CN109698016A - Disease automatic coding and device - Google Patents
Disease automatic coding and device Download PDFInfo
- Publication number
- CN109698016A CN109698016A CN201811512607.2A CN201811512607A CN109698016A CN 109698016 A CN109698016 A CN 109698016A CN 201811512607 A CN201811512607 A CN 201811512607A CN 109698016 A CN109698016 A CN 109698016A
- Authority
- CN
- China
- Prior art keywords
- coding
- icd
- disease
- word
- case history
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The present invention relates to automatic coding field, a kind of disease automatic coding and device are provided, wherein the described method includes: firstly, obtaining the disease data set in case history；Secondly, carrying out data prediction to disease data set, genius morbi word is obtained；Then, according to genius morbi word, judge disease type；Finally, encoding to disease type, coding result is obtained, coding result is ICD-10 coding.Compared with prior art, disease automatic coding and device provided by the invention improve the code efficiency of ICD coding.
Description
Technical field
The present invention relates to automatic coding fields, in particular to a kind of disease automatic coding and device.
Background technique
Deepening continuously and develop with Medical Informalization construction, the information systems such as electronic health record are obtained in clinic
It is widely applied, produces a large amount of health medical treatment data.The foundation of area medical system promotes medical data for correlation doctor
Treat that mechanism is shared to be used, how to make full use of the massive medical health data deposited is one under current big data environment important
Problem.However, information system is constantly to establish perfect, while medical diagnosis on disease coded system is also in the updating, at present extensively
International statistical classification ICD-10 is used, ICD coding needs stronger specialized capability, special personnel is needed to encode
Classification, code efficiency are low.
Summary of the invention
The purpose of the present invention is to provide a kind of disease automatic coding and device, with improve it is above-mentioned in the prior art
The low problem of ICD code efficiency.
To achieve the goals above, technical solution used in the embodiment of the present invention is as follows:
In a first aspect, the embodiment of the invention provides a kind of disease automatic codings, which comprises obtain case history
In disease data set；Data prediction is carried out to the disease data set, obtains genius morbi word；According to the genius morbi
Word judges disease type；The disease type is encoded, coding result is obtained, the coding result is ICD-10 coding.
Second aspect, the embodiment of the invention provides a kind of disease autocoding device, described device includes: acquisition mould
Block, for obtaining the disease data set in case history；Processing module is obtained for carrying out data prediction to the disease data set
To genius morbi word；According to the genius morbi word, disease type is judged；The disease type is encoded, is encoded
As a result, the coding result is ICD-10 coding.
Compared with the prior art, the embodiment of the present invention has the advantages that
A kind of disease automatic coding and device provided in an embodiment of the present invention, firstly, by obtaining the disease in case history
Sick data set simultaneously carries out data prediction to disease data set, obtains genius morbi word, then judges according to genius morbi word
Disease type obtains the coding result of ICD-10 type of coding finally, encoding to disease type.Compared with prior art,
By the data set in case history, the coding result of ICD-10 type of coding is finally obtained, doctor's raw diagnostic is solved and corresponds to
Standard diagnostics, which only pass through, to be accomplished manually, mainly by the medical knowledge of coder itself and coding specification knowledge, ability
This work is completed, a large amount of labour is saved, improves ICD code efficiency.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range without creative efforts, can also basis for ordinary skill user person
These attached drawings obtain other relevant attached drawings.
Fig. 1 shows the block diagram of electronic equipment provided in an embodiment of the present invention.
Fig. 2 shows the first pass figures of disease automatic coding provided in an embodiment of the present invention.
Fig. 3 shows the second flow chart of disease automatic coding provided in an embodiment of the present invention.
Fig. 4 shows the schematic diagram of coding dictionary provided in an embodiment of the present invention.
Fig. 5 shows the block diagram of disease autocoding device provided in an embodiment of the present invention.
Icon: 100- electronic equipment；110- processor；120- memory；130- bus；140- communication interface；150- is aobvious
Display screen；200- disease autocoding device；210- detection module；220- obtains module；230- processing module.
Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.Cause
This, is not intended to limit claimed invention to the detailed description of the embodiment of the present invention provided in the accompanying drawings below
Range, but it is merely representative of selected embodiment of the invention.Based on the embodiment of the present invention, art technology user person is not having
Every other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.Meanwhile of the invention
In description, term " first ", " second " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.
Disease automatic coding provided in an embodiment of the present invention is applied to electronic equipment 100, and electronic equipment 100 can be with
It is, but is not limited to smart phone, tablet computer, personal computer, vehicle-mounted computer, personal digital assistant (personal
Digital assistant, PDA) etc..Referring to Fig. 1, Fig. 1 shows electronic equipment 100 provided in an embodiment of the present invention
Block diagram, electronic equipment 100 include processor 110, memory 120, bus 130, communication interface 140 and display screen 150.
Processor 110, memory 120, communication interface 140 and display screen 150 are connected by bus 130, and processor 110 is deposited for executing
The executable module stored in reservoir 120, such as computer program.
