CN110362829A - Method for evaluating quality, device and the equipment of structured patient record data - Google Patents
Method for evaluating quality, device and the equipment of structured patient record data Download PDFInfo
- Publication number
- CN110362829A CN110362829A CN201910639668.3A CN201910639668A CN110362829A CN 110362829 A CN110362829 A CN 110362829A CN 201910639668 A CN201910639668 A CN 201910639668A CN 110362829 A CN110362829 A CN 110362829A
- Authority
- CN
- China
- Prior art keywords
- keyword
- type
- record data
- patient record
- medical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/258—Data format conversion from or to a database
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- 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
-
- 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
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Probability & Statistics with Applications (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
Method for evaluating quality, device and the equipment of structured patient record data provided in an embodiment of the present invention, this method comprises: according to medical type, the corresponding multiple structured patient record data to be assessed of the medical type are obtained from medical data base, wherein, each structured patient record data include at least one key-value pair data, and each key-value pair data includes keyword and the corresponding value of the keyword;The corresponding annotation results of each structured patient record data are obtained, include each keyword and the corresponding comparing result of each keyword in the annotation results;According to the corresponding annotation results of each structured patient record data, the quality of the corresponding structured patient record data of the medical type is assessed.By the above process, the quality evaluation process to structured patient record data is realized;Additionally it is possible to determine the quality of the structured patient record data of different medical type out, improves the accuracy of quality evaluation.
Description
Technical field
The present embodiments relate to field of computer technology more particularly to a kind of quality evaluation sides of structured patient record data
Method, device and equipment.
Background technique
Currently, medical record is led in clinical research, public health big data, hospital data intelligent management, intelligent follow-up etc.
Domain is widely used.Original medical record is usually unstructured form.In order to improve medical record answering in above-mentioned field
With convenience, need original medical record being converted to structured form.
Specifically, cleaning using data structured processing technique to unstructured data in original case history, make its turn
It is changed to structural data.Illustratively, by the data processing in original case history be as unit of chapters and sections, field name unified knot
Structure form, alternatively, extracting the duration of symptom, yin and yang attribute, diagnosis certainty of disease etc. from original case history
Feature.By data structured treatment process, the original case history that usually only doctor can just be understood, being converted to computer can
The structured patient record understood.
After original medical record data is converted to structured patient record data, need to the quality of structured patient record data into
Row assessment, to determine the reliability of structuring Processing Algorithm.
Summary of the invention
The embodiment of the present invention provides method for evaluating quality, device and the equipment of a kind of structured patient record data, to realize
The quality of structured patient record data is assessed.
In a first aspect, the embodiment of the present invention provides a kind of method for evaluating quality of structured patient record data, comprising:
According to medical type, the corresponding multiple structurings disease to be assessed of the medical type is obtained from medical data base
Count evidence one by one, wherein the medical data base is used to store the original medical record data of different medical type, and to each described original
Medical record data carries out the structured patient record data that structuring is handled, and each structured patient record data include at least one
Key-value pair data, each key-value pair data include keyword and the corresponding value of the keyword;
The corresponding annotation results of each structured patient record data are obtained, include each keyword in the annotation results
Comparing result corresponding with each keyword;Wherein, the annotation results are by the structured patient record data and the original
Beginning medical record data compares;
According to the corresponding annotation results of each structured patient record data, structured patient record corresponding to the medical type
The quality of data is assessed.
Optionally,
The type of the corresponding comparing result of each keyword is any in following: conversion is correct, transcription error, pass
Key word is accidentally recalled does not recall with keyword;It is described according to the corresponding annotation results of each structured patient record data, to the doctor
The quality for treating the corresponding structured patient record data of type is assessed, comprising:
For each first keyword, from the corresponding annotation results of the multiple structured patient record data, described in acquisition
The corresponding comparing result of first keyword, first keyword are any one in the keyword;
According to the corresponding comparing result of first keyword, the first interpretation of result information, first result point are obtained
Analysis information includes: that the type of comparing result is to convert the quantity of correct first keyword, the type of comparing result to turn
Change the quantity of first keyword of mistake, the number that the type of comparing result is first keyword that keyword is accidentally recalled
Amount, the quantity that the type of comparing result is first keyword that keyword is not recalled;
According to the first interpretation of result information, the corresponding accuracy rate of first keyword and recall rate are obtained;
According to the corresponding accuracy rate of each keyword and recall rate, structured patient record number corresponding to the medical type
According to quality assessed.
Optionally,
It is described that the corresponding accuracy rate of first keyword and recall rate are obtained according to the first interpretation of result information,
Include:
Type according to comparing result is to convert the quantity of correct first keyword, the type of comparing result to turn
The type of the quantity and comparing result of changing first keyword of mistake is first keyword that keyword is accidentally recalled
Quantity, obtain the quantity that first keyword is called back;
It is to convert the correctly quantity of first keyword and first keyword according to the type of comparing result
The quantity being called back obtains the corresponding accuracy rate of first keyword;
Quantity, the type of comparing result being called back according to first keyword are described first that keyword is accidentally recalled
The quantity of keyword and the type of comparing result are the quantity for first keyword that keyword is not recalled, described in acquisition
The corresponding recall rate of first keyword.
Optionally,
The type of the corresponding comparing result of each keyword is any in following: conversion is correct, transcription error, pass
Key word is accidentally recalled does not recall with keyword;It is described according to the corresponding annotation results of each structured patient record data, to the doctor
The quality for treating the corresponding structured patient record data of type is assessed, comprising:
According to the corresponding annotation results of each structured patient record data, the second interpretation of result information is obtained, described second
Interpretation of result information includes: that the type of comparing result is to convert the quantity of correct each keyword, the type of comparing result to turn
Change the quantity of each keyword of mistake, the quantity that the type of comparing result is each keyword that keyword is accidentally recalled and comparison
As a result type is the quantity for each keyword that keyword is not recalled;
According to the second interpretation of result information, the corresponding standard of the corresponding structured patient record data of the medical type is obtained
True rate and recall rate.
Optionally,
It further include correction result in the annotation results, the correction result includes: that the type of comparing result is wrong for conversion
The corresponding correction value of each keyword accidentally and the type of comparing result are each keyword and each keyword that keyword is not recalled
Corresponding value;
It is described according to the corresponding annotation results of each structured patient record data, structuring corresponding to the medical type
After the quality of medical record data is assessed, further includes:
Abnormal data in the multiple structured patient record data is shown, and the correction result is opened up
Show;Wherein, it is the key that transcription error, keyword are accidentally recalled or keyword is not recalled that the abnormal data, which is the type of comparing result,
Value is to data.
Optionally,
It is described according to medical type, the corresponding multiple structures to be assessed of the medical type are obtained from medical data base
Change medical record data, comprising:
According to assessment task, medical type and maximum assessment quantity to be assessed are obtained;
According to the medical type and the maximum assessment quantity, it is corresponding that the medical type is obtained from medical data base
Multiple structured patient record data to be assessed;Wherein, the quantity of the structured patient record data be less than or equal to it is described most
Big assessment quantity.
Optionally,
It is described that quantity is assessed according to the medical type and the maximum, the medical type is obtained from medical data base
Corresponding multiple structured patient record data to be assessed, comprising:
Target collection is obtained from the medical data base, includes the corresponding knot of the medical type in the target collection
Structure medical record data;
If the quantity of the structured patient record data in the target collection is greater than the maximum assessment quantity, from institute
The structured patient record data that maximum assessment quantity is randomly choosed in target collection are stated as the structured patient record number to be assessed
According to;
If the quantity of the structured patient record data in the target collection is less than or equal to the maximum assessment number
Amount, then regard the structured patient record data in the target collection as the structured patient record data to be assessed.
Second aspect, the embodiment of the present invention provide a kind of quality assessment device of structured patient record data, comprising:
First obtains module, for according to medical type, obtained from medical data base the medical type it is corresponding to
Multiple structured patient record data of assessment, wherein the medical data base is used to store the original case history number of different medical type
According to, and the structured patient record data that structuring is handled, each structuring are carried out to each original medical record data
Medical record data includes at least one key-value pair data, and each key-value pair data includes that keyword and the keyword are corresponding
Value;
Second obtains module, for obtaining the corresponding annotation results of each structured patient record data, the annotation results
In include each keyword and the corresponding comparing result of each keyword;Wherein, the annotation results are by the structure
Change what medical record data was compared with the original medical record data;
Quality assessment modules, for according to the corresponding annotation results of each structured patient record data, to the medical class
The quality of the corresponding structured patient record data of type is assessed.
