CN107833605A - A kind of coding method, device, server and the system of hospital's medical record information - Google Patents
A kind of coding method, device, server and the system of hospital's medical record information Download PDFInfo
- Publication number
- CN107833605A CN107833605A CN201711327971.7A CN201711327971A CN107833605A CN 107833605 A CN107833605 A CN 107833605A CN 201711327971 A CN201711327971 A CN 201711327971A CN 107833605 A CN107833605 A CN 107833605A
- Authority
- CN
- China
- Prior art keywords
- medical record
- record information
- coding
- target
- sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
This application discloses a kind of coding method, device, server and the system of hospital's medical record information, method includes：First sample set is obtained, the first sample set includes the disease code of at least one sample medical record information and each sample medical record information；Deep learning is carried out to the sample medical record information in the first sample set and its disease code, obtains case history coding rule model；When receiving target medical record information to be encoded, the target medical record information is encoded using the case history coding rule model, obtains the target disease coding of the target medical record information.
Description
This application claims submit Patent Office of the People's Republic of China, Application No. 201710145435.9, invention name on March 14th, 2017
The referred to as priority of the Chinese patent application of " medical record information intelligently encoding robot of hospital and method ".
Technical field
The application is related to medical information processing technology field, more particularly to a kind of hospital's medical record information coding method, device,
Server and system.
Background technology
With the development of society, the classification of diseases that high quality is carried out to hospital's case history encodes, for the hair of hospital information
Exhibition and the meaning of follow-up big data analysis and application are all significant, especially carry out the medical insurance based on classification of diseases to country and pay
Expense system reform is even more to have basic substantial worth, thereby it is ensured that the accuracy and high efficiency of medical record information classification, are extremely
Important element task.
In traditional hospital's medical record information encoding scheme, each case of hospital room is typically by manual type, to hospital's electricity
The medical record information that sub- medical records system is submitted carries out h coding, realized necessary according to certain classification of diseases coding standard
Classification of diseases encodes.
And it is increasingly extensive with hospital electronic case, the coding work amount of hospital's medical record information also significantly rises, people
Work does not only exist the relatively low problem of code efficiency to the coding work of hospital's medical record information, it is also possible to the inaccurate feelings of coding be present
Condition.
The content of the invention
In view of this, the purpose of the application be to provide a kind of coding method of hospital's medical record information, device, server and
System, the low and inaccurate technical problem of efficiency be present to solve h coding in the prior art.
This application provides a kind of coding method of hospital's medical record information, including：
Obtain first sample set, the first sample set include at least one sample medical record information and it is each described in
The disease code of sample medical record information；
Deep learning is carried out to the sample medical record information in the first sample set and its disease code, obtains case history volume
Code rule model；
When receiving target medical record information to be encoded, using the case history coding rule model to the target case history
Information is encoded, and obtains the target disease coding of the target medical record information.
The above method, it is preferred that also include：
Obtain the second sample set, second sample set includes at least one sample medical record information and each described
The disease code of sample medical record information；
Based on the sample medical record information and its disease code in second sample set, to the case history coding rule mould
Type optimizes.
The above method, it is preferred that also include：
The target medical record information and its target disease coding are transmitted.
The above method, it is preferred that also include：
The encoder feedback information of the target disease coding is received, the encoder feedback information includes：Medical supervision and doctor
Treat encoder feedback information of the application to target disease coding；
The case history coding rule model is optimized based on the encoder feedback information.
Present invention also provides a kind of code device of hospital's medical record information, including：
Unit is encoded, for obtaining first sample set, the first sample set includes at least one sample
The disease code of medical record information and each sample medical record information；To the sample medical record information in the first sample set and
Its disease code carries out deep learning, obtains case history coding rule model；
Generation unit is encoded, for when receiving target medical record information to be encoded, utilizing the case history coding rule
Model encodes to the target medical record information, obtains the target disease coding of the target medical record information.
Said apparatus, it is preferred that also include：
Code optimization unit, for obtaining the second sample set, second sample set includes at least one sample
The disease code of medical record information and each sample medical record information；Based on the sample medical record information in second sample set
And its disease code, the case history coding rule model is optimized.
Said apparatus, it is preferable that the coding unit is by selecting one or more packet standards to be based on the sample
This medical record information generates the disease grouping information of a variety of packet standards, is compiled to be met the case history of a variety of coding application demands
Code rule model.
Said apparatus, it is preferable that the coding unit is by selecting one or more target code standards to be based on institute
The coding information of sample medical record information generation plurality of target coding standard is stated, to meet that the case history of a variety of coding application demands is compiled
Code rule model.
Said apparatus, it is preferred that also include：
Transmission unit, for the target medical record information and its target disease coding to be transmitted；
The transmission unit is additionally operable to：Receive the encoder feedback information of the target disease coding, the encoder feedback letter
Breath includes：The encoder feedback information that medical supervision and medical applications encode to the target disease；
Code optimization unit is additionally operable to：It is described that the case history coding rule model is carried out based on the encoder feedback information
Optimization.
Present invention also provides a kind of encoder server of hospital's medical record information, including：
Memory, for storing data caused by application program and application program operation；
Processor, for running the application program in the memory, to realize following functions：Obtain first sample collection
Close, the first sample set includes at least one sample medical record information and the disease of each sample medical record information is compiled
Code；Deep learning is carried out to the sample medical record information in the first sample set and its disease code, obtains case history coding rule
Then model；When receiving target medical record information to be encoded, using the case history coding rule model to the target case history
Information is encoded, and obtains the target disease coding of the target medical record information.