Processor 110 may be a kind of IC chip, the processing capacity with signal.During realization, disease
Each step of automatic coding can pass through the integrated logic circuit of the hardware in processor 110 or the instruction of software form
It completes.Above-mentioned processor 110 can be general processor 110, including central processing unit (Central Processing
Unit, abbreviation CPU), network processing unit (Network Processor, abbreviation NP) etc.；It can also be digital signal processor
(Digital Signal Processor, abbreviation DSP), specific integrated circuit (Application Specific
Integrated Circuit, abbreviation ASIC), ready-made programmable gate array (Field-Programmable Gate Array,
Abbreviation FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hardware components.
Memory 120 may include high-speed random access memory (RAM:Random Access Memory), it is also possible to
It further include non-labile memory (non-volatile memory), for example, at least a magnetic disk storage.Memory 120
It may be, but not limited to, random access memory (Random Access Memory, RAM), read-only memory (Read Only
Memory, ROM), programmable read only memory (Programmable Read-Only Memory, PROM) is erasable read-only to deposit
Reservoir (Erasable Programmable Read-Only Memory, EPROM), electricallyerasable ROM (EEROM)
(Electric Erasable Programmable Read-Only Memory, EEPROM) etc..
Bus 130 can be ISA (Industry Standard Architecture) bus, PCI (Peripheral
Component Interconnect) bus or EISA (Extended Industry Standard Architecture) be total
Line etc..It is only indicated with a four-headed arrow in Fig. 1, it is not intended that an only bus 130 or a type of bus 130.
Electronic equipment 100 realizes the electronic equipment by least one communication interface 140 (can be wired or wireless)
Communication connection between 100 and external equipment.Memory 120 is for storing program, such as disease autocoding device 200.Disease
Sick autocoding device 200 includes that at least one can be stored in the memory in the form of software or firmware (firmware)
In 120 or the software function module that is solidificated in the operating system (operating system, OS) of electronic equipment 100.It is described
Processor 110 executes described program after receiving and executing instruction to realize disease automatic coding.
For display screen 150 for showing to image, the content of display can be some processing results of processor 110.
Display screen 150 can be touch display screen, display screen of no interactions function etc..Display screen 150 can show coding result
Show.
It should be understood that structure shown in FIG. 1 is only the structure application schematic diagram of electronic equipment 100, electronic equipment 100
It may also include than shown in Fig. 1 more perhaps less component or with the configuration different from shown in Fig. 1.Shown in Fig. 1
Each component can be realized using hardware, software, or its combination.
Based on above-mentioned electronic equipment 100, a kind of possible implementation of disease automatic coding, the party is given below
The executing subject of method can be above-mentioned electronic equipment 100, referring to Fig. 2, Fig. 2 shows disease provided in an embodiment of the present invention from
The first pass figure of dynamic coding method.Disease automatic coding may comprise steps of:
S101 obtains the disease data set in case history.
It in embodiments of the present invention, may include the essential information of patient in case history (for example, name, gender, age, connection
It is phone, address etc.) and disease data set, disease data set may be, but not limited to, clinical symptoms, interrogation record etc. for disease
The relevant description of disease.Case history can be electronic health record, be also possible to papery case history, when case history is electronic health record, electronic health record
It can be stored in internal storage 120 in electronic equipment 100, be also possible to receive other set by communication interface 140
The electronic health record that preparation is sent；When case history be papery case history when, can by camera (it is external by communication interface 140, either
The camera that electronic equipment 100 includes in itself) shooting obtains case history image, then identifies to case history image, and extract it
In disease data set.
S102 carries out data prediction to disease data set, obtains genius morbi word.
In embodiments of the present invention, genius morbi word can be disease data and concentrate characterization clinical picture, kinds of Diseases, disease
The related participles such as sick happening part, disease light and heavy degree.For example, having a fever, sweating, having a headache, leaf etc. on lung.To disease data set
The step of carrying out data prediction, obtaining genius morbi word, it can be understood as, disease data set is subjected to word segmentation processing, is obtained
Each participle is compared with preset genius morbi dictionary by multiple participles, when a participle and the spy in feature dictionary
When sign word is identical, then using the participle as genius morbi word.Genius morbi dictionary is that all kinds of characterizations that are stored with of default setting are faced
The related Feature Words such as bed phenomenon, kinds of Diseases, disease happening part, disease light and heavy degree.The number of genius morbi word can be with
It is one, is also possible to multiple, is not limited thereto.
S103 judges disease type according to genius morbi word.
In embodiments of the present invention, according to genius morbi word, the step of judging disease type, it can be understood as, by disease
Feature Words vectorization obtains genius morbi vector, and genius morbi vector is inputted preset convolutional neural networks and is classified, is obtained
To disease type.
S104 encodes disease type, obtains coding result, and coding result is ICD-10 coding.
In embodiments of the present invention, coding result can be the coding that coded format is ICD-10.Each disease type is equal
A corresponding coding result, by obtained disease code type in GB/T14396-2016 " classification of diseases and code " and the world
It is retrieved in disease criterion sorting code number ICD-10, obtains coding result.ICD-10 coding is letter+number+symbol shape
Formula specifically includes 3 classifications ([A-Z]+[0-9]+[0-9]), 4 classifications ([A-Z]+[0-9]+[0-9]+[0-9]) and 6 classes
Mesh ([A-Z]+[0-9]+[0-9]+[0-9]+[0-9]+[0-9]).