Optionally, the type of the corresponding comparing result of each keyword is any in following: conversion is correct, converts
Mistake, keyword are accidentally recalled does not recall with keyword;The quality assessment modules are specifically used for:
For each first keyword, from the corresponding annotation results of the multiple structured patient record data, described in acquisition
The corresponding comparing result of first keyword, first keyword are any one in the keyword;
According to the corresponding comparing result of first keyword, the first interpretation of result information, first result point are obtained
Analysis information includes: that the type of comparing result is to convert the quantity of correct first keyword, the type of comparing result to turn
Change the quantity of first keyword of mistake, the number that the type of comparing result is first keyword that keyword is accidentally recalled
Amount, the quantity that the type of comparing result is first keyword that keyword is not recalled;
According to the first interpretation of result information, the corresponding accuracy rate of first keyword and recall rate are obtained;
According to the corresponding accuracy rate of each keyword and recall rate, structured patient record number corresponding to the medical type
According to quality assessed.
Optionally, the quality assessment modules are specifically used for:
Type according to comparing result is to convert the quantity of correct first keyword, the type of comparing result to turn
The type of the quantity and comparing result of changing first keyword of mistake is first keyword that keyword is accidentally recalled
Quantity, obtain the quantity that first keyword is called back;
It is to convert the correctly quantity of first keyword and first keyword according to the type of comparing result
The quantity being called back obtains the corresponding accuracy rate of first keyword;
Quantity, the type of comparing result being called back according to first keyword are described first that keyword is accidentally recalled
The quantity of keyword and the type of comparing result are the quantity for first keyword that keyword is not recalled, described in acquisition
The corresponding recall rate of first keyword.
Optionally, the type of the corresponding comparing result of each keyword is any in following: conversion is correct, converts
Mistake, keyword are accidentally recalled does not recall with keyword;The quality assessment modules are specifically used for:
According to the corresponding annotation results of each structured patient record data, the second interpretation of result information is obtained, described second
Interpretation of result information includes: that the type of comparing result is to convert the quantity of correct each keyword, the type of comparing result to turn
Change the quantity of each keyword of mistake, the quantity that the type of comparing result is each keyword that keyword is accidentally recalled and comparison
As a result type is the quantity for each keyword that keyword is not recalled;
According to the second interpretation of result information, the corresponding standard of the corresponding structured patient record data of the medical type is obtained
True rate and recall rate.
It optionally, further include correction result in the annotation results, the correction result includes: that the type of comparing result is
The corresponding correction value of each keyword of transcription error and the type of comparing result are each keyword that keyword is not recalled and each
The corresponding value of keyword;Described device further include:
Display module, for being shown to the abnormal data in the multiple structured patient record data, and to described
Correction result is shown;Wherein, it is that transcription error, keyword are accidentally recalled or closed that the abnormal data, which is the type of comparing result,
The key-value pair data that key word is not recalled.
Optionally, the first acquisition module is specifically used for:
According to assessment task, medical type and maximum assessment quantity to be assessed are obtained;
According to the medical type and the maximum assessment quantity, it is corresponding that the medical type is obtained from medical data base
Multiple structured patient record data to be assessed;Wherein, the quantity of the structured patient record data be less than or equal to it is described most
Big assessment quantity.
Optionally, the first acquisition module is specifically used for:
Target collection is obtained from the medical data base, includes the corresponding knot of the medical type in the target collection
Structure medical record data;
If the quantity of the structured patient record data in the target collection is greater than the maximum assessment quantity, from institute
The structured patient record data that maximum assessment quantity is randomly choosed in target collection are stated as the structured patient record number to be assessed
According to;
If the quantity of the structured patient record data in the target collection is less than or equal to the maximum assessment number
Amount, then regard the structured patient record data in the target collection as the structured patient record data to be assessed.
The third aspect, the embodiment of the present invention provide a kind of quality assessment arrangement of structured patient record data, comprising: storage
Device, processor and computer program, in the memory, the processor runs the meter for the computer program storage
Calculation machine program executes such as the described in any item methods of first aspect.
Fourth aspect, the embodiment of the present invention provide a kind of computer readable storage medium, the computer-readable storage medium
Matter includes computer program, and such as first aspect described in any item methods are realized when the computer program is executed by processor.
Method for evaluating quality, device and the equipment of structured patient record data provided in an embodiment of the present invention, this method comprises:
According to medical type, the corresponding multiple structured patient record data to be assessed of the medical type are obtained from medical data base,
Wherein, the medical data base is used to store the original medical record data of different medical type, and to each original case history number
The structured patient record data handled according to structuring is carried out, each structured patient record data include at least one key-value pair
Data, each key-value pair data include keyword and the corresponding value of the keyword;Obtain each structured patient record number
It include each keyword and the corresponding comparing result of each keyword in the annotation results according to corresponding annotation results;
Wherein, the annotation results are to compare the structured patient record data and the original medical record data;According to
The corresponding annotation results of each structured patient record data, to the quality of the corresponding structured patient record data of the medical type into
Row assessment.By the above process, the quality evaluation process to structured patient record data is realized;In addition, the present embodiment is to knot
When structure medical record data is assessed, is assessed, can be determined not for the structured patient record data of different medical type
With the quality of the structured patient record data of medical treatment type, the accuracy of quality evaluation is improved.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention without any creative labor, may be used also for those of ordinary skill in the art
To obtain other drawings based on these drawings.
Fig. 1 is the quality evaluation process schematic of structured patient record data provided in an embodiment of the present invention;
Fig. 2 is the flow diagram of the method for evaluating quality for the structured patient record data that one embodiment of the invention provides;
Fig. 3 is the flow diagram provided in an embodiment of the present invention that quality evaluation is carried out using keyword dimension;
Fig. 4 is the flow diagram provided in an embodiment of the present invention that quality evaluation is carried out using whole dimension;
Fig. 5 be another embodiment of the present invention provides structured patient record data method for evaluating quality flow diagram;
Fig. 6 is the structural schematic diagram of the quality assessment device for the structured patient record data that one embodiment of the invention provides;
Fig. 7 be another embodiment of the present invention provides structured patient record data quality assessment device structural schematic diagram;
Fig. 8 is the structural schematic diagram of the quality assessment arrangement of structured patient record data provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Description and claims of this specification and term " first ", " second ", " third " " in above-mentioned attached drawing
The (if present)s such as four " are to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should manage
The data that solution uses in this way are interchangeable under appropriate circumstances, so that the embodiment of the present invention described herein for example can be to remove
Sequence other than those of illustrating or describe herein is implemented.In addition, term " includes " and " having " and theirs is any
Deformation, it is intended that cover it is non-exclusive include, for example, containing the process, method of a series of steps or units, system, production
Product or equipment those of are not necessarily limited to be clearly listed step or unit, but may include be not clearly listed or for this
A little process, methods, the other step or units of product or equipment inherently.
Data in computer information system are divided into structural data and unstructured data.For subsequent descriptions side
Just, the meaning and form of unstructured data and structural data are described first.
Unstructured data refers to that data structure is irregular or imperfect, does not have predefined data model, inconvenience
The data presented with database two dimension logical table.The format and standard of unstructured data have diversity, usually following
Form: text document, e-mail messages, chat record, picture, audio-video etc..
Structural data is also referred to as row data, is by two-dimentional table structure come the data of logical expression and realization, stringent abides by
Data format and length specification are followed, storage and management are mainly carried out by relevant database.Structural data generallys use key
The form of value pair is indicated that is, in the form of keyword (key)-keyword value (value).Certainly, crucial under some scenes
Word is referred to as field, and the value of keyword can also correspond to the attribute of referred to as field.
Since the format and standard of unstructured data have a diversity, unstructured data be difficult by computer understanding and
Processing, when a large amount of unstructured data is used for the fields such as storage, retrieval, intellectual analysis, can bring many inconvenience.Therefore,
In many scenes, the scene analyzed a large amount of unstructured datas is especially needed, is needed using structuring processing technique
Unstructured data is converted into structural data.Further, in order to guarantee conversion after structural data accuracy and
Validity, it is also necessary to which the quality of above structureization processing is assessed.
Fig. 1 is the quality evaluation process schematic of structured patient record data provided in an embodiment of the present invention.As shown in Figure 1,
Original medical record data is unstructured data, carries out structuring to original medical record data and handles to obtain structured patient record data.So
Afterwards, original medical record data and corresponding structured patient record data are compared into mark, obtains annotation results.Wherein, mark knot
Fruit can indicate which key-value pair is correct by conversion, which key-value pair is by transcription error etc..Finally, according to annotation results, to knot
The quality of structureization processing is assessed.
Wherein, in the present embodiment, " quality of structured patient record data " are referred to as " quality of structuring processing ",
Characterization is meant that: the structured patient record data and the original medical record data that original medical record data is handled by structuring it
Between the goodness of fit.Illustratively, it if the goodness of fit between structured patient record data and corresponding original medical record data is higher, says
The quality of bright structuring processing is higher, that is, the quality of structured patient record data is higher.If structured patient record data and corresponding original
The goodness of fit between beginning medical record data is lower, then illustrates that the quality of structuring processing is lower, that is, the quality of structured patient record data
It is lower.Illustratively, if original medical record data is passed through in the structured patient record data that structuring is handled, including 10 key assignments
It is right, it is assumed that the accuracy rate threshold value of quality evaluation is 80%, then is more than or is converted equal to 8 correct when having in 10 key-value pairs
When, it is believed that the quality of structuring processing is higher, when having correct by conversion less than 8, it is believed that the quality of structuring processing is lower.