Above-mentioned server, it is preferred that also include：
Coffret and interactive device, the coffret are connected between the server and interactive device, wherein：
The interactive device, for receiving the input operation of user, the input operation includes believing the target case history
The input operation of breath, the processor target medical record information being sent to by the coffret in the server, and
The target disease obtained by the coffret acquisition processor encodes and is exported target disease coding；
The interactive device, it is additionally operable to obtain encoder feedback information, and the encoder feedback information is passed through into the transmission
Interface is sent to the processor, and the encoder feedback information includes：Medical supervision and medical applications are compiled to the target disease
The encoder feedback information of code.
Above-mentioned server, it is preferable that the interactive device includes：Input equipment and output equipment.
Present invention also provides a kind of hospital's medical record information coded system, including：
Data source terminal；
Encoder server, for obtaining first sample set from the data source terminal, and to the first sample
Sample medical record information and its disease code in set carry out deep learning, obtain case history coding rule model；Treated receiving
During the target medical record information of coding, the target medical record information is encoded using the case history coding rule model, obtained
The target disease coding of the target medical record information.
From such scheme, coding method, device and the server of a kind of hospital's medical record information that the application provides, profit
Deep learning is carried out to the sample medical record information of known disease code with deep learning framework, obtains accurate case history coding rule
Model, afterwards, when needing to encode medical record information, target medical record information is compiled using case history coding rule model
Code encodes so as to obtain the target disease of target medical record information, realizes the autocoding of medical record information, without h coding, so that
Improve the coding accuracy rate and efficiency of medical record information.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
The embodiment of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can also basis
The accompanying drawing of offer obtains other accompanying drawings.
Fig. 1 is a kind of flow chart of the coding method for hospital's medical record information that the embodiment of the present application one provides；
Fig. 2-Fig. 4 is respectively a kind of another flow of the coding method for hospital's medical record information that the embodiment of the present application one provides
Figure；
Fig. 5 is a kind of structural representation of the code device for hospital's medical record information that the embodiment of the present application two provides；
Fig. 6 is a kind of structural representation of the encoder server for hospital's medical record information that the embodiment of the present application three provides；
Fig. 7 is a kind of structural representation of the coded system for hospital's medical record information that the embodiment of the present application four provides；
Fig. 8 is a kind of logic schematic configuration diagram of the coded system for hospital's medical record information that the embodiment of the present application four provides.
Embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although the disclosure is shown in accompanying drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
Limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Completely it is communicated to those skilled in the art.
With reference to figure 1, a kind of flow chart of the coding method of the hospital's medical record information provided for the embodiment of the present application one, this reality
Example is applied to be applicable to be good for using the health care administrative department of disease code, medical insurance payer, medical institutions or medical treatment
On the server of health Information application Fang Deng mechanisms, for being encoded to hospital's medical record information.Here medical treatment ＆ health information should
Include big data digging mechanism with side or resident is personal.
In the present embodiment, this method may comprise steps of：
Step 101：Obtain first sample set.
Wherein, the first sample set includes at least one sample medical record information and each sample medical record information
Disease code.
It should be noted that the sample medical record information in first sample set can be from medical institutions at different levels, medical insurance
Mechanism, health authorities, other enterprises and institutions database in obtain, information for hospital system that can also be out of institute and outside institute
Unite (Hospital Information System, HIS), medical record system (the Electronic Medical of computerization
Record, EMR) etc. obtain in medical information operation system or area medical information data center.The present embodiment can pass through net
Network connects these databases or data center, and sample medical record information and sample case history are obtained from these databases or data center
The known disease code of information.Wherein, include in medical institutions at different levels：Public hospital at different levels, Civilian Hospital at different levels or each
Level clinic.
Wherein, the disease code can be the coding of default target code standard generation, and target code standard can be with
Include：ICD-9, ICD-10, ICD-11, ICD-9-CM3, CCHI, traditional Chinese medical science disease code standard, tumor morphology coding mark
One or more in accurate, traditional Chinese medical science symptom coding standard.Sample set is generated based on target code standard in the present embodiment, specifically
Can by switching different coding standards, so as to generate different coded samples set, such as the of traditional Chinese medical science symptom coding standard
The first sample set of one sample set or ICD-9-CM3.
Step 102：Deep learning is carried out to the sample medical record information in the first sample set and its disease code, obtained
To case history coding rule model.
Wherein, deep learning here can use the network moulds such as the various artificial neural networks such as convolutional neural networks
Type is realized.For example, the sample medical record information in first sample set and its disease code are entered using convolutional neural networks framework
Row deep learning is trained, and generates case history coding rule model.
In one implementation, in the present embodiment during deep learning is carried out to sample medical record information, Ke Yitong
Cross one or more packet standards that select, and then the first page of illness case based on for example a case history of sample medical record information, progress note etc.
Information, the disease grouping information of a variety of packet standards is disposably generated, to be met the case history of a variety of coding application demands
Coding rule model, so as to be applied to different application demands.
In addition, in the present embodiment during deep learning is carried out to sample medical record information, it is also an option that a kind of or more
Kind all target code standards as noted above, and then first page of illness case to a case history, progress note equal samples case
Information disposably generates the coding information of plurality of target coding standard, the diagnosis of such as multiple standards, operation coding (or other arts
Language) necessary information, to meet the case history coding rule model of a variety of coding application demands, to be needed applied to different applications
Ask.
Step 103：Receive target medical record information to be encoded.
Wherein, goal medical record information can be by medical worker by electronic medical record system input or
Inputted by other staff by machines such as scanners.The target medical record information refers to need the disease for carrying out disease type coding
Go through information.
Step 104：The target medical record information is encoded using the case history coding rule model, obtains the mesh
Mark the target disease coding of medical record information.
Wherein, can include in the case history coding rule model：The rule of accurate coding is carried out to medical record information.Example
Such as：Case history coding rule includes：Each disease code corresponds to one or more keywords respectively and each keyword is encoding
In weight, in medical record information if with the keyword in case history coding rule model, then disease corresponding to the keyword
Disease coding and weight determine the disease code of the medical record information.
