of the processing method of electronic health record
The processing unit of the electronic health record of example, details are not described herein again.
The processing unit of the electronic health record of the embodiment of the present invention by obtaining case history text to be processed, and then identifies
Medicine entity and attribute information in case history text.Further determine that the corresponding pass between medicine entity and the attribute information
System generates structured patient record according to corresponding relationship.Thereby, it is possible to identify medical bodies and description medical bodies in electronic health record
Attribute information, and the expression of structuring improves efficiency, reduces costs, meet the structuring demand in practical application.It provides
The general understanding to electronic health record is as a result, cover the information such as most important medical bodies and attribute, Ke Yibang in case history
It helps the systems such as auxiliary diagnosis, case history retrieval to understand case history from semantic level, constructs the semantic feature of case history.
In order to realize above-described embodiment, the present invention also proposes a kind of computer equipment, including processor and memory；Its
In, processor runs journey corresponding with executable program code by reading the executable program code stored in memory
Sequence, with the processing method for realizing the electronic health record as described in aforementioned any embodiment.
In order to realize above-described embodiment, the present invention also proposes a kind of computer program product, when in computer program product
Instruction the processing method of the electronic health record as described in aforementioned any embodiment is realized when being executed by processor.
In order to realize above-described embodiment, the present invention also proposes a kind of computer readable storage medium, is stored thereon with calculating
Machine program realizes the processing method of the electronic health record as described in aforementioned any embodiment when the program is executed by processor.
Fig. 6 shows the block diagram for being suitable for the exemplary computer device for being used to realize the embodiment of the present invention.The meter that Fig. 6 is shown
Calculating machine equipment 12 is only an example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in fig. 6, computer equipment 12 is showed in the form of universal computing device.The component of computer equipment 12 can be with
Including but not limited to: one or more processor or processing unit 16, system storage 28 connect different system components
The bus 18 of (including system storage 28 and processing unit 16).
Bus 18 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (Industry Standard
Architecture；Hereinafter referred to as: ISA) bus, microchannel architecture (Micro Channel Architecture；Below
Referred to as: MAC) bus, enhanced isa bus, Video Electronics Standards Association (Video Electronics Standards
Association；Hereinafter referred to as: VESA) local bus and peripheral component interconnection (Peripheral Component
Interconnection；Hereinafter referred to as: PCI) bus.
Computer equipment 12 typically comprises a variety of computer system readable media.These media can be it is any can be by
The usable medium that computer equipment 12 accesses, including volatile and non-volatile media, moveable and immovable medium.
Memory 28 may include the computer system readable media of form of volatile memory, such as random access memory
Device (Random Access Memory；Hereinafter referred to as: RAM) 30 and/or cache memory 32.Computer equipment 12 can be with
It further comprise other removable/nonremovable, volatile/non-volatile computer system storage mediums.Only as an example,
Storage system 34 can be used for reading and writing immovable, non-volatile magnetic media, and (Fig. 6 do not show, commonly referred to as " hard drive
Device ").Although being not shown in Fig. 6, the disk for reading and writing to removable non-volatile magnetic disk (such as " floppy disk ") can be provided and driven
Dynamic device, and to removable anonvolatile optical disk (such as: compact disc read-only memory (Compact Disc Read Only
Memory；Hereinafter referred to as: CD-ROM), digital multi CD-ROM (Digital Video Disc Read Only
Memory；Hereinafter referred to as: DVD-ROM) or other optical mediums) read-write CD drive.In these cases, each driving
Device can be connected by one or more data media interfaces with bus 18.Memory 28 may include that at least one program produces
Product, the program product have one group of (for example, at least one) program module, and it is each that these program modules are configured to perform the application
The function of embodiment.
Program/utility 40 with one group of (at least one) program module 42 can store in such as memory 28
In, such program module 42 include but is not limited to operating system, one or more application program, other program modules and
It may include the realization of network environment in program data, each of these examples or certain combination.Program module 42 is usual
Execute the function and/or method in embodiments described herein.