Referring to Fig. 1, in a kind of possible scene, is realized using structuring processing unit and original medical record data is converted into knot
The process of structure medical record data compares structured patient record data and original medical record data using comparison annotation equipment realization
The process of mark, the process that annotation results are analyzed using quality assessment device.Wherein, above-mentioned structuring handles dress
It sets, compare annotation equipment and quality assessment device and can be respectively provided to different electronic equipments, can also be two therein
Or three devices are integrated into an electronic equipment.The present embodiment is not especially limited this.
Technical solution of the present invention is described in detail with specifically embodiment below.These specific implementations below
Example can be combined with each other, and the same or similar concept or process may be repeated no more in some embodiments.
Fig. 2 is the flow diagram of the method for evaluating quality for the structured patient record data that one embodiment of the invention provides, this
The method of embodiment can be executed by quality assessment device, which can be the form of software and/or hardware.As shown in Fig. 2,
The method of the present embodiment includes:
S201: according to medical type, the corresponding multiple knots to be assessed of the medical type are obtained from medical data base
Structure medical record data, wherein the medical data base is used to store the original medical record data of different medical type, and to each institute
It states original medical record data and carries out the structured patient record data that structuring is handled, each structured patient record data include extremely
A few key-value pair data, each key-value pair data includes keyword and the corresponding value of the keyword.
The method of the present embodiment can be used for assessing the quality of some corresponding structured patient record data of medical treatment type.Wherein,
Medical type can be by different partition dimensions.Can be divided according to case history type, such as: case history of being admitted to hospital, patient medical history,
Emergency record, discharge case history etc.;It can also be divided according to the type of hospital, such as: children's medical treatment, woman produce medical treatment, synthesis
Hospital etc.;It can also be divided according to the type of department, such as: paediatrics, obstetrics, surgery, internal medicine etc..Different medical type pair
The original medical record data and structured patient record data answered are stored in medical data base, when being assessed, according to be assessed
Medical type obtains the corresponding structured patient record data of the medical treatment type from medical data base.
It should be understood that original medical record data is usually non-structured form, can be incited somebody to action using structuring processing technique
Original medical record data is converted to structured patient record data.Illustratively, being by the data processing in original case history take chapters and sections as list
Position, field name unified structured form, alternatively, extracted from original case history the duration of such as symptom, yin and yang attribute,
The features such as the diagnosis certainty of disease.By structuring treatment process, the original case history that usually only doctor can just be understood turns
It is changed to the structured patient record that computer can be understood.It should be noted that the present embodiment is not made to have for structuring processing technique
Body limits.The process of structuring processing can be executed using structuring processing unit.
In the present embodiment, structured patient record data are stored in the form of key-value pair.Number in every part of original case history
It is stated to be original medical record data, the data that the data in a original case history are converted to is known as a structured patient record
Data.It should be understood that each structured patient record data include one or more key-value pair data.Each key-value pair data packet
Include keyword (key) and the corresponding value of the keyword (value).
S202: obtaining the corresponding annotation results of each structured patient record data, includes each described in the annotation results
Keyword and the corresponding comparing result of each keyword;Wherein, the annotation results be by the structured patient record data with
What the original medical record data compared.
Wherein, what annotation results indicated is the difference that structured patient record data and original medical record data compare.
Illustratively, whether correct by conversion the corresponding comparing result of each keyword may be used to indicate the keyword.
Optionally, the type of the corresponding comparing result of each keyword is any in following: conversion is correct, converts
Mistake, keyword are accidentally recalled does not recall with keyword.Illustratively, for some keyword, if the pass that structuring obtains
Key word and value all conversions are correct, then the type of the corresponding comparing result of the keyword is " conversion is correct ";What if structuring obtained
The value of keyword is transcription error, then the type of the corresponding comparing result of the keyword is " transcription error ";If the keyword
It does not need to identify with value, and structuring treatment process has identified the keyword, then the corresponding comparison of the keyword
As a result type is " keyword is accidentally recalled ";If desired some keyword and value are identified, but structuring treatment process is not known
It does not come out, then the type of the corresponding comparing result of the keyword is " keyword is not recalled ".
In a kind of possible embodiment, structured patient record data and original medical record data are compared to obtain mark knot
The process of fruit can be executed by comparison annotation equipment.Illustratively, comparison annotation equipment extracts the key in original medical record data
Word information and the corresponding value of keyword message, the information extracted and the key-value pair in structured patient record data are compared,
Comparing result is obtained, and is the respective comparing result of each keyword.
It, can also be by the mark personnel of profession to structured patient record data and original disease in alternatively possible embodiment
It counts one by one according to comparing, obtains the corresponding comparing result of each keyword in structured patient record data.
It optionally, can also include correction result in the annotation results, the correction result includes: the class of comparing result
Type is the corresponding correction value of each keyword of transcription error and the type of comparing result is each keyword that keyword is not recalled
Value corresponding with each keyword.
Illustratively, in above-mentioned comparison annotation process, the type for comparing result is the keyword of " transcription error ",
The corresponding correction value of the keyword can also be obtained according to original medical record data, and the correction value is also added to annotation results
In.
Illustratively, in above-mentioned comparison annotation process, the type for comparing result is the pass of " keyword is not recalled "
The value of the keyword and the keyword can also be added in annotation results by key word according to original medical record data.
In the present embodiment, the corresponding annotation results of each structured patient record data are stored in destination file.Illustratively,
Destination file can be JSON file.
Illustratively, the data in destination file are stored using following form, wherein that * * * is indicated is key corresponding
Value.
{ " key1 ": { " value ": " * * * " " type ": " converts correct/transcription error/keyword and accidentally recalls/keyword
Do not recall " },
" key2 ": " value ": " * * * ", " type ": " conversion is correct/transcription error/keyword accidentally recalls/keyword not
Recall " } }
S203: according to the corresponding annotation results of each structured patient record data, structure corresponding to the medical type
The quality for changing medical record data is assessed.
In the present embodiment, according to above-mentioned annotation results, the structured patient record quality of data corresponding to the medical treatment type
It is assessed.It is exemplary, threshold value can be respectively set for the type of comparing result, it is assumed that convert correct threshold value and be set as
80%, then: if in above-mentioned annotation results, the accounting for being noted as each keyword of conversion right type is more than or equal to
80%, it is determined that the quality of structuring processing is higher, that is to say, that the accuracy of structured patient record data is higher.If above-mentioned
In annotation results, the accounting of each keyword of conversion right type is noted as lower than 80%, it is determined that the matter of structuring processing
It measures lower, that is to say, that the accuracy of structured patient record data is lower.
It should be noted that different threshold values can be respectively set according to the type of various comparing results in practical application,
To carry out the quality evaluation of a variety of dimensions to structuring processing, the comprehensive of quality evaluation is improved.
It should be understood that being carried out in structuring treatment process to original medical record data, the same structuring Processing Algorithm
It may be different for the conversion quality of the data of different medical type.Illustratively, a pattern handling algorithm is to case history of being admitted to hospital
Conversion quality may be higher, and may be lower for the conversion quality for case history of leaving hospital.Therefore, the present embodiment is to structuring disease
When counting one by one according to being assessed, is assessed for the structured patient record data of different medical type, can determine different medical
The quality of the structured patient record data of type, improves the accuracy of quality evaluation.
Below with reference to two kinds of possible embodiments, using keyword dimension and whole dimension to specific quality evaluation
Journey is described.
In the first possible embodiment, quality evaluation can be carried out using keyword dimension.Fig. 3 is that the present invention is implemented
The flow diagram that quality evaluation is carried out using keyword dimension that example provides.As shown in figure 3, this method comprises:
S301: being directed to each first keyword, from the corresponding annotation results of the multiple structured patient record data, obtains
The corresponding comparing result of first keyword, first keyword are any one in the keyword.
S302: according to the corresponding comparing result of first keyword, the first interpretation of result information, first knot are obtained
Fruit analysis information includes: that the type of comparing result is to convert quantity, the type of comparing result of correctly first keyword
Quantity, the type of comparing result for first keyword of transcription error are first keyword that keyword is accidentally recalled
Quantity, the type of comparing result be the quantity of first keyword that keyword is not recalled.
S303: according to the first interpretation of result information, the corresponding accuracy rate of first keyword and recall rate are obtained.