It should be noted that the target disease coding obtained by the present embodiment can apply to the industry such as hospital HIS, EMR
In classification of diseases coding module required for business system, hospital, medical insurance mechanism, health care administrative department can also be applied to
In classification of diseases related system and platform, such as Single diseases categorizing system (Diagnosis Related Groups, DRGs).
From such scheme, a kind of coding method for hospital's medical record information that the embodiment of the present application one provides, depth is utilized
Spend learning framework and deep learning is carried out to the sample medical record information of known disease code, obtain accurate case history coding rule mould
Type, afterwards, when needing to encode medical record information, target medical record information is encoded using case history coding rule model
So as to obtain the target disease of target medical record information coding, the autocoding of medical record information is realized, without h coding, so as to carry
The coding accuracy rate and efficiency of high medical record information.
Based on the scheme shown in Fig. 1, the present embodiment, can also be according to demand by target after target disease coding is obtained
Disease code is transferred to other-end use, and as shown in Figure 2, this method can also comprise the following steps：
Step 105：The target medical record information and its target disease coding are transmitted.
Wherein, target medical record information and its target disease can be encoded by various data transmission interfaces in the present embodiment
It is transmitted, is such as transferred to display or projection screen terminal, there is provided hold a consultation etc. to medical personnel such as experts；Or
These target medical record informations and its target disease coding transmission are stored into terminal to disk etc., to store.
In order to improve the accuracy of disease type coding and reliability, it is necessary to be carried out to case history coding rule model persistently complete
Kind, renewal and optimization, therefore, based on the implementation in Fig. 1, after step 102, this method can also include following step
Suddenly, as shown in Figure 3：
Step 106：Obtain the second sample set.
Wherein, second sample set includes at least one sample medical record information and each sample medical record information
Disease code.
It should be noted that the sample medical record information in the second sample set can be the increment based on first sample set
Information, i.e., after the generation of case history coding rule model, the medical record information that newly increases, these medical record informations newly increased can be
Case history in the manual input of medical worker or other staff are inputted by machine or utilization the present embodiment is compiled
Code rule model is generated, that is to say, that, can be based on new disease code to case history after new disease code is obtained
Coding rule model optimizes.
Step 107：Based on the sample medical record information and its disease code in second sample set, the case history is compiled
Code rule model optimizes.
Wherein, case history coding rule model is optimized, can included：Increase the disease in case history coding rule model
Keyword corresponding to the sick quantity encoded or species, each disease code of renewal etc..Thus, encoded to improve disease type
Accuracy and reliability.
In addition, in order to carry out persistently perfect, renewal and optimization to case history coding rule model, based on the reality in Fig. 1
Existing scheme, after step 104, this method can also comprise the following steps, as shown in Figure 4：
Step 108：Receive the encoder feedback information of the target disease coding.
Wherein, the encoder feedback information includes：The coding that medical supervision and medical applications encode to the target disease
Feedback information.
Step 109：The case history coding rule model is optimized based on the encoder feedback information.
For example, after target disease coding is discussed, analyzed and confirmed by expert consultation or medical personnel, with
The structured message generation feedback information that machine can identify, and the feedback information is transmitted to progress case history coding in the present embodiment
The equipment of rule model generation, so as to realize coding and model optimization to some difficult case histories.
From such scheme, deep learning framework is based in the present embodiment, according to the disease in existing medical information system
Sick grouped data, such as the sample medical record information in first sample set, carry out sample analysis and optimization, realize it is a certain degree of from
Study, so as to generate and optimize case history coding rule model and associated weight.Further, realizing that classification of diseases encodes it
Afterwards, case history coding rule model can also be optimized according to manual feedback information, improves coding accuracy rate and reliability.
In order to realize the scheme shown in Fig. 1, with reference to figure 5, a kind of hospital's medical record information provided for the embodiment of the present application two
Code device structural representation, the device be applicable to using disease code health care administrative department, medical treatment protect
On the server of dangerous payer, medical institutions or medical treatment ＆ health Information application Fang Deng mechanisms, for being carried out to hospital's medical record information
Coding.Here medical treatment ＆ health Information application side includes big data digging mechanism or resident is personal.
In the present embodiment, the device can include following structure：
Unit 501 is encoded, for obtaining first sample set, the first sample set includes at least one sample
The disease code of this medical record information and each sample medical record information；To the sample medical record information in the first sample set
And its disease code carries out deep learning, obtains case history coding rule model.
In one implementation, unit 501 is encoded during deep learning is carried out to sample medical record information, can
With by selecting one or more packet standards, and then the first page of illness case based on for example a case history of sample medical record information, the course of disease note
The information such as record, the disease grouping information of a variety of packet standards is disposably generated, to be met a variety of coding application demands
Case history coding rule model, so as to be applied to different application demands.
In addition, unit 501 is encoded during deep learning is carried out to sample medical record information, it is also an option that a kind of
Or plurality of target coding standard, and then first page of illness case, the progress note equal samples case information to a case history disposably generate
The diagnosis of the coding information of plurality of target coding standard, such as multiple standards, operation coding (or other terms) necessary information, are used
To meet the case history coding rule model of a variety of coding application demands, with applied to different application demands.
Generation unit 502 is encoded, for when receiving target medical record information to be encoded, encoding and advising using the case history
Then model encodes to the target medical record information, obtains the target disease coding of the target medical record information.
Code optimization unit 503, for obtaining the second sample set, second sample set includes at least one sample
The disease code of this medical record information and each sample medical record information；Based on the sample case history letter in second sample set
Breath and its disease code, are optimized to the case history coding rule model.
Transmission unit 504, for the target medical record information and its target disease coding to be transmitted.
In addition, the transmission unit 504 is additionally operable to：Receive the encoder feedback information of the target disease coding, the volume
Code feedback information includes：The encoder feedback information that medical supervision and medical applications encode to the target disease；
Accordingly, the code optimization unit 503 is additionally operable to：It is described that the case history is compiled based on the encoder feedback information
Code rule model optimizes.