Computer equipment 12 can also be with one or more external equipments 14 (such as keyboard, sensing equipment, display 24
Deng) communication, the equipment interacted with the computer system/server 12 can be also enabled a user to one or more to be communicated, and/
Or with enable the computer system/server 12 and one or more of the other any equipment (example for being communicated of calculating equipment
Such as network interface card, modem etc.) communication.This communication can be carried out by input/output (I/O) interface 22.Also, it calculates
Machine equipment 12 can also pass through network adapter 20 and one or more network (such as local area network (Local Area
Network；Hereinafter referred to as: LAN), wide area network (Wide Area Network；Hereinafter referred to as: WAN) and/or public network, example
Such as internet) communication.As shown, network adapter 20 is communicated by bus 18 with other modules of computer equipment 12.It answers
When understanding, although not shown in the drawings, other hardware and/or software module can be used in conjunction with computer equipment 12, including but not
Be limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
Processing unit 16 by the program that is stored in system storage 28 of operation, thereby executing various function application and
Data processing, such as realize the method referred in previous embodiment.
In the description of the present invention, it is to be understood that, term " first ", " second " are used for description purposes only, and cannot
It is interpreted as indication or suggestion relative importance or implicitly indicates the quantity of indicated technical characteristic.Define as a result, " the
One ", the feature of " second " can explicitly or implicitly include at least one of the features.In the description of the present invention, " multiple "
It is meant that at least two, such as two, three etc., unless otherwise specifically defined.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
It must be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be in office
It can be combined in any suitable manner in one or more embodiment or examples.In addition, without conflicting with each other, the skill of this field
Art personnel can tie the feature of different embodiments or examples described in this specification and different embodiments or examples
It closes and combines.
Although the embodiments of the present invention has been shown and described above, it is to be understood that above-described embodiment is example
Property, it is not considered as limiting the invention, those skilled in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, modifies, replacement and variant.
Claims (20)
1. a kind of processing method of electronic health record characterized by comprising
Obtain case history text to be processed；
Identify the medicine entity and attribute information in the case history text；
Determine the corresponding relationship between the medicine entity and the attribute information；
Structured patient record is generated according to the corresponding relationship.
2. the method as described in claim 1, which is characterized in that the medicine entity packet identified in the case history text
It includes:
Obtain preset medical vocabulary, wherein include candidate medicine entity in the medical vocabulary；
The candidate medicine entity is matched with the case history text, determines the medicine entity in the case history text.
3. the method as described in claim 1, which is characterized in that the medicine entity packet identified in the case history text
It includes:
The case history text input is handled into sequence labelling model trained in advance, obtains the reality of the case history text
Body markup information；
The medicine entity in the case history text is determined according to the entity markup information.
4. the method as described in claim 1, which is characterized in that the attribute information packet identified in the case history text
It includes:
Obtain preset attribute vocabulary, wherein include candidate attribute in the attribute vocabulary；
The candidate attribute is matched with the case history text, determines the attribute information in the case history text.
5. the method as described in claim 1, which is characterized in that determining between the medicine entity and the attribute information
After corresponding relationship, further includes:
The candidate categories for obtaining the medicine entity extract the medicine entity attributes for each candidate categories respectively, will
Classification of the largest number of candidate categories of the attribute extracted as the medicine entity；
And/or
According to contextual information of the medicine entity in the case history text, the classification of the medicine entity is determined.
6. the method as described in claim 1, which is characterized in that described to obtain case history text to be processed and include:
Obtain plain text case history；
It is matched according to preset field name dictionary with the plain text case history, determines the field in the plain text case history
Name；
Field contents corresponding with the field name are determined from the plain text case history according to the field name, according to the word
Field contents described in Duan Minghe carry out cutting to the plain text case history.
7. method as claimed in claim 6, which is characterized in that after determining the field name in the plain text case history, also
Include:
The field name is mapped as to the field name of standard based on keyword match and/or semantic similarity model.
8. method according to claim 6 or 7, which is characterized in that according to the field name and the field contents to institute
State plain text case history carry out cutting after, further includes:
In plain text case history after judging cutting whether absent field content；
If so, based on keyword match and/or textual classification model out of, field that obtain missing in the plain text case history
Hold；
The field contents of missing are added to the position of aiming field name in the plain text case history after the cutting.
9. the method as described in claim 1, which is characterized in that further include:
Subordinate sentence is carried out to the case history text, and determines candidate sentence from the case history text according to preset rules；
Corresponding with preset output title output content is extracted from the candidate sentence, according to the output title and described defeated
Content generates the structured message of customization out.