Illustratively, it is assumed that in 1000 structured patient record data to be assessed, each structured patient record data include 10
A keyword, respectively key1 are to key10.It include 10 above-mentioned passes in the corresponding annotation results of each structured patient record data
The corresponding comparing result of key word.Such as: the corresponding annotation results of one of structured patient record data are as follows:
" key1 ": { " value ": " * * * ", " type ": " conversion is correct " },
" key2 ": { " value ": " * * * ", " type ": " conversion is correct " },
" key3 ": { " value ": " * * * ", " type ": " transcription error " },
" key4 ": { " value ": " * * * ", " type ": " transcription error " },
" key5 ": { " value ": " * * * ", " type ": " conversion is correct " },
" key6 ": { " value ": " * * * ", " type ": " conversion is correct " },
" key7 ": { " value ": " * * * ", " type ": " keyword is accidentally recalled " },
" key8 ": { " value ": " * * * ", " type ": " conversion is correct " },
" key9 ": { " value ": " * * * ", " type ": " keyword is not recalled " },
" key10 ": { " value ": " * * * ", " type ": " conversion is correct " } }
In the present embodiment, the dimension of each keyword quality evaluation can be carried out from above-mentioned 10 keywords.Specifically,
It is assessed using the corresponding accuracy rate of each keyword and recall rate.
Illustratively, for each keyword in above-mentioned 10 keywords, S301 in the present embodiment is executed respectively extremely
S303.By taking keyword key1 as an example, from the corresponding annotation results of 1000 structured patient record data, key1 pairs of keyword is obtained
The comparing result answered.
Further, from the corresponding comparing result of keyword key1, the first interpretation of result information is obtained, comprising: comparison
As a result type is to convert the quantity of correct keyword key1, the type of comparing result as the keyword key1 of transcription error
Quantity, the type of comparing result be the quantity of keyword key1, the type of comparing result that keyword is accidentally recalled be keyword not
The quantity of the keyword key1 recalled.
Further, according to above-mentioned first interpretation of result information, the corresponding accuracy rate of keyword key1 and recall rate are obtained.
Wherein, accuracy rate instruction be the keyword of how many ratio in the keyword that is identified in structuring processing is to be converted
Correctly convert.Recall rate instruction is the key that how many ratio in the keyword that should be identified in structuring processing
Word is identified.
In a kind of possible embodiment, according to the type of comparing result be convert the quantity of correct keyword key1,
The type of comparing result is the quantity of keyword key1 of transcription error and the type of comparing result is that keyword is accidentally recalled
The quantity of keyword key1 obtains the quantity that keyword key1 is called back.It is that conversion is correctly closed according to the type of comparing result
The quantity that the quantity and keyword key1 of key word key1 is called back obtains the corresponding accuracy rate of keyword key1.According to key
The quantity and comparison knot that the type of quantity, comparing result that word key1 is called back is the keyword key1 that keyword is accidentally recalled
The type of fruit is the quantity for the keyword key1 that keyword is not recalled, obtains the corresponding recall rate of keyword key1.
Illustratively, quantity=comparing result type that keyword key1 is called back is to convert correct keyword key1
Quantity+comparing result type be quantity+comparing result type of keyword key1 of transcription error be that keyword is accidentally called together
The quantity of the keyword key1 returned.
The type of the corresponding accuracy rate=comparing result of keyword key1 is to convert quantity/pass of correct keyword key1
The quantity that key word key1 is called back
The corresponding recall rate of keyword key1=(quantity-comparing result type that keyword key1 is called back is key
The quantity for the keyword key1 that word is accidentally recalled)/(quantity-comparing result type that keyword key1 is called back is keyword mistake
Quantity+comparing result type of the keyword key1 recalled is the quantity for the keyword key1 that keyword is not recalled)
S304: according to the corresponding accuracy rate of each keyword and recall rate, structuring corresponding to the medical type
The quality of medical record data is assessed.
For above-mentioned 10 keywords, S301 to S303 is executed respectively, is obtained the corresponding accuracy rate of 10 keywords and is called together
The rate of returning.In step S304, by the corresponding accuracy rate of each keyword and recall rate, the matter of structuring processing can be intuitively obtained
Amount.It illustratively, can be according to the corresponding original disease of the keyword if the accuracy rate or recall rate of some keyword are lower
It counts evidence one by one, structuring Processing Algorithm is optimized.
Certainly, it in the case where keyword quantity is more, can also further to the corresponding accuracy rate of each keyword and call together
The rate of returning is weighted, and obtains the corresponding total quality assessment result of multiple structured patient record data.
In second of possible embodiment, quality evaluation can be carried out using whole dimension.Fig. 4 is the embodiment of the present invention
The flow diagram that quality evaluation is carried out using whole dimension of offer.As shown in figure 4, this method comprises:
S401: according to the corresponding annotation results of each structured patient record data, obtaining the second interpretation of result information, described
Second interpretation of result information includes: that the type of comparing result is to convert quantity, the type of comparing result of correctly each keyword
The quantity of each keyword, the type of comparing result for transcription error be each keyword that keyword is accidentally recalled quantity and
The type of comparing result is the quantity for each keyword that keyword is not recalled.
S402: according to the second interpretation of result information, the corresponding structured patient record data pair of the medical type are obtained
The accuracy rate and recall rate answered.
The specific embodiment of the present embodiment is similar with embodiment illustrated in fig. 3, the difference is that keyword is not distinguished, it will
All keywords are unified to be considered.That is, including in the second interpretation of result information: 1000 structured patient record data pair
In the annotation results answered, the type of comparing result is to convert the quantity of correct each keyword, the type of comparing result as conversion
The quantity of each keyword of mistake, the quantity that the type of comparing result is each keyword that keyword is accidentally recalled and comparison knot
The type of fruit is the quantity for each keyword that keyword is not recalled.
Further, structuring handles the similar with embodiment illustrated in fig. 3 of corresponding accuracy rate and recall rate in S402, this
Place repeats no more.
Accuracy rate and recall rate in the present embodiment can also be shown using diagrammatic form, such as: line chart, column
Figure etc..Further, the assessment result of different batches or different medical type can also be shown, in the graph intuitively to reflect
Structuring handles the quality change situation in iterative process.
The method for evaluating quality of structured patient record data provided in this embodiment, comprising: according to medical type, from medical number
According to obtaining the corresponding multiple structured patient record data to be assessed of the medical type in library, wherein the medical data base is used
Carry out what structuring was handled in the original medical record data of storage different medical type, and to each original medical record data
Structured patient record data, each structured patient record data include at least one key-value pair data, each key assignments logarithm
According to including keyword and the corresponding value of the keyword;The corresponding annotation results of each structured patient record data are obtained, it is described
It include each keyword and the corresponding comparing result of each keyword in annotation results;Wherein, the annotation results be by
What the structured patient record data and the original medical record data compared;According to each structured patient record data pair
The annotation results answered assess the quality of the corresponding structured patient record data of the medical treatment type.By the above process, real
The quality evaluation process to structured patient record data is showed;In addition, the present embodiment is when assessing structured patient record data,
It is assessed for the structured patient record data of different medical type, can determine the structured patient record number of different medical type
According to quality, improve the accuracy of quality evaluation.
Fig. 5 be another embodiment of the present invention provides structured patient record data method for evaluating quality flow diagram.
As shown in figure 5, the method for the present embodiment includes:
S501: according to assessment task, medical type and maximum assessment quantity to be assessed are obtained.
S502: according to the medical type and the maximum assessment quantity, the medical class is obtained from medical data base
The corresponding multiple structured patient record data to be assessed of type.
Wherein, the quantity of the structured patient record data is less than or equal to the maximum assessment quantity.
In a kind of possible embodiment, user creates assessment task in quality assessment device, and formulates this assessment and appoint
Corresponding medical type of being engaged in and maximum assessment quantity.After task creation success, quality assessment device is screened in medical data base
Structured patient record data to be assessed out.
Optionally, target collection is obtained from the medical data base, includes the medical type in the target collection
Corresponding structured patient record data;It is commented if the quantity of the structured patient record data in the target collection is greater than the maximum
Estimate quantity, then randomly chooses the structured patient record data of maximum assessment quantity from the target collection as structure to be assessed
Change medical record data;If the quantity of the structured patient record data in the target collection is less than or equal to the maximum assessment
Structured patient record data in the target collection are then used as structured patient record data to be assessed by quantity.
Above-mentioned randomly selected process can be realized using stochastic selection algorithm.It illustratively, is each in target collection
Structured patient record data distribute unique identification, are upset the data in target collection using algorithm is upset at random.Assuming that most
Big assessment quantity is that N identifies the selection as the structured patient record data of 0-N-1 as data to be assessed then since 0.
S503: obtaining the corresponding annotation results of each structured patient record data, includes each described in the annotation results
Keyword and the corresponding comparing result of each keyword, the type of the comparing result are any in following: conversion is correct,
Transcription error, keyword are accidentally recalled does not recall with keyword.
S504: according to the corresponding annotation results of each structured patient record data, structure corresponding to the medical type
The quality for changing medical record data is assessed.