In the present embodiment, the device can include processor and memory, and processor and memory are server etc.
The component in the equipment of above the present embodiment is carried, above-mentioned coding unit 501, coding generation unit 502, coding are excellent
Change unit 503 and the grade of transmission unit 504 to store in memory as program unit, memory is stored in by computing device
In said procedure unit realize corresponding function.
For example, above-mentioned each program unit is stored in memory in the form of installation kit or processing class, simultaneous memory
In be also stored with the configuration file pre-set, processor is by calling installation kit to handle class, to perform each program list of the above
Member, realize corresponding function.
Specifically, including kernel in processor, gone in memory to transfer corresponding program unit by kernel, kernel can be set
One or more is put, first sample set is obtained by adjusting kernel parameter, to the sample disease in the first sample set
Go through information and its disease code carries out deep learning, obtain case history coding rule model；Receiving target case history to be encoded
During information, the target medical record information is encoded using the case history coding rule model, obtains the target case history letter
The target disease coding of breath.
Wherein, memory may include the volatile memory in computer-readable medium, random access memory
(RAM) and/or the form such as Nonvolatile memory, such as read-only storage (ROM) or flash memory (flash RAM), memory is included extremely
A few storage chip.
From such scheme, a kind of code device for hospital's medical record information that the embodiment of the present application two provides, depth is utilized
Spend learning framework and deep learning is carried out to the sample medical record information of known disease code, obtain accurate case history coding rule mould
Type, afterwards, when needing to encode medical record information, target medical record information is encoded using case history coding rule model
So as to obtain the target disease of target medical record information coding, the autocoding of medical record information is realized, without h coding, so as to carry
The coding accuracy rate and efficiency of high medical record information.
The embodiments of the invention provide a kind of storage medium, program is stored thereon with, it is real when the program is executed by processor
The coding method of existing hospital's medical record information.
The embodiments of the invention provide a kind of processor, the processor is used for operation program, wherein, described program operation
The coding method of hospital's medical record information described in Shi Zhihang.
The embodiments of the invention provide a kind of equipment, equipment includes processor, memory and storage on a memory and can
The program run on a processor, following steps are realized during computing device program：First sample set is obtained, to described first
Sample medical record information and its disease code in sample set carry out deep learning, obtain case history coding rule model；Receiving
During to target medical record information to be encoded, the target medical record information is encoded using the case history coding rule model,
Obtain the target disease coding of the target medical record information.
Wherein, equipment herein can be server, PC, PAD, mobile phone etc..
Present invention also provides a kind of computer program product, when being performed on data processing equipment, is adapted for carrying out just
The program code of beginningization there are as below methods step：First sample set is obtained, to the sample case history in the first sample set
Information and its disease code carry out deep learning, obtain case history coding rule model；Receiving target case history letter to be encoded
During breath, the target medical record information is encoded using the case history coding rule model, obtains the target medical record information
Target disease coding.
With reference to figure 6, a kind of structural representation of the encoder server of the hospital's medical record information provided for the embodiment of the present application three
Figure, the server is health care administrative department, medical insurance payer, medical institutions or the medical treatment for needing to use disease code
The server of health and fitness information application Fang Deng mechanisms, for being encoded to hospital's medical record information.Here medical treatment ＆ health information should
Include big data digging mechanism with side or resident is personal.
In the present embodiment, the server can include following structure：
Memory 601, for storing data caused by application program and application program operation.
Processor 602, for running the application program in the memory, to realize following functions：Obtain first sample
Set；Deep learning is carried out to the sample medical record information in the first sample set and its disease code, obtains case history coding
Rule model；When receiving target medical record information to be encoded, using the case history coding rule model to target disease
Go through information to be encoded, obtain the target disease coding of the target medical record information.
The interactive device, for receiving the input operation of user, the input operation includes believing the target case history
The input operation of breath, the processor target medical record information being sent to by the coffret in the server, and
The target disease obtained by the coffret acquisition processor encodes and is exported target disease coding；
The interactive device, it is additionally operable to obtain encoder feedback information, and the encoder feedback information is passed through into the transmission
Interface is sent to the processor, and the encoder feedback information includes：Medical supervision and medical applications are compiled to the target disease
The encoder feedback information of code
Wherein, can be connected between processor 602 and memory 601 by bus 603,
The server can also include：Coffret 604 and interactive device 605, the coffret 604 are connected to institute
State between server and interactive device 605, as shown in Figure 6.
Wherein, the interactive device is used for the input operation for receiving user, and the input operation includes believing target case history
The input operation of breath, afterwards, the processor target medical record information being sent to by the coffret 604 in server
602, and the target disease obtained by the acquisition processor of coffret 604 encodes and is exported target disease coding.
In addition, interactive device 605 can be also used for obtaining encoder feedback information, and encoder feedback information is connect by transmission
Mouth 604 is sent to processor 602, and can include in encoder feedback information：Medical supervision and medical applications are compiled to target disease
The encoder feedback information of code.
In addition, the processor 602 is also based on the encoder feedback information to the case history coding rule mould
Type optimizes.
In one implementation, can be by setting coding interactive application module to realize its work(in interactive device 605
Can, wherein, the coding interactive module is used for all kinds of input-output operations that server is related to.Specifically, coding interactive module can
To realize that information input when being encoded to server is controlled, coding parameter is matched somebody with somebody by certain interactive mode suitable for user
Put, coded command execution, coding rule manual confirmation, doubt coding bar code manually demarcation etc..
And its function can be realized in interactive device 605 using a variety of interactive modes, such as input through keyboard, mouse action, screen
Curtain display, the device of speech recognition/synthesis output or equipment, gesture operation, the operation of the VR helmets, anthropomorphic robot interactive operation
(comprising becoming to control) etc..