10. a kind of processing unit of electronic health record characterized by comprising
Module is obtained, for obtaining case history text to be processed；
Identification module, for identification the medicine entity and attribute information in the case history text out；
Determining module, for determining the corresponding relationship between the medicine entity and the attribute information；
Generation module, for generating structured patient record according to the corresponding relationship.
11. device as claimed in claim 10, which is characterized in that the identification module is specifically used for:
Obtain preset medical vocabulary, wherein include candidate medicine entity in the medical vocabulary；
The candidate medicine entity is matched with the case history text, determines the medicine entity in the case history text.
12. device as claimed in claim 10, which is characterized in that the identification module is specifically used for:
The case history text input is handled into sequence labelling model trained in advance, obtains the reality of the case history text
Body markup information；
The medicine entity in the case history text is determined according to the entity markup information.
13. device as claimed in claim 10, which is characterized in that the identification module is specifically used for:
Obtain preset attribute vocabulary, wherein include candidate attribute in the attribute vocabulary；
The candidate attribute is matched with the case history text, determines the attribute information in the case history text.
14. device as claimed in claim 10, which is characterized in that further include:
Categorization module extracts the medicine for each candidate categories for obtaining the candidate categories of the medicine entity respectively
Entity attributes, using the largest number of candidate categories of the attribute extracted as the classification of the medicine entity；
And/or
According to contextual information of the medicine entity in the case history text, the classification of the medicine entity is determined.
15. device as claimed in claim 10, which is characterized in that the acquisition module includes:
Acquiring unit, for obtaining plain text case history；
Matching unit determines the plain text for being matched according to preset field name dictionary with the plain text case history
Field name in case history；
Cutting unit, for being determined in field corresponding with the field name according to the field name from the plain text case history
Hold, cutting is carried out to the plain text case history according to the field name and the field contents.
16. device as claimed in claim 15, which is characterized in that the acquisition module further include:
Map unit, for the field name to be mapped as to the word of standard based on keyword match and/or semantic similarity model
Section name.
17. the device as described in claim 15 or 16, which is characterized in that the acquisition module further include:
Judging unit, for judge in the plain text case history after cutting whether absent field content；
If so, based on keyword match and/or textual classification model out of, field that obtain missing in the plain text case history
Hold；
The field contents of missing are added to the position of aiming field name in the plain text case history after the cutting.
18. device as claimed in claim 10, which is characterized in that further include:
Processing module for carrying out subordinate sentence to the case history text, and is determined from the case history text according to preset rules and is waited
Select sentence；
Corresponding with preset output title output content is extracted from the candidate sentence, according to the output title and described defeated
Content generates the structured message of customization out.
19. a kind of computer equipment, which is characterized in that including processor and memory；
Wherein, the processor is run by reading the executable program code stored in the memory can be performed with described
The corresponding program of program code, with the processing method for realizing electronic health record as claimed in any one of claims 1-9 wherein.
20. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The processing method of electronic health record as claimed in any one of claims 1-9 wherein is realized when execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910579541.7A CN110277149A (en) | 2019-06-28 | 2019-06-28 | Processing method, device and the equipment of electronic health record |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910579541.7A CN110277149A (en) | 2019-06-28 | 2019-06-28 | Processing method, device and the equipment of electronic health record |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110277149A true CN110277149A (en) | 2019-09-24 |
Family
ID=67963764
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910579541.7A Pending CN110277149A (en) | 2019-06-28 | 2019-06-28 | Processing method, device and the equipment of electronic health record |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110277149A (en) |
Cited By (46)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110931128A (en) * | 2019-12-05 | 2020-03-27 | 中国科学院自动化研究所 | Method, system and device for automatically identifying unsupervised symptoms of unstructured medical texts |
| CN110956140A (en) * | 2019-12-02 | 2020-04-03 | 支付宝(杭州)信息技术有限公司 | Image information extraction method and device |
| CN111028954A (en) * | 2019-11-29 | 2020-04-17 | 成都易欧科技有限公司 | Infectious disease early warning analysis method and system based on Chinese semantic technology |
| CN111028903A (en) * | 2019-11-06 | 2020-04-17 | 云知声智能科技股份有限公司 | Method and device for grouping operation-related documents in electronic medical record |
| CN111048167A (en) * | 2019-10-31 | 2020-04-21 | 中电药明数据科技(成都)有限公司 | Hierarchical case structuring method and system |
| CN111079420A (en) * | 2019-12-19 | 2020-04-28 | 天津新开心生活科技有限公司 | Text recognition method and device, computer readable medium and electronic equipment |
| CN111091883A (en) * | 2019-12-16 | 2020-05-01 | 东软集团股份有限公司 | Medical text processing method and device, storage medium and equipment |
| CN111104400A (en) * | 2019-12-24 | 2020-05-05 | 天津新开心生活科技有限公司 | Data normalization method and device, electronic equipment and storage medium |
| CN111210887A (en) * | 2019-12-02 | 2020-05-29 | 泰康保险集团股份有限公司 | Medical text processing method and related equipment |
| CN111241084A (en) * | 2020-01-14 | 2020-06-05 | 平安医疗健康管理股份有限公司 | Medical information cleaning method, device, computer equipment and storage medium |
| CN111241806A (en) * | 2019-12-23 | 2020-06-05 | 望海康信(北京)科技股份公司 | Method and system for checking consistency of diagnosis of electronic medical record and medical record home page |
| CN111259664A (en) * | 2020-01-14 | 2020-06-09 | 腾讯科技（深圳）有限公司 | Method, device and equipment for determining medical text information and storage medium |
| CN111326226A (en) * | 2020-02-14 | 2020-06-23 | 腾讯科技（深圳）有限公司 | Analysis processing and display method, device, equipment and storage medium of electronic medical record |
| 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 |
| CN111444686A (en) * | 2020-03-16 | 2020-07-24 | 上海联影智能医疗科技有限公司 | Medical data labeling method, device, storage medium and computer equipment |
| CN111554369A (en) * | 2020-04-29 | 2020-08-18 | 杭州依图医疗技术有限公司 | Medical data processing method, interaction method and storage medium |
| CN111611780A (en) * | 2020-05-15 | 2020-09-01 | 山东大学 | Digestive endoscopy report structuring method and system based on deep learning |
| CN111710383A (en) * | 2020-06-16 | 2020-09-25 | 平安科技（深圳）有限公司 | Medical record quality control method and device, computer equipment and storage medium |
| CN111724873A (en) * | 2020-06-18 | 2020-09-29 | 北京嘉和海森健康科技有限公司 | Data processing method and device |
| CN111785388A (en) * | 2020-07-01 | 2020-10-16 | 医渡云（北京）技术有限公司 | Medical data processing method and device, storage medium and electronic equipment |
| CN111798948A (en) * | 2020-07-01 | 2020-10-20 | 微医云(杭州)控股有限公司 | Medical record information processing method, device, equipment and storage medium |
| CN111916169A (en) * | 2020-06-29 | 2020-11-10 | 南京大经中医药信息技术有限公司 | Traditional Chinese medicine electronic medical record structuring method and terminal |
| CN112016279A (en) * | 2020-09-04 | 2020-12-01 | 平安科技（深圳）有限公司 | Electronic medical record structuring method and device, computer equipment and storage medium |