In the present embodiment, the specific implementation process of S503 and S504 are similar to the above embodiments, and details are not described herein again.
S505: the abnormal data in the multiple structured patient record data is shown, and to the correction result
It is shown.
Wherein, it is that transcription error, keyword are accidentally recalled or keyword is not called together that the abnormal data, which is the type of comparing result,
The key-value pair data returned.The correction result includes: that the type of comparing result is the corresponding amendment of each keyword of transcription error
Value and the type of comparing result are each keyword and the corresponding value of each keyword that keyword is not recalled.
Illustratively, above-mentioned abnormal data and correction result are exported and is shown from medical data base.What these showed
Data can be used as the analysis foundation of medical record data structuring increased quality.Further, it can also be tied according to being corrected after assessment
Fruit is updated the structured patient record data in medical data base, improves the accuracy of structured patient record data.
Fig. 6 is the structural schematic diagram of the quality assessment device for the structured patient record data that one embodiment of the invention provides.Such as
Shown in Fig. 6, the quality assessment device 600 of structured patient record data provided in this embodiment, comprising: first obtains module 601, the
Two obtain module 602 and quality assessment modules 603.
Wherein, first module 601 is obtained, for according to medical type, obtaining the medical type from medical data base
Corresponding multiple structured patient record data to be assessed, wherein the medical data base is used to store the original of different medical type
Beginning medical record data, and the structured patient record data that structuring is handled, Mei Gesuo are carried out to each original medical record data
Stating structured patient record data includes at least one key-value pair data, and each key-value pair data includes keyword and the key
The corresponding value of word;
Second obtains module 602, for obtaining the corresponding annotation results of each structured patient record data, the mark knot
It include each keyword and the corresponding comparing result of each keyword in fruit;Wherein, the annotation results are by the knot
What structure medical record data and the original medical record data compared;
Quality assessment modules 603, for according to the corresponding annotation results of each structured patient record data, to the medical treatment
The quality of the corresponding structured patient record data of type is assessed.
Device provided in this embodiment can be used for executing embodiment of the method as shown in Figure 2, realization principle and technology effect
Seemingly, details are not described herein again for fruit.
Fig. 7 be another embodiment of the present invention provides structured patient record data quality assessment device structural schematic diagram.
As shown in fig. 7, on the basis of embodiment shown in Fig. 6, the quality assessment device of structured patient record data provided in this embodiment
600, it can also include: display module 604.
Optionally, the type of the corresponding comparing result of each keyword is any in following: conversion is correct, converts
Mistake, keyword are accidentally recalled does not recall with keyword;The quality assessment modules 603 are specifically used for:
For each first keyword, from the corresponding annotation results of the multiple structured patient record data, described in acquisition
The corresponding comparing result of first keyword, first keyword are any one in the keyword;
According to the corresponding comparing result of first keyword, the first interpretation of result information, first result point are obtained
Analysis information includes: that the type of comparing result is to convert the quantity of correct first keyword, the type of comparing result to turn
Change the quantity of first keyword of mistake, the number that the type of comparing result is first keyword that keyword is accidentally recalled
Amount, the quantity that the type of comparing result is first keyword that keyword is not recalled;
According to the first interpretation of result information, the corresponding accuracy rate of first keyword and recall rate are obtained;
According to the corresponding accuracy rate of each keyword and recall rate, structured patient record number corresponding to the medical type
According to quality assessed.
Optionally, the quality assessment modules 603 are specifically used for:
Type according to comparing result is to convert the quantity of correct first keyword, the type of comparing result to turn
The type of the quantity and comparing result of changing first keyword of mistake is first keyword that keyword is accidentally recalled
Quantity, obtain the quantity that first keyword is called back;
It is to convert the correctly quantity of first keyword and first keyword according to the type of comparing result
The quantity being called back obtains the corresponding accuracy rate of first keyword;
Quantity, the type of comparing result being called back according to first keyword are described first that keyword is accidentally recalled
The quantity of keyword and the type of comparing result are the quantity for first keyword that keyword is not recalled, described in acquisition
The corresponding recall rate of first keyword.
Optionally, the type of the corresponding comparing result of each keyword is any in following: conversion is correct, converts
Mistake, keyword are accidentally recalled does not recall with keyword;The quality assessment modules 603 are specifically used for:
According to the corresponding annotation results of each structured patient record data, the second interpretation of result information is obtained, described second
Interpretation of result information includes: that the type of comparing result is to convert the quantity of correct each keyword, the type of comparing result to turn
Change the quantity of each keyword of mistake, the quantity that the type of comparing result is each keyword that keyword is accidentally recalled and comparison
As a result type is the quantity for each keyword that keyword is not recalled;
According to the second interpretation of result information, the corresponding standard of the corresponding structured patient record data of the medical type is obtained
True rate and recall rate.
It optionally, further include correction result in the annotation results, the correction result includes: that the type of comparing result is
The corresponding correction value of each keyword of transcription error and the type of comparing result are each keyword that keyword is not recalled and each
The corresponding value of keyword;
The display module 604, for being shown to the abnormal data in the multiple structured patient record data, and
The correction result is shown;Wherein, it is that transcription error, keyword are accidentally called together that the abnormal data, which is the type of comparing result,
It returns or the key-value pair data do not recalled of keyword.
Optionally, the first acquisition module 601 is specifically used for:
According to assessment task, medical type and maximum assessment quantity to be assessed are obtained;
According to the medical type and the maximum assessment quantity, it is corresponding that the medical type is obtained from medical data base
Multiple structured patient record data to be assessed;Wherein, the quantity of the structured patient record data be less than or equal to it is described most
Big assessment quantity.
Optionally, the first acquisition module 601 is specifically used for:
Target collection is obtained from the medical data base, includes the corresponding knot of the medical type in the target collection
Structure medical record data;
If the quantity of the structured patient record data in the target collection is greater than the maximum assessment quantity, from institute
The structured patient record data that maximum assessment quantity is randomly choosed in target collection are stated as the structured patient record number to be assessed
According to;
If the quantity of the structured patient record data in the target collection is less than or equal to the maximum assessment number
Amount, then regard the structured patient record data in the target collection as the structured patient record data to be assessed.
Device provided in this embodiment can be used for executing the technical solution of any of the above-described embodiment of the method, realization principle
Similar with technical effect, details are not described herein again.
Fig. 8 is the structural schematic diagram of the quality assessment arrangement of structured patient record data provided in an embodiment of the present invention.Such as Fig. 8
It is shown, the quality assessment arrangement 800 of structured patient record data provided in this embodiment, comprising: processor 801 and memory
802;Wherein, memory 802, for storing computer program;Processor 801, for executing the computer journey of memory storage
Sequence, to realize the method in above-described embodiment.It specifically may refer to the associated description in preceding method embodiment.
Optionally, memory 802 can also be integrated with processor 801 either independent.
When the memory 802 is independently of the device except processor 801, the quality of the structured patient record data
Assessment equipment 800 can also include: bus 803, for connecting the memory 802 and processor 801.
The quality assessment arrangement of structured patient record data provided in this embodiment can be used for executing any of the above-described method and implement
Technical solution in example, it is similar that the realization principle and technical effect are similar, and details are not described herein again for the present embodiment.
The embodiment of the present invention also provides a kind of computer readable storage medium, and the computer readable storage medium includes meter
Calculation machine program, the computer program is for realizing the technical solution in either method embodiment as above.
The embodiment of the present invention also provides a kind of chip, comprising: memory, processor and computer program, the calculating
Machine program stores in the memory, and the processor runs the computer program and executes in any of the above-described embodiment of the method
Technical solution.
In several embodiments provided by the present invention, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, apparatus embodiments described above are merely indicative, for example, the division of the module, only
Only a kind of logical function partition, there may be another division manner in actual implementation, for example, multiple modules can combine or
It is desirably integrated into another system, or some features can be ignored or not executed.Another point, it is shown or discussed it is mutual it
Between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication link of device or module
It connects, can be electrical property, mechanical or other forms.
The module as illustrated by the separation member may or may not be physically separated, aobvious as module
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.Some or all of the modules therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
It, can also be in addition, each functional module in each embodiment of the present invention can integrate in one processing unit
It is that modules physically exist alone, can also be integrated in one unit with two or more modules.Above-mentioned module at
Unit both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
The above-mentioned integrated module realized in the form of software function module, can store and computer-readable deposit at one
In storage media.Above-mentioned software function module is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or the network equipment etc.) or processor (English: processor) execute this hair
The part steps of bright each embodiment the method.
It should be understood that above-mentioned processor can be central processing unit (English: Central Processing Unit, letter
Claim: CPU), can also be other general processors, digital signal processor (English: Digital Signal Processor,
Referred to as: DSP), specific integrated circuit (English: Application Specific Integrated Circuit, referred to as:
ASIC) etc..General processor can be microprocessor or the processor is also possible to any conventional processor etc..In conjunction with Shen
Please be disclosed method the step of can be embodied directly in hardware processor and execute completion, or with hardware in processor and soft
Part block combiner executes completion.