It may be implemented to automatically generate a case history into an ICD-10 coding by step S101~S104, solve doctor
Raw diagnostic, which corresponds to standard diagnostics and only passes through, to be accomplished manually, mainly by the medical knowledge and coding of coder itself
Classificating knowledge could complete the problem of this works, save a large amount of labour, improve ICD code efficiency.
Mainly in national standard diagnosis coding library, version in 2009 combines the code database that current hospital each on the market uses
The demand modifications and extensions of each hospital oneself, which are spread out, to be stretched the parts of modifications and extensions there is no special organisations and institutions to unite
One management and distribution, the version between hospital and hospital can not be completely compatible, or even has hospital to use country earlier
Standard Edition change, which is spread out, to be stretched, so causing even if the same disease, encoding used in Different hospital can not protect
Card complete unity, and each hospital just less can guarantee and be identical by the national standard version part stretched of spreading out.
Case history in hospital has part encoded, has part not encoded also, and what is encoded may be to compile
Code is encoded at ICD-9, it is also possible to and it is ICD-10 coding, unusual disunity, so, for above situation, needing will be all
The corresponding coding of case history is unified for ICD-10 coding, so that hospital is efficiently managed.
Based on above-mentioned electronic equipment 100, another possible implementation of disease automatic coding is given below, it should
The executing subject of method can be above-mentioned electronic equipment 100, referring to Fig. 3, Fig. 3 shows disease provided in an embodiment of the present invention
The second flow chart of automatic coding.
Disease automatic coding can with the following steps are included:
S201 is detected to whether there is ICD-10 coding in case history.
In embodiments of the present invention, ICD-10 coding is for letter+number+symbol form, specifically includes 3 classifications
([A-Z]+[0-9]+[0-9]), 4 classifications ([A-Z]+[0-9]+[0-9]+[0-9]) and 6 classification ([A-Z]+[0-9]+[0-
9]+[0-9]+[0-9]+[0-9]).The step of being detected in case history with the presence or absence of ICD-10 coding, it can be understood as, judgement
It whether there is the coding of 3 classifications, 4 classifications or 6 classifications in case history, if the volume of any one classification is not present in case history
Code, then it is assumed that the case history thens follow the steps S203 there is no ICD-10 coding；If there are the coding of any one classification in case history,
Then think that the case history there are ICD-10 coding, thens follow the steps S202.
S202 exports the ICD-10 coding in case history.
In embodiments of the present invention, it detects then to export in the case history in case history there are when ICD-10 coding by S201
ICD-10 coding.
S203 is detected to whether there is ICD-9 coding in case history.
In embodiments of the present invention, ICD-9 coding is the form of pure digi-tal or E/V+ number, to whether there is in case history
The step of ICD-9 coding is detected, it can be understood as, judge whether there is pure digi-tal or E/V+ number in case history, if case history
In both without pure digi-tal, also without the coding of E/V+ numeric type, then it is assumed that in the case history there is no ICD-9 encode, then execute
Step S101；If there are pure digi-tal or the codings of E/V+ numeric type in case history, then it is assumed that there are ICD-9 volumes in the case history
Code, thens follow the steps S204.
S204 judges that ICD-9 coding whether there is one-to-one relationship with ICD-10 coding according to preset coding dictionary,
Coding dictionary includes the corresponding relationship of ICD-9 coding with ICD-10 coding.
In embodiments of the present invention, coding dictionary includes the corresponding relationship of ICD-9 coding with ICD-10 coding, in view of ICD-
9 coding classification detailed rules and regulations are 10000 or so, and 6 classifications of ICD-10 at least 22753, corresponding relationship between the two
There may be the following two kinds: the first, the corresponding ICD-10 of an ICD-9 coding classification encodes classification, i.e. ICD-9 coding
With ICD-10 coding there are one-to-one relationship, such case can directly by corresponding relationship by ICD-9 code conversion at
ICD-10 coding；Second, an ICD-9 coding classification corresponds to multiple ICD-10 coding classifications, and is that multiple ICD-10 are compiled
The union of code classification, i.e. one-to-one relationship is not present with ICD-10 coding in ICD-9 coding, at this time, it may be necessary to encode to the ICD-9
Corresponding case history re-starts sorting code number.
Step of the ICD-9 coding with ICD-10 coding with the presence or absence of one-to-one relationship is judged according to preset coding dictionary
Suddenly, it can be understood as, ICD-9 coding classification is obtained, ICD-9 coding classification and its corresponding is found in coding dictionary
ICD-10 encodes classification, when the corresponding ICD-10 coding classification of ICD-9 coding classification, then it is assumed that ICD-9 coding
There are one-to-one relationships with ICD-10 coding, then follow the steps S205；As the corresponding ICD-10 of ICD-9 coding classification
When encoding classification, then it is assumed that one-to-one relationship is not present with ICD-10 coding in ICD-9 coding, thens follow the steps S101.
S205 encodes according to ICD-9 and encodes dictionary, obtains the corresponding ICD-10 of ICD-9 coding and encodes and export.
In embodiments of the present invention, dictionary is encoded and encoded according to ICD-9, is obtained ICD-9 and is encoded corresponding ICD-10
The step of encoding and exporting, it can be understood as, ICD-9 coding classification is obtained, ICD-9 coding class is found in coding dictionary
Mesh and its corresponding ICD-10 encode classification, and obtain the corresponding ICD-10 of ICD-10 coding classification and encode and export.For example,
Referring to Fig. 4, Fig. 4 is shown, the embodiment of the invention provides the schematic diagrames of coding dictionary.ICD-9 coding classification is obtained, i.e.,
1 corresponding classification 1 is encoded, finds the corresponding classification 2 of classification 1 in coding dictionary, wherein classification 1 and classification 2 are identical, by class
The corresponding coding 2 of mesh 2 encodes corresponding ICD-10 as the ICD-9 and encodes and export.
By to whether including that ICD-10 coding and ICD-9 coding judge in case history, when there is ICD-10 coding
When, then ICD-10 coding is directly exported, when there is ICD-9 coding, judges that ICD-9 coding whether there is with ICD-10 coding
One-to-one relationship, and there are when one-to-one relationship, export ICD-10 coding with ICD-10 coding in ICD-9 coding.
By above-mentioned judgement, the data for having carried out coding do not need to carry out duplicate sorting code number work, reduce number
According to treating capacity, further improve code efficiency.
S101 obtains the disease data set in case history.
In embodiments of the present invention, it is detected with the presence or absence of ICD-9 coding in case history, obtains being not present in case history
When ICD-9 is encoded, the disease data set obtained in case history is executed；When according to preset coding dictionary judge ICD-9 coding with
ICD-10, which is encoded, whether there is one-to-one relationship, obtains ICD-9 coding and ICD-10 is encoded when one-to-one relationship is not present,
The disease data set obtained in case history can also be executed.
It may include the essential information (for example, name, gender, age, telephone number, address etc.) and disease of patient in case history
Sick data set, disease data set may be, but not limited to, the descriptions relevant for disease such as clinical symptoms, interrogation record.Case history
It can be electronic health record, be also possible to papery case history, when case history is electronic health record, electronic health record can be stored in electronics and set
Internal storage 120 in standby 100 is also possible to receive the electronic health record that other equipment are sent by communication interface 140；When
When case history is papery case history, it can shoot to obtain case history image by camera, then identify case history image, and extract
Disease data set therein.
S102 carries out data prediction to disease data set, obtains genius morbi word.
In embodiments of the present invention, S102 can also include following sub-step: S121 carries out at participle disease data set
Reason, obtains the word segmentation result comprising multiple participles；S122 filters out all stop words in word segmentation result, obtains multiple first points
Word；S123 determines genius morbi word according to preset rules from multiple first participles.
S121 carries out word segmentation processing to disease data set, obtains the word segmentation result comprising multiple participles.
In embodiments of the present invention, word segmentation result can be all comprising obtaining to disease data set progress word segmentation processing
Participle.Disease data set by the segmenting method based on string matching, the segmenting method based on understanding and can be based on
The segmenting method of statistics carries out word segmentation processing, obtains word segmentation result.For example, disease data set is " 39 DEG C of the body temperature of patient, micro- burning
And with abdominal pain and rhinorrhea symptom " when, then, word segmentation processing is carried out to disease data set, obtained word segmentation result can be
" patient ", " ", " body temperature ", " 39 DEG C ", ", " " micro- burning ", " and ", " with ", " abdominal pain ", "and", " rhinorrhea ", " symptom ".
S122 filters out all stop words in word segmentation result, obtains multiple first participles.
In embodiments of the present invention, stop words may be, but not limited to, English character, number, mathematical character, punctuation mark
With the higher word of frequency of use etc..For example, "and", " ", " " etc..The first participle can be not including in word segmentation result and deactivate
The participle of word.The step of filtering out all stop words in word segmentation result, obtaining multiple first participles, it can be understood as, it will segment
As a result the stop words in all participles filters out, and obtains multiple first participles.For example, when word segmentation result be " patient ", " ",
" body temperature ", " 39 DEG C ", ", " " micro- burning ", " and ", " with ", " abdominal pain ", "and", " rhinorrhea ", " symptom " when, it is therein deactivate
Word have " ", ", ", " and ", "and", filter out the stop words in word segmentation result, obtained multiple first participles be " patient ", " body
Temperature ", " 39 DEG C ", " micro- burning ", " with ", " abdominal pain ", " rhinorrhea ", " symptom ".
S123 determines genius morbi word according to preset rules from multiple first participles.
In embodiments of the present invention, genius morbi word can be disease data and concentrate characterization clinical picture, kinds of Diseases, disease
The related participles such as sick happening part, disease light and heavy degree.For example, having a fever, sweating, having a headache, leaf etc. on lung.According to default rule
Then, the step of genius morbi word is determined from multiple first participles, it can be understood as, by each first participle with it is preset
Genius morbi dictionary is compared, when a first participle is identical as the Feature Words in feature dictionary, then by the first participle
As genius morbi word.Genius morbi dictionary is that be stored with all kinds of characterization clinical pictures, kinds of Diseases, the disease of default setting are sent out
The related Feature Words such as raw position, disease light and heavy degree.The number of genius morbi word can be one, be also possible to it is multiple,
This is not construed as limiting.
For example, include Feature Words " micro- burning ", " abdominal pain ", " rhinorrhea " and other some Feature Words in feature dictionary,
Multiple first participles " patient " that S122 is obtained, " body temperature ", " 39 DEG C ", " micro- burning ", " with ", " abdominal pain ", " rhinorrhea ",
" symptom " is compared with the Feature Words in feature dictionary, determines that genius morbi word is " micro- burning ", " abdominal pain ", " flows nose
Tears ".
S103 judges disease type according to genius morbi word.
In embodiments of the present invention, S103 can also include following sub-step: S131, and genius morbi word is carried out vector
Change, obtains genius morbi vector；Genius morbi vector is inputted preset convolutional neural networks and classified, obtains disease by S132
Sick type.
Genius morbi word is carried out vectorization, obtains genius morbi vector by S131.
In embodiments of the present invention, genius morbi vector can be after genius morbi word carries out vectorization, obtained feature
Vector.It specifically, can be by word to vector (word to vector, word2vec) model, term frequency-inverse document frequency
Genius morbi word is carried out vectorization by (Term Frequency-Inverse Document Frequency, TF-IDF) algorithm,
Obtain one group of real vector, as genius morbi vector.
Genius morbi vector is inputted preset convolutional neural networks and classified, obtains disease type by S132.
In embodiments of the present invention, preset convolutional neural networks can be the convolutional Neural net of deep learning algorithm
Network, the convolutional neural networks can carry out self study to the relationship of its inside by internal deep learning algorithm.For example, volume
It is stored with A-B and B-C in product neural network, by the self study of the convolutional neural networks, A-B-C can be obtained, wherein A-B
Indicate the relationship between A and B, B-C indicates the relationship between B and C, and A-B-C indicates the relationship between A and B and C three.
Genius morbi vector is inputted into the step of preset convolutional neural networks classify, obtain disease type, it can be with
It is interpreted as, there are the convolutional neural networks of self-learning function to classify genius morbi vector data, obtain the class of the disease
Type, and using the genius morbi vector of this input as the input data of the training convolutional neural networks, it is learnt by oneself with having to this
The convolutional neural networks of habit function carry out perfect.
S104 encodes disease type, obtains coding result, and coding result is ICD-10 coding.
In embodiments of the present invention, coding result can be the coding that coded format is ICD-10.Each disease type is equal
A corresponding coding result, by obtained disease code type in GB/T14396-2016 " classification of diseases and code " and the world
It is retrieved in disease criterion sorting code number ICD-10, obtains coding result.ICD-10 coding is letter+number+symbol shape
Formula specifically includes 3 classifications ([A-Z]+[0-9]+[0-9]), 4 classifications ([A-Z]+[0-9]+[0-9]+[0-9]) and 6 classes
Mesh ([A-Z]+[0-9]+[0-9]+[0-9]+[0-9]+[0-9]).
For the method flow of above-mentioned Fig. 2-Fig. 3, a kind of possible realization of disease autocoding device 200 is given below
Mode, the disease autocoding device 200 can use the device architecture of the electronic equipment 100 in above-described embodiment to realize,
It can be realized for the processor 110 in the electronic equipment 100, referring to Fig. 4, Fig. 4 shows disease provided in an embodiment of the present invention
The block diagram of sick autocoding device.Disease autocoding device 200 includes detection module 210, obtains module 220 and place
Manage module 230.
Detection module 210, for being detected in case history with the presence or absence of ICD-10 coding；If so, in output case history
ICD-10 coding；If it is not, then continuing to detect in case history with the presence or absence of ICD-9 coding.
In embodiments of the present invention, detection module 210 is specifically used for: when, there are when ICD-9 coding, foundation is default in case history
Coding dictionary judge ICD-9 coding with ICD-10 coding with the presence or absence of one-to-one relationship, wherein coding dictionary includes ICD-
The corresponding relationship of 9 codings and ICD-10 coding；When ICD-9 coding is not present in case history, the disease number obtained in case history is executed
According to collection.
In embodiments of the present invention, detection module 210 can also be specifically used for: when ICD-9 coding and ICD-10 coding are deposited
In one-to-one relationship, dictionary is encoded and encoded according to ICD-9, is obtained ICD-9 and is encoded corresponding ICD-10 coding and defeated
Out；When one-to-one relationship is not present with ICD-10 coding in ICD-9 coding, the disease data set obtained in case history is executed.
Module 220 is obtained, for obtaining the disease data set in case history.
Processing module 230 obtains genius morbi word for carrying out data prediction to disease data set；It is special according to disease
Word is levied, judges disease type；Disease type is encoded, coding result is obtained, coding result is ICD-10 coding.
In embodiments of the present invention, processing module 230 can be specifically used for: carrying out word segmentation processing to disease data set, obtain
To the word segmentation result comprising multiple participles；All stop words in word segmentation result are filtered out, multiple first participles are obtained；According to default
Rule determines genius morbi word from multiple first participles.
In embodiments of the present invention, processing module 230 can also be specifically used for: genius morbi word being carried out vectorization, is obtained
To genius morbi vector；Genius morbi vector is inputted preset convolutional neural networks to classify, obtains disease type.
In conclusion the embodiment of the present invention provides a kind of disease automatic coding and device, by being in case history
No includes that ICD-10 coding and ICD-9 coding are judged, when there is ICD-10 coding, then directly exports ICD-10 volume
Code judges that ICD-9 coding whether there is one-to-one relationship with ICD-10 coding, and in the ICD- when there is ICD-9 coding
There are when one-to-one relationship, export ICD-10 coding with ICD-10 coding for 9 codings.By above-mentioned judgement, for
The data for carrying out coding do not need to carry out duplicate sorting code number work, reduce the treating capacity of data, improve coding effect
Rate.For the case history encoded, firstly, obtaining the disease data set in case history；Secondly, being counted to disease data set
Data preprocess obtains genius morbi word；Then, according to genius morbi word, judge disease type；Finally, being carried out to disease type
Coding, obtains coding result, and coding result is ICD-10 coding.Compared with prior art, by the data set in case history, finally
Obtain the coding result of ICD-10 type of coding, solve doctor's raw diagnostic correspond to standard diagnostics only pass through it is artificial complete
At, mainly by the medical knowledge of coder itself and coding specification knowledge, could complete this work the problem of, save
A large amount of labour, improves ICD code efficiency.
In several embodiments provided herein, it should be understood that disclosed device and method can also pass through
Other modes are realized.The apparatus embodiments described above are merely exemplary, for example, flow chart and block diagram in attached drawing
Show the device of multiple embodiments according to the present invention, the architectural framework in the cards of method and computer program product,
Function and operation.In this regard, each box in flowchart or block diagram can represent the one of a module, section or code
Part, a part of module, section or code include one or more executable fingers for implementing the specified logical function
It enables.It should also be noted that function marked in the box can also be to be different from attached drawing in some implementations as replacement
Middle marked sequence occurs.For example, two continuous boxes can actually be basically executed in parallel, they sometimes can also be with
It executes in the opposite order, this depends on the function involved.It is also noted that each side in block diagram and or flow chart
The combination of box in frame and block diagram and or flow chart can be based on firmly with the defined function of execution or the dedicated of movement
The system of part is realized, or can be realized using a combination of dedicated hardware and computer instructions.
In addition, each functional module in each embodiment of the present invention can integrate one independent portion of formation together
Point, it is also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
If function is realized and when sold or used as an independent product in the form of software function module, can store
In a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words to existing
Having the part for the part or the technical solution that technology contributes can be embodied in the form of software products, the computer
Software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be personal meter
Calculation machine, server or network equipment etc.) execute all or part of the steps of each embodiment method of the present invention.And it is above-mentioned
Storage medium includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory
The various media that can store program code such as (RAM, Random Access Memory), magnetic or disk.It needs to illustrate
, herein, relational terms such as first and second and the like be used merely to by an entity or operation with it is another
A entity or operation distinguish, and without necessarily requiring or implying between these entities or operation, there are any this actual
Relationship or sequence.Moreover, the terms "include", "comprise" or any other variant thereof is intended to cover non-exclusive inclusion,
So that the process, method, article or equipment for including a series of elements not only includes those elements, but also including not having
The other element being expressly recited, or further include for elements inherent to such a process, method, article, or device.Do not having
There is the element limited in the case where more limiting by sentence "including a ...", it is not excluded that including process, the side of element
There is also other identical elements in method, article or equipment.
These are only the preferred embodiment of the present invention, is not intended to restrict the invention, for those skilled in the art
For member, the invention may be variously modified and varied.All within the spirits and principles of the present invention, it is made it is any modification,
Equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.It should also be noted that similar label and letter are under
Similar terms are indicated in the attached drawing in face, therefore, once being defined in a certain Xiang Yi attached drawing, are not then needed in subsequent attached drawing
It is further defined and explained.
Claims (10)
1. a kind of disease automatic coding, which is characterized in that the described method includes:
Obtain the disease data set in case history；
Data prediction is carried out to the disease data set, obtains genius morbi word；
According to the genius morbi word, disease type is judged；
The disease type is encoded, coding result is obtained, the coding result is ICD-10 coding.
2. the method as described in claim 1, which is characterized in that it is described that data prediction is carried out to the disease data set, it obtains
The step of to genius morbi word, comprising:
Word segmentation processing is carried out to the disease data set, obtains the word segmentation result comprising multiple participles；
All stop words in the word segmentation result are filtered out, multiple first participles are obtained；
According to preset rules, genius morbi word is determined from the multiple first participle.
3. the method as described in claim 1, which is characterized in that it is described according to the genius morbi word, judge disease type
Step, comprising:
The genius morbi word is subjected to vectorization, obtains genius morbi vector；
The genius morbi vector is inputted preset convolutional neural networks to classify, obtains disease type.
4. the method as described in claim 1, which is characterized in that it is described acquisition case history in disease data set the step of it
Before, the method also includes:
It is detected to whether there is ICD-10 coding in case history；
If so, exporting the ICD-10 coding in the case history；
If it is not, then continuing to detect in the case history with the presence or absence of ICD-9 coding.
5. method as claimed in claim 4, which is characterized in that examined in case history with the presence or absence of ICD-9 coding described
After the step of survey, the method also includes:
If it is not, then executing the disease data set obtained in case history；
If so, judging that the ICD-9 coding is closed with ICD-10 coding with the presence or absence of one-to-one correspondence according to preset coding dictionary
System, wherein the coding dictionary includes the corresponding relationship of ICD-9 coding with ICD-10 coding.
6. method as claimed in claim 5, which is characterized in that judge the ICD-9 according to preset coding dictionary described
After the step of coding whether there is one-to-one relationship with ICD-10 coding, the method also includes:
If so, obtaining the ICD-9 according to ICD-9 coding and the coding dictionary and encoding corresponding ICD-10 volume
Code simultaneously exports；
If it is not, then executing the disease data set obtained in case history.
7. a kind of disease autocoding device, which is characterized in that described device includes:
Module is obtained, for obtaining the disease data set in case history；
Processing module obtains genius morbi word for carrying out data prediction to the disease data set；It is special according to the disease
Word is levied, judges disease type；The disease type is encoded, coding result is obtained, the coding result is ICD-10 volume
Code.
8. device as claimed in claim 7, which is characterized in that the processing module is specifically used for:
Word segmentation processing is carried out to the disease data set, obtains the word segmentation result comprising multiple participles；
All stop words in the word segmentation result are filtered out, multiple first participles are obtained；
According to preset rules, genius morbi word is determined from the multiple first participle.
9. device as claimed in claim 7, which is characterized in that the processing module also particularly useful for:
The genius morbi word is subjected to vectorization, obtains genius morbi vector；
The genius morbi vector is inputted preset convolutional neural networks to classify, obtains disease type.
10. device as claimed in claim 7, which is characterized in that described device further include:
Detection module, for being detected in case history with the presence or absence of ICD-10 coding；If so, exporting in the case history
ICD-10 coding；If it is not, then continuing to detect in the case history with the presence or absence of ICD-9 coding.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811512607.2A CN109698016A (en) | 2018-12-11 | 2018-12-11 | Disease automatic coding and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811512607.2A CN109698016A (en) | 2018-12-11 | 2018-12-11 | Disease automatic coding and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109698016A true CN109698016A (en) | 2019-04-30 |
Family
ID=66230474
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811512607.2A Pending CN109698016A (en) | 2018-12-11 | 2018-12-11 | Disease automatic coding and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109698016A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110827929A (en) * | 2019-11-05 | 2020-02-21 | 中山大学 | Disease classification code recognition method and device, computer equipment and storage medium |
| CN110827947A (en) * | 2019-10-31 | 2020-02-21 | 北京东软望海科技有限公司 | ICD (interface control document) code determining method and device, electronic device and readable storage medium |
| CN110837494A (en) * | 2019-10-12 | 2020-02-25 | 云知声智能科技股份有限公司 | Method and device for identifying unspecified diagnosis coding errors of medical record home page |
| CN111243692A (en) * | 2019-12-23 | 2020-06-05 | 望海康信(北京)科技股份公司 | Automatic coding method and system for medical record |
| CN111309703A (en) * | 2019-09-06 | 2020-06-19 | 北京交通大学 | Automatic transformation method and device for disease codes |
| CN111739601A (en) * | 2020-06-28 | 2020-10-02 | 山东健康医疗大数据有限公司 | Normalization method, device and readable medium for non-standard disease names |
| CN111863158A (en) * | 2020-07-06 | 2020-10-30 | 天津市疾病预防控制中心 | Automatic coding system for tumor registration |
| CN112183026A (en) * | 2020-11-27 | 2021-01-05 | 北京惠及智医科技有限公司 | ICD (interface control document) encoding method and device, electronic device and storage medium |
| CN113436730A (en) * | 2021-07-14 | 2021-09-24 | 山大地纬软件股份有限公司 | Hospital disease diagnosis classification automatic coding method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5419143B2 (en) * | 2009-04-27 | 2014-02-19 | トランス・コスモス株式会社 | Code conversion support device, code conversion support method, and code conversion support program |
| CN107705839A (en) * | 2017-10-25 | 2018-02-16 | 山东众阳软件有限公司 | Disease automatic coding and system |
| CN107863147A (en) * | 2017-10-24 | 2018-03-30 | 清华大学 | The method of medical diagnosis based on depth convolutional neural networks |
| CN108932979A (en) * | 2018-07-04 | 2018-12-04 | 泰康保险集团股份有限公司 | Recognition methods, device, terminal and the computer storage medium of classification of diseases information |
-
2018
- 2018-12-11 CN CN201811512607.2A patent/CN109698016A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5419143B2 (en) * | 2009-04-27 | 2014-02-19 | トランス・コスモス株式会社 | Code conversion support device, code conversion support method, and code conversion support program |
| CN107863147A (en) * | 2017-10-24 | 2018-03-30 | 清华大学 | The method of medical diagnosis based on depth convolutional neural networks |
| CN107705839A (en) * | 2017-10-25 | 2018-02-16 | 山东众阳软件有限公司 | Disease automatic coding and system |
| CN108932979A (en) * | 2018-07-04 | 2018-12-04 | 泰康保险集团股份有限公司 | Recognition methods, device, terminal and the computer storage medium of classification of diseases information |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111309703A (en) * | 2019-09-06 | 2020-06-19 | 北京交通大学 | Automatic transformation method and device for disease codes |
| CN110837494A (en) * | 2019-10-12 | 2020-02-25 | 云知声智能科技股份有限公司 | Method and device for identifying unspecified diagnosis coding errors of medical record home page |
| CN110837494B (en) * | 2019-10-12 | 2022-03-25 | 云知声智能科技股份有限公司 | Method and device for identifying unspecified diagnosis coding errors of medical record home page |
| CN110827947A (en) * | 2019-10-31 | 2020-02-21 | 北京东软望海科技有限公司 | ICD (interface control document) code determining method and device, electronic device and readable storage medium |
| CN110827929A (en) * | 2019-11-05 | 2020-02-21 | 中山大学 | Disease classification code recognition method and device, computer equipment and storage medium |
| CN110827929B (en) * | 2019-11-05 | 2022-06-07 | 中山大学 | Disease classification code recognition method and device, computer equipment and storage medium |
| CN111243692A (en) * | 2019-12-23 | 2020-06-05 | 望海康信(北京)科技股份公司 | Automatic coding method and system for medical record |
| CN111739601A (en) * | 2020-06-28 | 2020-10-02 | 山东健康医疗大数据有限公司 | Normalization method, device and readable medium for non-standard disease names |
| CN111739601B (en) * | 2020-06-28 | 2022-03-29 | 山东健康医疗大数据有限公司 | Normalization method, device and readable medium for non-standard disease names |
| CN111863158A (en) * | 2020-07-06 | 2020-10-30 | 天津市疾病预防控制中心 | Automatic coding system for tumor registration |
| CN112183026A (en) * | 2020-11-27 | 2021-01-05 | 北京惠及智医科技有限公司 | ICD (interface control document) encoding method and device, electronic device and storage medium |
| CN113436730A (en) * | 2021-07-14 | 2021-09-24 | 山大地纬软件股份有限公司 | Hospital disease diagnosis classification automatic coding method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109698016A (en) | Disease automatic coding and device | |
| US20200357118A1 (en) | Medical scan viewing system with enhanced training and methods for use therewith | |
| CN113159147B (en) | Image recognition method and device based on neural network and electronic equipment | |
| CN109033200B (en) | Event extraction method, device, equipment and computer readable medium | |
| CN111581046A (en) | Data anomaly detection method and device, electronic equipment and storage medium | |
| CN105469376B (en) | The method and apparatus for determining picture similarity | |
| CN107833603A (en) | Electronic medical record document sorting technique, device, electronic equipment and storage medium | |
| Luo et al. | A deep convolutional neural network for diabetic retinopathy detection via mining local and long‐range dependence | |
| CN111785384A (en) | Abnormal data identification method based on artificial intelligence and related equipment | |
| CN108197250A (en) | Picture retrieval method, electronic equipment and storage medium | |
| CN110490750B (en) | Data identification method, system, electronic equipment and computer storage medium | |
| CN113657548A (en) | Medical insurance abnormity detection method and device, computer equipment and storage medium | |
| US20210174968A1 (en) | Visualization of Social Determinants of Health | |
| Banerjee et al. | Using complex networks towards information retrieval and diagnostics in multidimensional imaging | |
| CN109493931A (en) | A kind of coding method of patient file, server and computer readable storage medium | |
| CN110752027B (en) | Electronic medical record data pushing method, device, computer equipment and storage medium | |
| Ullah et al. | Detecting High‐Risk Factors and Early Diagnosis of Diabetes Using Machine Learning Methods | |
| Huang et al. | Recent advances in medical image processing | |
| Yazdani et al. | Diagnosis of COVID‐19 Disease in Chest CT‐Scan Images Based on Combination of Low‐Level Texture Analysis and MobileNetV2 Features | |
| CN110675270A (en) | Method and device for determining medical insurance deduction amount based on invoice information | |
| AlSheikh et al. | Dental X-ray identification system based on association rules extracted by k-Symbol fractional haar functions | |
| Ampavathi | Research challenges and future directions towards medical data processing | |
| CN113223734A (en) | Disease diagnosis and big health management platform based on algorithm, medical image and big data | |
| CN116884612A (en) | Intelligent analysis method, device, equipment and storage medium for disease risk level | |
| CN109635112A (en) | Abnormal dialysis data screening method, apparatus, equipment and storage 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190430 |