Wherein, the processor 602 can be by obtaining first sample set and second in multiple data source terminals 606
Sample set, data source terminal 606 can be healthcare structures at different levels, Medical Insurance Organizations, health authorities, other enterprise's things
The terminals such as industry unit, it is deployed in the equipment such as physical machine computer, virtual machine or Cloud Server, processor 602 comes from these data
Sample medical record information and its disease code are obtained on the relevant device of source terminal 606, wherein, the medical institutions at different levels include each
Level public hospital, Civilian Hospital at different levels or clinic at different levels.
From such scheme, a kind of encoder server for hospital's medical record information that the embodiment of the present application three provides, utilize
Deep learning framework carries out deep learning to the sample medical record information of known disease code, obtains accurate case history coding rule mould
Type, afterwards, when needing to encode medical record information, target medical record information is encoded using case history coding rule model
So as to obtain the target disease of target medical record information coding, the autocoding of medical record information is realized, without h coding, so as to carry
The coding accuracy rate and efficiency of high medical record information.
With reference to figure 7, a kind of structural representation of the coded system of the hospital's medical record information provided for the embodiment of the present application four,
The system can include following structure：
Data source terminal 701, the data source terminal 701 are one or more, can be that medical electronics case history is related
Data source terminal 701；
Coded data supervisory terminal 702, the equipment such as connection physics electromechanics brain, virtual machine or Cloud Server can be deployed in
On；
Encoding machine people 703, it can be realized by encoder server as shown in Figure 6, on the encoding machine people 703
Software can be deployed in (containing its main operational and encoding software module) on server hardware；
The man-machine interaction application terminal 704 of medical record writing doctor interaction；
Storage device 705, for data storage.
Wherein, the encoding machine people 703 can be programmed reality based on deep learning models coupling case history coding rule
It is existing；The coded data supervisory terminal 702 can be monitored, analyze and audit to system running state, coding situation；It is described
Interactive application terminal 704 can realize volume by modes such as voice, text, virtual display (Virtual Reality, VR) promptings
Information notice, feedback and interactive operation between code robot and the medical personnel of Clinical practice；The data source terminal 701
Can be the medical information such as HIS, EMR in institute and outside institute operation system or area medical information data center.
In one implementation, each terminal of the above and server can be deployed to physical machine computer, virtual machine or cloud clothes
It is engaged in the equipment such as device, can be by way of shared cloud deployment way be applied by internet access or disposed by hospital's Intranet
Applied in institute.
Specifically, the encoding machine people 703 is based on deep learning model, can dynamic adjusting and optimizing coding rule and
Differentiate weight.For example, sample analysis, study and excellent can be carried out according to the classification of diseases data in existing medical information system
Change, realize a certain degree of self study, so as to Optimized Coding Based model and associated weight.The knot encoded for encoding machine people 703
Fruit, the difference with original h coding's result, can provide prompting feedback information, for examining for coded data supervisory terminal 702
Core confirms and interactive application terminal 704 is carried out according to study.
As shown in Figure 8, in logic realization, encoding machine people 703 is in medical electronics medical record data source Nodes
(terminal) and more than one coded data supervisory node (terminal), more than one is used for encoding machine people and medical record writing doctor hands over
In information-based grid constructed by mutual man-machine interaction application node (terminal), and encoding machine people 703 can in specific implementation
To be realized by following logic module：Encode study module, coding rule knowledge tree module, coding generation module, encoder feedback
Adjusting module, coding application interactive module.
Wherein, coding study module is based on deep learning model, can carry out case history coding study；
Coding rule knowledge tree module, it is possible to achieve dynamic coding rule accumulation and extension；
Coding generation module is used to encode case history；
Encoder feedback adjusting module, for coding result and rule to be fed back into each association supervision, using side, and it can receive
Collect relevant feedback, carry out encoding tuning and rule optimization；
Coding application interactive module provides relevant interface, and integrated use is carried out for related service system, and for passing through
The modes such as voice, VR, simulation type robot, large screen display realize interacting for robot and user of service.
And the disease code that encoding machine people 703 is generated can apply to needed for the operation systems such as hospital HIS, EMR
In classification of diseases coding module, the classification of diseases phase relation of hospital, medical insurance mechanism, health care administrative department can also be applied to
In system and platform, such as Single diseases categorizing system (DRGs).
Wherein, the coded data supervisory terminal 702, interactive application terminal 704 may be constructed expert consultation terminal, pass through
Brainstorming mode, robot coding result is discussed, analyze, confirmed, and the knot that can be identified with encoding machine people 703
Structure information mode, feedback result realize the encoding model of some difficult case histories and the optimization of weight to encoding machine people 703.
And data source terminal 701 can be healthcare structures at different levels, Medical Insurance Organizations, health authorities, other enterprises
The terminals such as public institution, the medical institutions at different levels include public hospitals at different levels, Civilian Hospital at different levels or clinic at different levels；The coding
The application side of robot includes health care administrative department, medical insurance payer, medical institutions or medical treatment ＆ health Information application
Side, the medical treatment ＆ health Information application side includes big data digging mechanism or resident is personal；
Or, the data source terminal 701, coded data supervisory terminal 702, interactive application terminal 704 be all from it is single
Medical institutions, some data source sides include each section office of medical institutions, and data application side includes the associated department of medical institutions.
From such scheme, the scheme in the present embodiment carries out sample learning by magnanimity hospital medical record information, and then
High-caliber coding rule and scheme are formed, so as to realize the robot case history coding of high quality, can be so effectively reduced
Case history coding work also can solve the problem that h coding's working strength is big, quality is unstable, replicability and expansion to artificial dependence
The problems such as malleability difference.Scheme in the present embodiment specifically can apply to medical institutions, health care supervision department, medical insurance machine
Structure, the mechanism of Analysis of Medical Treatment Data application and individual.Due to using the side for possessing deep learning, enhancing study, cloud framework tuning
Method is realized, can very well meet the need of work of case history coding in the case of mass data.