Memory may include high speed RAM memory, it is also possible to and it further include non-volatile memories NVM, for example, at least one
Magnetic disk storage can also be USB flash disk, mobile hard disk, read-only memory, disk or CD etc..
Bus can be industry standard architecture (Industry Standard Architecture, ISA) bus, outer
Portion's apparatus interconnection (Peripheral Component, PCI) bus or extended industry-standard architecture (Extended
Industry Standard Architecture, EISA) bus etc..Bus can be divided into address bus, data/address bus, control
Bus etc..For convenient for indicating, the bus in attached drawing of the present invention does not limit only a bus or a type of bus.
Above-mentioned storage medium can be by any kind of volatibility or non-volatile memory device or their combination
It realizes, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable
Read-only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, flash memory,
Disk or CD.Storage medium can be any usable medium that general or specialized computer can access.
A kind of illustrative storage medium is coupled to processor, believes to enable a processor to read from the storage medium
Breath, and information can be written to the storage medium.Certainly, storage medium is also possible to the component part of processor.It processor and deposits
Storage media can be located at specific integrated circuit (Application Specific Integrated Circuits, referred to as:
ASIC in).Certainly, pocessor and storage media can also be used as discrete assembly and be present in electronic equipment or main control device.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above-mentioned each method embodiment can lead to
The relevant hardware of program instruction is crossed to complete.Program above-mentioned can be stored in a computer readable storage medium.The journey
When being executed, execution includes the steps that above-mentioned each method embodiment to sequence;And storage medium above-mentioned include: ROM, RAM, magnetic disk or
The various media that can store program code such as person's CD.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations;To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement;And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (16)
1. a kind of method for evaluating quality of structured patient record data characterized by comprising
According to medical type, the corresponding multiple structured patient record numbers to be assessed of the medical type are obtained from medical data base
According to, wherein the medical data base is used to store the original medical record data of different medical type, and to each original case history
Data carry out the structured patient record data that structuring is handled, and each structured patient record data include at least one key assignments
To data, each key-value pair data includes keyword and the corresponding value of the keyword;
It obtains the corresponding annotation results of each structured patient record data, includes each keyword in the annotation results and each
The corresponding comparing result of the keyword;Wherein, the annotation results are by the structured patient record data and the original disease
Count what evidence compared one by one;
According to the corresponding annotation results of each structured patient record data, structured patient record data corresponding to the medical type
Quality assessed.
2. the method according to claim 1, wherein the type of the corresponding comparing result of each keyword is
Any in following: conversion is correct, transcription error, keyword are accidentally recalled and do not recalled with keyword;It is described according to each structure
Change the corresponding annotation results of medical record data, the quality of the corresponding structured patient record data of the medical treatment type is assessed, is wrapped
It includes:
For each first keyword, from the corresponding annotation results of the multiple structured patient record data, described first is obtained
The corresponding comparing result of keyword, first keyword are any one in the keyword;
According to the corresponding comparing result of first keyword, the first interpretation of result information, the first interpretation of result letter are obtained
Breath includes: that the type of comparing result is that correctly quantity, the type of comparing result of first keyword are to convert mistake for conversion
The quantity of first keyword accidentally, the quantity that the type of comparing result is first keyword that keyword is accidentally recalled,
The type of comparing result is the quantity for first keyword that keyword is not recalled;
According to the first interpretation of result information, the corresponding accuracy rate of first keyword and recall rate are obtained;
According to the corresponding accuracy rate of each keyword and recall rate, to the corresponding structured patient record data of the medical type
Quality is assessed.
3. according to the method described in claim 2, it is characterized in that, described according to the first interpretation of result information, acquisition institute
State the corresponding accuracy rate of the first keyword and recall rate, comprising:
Type according to comparing result is that correctly quantity, the type of comparing result of first keyword are to convert mistake for conversion
The quantity of first keyword accidentally and the type of comparing result are the number for first keyword that keyword is accidentally recalled
Amount obtains the quantity that first keyword is called back;
It is to convert the correctly quantity of first keyword and first keyword to be called together according to the type of comparing result
The quantity returned obtains the corresponding accuracy rate of first keyword;
Quantity, the type of comparing result being called back according to first keyword are first key that keyword is accidentally recalled
The quantity of word and the type of comparing result are the quantity for first keyword that keyword is not recalled, obtain described first
The corresponding recall rate of keyword.
4. the method according to claim 1, wherein the type of the corresponding comparing result of each keyword is
Any in following: conversion is correct, transcription error, keyword are accidentally recalled and do not recalled with keyword;It is described according to each structure
Change the corresponding annotation results of medical record data, the quality of the corresponding structured patient record data of the medical treatment type is assessed, is wrapped
It includes:
According to the corresponding annotation results of each structured patient record data, the second interpretation of result information, second result are obtained
Analysis information includes: that the type of comparing result is that correctly the quantity of each keyword, the type of comparing result are that conversion is wrong for conversion
The quantity of each keyword accidentally, the quantity and comparing result that the type of comparing result is each keyword that keyword is accidentally recalled
Type be the quantity of each keyword that keyword is not recalled;
According to the second interpretation of result information, the corresponding accuracy rate of the corresponding structured patient record data of the medical type is obtained
And recall rate.
5. method according to any one of claims 1 to 4, which is characterized in that further include amendment knot in the annotation results
Fruit, the correction result include: that the type of comparing result is the corresponding correction value of each keyword of transcription error, and comparison is tied
The type of fruit is each keyword and the corresponding value of each keyword that keyword is not recalled;
It is described according to the corresponding annotation results of each structured patient record data, structured patient record corresponding to the medical type
After the quality of data is assessed, further includes:
Abnormal data in the multiple structured patient record data is shown, and the correction result is shown;
Wherein, it is the key assignments that transcription error, keyword are accidentally recalled or keyword is not recalled that the abnormal data, which is the type of comparing result,
To data.
6. method according to any one of claims 1 to 4, which is characterized in that it is described according to medical type, from medical data
The corresponding multiple structured patient record data to be assessed of the medical type are obtained in library, comprising:
According to assessment task, medical type and maximum assessment quantity to be assessed are obtained;
According to the medical type and the maximum assessment quantity, obtained from medical data base the medical type it is corresponding to
Multiple structured patient record data of assessment;Wherein, the quantity of the structured patient record data is less than or equal to the maximum and comments
Estimate quantity.
7. according to the method described in claim 6, it is characterized in that, described according to the medical type and the maximum assessment number
Amount obtains the corresponding multiple structured patient record data to be assessed of the medical type from medical data base, comprising:
Target collection is obtained from the medical data base, includes the corresponding structuring of the medical type in the target collection
Medical record data;
If the quantity of the structured patient record data in the target collection is greater than the maximum assessment quantity, from the mesh
The structured patient record data of the maximum assessment quantity of random selection are as the structured patient record data to be assessed in mark set;
If the quantity of the structured patient record data in the target collection is less than or equal to the maximum assessment quantity,
It regard the structured patient record data in the target collection as the structured patient record data to be assessed.
8. a kind of quality assessment device of structured patient record data characterized by comprising
First obtains module, corresponding to be assessed for according to medical type, obtaining the medical type from medical data base
Multiple structured patient record data, wherein the medical data base is used to store the original medical record data of different medical type, with
And the structured patient record data that structuring is handled, each structured patient record number are carried out to each original medical record data
According to including at least one key-value pair data, each key-value pair data includes keyword and the corresponding value of the keyword;
Second acquisition module is wrapped in the annotation results for obtaining each structured patient record data corresponding annotation results
Include each keyword and the corresponding comparing result of each keyword;Wherein, the annotation results are by the structuring disease
Count what evidence was compared with the original medical record data one by one;
Quality assessment modules, for according to the corresponding annotation results of each structured patient record data, to the medical type pair
The quality for the structured patient record data answered is assessed.
9. device according to claim 8, which is characterized in that the type of the corresponding comparing result of each keyword is
Any in following: conversion is correct, transcription error, keyword are accidentally recalled and do not recalled with keyword;The quality assessment modules tool
Body is used for:
For each first keyword, from the corresponding annotation results of the multiple structured patient record data, described first is obtained
The corresponding comparing result of keyword, first keyword are any one in the keyword;
According to the corresponding comparing result of first keyword, the first interpretation of result information, the first interpretation of result letter are obtained
Breath includes: that the type of comparing result is that correctly quantity, the type of comparing result of first keyword are to convert mistake for conversion
The quantity of first keyword accidentally, the quantity that the type of comparing result is first keyword that keyword is accidentally recalled,
The type of comparing result is the quantity for first keyword that keyword is not recalled;
According to the first interpretation of result information, the corresponding accuracy rate of first keyword and recall rate are obtained;
According to the corresponding accuracy rate of each keyword and recall rate, to the corresponding structured patient record data of the medical type
Quality is assessed.