| CN112101034A (en) * | 2020-09-09 | 2020-12-18 | 沈阳东软智能医疗科技研究院有限公司 | Method and device for distinguishing attribute of medical entity and related product |
| CN112259183A (en) * | 2020-11-11 | 2021-01-22 | 北京嘉和海森健康科技有限公司 | Method and device for extracting patient health time axis based on electronic medical record |
| CN112307134A (en) * | 2020-10-30 | 2021-02-02 | 北京百度网讯科技有限公司 | Entity information processing method, entity information processing device, electronic equipment and storage medium |
| CN112365937A (en) * | 2020-09-11 | 2021-02-12 | 北京欧应信息技术有限公司 | Method for rapidly collecting highly structured medical records |
| CN112420145A (en) * | 2020-12-08 | 2021-02-26 | 医惠科技有限公司 | Electronic medical record document data processing method and device and computer readable storage medium |
| CN112687365A (en) * | 2020-12-24 | 2021-04-20 | 零氪科技(天津)有限公司 | Medical record data processing method and device based on voice recognition |
| CN112735545A (en) * | 2020-12-31 | 2021-04-30 | 杭州依图医疗技术有限公司 | Self-training method, model, processing method, device and storage medium |
| CN112800759A (en) * | 2021-04-14 | 2021-05-14 | 北京金山云网络技术有限公司 | Standardized data generation method and device and medical text data processing method and device |
| CN112925876A (en) * | 2019-12-05 | 2021-06-08 | 金色熊猫有限公司 | Method, device, medium and equipment for processing cross-site migration structured medical records |
| CN112992301A (en) * | 2019-12-02 | 2021-06-18 | 金色熊猫有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN113033177A (en) * | 2019-12-24 | 2021-06-25 | 医渡云（北京）技术有限公司 | Method and device for analyzing electronic medical record data |
| CN113220841A (en) * | 2021-05-17 | 2021-08-06 | 北京百度网讯科技有限公司 | Method, apparatus, electronic device and storage medium for determining authentication information |
| CN113343680A (en) * | 2021-05-19 | 2021-09-03 | 大连东软教育科技集团有限公司 | Structured information extraction method based on multi-type case history texts |
| CN113450884A (en) * | 2021-01-06 | 2021-09-28 | 心医国际数字医疗系统(大连)有限公司 | Medical record generation method and device and electronic equipment |
| CN113468307A (en) * | 2021-06-30 | 2021-10-01 | 网易（杭州）网络有限公司 | Text processing method and device, electronic equipment and storage medium |
| CN113553840A (en) * | 2021-08-12 | 2021-10-26 | 卫宁健康科技集团股份有限公司 | Text information processing method, device, equipment and storage medium |
| CN113657102A (en) * | 2021-08-17 | 2021-11-16 | 北京百度网讯科技有限公司 | Information extraction method, information extraction device, information extraction apparatus, storage medium, and program |
| CN113836292A (en) * | 2021-09-15 | 2021-12-24 | 灵犀量子(北京)医疗科技有限公司 | Method, system, device and medium for structuring a summary of a biomedical document |
| CN114140810A (en) * | 2022-01-30 | 2022-03-04 | 北京欧应信息技术有限公司 | Method, apparatus and medium for structured recognition of documents |
| CN116010593A (en) * | 2021-10-20 | 2023-04-25 | 腾讯科技（深圳）有限公司 | Method, device, computer equipment and storage medium for determining disease emotion information |
| CN116312916A (en) * | 2023-05-22 | 2023-06-23 | 江西曼荼罗软件有限公司 | Electronic medical record recording method, system, computer and readable storage medium |
| CN116562271A (en) * | 2023-07-10 | 2023-08-08 | 之江实验室 | Quality control method and device for electronic medical record, storage medium and electronic equipment |
| CN116992839A (en) * | 2023-09-25 | 2023-11-03 | 北京亚信数据有限公司 | Automatic generation method, device and equipment for medical records front page |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109637605A (en) * | 2018-12-11 | 2019-04-16 | 北京大学 | Electronic health record structural method and computer readable storage medium |
-
2019
- 2019-06-28 CN CN201910579541.7A patent/CN110277149A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109637605A (en) * | 2018-12-11 | 2019-04-16 | 北京大学 | Electronic health record structural method and computer readable storage medium |
Cited By (69)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111048167B (en) * | 2019-10-31 | 2023-08-18 | 中电药明数据科技(成都)有限公司 | Hierarchical case structuring method and system |
| CN111048167A (en) * | 2019-10-31 | 2020-04-21 | 中电药明数据科技(成都)有限公司 | Hierarchical case structuring method and system |