It should be noted that herein, such as first and second or the like relational terms are used merely to a reality
Body or operation make a distinction with another entity or operation, and not necessarily require or imply and deposited between these entities or operation
In any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant are intended to
Nonexcludability includes, so that process, method, article or equipment including a series of elements not only will including those
Element, but also the other element including being not expressly set out, or it is this process, method, article or equipment also to include
Intrinsic key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that
Other identical element also be present in process, method, article or equipment including the key element.
It should be understood by those skilled in the art that, embodiments herein can be provided as method, system or computer program
Product.Therefore, the application can use the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Apply the form of example.Moreover, the application can use the computer for wherein including computer usable program code in one or more
The computer program production that usable storage medium is implemented on (including but is not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The application is with reference to the flow according to the method for the embodiment of the present application, equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that can be by every first-class in computer program instructions implementation process figure and/or block diagram
Journey and/or the flow in square frame and flow chart and/or block diagram and/or the combination of square frame.These computer programs can be provided
The processors of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that produced by the instruction of computer or the computing device of other programmable data processing devices for real
The device for the function of being specified in present one flow of flow chart or one square frame of multiple flows and/or block diagram or multiple square frames.
These computer program instructions, which may be alternatively stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory, which produces, to be included referring to
Make the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one square frame of block diagram or
The function of being specified in multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that counted
Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented processing, so as in computer or
The instruction performed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in individual square frame or multiple square frames.
In a typical configuration, computing device includes one or more processors (CPU), input/output interface, net
Network interface and internal memory.
Memory may include computer-readable medium in volatile memory, random access memory (RAM) and/
Or the form such as Nonvolatile memory, such as read-only storage (ROM) or flash memory (flash RAM).Memory is computer-readable Jie
The example of matter.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer-readable instruction, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM (SRAM), moved
State random access memory (DRAM), other kinds of random access memory (RAM), read-only storage (ROM), electric erasable
Programmable read only memory (EEPROM), fast flash memory bank or other memory techniques, read-only optical disc read-only storage (CD-ROM),
Digital versatile disc (DVD) or other optical storages, magnetic cassette tape, the storage of tape magnetic rigid disk or other magnetic storage apparatus
Or any other non-transmission medium, the information that can be accessed by a computing device available for storage.Define, calculate according to herein
Machine computer-readable recording medium does not include temporary computer readable media (transitory media), such as data-signal and carrier wave of modulation.
Above to coding method, device, server and the systems approach of a kind of hospital's medical record information provided herein
And device is described in detail, the foregoing description of the disclosed embodiments, professional and technical personnel in the field are enable to realize
Or use the application.A variety of modifications to these embodiments will be apparent for those skilled in the art,
Generic principles defined herein can be real in other embodiments in the case where not departing from spirit herein or scope
It is existing.Therefore, the application is not intended to be limited to the embodiments shown herein, and is to fit to and principles disclosed herein
The most wide scope consistent with features of novelty.
Claims (13)
- A kind of 1. coding method of hospital's medical record information, it is characterised in that including：First sample set is obtained, the first sample set includes at least one sample medical record information and each sample The disease code of medical record information；Deep learning is carried out to the sample medical record information in the first sample set and its disease code, obtains case history coding rule Then model；When receiving target medical record information to be encoded, using the case history coding rule model to the target medical record information Encoded, obtain the target disease coding of the target medical record information.
- 2. according to the method for claim 1, it is characterised in that also include：The second sample set is obtained, second sample set includes at least one sample medical record information and each sample The disease code of medical record information；Based on the sample medical record information and its disease code in second sample set, the case history coding rule model is entered Row optimization.
- 3. according to the method for claim 1, it is characterised in that also include：The target medical record information and its target disease coding are transmitted.
- 4. according to the method for claim 3, it is characterised in that also include：The encoder feedback information of the target disease coding is received, the encoder feedback information includes：Medical supervision and medical treatment should With the encoder feedback information encoded to the target disease；The case history coding rule model is optimized based on the encoder feedback information.
- A kind of 5. code device of hospital's medical record information, it is characterised in that including：Unit is encoded, for obtaining first sample set, the first sample set includes at least one sample case history The disease code of information and each sample medical record information；To the sample medical record information and its disease in the first sample set Disease coding carries out deep learning, obtains case history coding rule model；Generation unit is encoded, for when receiving target medical record information to be encoded, utilizing the case history coding rule model The target medical record information is encoded, obtains the target disease coding of the target medical record information.
- 6. device according to claim 5, it is characterised in that also include：Code optimization unit, for obtaining the second sample set, second sample set includes at least one sample case history The disease code of information and each sample medical record information；Based on the sample medical record information in second sample set and its Disease code, the case history coding rule model is optimized.
- 7. device according to claim 5, it is characterised in that the coding unit is by selecting one or more points Group standard generates the disease grouping information of a variety of packet standards based on the sample medical record information, to be met a variety of codings The case history coding rule model of application demand.
- 8. device according to claim 5, it is characterised in that the coding unit is by selecting one or more mesh Coding information of the coding standard based on sample medical record information generation plurality of target coding standard is marked, to meet a variety of codings The case history coding rule model of application demand.
- 9. device according to claim 5, it is characterised in that also include：Transmission unit, for the target medical record information and its target disease coding to be transmitted；The transmission unit is additionally operable to：Receive the encoder feedback information of the target disease coding, the encoder feedback packet Include：The encoder feedback information that medical supervision and medical applications encode to the target disease；Code optimization unit is additionally operable to：It is described excellent to case history coding rule model progress based on the encoder feedback information Change.