10. device according to claim 9, which is characterized in that the quality assessment modules are specifically used for:
Type according to comparing result is that correctly quantity, the type of comparing result of first keyword are to convert mistake for conversion
The quantity of first keyword accidentally and the type of comparing result are the number for first keyword that keyword is accidentally recalled
Amount obtains the quantity that first keyword is called back;
It is to convert the correctly quantity of first keyword and first keyword to be called together according to the type of comparing result
The quantity returned obtains the corresponding accuracy rate of first keyword;
Quantity, the type of comparing result being called back according to first keyword are first key that keyword is accidentally recalled
The quantity of word and the type of comparing result are the quantity for first keyword that keyword is not recalled, obtain described first
The corresponding recall rate of keyword.
11. device according to claim 8, which is characterized in that the type of the corresponding comparing result of each keyword
For any in following: conversion is correct, transcription error, keyword are accidentally recalled and do not recalled with keyword;The quality assessment modules
It is specifically used for:
According to the corresponding annotation results of each structured patient record data, the second interpretation of result information, second result are obtained
Analysis information includes: that the type of comparing result is that correctly the quantity of each keyword, the type of comparing result are that conversion is wrong for conversion
The quantity of each keyword accidentally, the quantity and comparing result that the type of comparing result is each keyword that keyword is accidentally recalled
Type be the quantity of each keyword that keyword is not recalled;
According to the second interpretation of result information, the corresponding accuracy rate of the corresponding structured patient record data of the medical type is obtained
And recall rate.
12. device according to any one of claims 8 to 11, which is characterized in that further include amendment in the annotation results
As a result, it is the corresponding correction value of each keyword of transcription error that the correction result, which includes: the type of comparing result, and comparison
As a result type is each keyword and the corresponding value of each keyword that keyword is not recalled;Described device further include:
Display module, for being shown to the abnormal data in the multiple structured patient record data, and to the amendment
As a result it is shown;Wherein, it is that transcription error, keyword are accidentally recalled or keyword that the abnormal data, which is the type of comparing result,
The key-value pair data that do not recall.
13. device according to any one of claims 8 to 11, which is characterized in that the first acquisition module is specifically used for:
According to assessment task, medical type and maximum assessment quantity to be assessed are obtained;
According to the medical type and the maximum assessment quantity, obtained from medical data base the medical type it is corresponding to
Multiple structured patient record data of assessment;Wherein, the quantity of the structured patient record data is less than or equal to the maximum and comments
Estimate quantity.
14. device according to claim 13, which is characterized in that the first acquisition module is specifically used for:
Target collection is obtained from the medical data base, includes the corresponding structuring of the medical type in the target collection
Medical record data;
If the quantity of the structured patient record data in the target collection is greater than the maximum assessment quantity, from the mesh
The structured patient record data of the maximum assessment quantity of random selection are as the structured patient record data to be assessed in mark set;
If the quantity of the structured patient record data in the target collection is less than or equal to the maximum assessment quantity,
It regard the structured patient record data in the target collection as the structured patient record data to be assessed.
15. a kind of quality assessment arrangement of structured patient record data characterized by comprising memory, processor and calculating
Machine program, in the memory, the processor runs the computer program and executes as weighed for the computer program storage
Benefit requires 1 to 7 described in any item methods.
16. a kind of computer readable storage medium, which is characterized in that the computer readable storage medium includes computer journey
Sequence, the computer program realize method as described in any one of claim 1 to 7 when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910639668.3A CN110362829B (en) | 2019-07-16 | 2019-07-16 | Quality evaluation method, device and equipment for structured medical record data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910639668.3A CN110362829B (en) | 2019-07-16 | 2019-07-16 | Quality evaluation method, device and equipment for structured medical record data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110362829A true CN110362829A (en) | 2019-10-22 |
CN110362829B CN110362829B (en) | 2023-01-03 |
Family
ID=68219379
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910639668.3A Active CN110362829B (en) | 2019-07-16 | 2019-07-16 | Quality evaluation method, device and equipment for structured medical record data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110362829B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110866557A (en) * | 2019-11-12 | 2020-03-06 | 贵州医渡云技术有限公司 | Data evaluation method and device, storage medium and electronic device |
CN111986750A (en) * | 2020-07-27 | 2020-11-24 | 北京天健源达科技股份有限公司 | Electronic medical record template structured detection method |
CN112184084A (en) * | 2020-11-05 | 2021-01-05 | 北京嘉和海森健康科技有限公司 | Medical record learning quality assessment method and device |
CN113052410A (en) * | 2019-12-26 | 2021-06-29 | 医渡云(北京)技术有限公司 | Quality control method and device for electronic medical record data |
CN113380363A (en) * | 2021-06-24 | 2021-09-10 | 湖南创星科技股份有限公司 | Medical data quality evaluation method and system based on artificial intelligence |
Citations (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050027463A1 (en) * | 2003-08-01 | 2005-02-03 | Goode Paul V. | System and methods for processing analyte sensor data |
US20120245952A1 (en) * | 2011-03-23 | 2012-09-27 | University Of Rochester | Crowdsourcing medical expertise |
US20140324553A1 (en) * | 2012-08-01 | 2014-10-30 | Michael Joseph Rosenberg | Computer-Assisted Method for Adaptive, Risk-Based Monitoring of Clinical Studies |
CN104182844A (en) * | 2014-08-27 | 2014-12-03 | 浪潮软件股份有限公司 | Hospitalization service performance evaluation method of medical institutions |
US20150043801A1 (en) * | 2013-08-08 | 2015-02-12 | Washington University In St. Louis | System and Method for the Validation and Quality Assurance of Computerized Contours of Human Anatomy |
CN104408667A (en) * | 2014-11-20 | 2015-03-11 | 深圳供电局有限公司 | Method and system for comprehensively evaluating power quality |
CN105808951A (en) * | 2016-03-10 | 2016-07-27 | 宁波金唐软件有限公司 | Quality control method and apparatus for electronic medical record |
CN106383853A (en) * | 2016-08-30 | 2017-02-08 | 刘勇 | Realization method and system for electronic medical record post-structuring and auxiliary diagnosis |
CN106445901A (en) * | 2016-09-28 | 2017-02-22 | 医渡云(北京)技术有限公司 | Method and device for designing case report form |
CN106951705A (en) * | 2017-03-16 | 2017-07-14 | 天津艾登科技有限公司 | A kind of data quality accessment system serviced for inpatient medical |
US20170269899A1 (en) * | 2016-03-21 | 2017-09-21 | Patient Prism LLC | Interactive keyword cloud |
CN107683477A (en) * | 2015-06-05 | 2018-02-09 | 利姆博思医学科技有限责任公司 | Data quality management system and method |
CN107767929A (en) * | 2017-11-13 | 2018-03-06 | 医渡云(北京)技术有限公司 | CRF filling method, device, electronic equipment and storage medium |
CN107833595A (en) * | 2017-10-12 | 2018-03-23 | 山东大学 | Medical big data multicenter integration platform and method |
CN107908768A (en) * | 2017-09-30 | 2018-04-13 | 北京颐圣智能科技有限公司 | Method, apparatus, computer equipment and the storage medium of electronic health record processing |
CN108038131A (en) * | 2017-11-17 | 2018-05-15 | 上海数据交易中心有限公司 | Data Quality Analysis preprocess method and device, storage medium, terminal |
US20180160942A1 (en) * | 2015-12-11 | 2018-06-14 | SameDay Security, Inc. | Intelligent system for multi-function electronic caregiving to facilitate advanced health diagnosis, health monitoring, fall and injury prediction, health maintenance and support, and emergency response |
CN108170468A (en) * | 2017-12-28 | 2018-06-15 | 中山大学 | The method and its system of a kind of automatic detection annotation and code consistency |
CN108897682A (en) * | 2018-06-25 | 2018-11-27 | 郑州云海信息技术有限公司 | A kind of iteration tests outcome evaluation method based on Python |
CN109256212A (en) * | 2018-08-17 | 2019-01-22 | 上海米因医疗器械科技有限公司 | Bone health assessment models construction method, device, equipment, medium and appraisal procedure |
CN109445948A (en) * | 2018-11-15 | 2019-03-08 | 济南浪潮高新科技投资发展有限公司 | A kind of data mark crowdsourcing plateform system and crowdsourcing data mask method based on intelligent contract |
CN109473149A (en) * | 2018-11-09 | 2019-03-15 | 天津开心生活科技有限公司 | Data Quality Assessment Methodology, device, electronic equipment and computer-readable medium |
CN109522302A (en) * | 2018-11-09 | 2019-03-26 | 南京医渡云医学技术有限公司 | Medical data processing method, device, electronic equipment and computer-readable medium |
CN109582661A (en) * | 2018-11-23 | 2019-04-05 | 金色熊猫有限公司 | Data structured appraisal procedure, device, storage medium and electronic equipment |
CN109710670A (en) * | 2018-12-11 | 2019-05-03 | 河南通域医疗科技有限公司 | A method of case history text is converted into structural metadata from natural language |
US20190156923A1 (en) * | 2017-11-17 | 2019-05-23 | LunaPBC | Personal, omic, and phenotype data community aggregation platform |
-
2019
- 2019-07-16 CN CN201910639668.3A patent/CN110362829B/en active Active
Patent Citations (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050027463A1 (en) * | 2003-08-01 | 2005-02-03 | Goode Paul V. | System and methods for processing analyte sensor data |
US20120245952A1 (en) * | 2011-03-23 | 2012-09-27 | University Of Rochester | Crowdsourcing medical expertise |
US20140324553A1 (en) * | 2012-08-01 | 2014-10-30 | Michael Joseph Rosenberg | Computer-Assisted Method for Adaptive, Risk-Based Monitoring of Clinical Studies |
US20150043801A1 (en) * | 2013-08-08 | 2015-02-12 | Washington University In St. Louis | System and Method for the Validation and Quality Assurance of Computerized Contours of Human Anatomy |
CN104182844A (en) * | 2014-08-27 | 2014-12-03 | 浪潮软件股份有限公司 | Hospitalization service performance evaluation method of medical institutions |
CN104408667A (en) * | 2014-11-20 | 2015-03-11 | 深圳供电局有限公司 | Method and system for comprehensively evaluating power quality |
CN107683477A (en) * | 2015-06-05 | 2018-02-09 | 利姆博思医学科技有限责任公司 | Data quality management system and method |
US20180160942A1 (en) * | 2015-12-11 | 2018-06-14 | SameDay Security, Inc. | Intelligent system for multi-function electronic caregiving to facilitate advanced health diagnosis, health monitoring, fall and injury prediction, health maintenance and support, and emergency response |
CN105808951A (en) * | 2016-03-10 | 2016-07-27 | 宁波金唐软件有限公司 | Quality control method and apparatus for electronic medical record |
US20180046433A1 (en) * | 2016-03-21 | 2018-02-15 | Patient Prism LLC | Interactive keyword cloud |
US20170269899A1 (en) * | 2016-03-21 | 2017-09-21 | Patient Prism LLC | Interactive keyword cloud |
CN106383853A (en) * | 2016-08-30 | 2017-02-08 | 刘勇 | Realization method and system for electronic medical record post-structuring and auxiliary diagnosis |
CN106445901A (en) * | 2016-09-28 | 2017-02-22 | 医渡云(北京)技术有限公司 | Method and device for designing case report form |
CN106951705A (en) * | 2017-03-16 | 2017-07-14 | 天津艾登科技有限公司 | A kind of data quality accessment system serviced for inpatient medical |
CN107908768A (en) * | 2017-09-30 | 2018-04-13 | 北京颐圣智能科技有限公司 | Method, apparatus, computer equipment and the storage medium of electronic health record processing |
CN107833595A (en) * | 2017-10-12 | 2018-03-23 | 山东大学 | Medical big data multicenter integration platform and method |
CN107767929A (en) * | 2017-11-13 | 2018-03-06 | 医渡云(北京)技术有限公司 | CRF filling method, device, electronic equipment and storage medium |
US20190156923A1 (en) * | 2017-11-17 | 2019-05-23 | LunaPBC | Personal, omic, and phenotype data community aggregation platform |
CN108038131A (en) * | 2017-11-17 | 2018-05-15 | 上海数据交易中心有限公司 | Data Quality Analysis preprocess method and device, storage medium, terminal |
CN108170468A (en) * | 2017-12-28 | 2018-06-15 | 中山大学 | The method and its system of a kind of automatic detection annotation and code consistency |
CN108897682A (en) * | 2018-06-25 | 2018-11-27 | 郑州云海信息技术有限公司 | A kind of iteration tests outcome evaluation method based on Python |
CN109256212A (en) * | 2018-08-17 | 2019-01-22 | 上海米因医疗器械科技有限公司 | Bone health assessment models construction method, device, equipment, medium and appraisal procedure |
CN109473149A (en) * | 2018-11-09 | 2019-03-15 | 天津开心生活科技有限公司 | Data Quality Assessment Methodology, device, electronic equipment and computer-readable medium |
CN109522302A (en) * | 2018-11-09 | 2019-03-26 | 南京医渡云医学技术有限公司 | Medical data processing method, device, electronic equipment and computer-readable medium |
CN109445948A (en) * | 2018-11-15 | 2019-03-08 | 济南浪潮高新科技投资发展有限公司 | A kind of data mark crowdsourcing plateform system and crowdsourcing data mask method based on intelligent contract |
CN109582661A (en) * | 2018-11-23 | 2019-04-05 | 金色熊猫有限公司 | Data structured appraisal procedure, device, storage medium and electronic equipment |
CN109710670A (en) * | 2018-12-11 | 2019-05-03 | 河南通域医疗科技有限公司 | A method of case history text is converted into structural metadata from natural language |
Non-Patent Citations (1)
Title |
---|
阮彤 等: ""基于电子病历的临床医疗大数据挖掘流程与方法"", 《大数据》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110866557A (en) * | 2019-11-12 | 2020-03-06 | 贵州医渡云技术有限公司 | Data evaluation method and device, storage medium and electronic device |
CN110866557B (en) * | 2019-11-12 | 2022-12-13 | 贵州医渡云技术有限公司 | Data evaluation method and device, storage medium and electronic device |
CN113052410A (en) * | 2019-12-26 | 2021-06-29 | 医渡云(北京)技术有限公司 | Quality control method and device for electronic medical record data |
CN113052410B (en) * | 2019-12-26 | 2024-07-19 | 医渡云(北京)技术有限公司 | Quality control method and device for electronic medical record data |
CN111986750A (en) * | 2020-07-27 | 2020-11-24 | 北京天健源达科技股份有限公司 | Electronic medical record template structured detection method |
CN111986750B (en) * | 2020-07-27 | 2023-12-26 | 北京天健源达科技股份有限公司 | Structural detection method for electronic medical record template |
CN112184084A (en) * | 2020-11-05 | 2021-01-05 | 北京嘉和海森健康科技有限公司 | Medical record learning quality assessment method and device |
CN112184084B (en) * | 2020-11-05 | 2023-08-08 | 北京嘉和海森健康科技有限公司 | Medical record learning quality assessment method and device |
CN113380363A (en) * | 2021-06-24 | 2021-09-10 | 湖南创星科技股份有限公司 | Medical data quality evaluation method and system based on artificial intelligence |
Also Published As
Publication number | Publication date |
---|---|
CN110362829B (en) | 2023-01-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110362829A (en) | Method for evaluating quality, device and the equipment of structured patient record data | |
Jiang et al. | Time series analysis of COVID-19 infection curve: A change-point perspective | |
Wu et al. | Accurate Markov boundary discovery for causal feature selection | |
CN107610770B (en) | Question generation system and method for automated diagnosis | |
EP3292492B1 (en) | Predicting likelihoods of conditions being satisfied using recurrent neural networks | |
CN110223751A (en) | Prescription evaluation method, system and computer equipment based on medical knowledge map | |
CN109817339A (en) | Patient's group technology and device based on big data | |
CN107153775B (en) | Intelligent triage method and device | |
CN106815226A (en) | Text matching technique and device | |
WO2022134472A1 (en) | Method, device and terminal for electrocardiosignal detection and storage medium | |
CN108171189A (en) | Video coding method, video coding device and electronic equipment | |
CN109543718B (en) | Method and device for modifying disease type description | |
CN112669188A (en) | Critical event early warning model construction method, critical event early warning method and electronic equipment | |
CN109255721A (en) | Insurance recommended method, equipment, server and readable medium based on Cost Forecast | |
CN109902157A (en) | A kind of training sample validation checking method and device | |
CN111046882B (en) | Disease name standardization method and system based on profile hidden Markov model | |
CN109243592A (en) | Medical item based on artificial intelligence uses method for detecting abnormality and relevant apparatus | |
CN114116013B (en) | Data processing method and device, electronic equipment and storage medium | |
CN111159481A (en) | Edge prediction method and device of graph data and terminal equipment | |
CN109102845B (en) | Medical document auditing method, device, computer equipment and storage medium | |
CN109767819B (en) | Medical record grouping method and device, storage medium and electronic equipment | |
CN109741833B (en) | Data processing method and device | |
CN110648734B (en) | Method and device for identifying abnormal cases in medical treatment based on mean value | |
CN111710431A (en) | Method, device, equipment and storage medium for identifying synonymous diagnosis name | |
CN112022142B (en) | Electrocardiosignal type identification method, device and medium |
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 |