| CN111028903A (en) * | 2019-11-06 | 2020-04-17 | 云知声智能科技股份有限公司 | Method and device for grouping operation-related documents in electronic medical record |
| CN111028903B (en) * | 2019-11-06 | 2023-10-20 | 云知声智能科技股份有限公司 | Method and device for grouping operation related documents in electronic medical records |
| CN111028954A (en) * | 2019-11-29 | 2020-04-17 | 成都易欧科技有限公司 | Infectious disease early warning analysis method and system based on Chinese semantic technology |
| CN110956140B (en) * | 2019-12-02 | 2022-09-02 | 蚂蚁胜信(上海)信息技术有限公司 | Image information extraction method, device, equipment and storage medium |
| CN110956140A (en) * | 2019-12-02 | 2020-04-03 | 支付宝(杭州)信息技术有限公司 | Image information extraction method and device |
| CN111210887B (en) * | 2019-12-02 | 2023-06-02 | 泰康保险集团股份有限公司 | Medical text processing method and related equipment |
| CN111210887A (en) * | 2019-12-02 | 2020-05-29 | 泰康保险集团股份有限公司 | Medical text processing method and related equipment |
| CN112992301A (en) * | 2019-12-02 | 2021-06-18 | 金色熊猫有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN112992301B (en) * | 2019-12-02 | 2024-03-29 | 金色熊猫有限公司 | Data processing method, device, electronic equipment and storage medium |
| CN112925876B (en) * | 2019-12-05 | 2023-11-10 | 金色熊猫有限公司 | Method, device, medium and equipment for processing structured medical record migrated across sites |
| CN110931128B (en) * | 2019-12-05 | 2023-04-07 | 中国科学院自动化研究所 | Method, system and device for automatically identifying unsupervised symptoms of unstructured medical texts |
| CN110931128A (en) * | 2019-12-05 | 2020-03-27 | 中国科学院自动化研究所 | Method, system and device for automatically identifying unsupervised symptoms of unstructured medical texts |
| CN112925876A (en) * | 2019-12-05 | 2021-06-08 | 金色熊猫有限公司 | Method, device, medium and equipment for processing cross-site migration structured medical records |
| CN111091883A (en) * | 2019-12-16 | 2020-05-01 | 东软集团股份有限公司 | Medical text processing method and device, storage medium and equipment |
| CN111079420A (en) * | 2019-12-19 | 2020-04-28 | 天津新开心生活科技有限公司 | Text recognition method and device, computer readable medium and electronic equipment |
| CN111079420B (en) * | 2019-12-19 | 2023-04-07 | 天津新开心生活科技有限公司 | Text recognition method and device, computer readable medium and electronic equipment |
| CN111241806A (en) * | 2019-12-23 | 2020-06-05 | 望海康信(北京)科技股份公司 | Method and system for checking consistency of diagnosis of electronic medical record and medical record home page |
| CN113033177A (en) * | 2019-12-24 | 2021-06-25 | 医渡云（北京）技术有限公司 | Method and device for analyzing electronic medical record data |
| CN111104400A (en) * | 2019-12-24 | 2020-05-05 | 天津新开心生活科技有限公司 | Data normalization method and device, electronic equipment and storage medium |
| CN111241084A (en) * | 2020-01-14 | 2020-06-05 | 平安医疗健康管理股份有限公司 | Medical information cleaning method, device, computer equipment and storage medium |
| CN111259664A (en) * | 2020-01-14 | 2020-06-09 | 腾讯科技（深圳）有限公司 | Method, device and equipment for determining medical text information and storage medium |
| CN111326226B (en) * | 2020-02-14 | 2023-03-03 | 腾讯科技（深圳）有限公司 | Analysis processing and display method, device, equipment and storage medium of electronic medical record |
| CN111326226A (en) * | 2020-02-14 | 2020-06-23 | 腾讯科技（深圳）有限公司 | Analysis processing and display method, device, equipment and storage medium of electronic medical record |
| CN111444686A (en) * | 2020-03-16 | 2020-07-24 | 上海联影智能医疗科技有限公司 | Medical data labeling method, device, storage medium and computer equipment |
| 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 |
| CN111554369B (en) * | 2020-04-29 | 2023-08-04 | 杭州依图医疗技术有限公司 | Medical data processing method, interaction method and storage medium |
| CN111554369A (en) * | 2020-04-29 | 2020-08-18 | 杭州依图医疗技术有限公司 | Medical data processing method, interaction method and storage medium |
| CN111611780A (en) * | 2020-05-15 | 2020-09-01 | 山东大学 | Digestive endoscopy report structuring method and system based on deep learning |
| CN111710383A (en) * | 2020-06-16 | 2020-09-25 | 平安科技（深圳）有限公司 | Medical record quality control method and device, computer equipment and storage medium |
| CN111724873A (en) * | 2020-06-18 | 2020-09-29 | 北京嘉和海森健康科技有限公司 | Data processing method and device |
| CN111724873B (en) * | 2020-06-18 | 2024-01-09 | 北京嘉和海森健康科技有限公司 | Data processing method and device |
| CN111916169A (en) * | 2020-06-29 | 2020-11-10 | 南京大经中医药信息技术有限公司 | Traditional Chinese medicine electronic medical record structuring method and terminal |
| CN111798948A (en) * | 2020-07-01 | 2020-10-20 | 微医云(杭州)控股有限公司 | Medical record information processing method, device, equipment and storage medium |
| CN111785388A (en) * | 2020-07-01 | 2020-10-16 | 医渡云（北京）技术有限公司 | Medical data processing method and device, storage medium and electronic equipment |
| CN111798948B (en) * | 2020-07-01 | 2024-02-27 | 微医云(杭州)控股有限公司 | Medical record information processing method, device, equipment and storage medium |
| CN112016279A (en) * | 2020-09-04 | 2020-12-01 | 平安科技（深圳）有限公司 | Electronic medical record structuring method and device, computer equipment and storage medium |
| CN112016279B (en) * | 2020-09-04 | 2023-11-14 | 平安科技（深圳）有限公司 | Method, device, computer equipment and storage medium for structuring electronic medical record |
| CN112101034B (en) * | 2020-09-09 | 2024-02-27 | 沈阳东软智能医疗科技研究院有限公司 | Method and device for judging attribute of medical entity and related product |
| CN112101034A (en) * | 2020-09-09 | 2020-12-18 | 沈阳东软智能医疗科技研究院有限公司 | Method and device for distinguishing attribute of medical entity and related product |
| CN112365937A (en) * | 2020-09-11 | 2021-02-12 | 北京欧应信息技术有限公司 | Method for rapidly collecting highly structured medical records |
| CN112307134B (en) * | 2020-10-30 | 2024-02-06 | 北京百度网讯科技有限公司 | Entity information processing method, device, electronic equipment and storage medium |
| CN112307134A (en) * | 2020-10-30 | 2021-02-02 | 北京百度网讯科技有限公司 | Entity information processing method, entity information processing device, electronic equipment and storage medium |
| CN112259183A (en) * | 2020-11-11 | 2021-01-22 | 北京嘉和海森健康科技有限公司 | Method and device for extracting patient health time axis based on electronic medical record |
| CN112259183B (en) * | 2020-11-11 | 2023-08-08 | 北京嘉和海森健康科技有限公司 | Method and device for extracting patient health time axis based on electronic medical record |
| CN112420145A (en) * | 2020-12-08 | 2021-02-26 | 医惠科技有限公司 | Electronic medical record document data processing method and device and computer readable storage medium |
| CN112687365A (en) * | 2020-12-24 | 2021-04-20 | 零氪科技(天津)有限公司 | Medical record data processing method and device based on voice recognition |
| CN112735545A (en) * | 2020-12-31 | 2021-04-30 | 杭州依图医疗技术有限公司 | Self-training method, model, processing method, device and storage medium |
| CN113450884A (en) * | 2021-01-06 | 2021-09-28 | 心医国际数字医疗系统(大连)有限公司 | Medical record generation method and device and electronic equipment |
| CN112800759B (en) * | 2021-04-14 | 2021-08-06 | 北京金山云网络技术有限公司 | Standardized data generation method and device and medical text data processing method and device |
| CN112800759A (en) * | 2021-04-14 | 2021-05-14 | 北京金山云网络技术有限公司 | Standardized data generation method and device and medical text data processing method and device |
| CN113220841A (en) * | 2021-05-17 | 2021-08-06 | 北京百度网讯科技有限公司 | Method, apparatus, electronic device and storage medium for determining authentication information |
| CN113220841B (en) * | 2021-05-17 | 2023-11-17 | 北京百度网讯科技有限公司 | Method, apparatus, electronic device and storage medium for determining authentication information |
| CN113343680A (en) * | 2021-05-19 | 2021-09-03 | 大连东软教育科技集团有限公司 | Structured information extraction method based on multi-type case history texts |
| CN113468307A (en) * | 2021-06-30 | 2021-10-01 | 网易（杭州）网络有限公司 | Text processing method and device, electronic equipment and storage medium |
| CN113468307B (en) * | 2021-06-30 | 2023-06-30 | 网易（杭州）网络有限公司 | Text processing method, device, electronic equipment and storage medium |
| CN113553840A (en) * | 2021-08-12 | 2021-10-26 | 卫宁健康科技集团股份有限公司 | Text information processing method, device, equipment and storage medium |
| CN113657102A (en) * | 2021-08-17 | 2021-11-16 | 北京百度网讯科技有限公司 | Information extraction method, information extraction device, information extraction apparatus, storage medium, and program |
| CN113836292B (en) * | 2021-09-15 | 2024-01-09 | 灵犀量子(北京)医疗科技有限公司 | Structuring method, system, device and medium for biomedical literature abstract |
| CN113836292A (en) * | 2021-09-15 | 2021-12-24 | 灵犀量子(北京)医疗科技有限公司 | Method, system, device and medium for structuring a summary of a biomedical document |
| CN116010593A (en) * | 2021-10-20 | 2023-04-25 | 腾讯科技（深圳）有限公司 | Method, device, computer equipment and storage medium for determining disease emotion information |
| CN114140810A (en) * | 2022-01-30 | 2022-03-04 | 北京欧应信息技术有限公司 | Method, apparatus and medium for structured recognition of documents |
| CN114140810B (en) * | 2022-01-30 | 2022-04-22 | 北京欧应信息技术有限公司 | Method, apparatus and medium for structured recognition of documents |
| CN116312916A (en) * | 2023-05-22 | 2023-06-23 | 江西曼荼罗软件有限公司 | Electronic medical record recording method, system, computer and readable storage medium |
| CN116562271B (en) * | 2023-07-10 | 2023-10-10 | 之江实验室 | Quality control method and device for electronic medical record, storage medium and electronic equipment |
| CN116562271A (en) * | 2023-07-10 | 2023-08-08 | 之江实验室 | Quality control method and device for electronic medical record, storage medium and electronic equipment |
| CN116992839A (en) * | 2023-09-25 | 2023-11-03 | 北京亚信数据有限公司 | Automatic generation method, device and equipment for medical records front page |
| CN116992839B (en) * | 2023-09-25 | 2024-01-26 | 北京亚信数据有限公司 | Automatic generation method, device and equipment for medical records front page |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110277149A (en) | Processing method, device and the equipment of electronic health record | |
| Popovski et al. | A survey of named-entity recognition methods for food information extraction | |
| Dalianis et al. | HEALTH BANK-A Workbench for Data Science Applications in Healthcare. | |
| Wang et al. | Extracting important information from Chinese Operation Notes with natural language processing methods | |
| Huddar et al. | Predicting complications in critical care using heterogeneous clinical data | |
| Lou et al. | Automated detection of radiology reports that require follow-up imaging using natural language processing feature engineering and machine learning classification | |
| CN108538395A (en) | A kind of construction method of general medical disease that calls for specialized treatment data system | |
| CN109920540A (en) | Construction method, device and the computer equipment of assisting in diagnosis and treatment decision system | |
| US11017033B2 (en) | Systems and methods for modeling free-text clinical documents into a hierarchical graph-like data structure based on semantic relationships among clinical concepts present in the documents | |
| Friedman et al. | Natural language and text processing in biomedicine | |
| Kim et al. | Extraction of left ventricular ejection fraction information from various types of clinical reports | |
| Canino et al. | On the analysis of diseases and their related geographical data | |
| CN111177309A (en) | Medical record data processing method and device | |
| Leng et al. | Bi-level artificial intelligence model for risk classification of acute respiratory diseases based on Chinese clinical data | |
| Friedman | Semantic text parsing for patient records | |
| Wang et al. | Research on named entity recognition of doctor-patient question answering community based on bilstm-crf model | |
| Dai et al. | Phenotyping hypotensive patients in critical care using hospital discharge summaries | |
| Visser et al. | Automatic detection of actionable findings and communication mentions in radiology reports using natural language processing | |
| Røst et al. | Identifying catheter-related events through sentence classification | |
| US11961622B1 (en) | Application-specific processing of a disease-specific semantic model instance | |
| US20240135108A1 (en) | Clinical Trial Screening Using Disease-Specific Semantic Models | |
| US20240136070A1 (en) | Application-Specific Processing of a Disease-Specific Semantic Model Instance | |
| US20240136065A1 (en) | Disease-Specific Semantic Model Instance Generation and Maintenance | |
| CN111026282B (en) | Control method for judging whether medical data labeling is carried out in input process | |
| CN116737945A (en) | Mapping method for EMR knowledge map of patient |
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 |