- A kind of 10. encoder server of hospital's medical record information, it is characterised in that including：Memory, for storing data caused by application program and application program operation；Processor, for running the application program in the memory, to realize following functions：Obtain first sample set, institute Stating first sample set includes the disease code of at least one sample medical record information and each sample medical record information；To institute State the sample medical record information in first sample set and its disease code carries out deep learning, obtain case history coding rule model； When receiving target medical record information to be encoded, the target medical record information is carried out using the case history coding rule model Coding, obtain the target disease coding of the target medical record information.
- 11. server according to claim 11, it is characterised in that also include：Coffret and interactive device, the coffret are connected between the server and interactive device, wherein：The interactive device, for receiving the input operation of user, the input operation is included to the target medical record information Input operation, the processor target medical record information being sent to by the coffret in the server, and pass through The coffret obtains the target disease coding that the processor obtains and is exported target disease coding；The interactive device, it is additionally operable to obtain encoder feedback information, and the encoder feedback information is passed through into the coffret The processor is sent to, the encoder feedback information includes：What medical supervision and medical applications encoded to the target disease Encoder feedback information.
- 12. server according to claim 11, it is characterised in that the interactive device includes：Input equipment and output Equipment.
- A kind of 13. hospital's medical record information coded system, it is characterised in that including：Data source terminal；Encoder server, for obtaining first sample set from the data source terminal, and to the first sample set In sample medical record information and its disease code carry out deep learning, obtain case history coding rule model；It is to be encoded receiving Target medical record information when, the target medical record information is encoded using the case history coding rule model, obtained described The target disease coding of target medical record information.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710145435 | 2017-03-14 | ||
| CN2017101454359 | 2017-03-14 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107833605A true CN107833605A (en) | 2018-03-23 |
Family
ID=61644202
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711327971.7A Pending CN107833605A (en) | 2017-03-14 | 2017-12-13 | A kind of coding method, device, server and the system of hospital's medical record information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107833605A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109493931A (en) * | 2018-10-25 | 2019-03-19 | 平安科技（深圳）有限公司 | A kind of coding method of patient file, server and computer readable storage medium |
| CN109545297A (en) * | 2018-10-30 | 2019-03-29 | 平安医疗健康管理股份有限公司 | A kind of disease coding method and calculating equipment based on big data |
| CN109993227A (en) * | 2019-03-29 | 2019-07-09 | 京东方科技集团股份有限公司 | Method, system, device and the medium of automatic addition International Classification of Diseases coding |
| CN110491465A (en) * | 2019-08-20 | 2019-11-22 | 山东众阳健康科技集团有限公司 | Classification of diseases coding method, system, equipment and medium based on deep learning |
| CN110517787A (en) * | 2019-08-30 | 2019-11-29 | 山东健康医疗大数据有限公司 | A kind of clinical data group classification method based on Chinese medical main suit's analysis |
| CN110895580A (en) * | 2019-12-12 | 2020-03-20 | 山东众阳健康科技集团有限公司 | ICD operation and operation code automatic matching method based on deep learning |
| CN111309703A (en) * | 2019-09-06 | 2020-06-19 | 北京交通大学 | Automatic transformation method and device for disease codes |
| CN111339126A (en) * | 2020-02-27 | 2020-06-26 | 平安医疗健康管理股份有限公司 | Medical data screening method and device, computer equipment and storage medium |
| CN111370081A (en) * | 2020-05-27 | 2020-07-03 | 杭州联众医疗科技股份有限公司 | Artificial intelligence data collection method in time coding mode |
| CN111524569A (en) * | 2020-04-24 | 2020-08-11 | 常州昊泽信息科技有限公司 | Electronic medical record diagnosis and maintenance system |
| CN111640517A (en) * | 2020-05-27 | 2020-09-08 | 医渡云（北京）技术有限公司 | Medical record encoding method and device, storage medium and electronic equipment |
| CN113031943A (en) * | 2021-03-29 | 2021-06-25 | 北京大米科技有限公司 | Code generation method, device, storage medium and electronic equipment |
| WO2022152280A1 (en) * | 2021-01-18 | 2022-07-21 | 阿里巴巴集团控股有限公司 | Disease type identification method, device and system, and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104866727A (en) * | 2015-06-02 | 2015-08-26 | 陈宽 | Deep learning-based method for analyzing medical data and intelligent analyzer thereof |
| CN105069124A (en) * | 2015-08-13 | 2015-11-18 | 易保互联医疗信息科技（北京）有限公司 | Automatic ICD (International Classification of Diseases) coding method and system |
| US20170032221A1 (en) * | 2015-07-29 | 2017-02-02 | Htc Corporation | Method, electronic apparatus, and computer readable medium of constructing classifier for disease detection |
| CN106484674A (en) * | 2016-09-20 | 2017-03-08 | 北京工业大学 | A kind of Chinese electronic health record concept extraction method based on deep learning |
| CN106844308A (en) * | 2017-01-20 | 2017-06-13 | 天津艾登科技有限公司 | A kind of use semantics recognition carries out the method for automating disease code conversion |
-
2017
- 2017-12-13 CN CN201711327971.7A patent/CN107833605A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104866727A (en) * | 2015-06-02 | 2015-08-26 | 陈宽 | Deep learning-based method for analyzing medical data and intelligent analyzer thereof |
| US20170032221A1 (en) * | 2015-07-29 | 2017-02-02 | Htc Corporation | Method, electronic apparatus, and computer readable medium of constructing classifier for disease detection |
| CN105069124A (en) * | 2015-08-13 | 2015-11-18 | 易保互联医疗信息科技（北京）有限公司 | Automatic ICD (International Classification of Diseases) coding method and system |
| CN106484674A (en) * | 2016-09-20 | 2017-03-08 | 北京工业大学 | A kind of Chinese electronic health record concept extraction method based on deep learning |
| CN106844308A (en) * | 2017-01-20 | 2017-06-13 | 天津艾登科技有限公司 | A kind of use semantics recognition carries out the method for automating disease code conversion |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109493931A (en) * | 2018-10-25 | 2019-03-19 | 平安科技（深圳）有限公司 | A kind of coding method of patient file, server and computer readable storage medium |
| CN109493931B (en) * | 2018-10-25 | 2024-06-04 | 平安科技（深圳）有限公司 | Medical record file encoding method, server and computer readable storage medium |
| CN109545297A (en) * | 2018-10-30 | 2019-03-29 | 平安医疗健康管理股份有限公司 | A kind of disease coding method and calculating equipment based on big data |
| CN109993227A (en) * | 2019-03-29 | 2019-07-09 | 京东方科技集团股份有限公司 | Method, system, device and the medium of automatic addition International Classification of Diseases coding |
| CN109993227B (en) * | 2019-03-29 | 2021-09-24 | 京东方科技集团股份有限公司 | Method, system, apparatus and medium for automatically adding international disease classification code |
| CN110491465A (en) * | 2019-08-20 | 2019-11-22 | 山东众阳健康科技集团有限公司 | Classification of diseases coding method, system, equipment and medium based on deep learning |
| AU2020333132B2 (en) * | 2019-08-20 | 2023-07-13 | Shan Dong Msun Health Technology Group Co., Ltd. | Method and system for disease classification coding based on deep learning, and device and medium |
| WO2021032219A3 (en) * | 2019-08-20 | 2021-04-15 | 山东众阳健康科技集团有限公司 | Method and system for disease classification coding based on deep learning, and device and medium |
| CN110491465B (en) * | 2019-08-20 | 2020-09-15 | 山东众阳健康科技集团有限公司 | Disease classification coding method, system, device and medium based on deep learning |
| CN110517787A (en) * | 2019-08-30 | 2019-11-29 | 山东健康医疗大数据有限公司 | A kind of clinical data group classification method based on Chinese medical main suit's analysis |
| CN111309703A (en) * | 2019-09-06 | 2020-06-19 | 北京交通大学 | Automatic transformation method and device for disease codes |
| CN110895580A (en) * | 2019-12-12 | 2020-03-20 | 山东众阳健康科技集团有限公司 | ICD operation and operation code automatic matching method based on deep learning |
| CN111339126A (en) * | 2020-02-27 | 2020-06-26 | 平安医疗健康管理股份有限公司 | Medical data screening method and device, computer equipment and storage medium |
| CN111339126B (en) * | 2020-02-27 | 2023-02-07 | 平安医疗健康管理股份有限公司 | Medical data screening method and device, computer equipment and storage medium |
| CN111524569A (en) * | 2020-04-24 | 2020-08-11 | 常州昊泽信息科技有限公司 | Electronic medical record diagnosis and maintenance system |
| CN111640517A (en) * | 2020-05-27 | 2020-09-08 | 医渡云（北京）技术有限公司 | Medical record encoding method and device, storage medium and electronic equipment |
| CN111640517B (en) * | 2020-05-27 | 2023-05-26 | 医渡云（北京）技术有限公司 | Medical record coding method and device, storage medium and electronic equipment |
| CN111370081A (en) * | 2020-05-27 | 2020-07-03 | 杭州联众医疗科技股份有限公司 | Artificial intelligence data collection method in time coding mode |
| WO2022152280A1 (en) * | 2021-01-18 | 2022-07-21 | 阿里巴巴集团控股有限公司 | Disease type identification method, device and system, and storage medium |
| CN113031943A (en) * | 2021-03-29 | 2021-06-25 | 北京大米科技有限公司 | Code generation method, device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107833605A (en) | A kind of coding method, device, server and the system of hospital's medical record information | |
| US11232365B2 (en) | Digital assistant platform | |
| Uysal et al. | Smart manufacturing in intelligent digital mesh: Integration of enterprise architecture and software product line engineering | |
| CN111506723B (en) | Question-answer response method, device, equipment and storage medium | |
| CA3046247C (en) | Data platform for automated data extraction, transformation, and/or loading | |
| Chattopadhyay et al. | A Case‐Based Reasoning system for complex medical diagnosis | |
| US20200227175A1 (en) | Document improvement prioritization using automated generated codes | |
| US20210005312A1 (en) | Health management system with multidimensional performance representation | |
| CA2833779A1 (en) | Predictive modeling | |
| El-Banna | Patient discharge time improvement by using the six sigma approach: a case study | |
| Liu et al. | Requirements engineering for health data analytics: Challenges and possible directions | |
| Theodorou et al. | Synthesize high-dimensional longitudinal electronic health records via hierarchical autoregressive language model | |
| Upjohn et al. | Demystifying AI in healthcare: historical perspectives and current considerations | |
| CN108122613A (en) | Health forecast method and apparatus based on health forecast model | |
| Best et al. | Predicting the COVID-19 pandemic impact on clinical trial recruitment | |
| CN111445969A (en) | Sales prediction method and system capable of flexibly adapting to noise | |
| Varuna et al. | Trend prediction of GitHub using time series analysis | |
| Wang et al. | A novel parallel clock-driven algorithm for simulation of neuronal networks based on virtual synapse | |
| Močarníková et al. | Conceptualization of predictive analytics by literature review | |
| CN115525192A (en) | User-oriented quotation charging method and device, computer equipment and storage medium | |
| Zabawa et al. | Overcoming challenges in hybrid simulation design and experiment | |
| Mishra | Nature-Inspired Algorithms: For Engineers and Scientists | |
| US20190258776A1 (en) | Single sample genetic classification via tensor motifs | |
| Huang et al. | Time-guided high-order attention model of longitudinal heterogeneous healthcare data | |
| US12002557B2 (en) | Creating and updating problem lists for electronic health records |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |