CN108538395A - A kind of construction method of general medical disease that calls for specialized treatment data system - Google Patents
A kind of construction method of general medical disease that calls for specialized treatment data system Download PDFInfo
- Publication number
- CN108538395A CN108538395A CN201810282025.3A CN201810282025A CN108538395A CN 108538395 A CN108538395 A CN 108538395A CN 201810282025 A CN201810282025 A CN 201810282025A CN 108538395 A CN108538395 A CN 108538395A
- Authority
- CN
- China
- Prior art keywords
- disease
- calls
- specialized treatment
- dictionary
- data
- 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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Abstract
The invention discloses a kind of construction methods of general medical disease that calls for specialized treatment data system, it is extracted by clinical text analyzing and knowledge, integrate unstructured case history and two kinds of structural clinical data heterogeneous clinical data sources, final structure by genius morbi analyze for the purpose of general medical disease that calls for specialized treatment data system.Its technical solution is：On the basis of disease that calls for specialized treatment dictionary for word segmentation collection, it is analyzed in conjunction with case history context relation, complete the structuring of electronic health record, application mode matches and feature is dug according to technology, obtain the characteristic value of disease in case history, complete the analysis mining of case history semanteme, the state of an illness feature and Prognosis situation for excavating disease in the non-structured electronic health record of Chinese can be provided, integrated structure clinical data, the genius morbi of medical disease that calls for specialized treatment, the analysis mining of prognosis of disease, therapeutic process are completed, a complete medical disease that calls for specialized treatment data system comprehensively is built.
Description
Technical field
The present invention relates to the administrative skills of medical disease that calls for specialized treatment data, more particularly to the Chinese electronic health record in medical field after
The method of structuring processing and genius morbi extraction.
Background technology
Medical disease that calls for specialized treatment refers to certain single disease in clinical treatment activity.Medical disease that calls for specialized treatment data system is special for medical treatment
Data processing, analysis, integration and the management of disease refer to the complete clinical medical information for managing certain single disease concentratedly, to
It supports the retrospective studies such as clinical research, adjuvant clinical medical treatment and meets clinic scientific research.
Completely, full and accurate medical disease that calls for specialized treatment data be carry out disease research, clinical treatment, teaching and scientific research work important base
Plinth.How to acquire to complete and specification, managed care disease data, and quickly find in these information to medical treatment, teaching and
The valuable data of scientific research become numerous medical staff problem in the urgent need to address.
Genius morbi is the peculiar symptom occurred in certain stages in entire disease progression, includes the symptom spy of disease
Sign, sign feature, image feature and verification characteristics.In order to standardize, sequencing, the medical treatment for being intelligently directed to a certain disease
Information data is collected, analyzes, counting and research work, and the symptom characteristic of disease is most important for the analysis of disease.
Existing clinical treatment disease that calls for specialized treatment data system is mainly directed towards clinical research, is searched by the data target based on structuring
Index holds up the lookup for carrying out research patient, and introduces the CRF form datas of acquisition, in conjunction with the inspection inspection data etc. of patient, uses
In the retrospective and prospective analysis for supporting clinical research.But existing clinical treatment disease that calls for specialized treatment data system lacks to non-structural
Change the method for the efficient process and parsing of history data, and history data exactly describes the corresponding clinical symptoms performance of disease, is
Crucial effect is played the differentiation of disease in the important composition of genius morbi.
Invention content
A brief summary of one or more aspects is given below to provide to the basic comprehension in terms of these.This general introduction is not
The extensive overview of all aspects contemplated, and be both not intended to identify critical or decisive element in all aspects also non-
Attempt to define the range in terms of any or all.Its unique purpose is to provide the one of one or more aspects in simplified form
A little concepts are with the sequence for more detailed description given later.
It is an object of the invention to solve the above problems, a kind of structure side of general medical disease that calls for specialized treatment data system is provided
Method is extracted by clinical text analyzing and knowledge, integrates unstructured case history and two kinds of structural clinical data is heterogeneous clinical
Data source, final structure by genius morbi analyze for the purpose of general disease data system.
The technical scheme is that：Present invention is disclosed a kind of construction method of general medical disease that calls for specialized treatment data system,
Including：
Step 1：Acquire clinical medical data；
Step 2：Collected clinical medical data is subjected to data cleansing；
Step 3：Non-structured medical data is handled, process content includes the participle technique based on Chinese case history
The structuring that electronic health record is completed with mode identification technology, by semantic parsing, character representation, the feature extraction of electronic health record,
What Disease Clinical showed in excavation case history lapses to situation；
Step 4：Unstructured data treated clinical medical data is integrated, the medical data of integrated structure is formed
The medical disease that calls for specialized treatment data of full dimension, construct medical disease that calls for specialized treatment data system.
One embodiment of the construction method of general medical disease that calls for specialized treatment data system according to the present invention acquires in step 1
Medical data includes patient's essential information, Prescriptions for Out-patients, clinic electronic medical recorder, doctor's advice of being hospitalized, diagnosis of being hospitalized, inpatient cases, lives
Including institute's nursing record, physical signs of patient information, patient's survey report data, patient's audit report data, operation record data
Clinical medical data, acquisition means include being obtained by retrieving the acquisition of clinical document database or by accessing clinical data center
Obtain patient's relevant clinical medical data.
One embodiment of the construction method of general medical disease that calls for specialized treatment data system according to the present invention, the data in step 2
Cleaning is to carry out Main index of patients management, timestamp management, inspection on the basis of patient's holographic diagnosis and treatment Information Data model of structure
Data consistency is looked into, the initial data material for completing medical disease that calls for specialized treatment data system prepares.
One embodiment of the construction method of general medical disease that calls for specialized treatment data system according to the present invention, the data in step 2
Cleaning includes the action of four aspects, is respectively：(1) character is converted：Including unified full-shape English character and full-shape number
Word character is converted to half-angle English and numerical character, and half-angle punctuation mark is converted to full-shape punctuation mark；(2) abnormality processing：
The extra symbol including space, newline, bracket in removal case history text；(3) uniform format：Including to case history
Yin and yang attribute text in text carries out unified formatting processing；(4) common-use words are converted：Including turning to the common abbreviation of clinic
It changes.
One embodiment of the construction method of general medical disease that calls for specialized treatment data system according to the present invention, step 3 are further wrapped
It includes：
Prepare material：Prepare the unstructured disease that calls for specialized treatment case history material cleaned；
Word segmentation processing：Based on disease that calls for specialized treatment dictionary, Medical Dictionary, coordinates basic dictionary, form disease that calls for specialized treatment dictionary for word segmentation collection, pass through
Unstructured disease that calls for specialized treatment case history participle is completed in the cycle matching of disease that calls for specialized treatment dictionary for word segmentation collection；
Medicine part-of-speech tagging：Pass through the medicine part of speech of disease that calls for specialized treatment dictionary and basic medical dictionary, mark case history structuring participle
Word part of speech, part of speech includes symptom, diagnosis, drug, inspection project；
Medicine semantic tagger：By synonym, the restriction dictionary in disease that calls for specialized treatment dictionary, parsing medicine is semantic, mark case history point
Attribute part of speech after word, indicates the symptomatic condition of case history；
Disease that calls for specialized treatment index identifies：By the part of speech and semantic tagger of case history, inspection, inspection, symptom, treatment and document are completed
Disease that calls for specialized treatment index parses；
Data structured：Form the disease that calls for specialized treatment medical record data collection of structuring.
One embodiment of the construction method of general medical disease that calls for specialized treatment data system according to the present invention, basic dictionary mainly wrap
Case history everyday words and its frequency of use information are included, there is attribute part of speech；Medical Dictionary includes mainly clinical diagnosis coding dictionary, body
Body region anatomy dictionary, Drug Dictionary check dictionary, examine dictionary, operation dictionary have medicine part of speech；Disease that calls for specialized treatment dictionary master
To include the index of making the rounds of the wards of the symptom dictionary of disease, the treatment dictionary of disease, disease, there is disease that calls for specialized treatment part of speech.
One embodiment of the construction method of general medical disease that calls for specialized treatment data system according to the present invention, disease that calls for specialized treatment dictionary is to pass through
What the self study of disease that calls for specialized treatment case history corpus was formed, formation includes the combination that two aspects are handled,
The processing of one side includes：
After clinic information system acquisition, conversion, cleaning, the corpus of disease that calls for specialized treatment case history is generated, case history is generated and trains language
Material collection；
Modeling learning training is carried out based on the case history language material manually marked, by new case history language material, based on context, is led to
It crosses including hidden Markov model (Hidden Markov Model, HMM) and conditional random field models (Conditional
Random Field Algorithm, CRF) including machine learning model, complete language material participle analysis；
Statistical nature based on Concordance counts the frequency of tagged words, and wherein word frequency is according to word in entire language material
The number of middle appearance determines that word frequency needs are normalized according to corpus size；
Coefficient of frequency based on each word is compared selection with certain threshold value, and disease that calls for specialized treatment word is then selected into automatically higher than threshold value
Allusion quotation automatically generates disease that calls for specialized treatment dictionary；
The medicine part-of-speech tagging that the disease that calls for specialized treatment dictionary of generation is carried out to disease that calls for specialized treatment word carries out the doctor of disease that calls for specialized treatment word in conjunction with manual examination and verification
Learn part-of-speech tagging；
Calculate the position relationship of medicine word context in case history text, bluebeard compound embedded mobile GIS and open insertion
Database medicine semanteme dictionary library carries out the medicine semantic tagger of disease that calls for specialized treatment word in conjunction with manual examination and verification；
The processing of another aspect includes：
Timing analysis diagnosis, inspection, inspection and drug dictionary library；
It obtains diagnosis, examine, the increment word of inspection and drug dictionary library；
Disease that calls for specialized treatment dictionary is ultimately formed in conjunction with the handling result of two aspects.
One embodiment of the construction method of general medical disease that calls for specialized treatment data system according to the present invention, disease that calls for specialized treatment characteristic value index
The step of identification, further comprises：
Disease that calls for specialized treatment characteristic value index to be resolved is got from analysis of medical record result, and disease that calls for specialized treatment feature is obtained after targets match
Index value, then carries out classification parsing, and classification includes inspection, laboratory assay, symptom and sign, essential information, index and case history
Document, then by the management of timestamp, form the association sexual intercourse between index and the variation tendency based on time shaft.
One embodiment of the construction method of general medical disease that calls for specialized treatment data system according to the present invention, the medical treatment in step 4
Disease that calls for specialized treatment data system mainly by disease that calls for specialized treatment index storehouse, disease that calls for specialized treatment dictionary library, new word library, structured electronic patient record, disease that calls for specialized treatment search engine, specially
Sick analysis platform composition.
One embodiment of the construction method of general medical disease that calls for specialized treatment data system according to the present invention, method further includes step
Step 5 after 4：
Front end applications are carried out on the basis of medical disease that calls for specialized treatment data system, front end applications include mainly clinical assistant decision making support
It holds, disease that calls for specialized treatment analysis and research, case history is retrieved, case history is described, the analysis digging for carrying out genius morbi, prognosis of disease, therapeutic process
Pick.
The present invention, which compares the prior art, following advantageous effect：The present invention on the basis of medical professionalism dictionary, in conjunction with
Case history context relation is analyzed, and after the structuring for completing electronic health record, application mode matching and feature are dug according to technology, and case history is obtained
The characteristic value of middle disease completes the analysis mining of case history semanteme, can provide disease in the non-structured electronic health record of excavation Chinese
Disease state of an illness feature and Prognosis situation, complete genius morbi, disease development symptom, therapeutic process analysis mining, build
One comprehensive complete medical disease that calls for specialized treatment data system, provides service support, realization is new for clinical retrospective and perspective study
The electronic health record Analysis Service type knowledge base system of type, the scientific research analysis towards medical disease that calls for specialized treatment and clinical decision, to make text
The data source of type establishes semantic interoperability.Research and analysis for a certain disease, establish have related disorders symptom,
Disease treats correlation rule, is assessed according to disease forecasting, disease cluster, disease severity, proposes such as antibiosis extract for treating, resists
The all types for the treatment of recommendations such as scorching treatment, symptomatic treatment, oxygen therapy, supportive treatment, can benefit the medical treatment, teaching, section of clinical training
Grind work.
Description of the drawings
After reading the detailed description of embodiment of the disclosure in conjunction with the following drawings, it better understood when the present invention's
Features described above and advantage.In the accompanying drawings, each component is not necessarily drawn to scale, and has similar correlation properties or feature
Component may have same or similar reference numeral.
Fig. 1 shows the overview flow chart of the construction method of the general medical disease that calls for specialized treatment data system of the present invention.
Fig. 2 shows the unstructured process charts of case history in method.
Fig. 3 shows the flow chart that the disease that calls for specialized treatment dictionary in method is built automatically.
Fig. 4 shows the flow chart of the extraction of the electronic health record genius morbi in method.
Fig. 5 shows an exemplary schematic diagram of semantic analysis result.
Specific implementation mode
Below in conjunction with the drawings and specific embodiments, the present invention is described in detail.Note that below in conjunction with attached drawing and specifically real
The aspects for applying example description is merely exemplary, and is understood not to carry out any restrictions to protection scope of the present invention.
Fig. 1 shows the overall procedure of the construction method of the general medical disease that calls for specialized treatment data system of the present invention.Refer to figure
1, here is the detailed description to each step in overall procedure.
Step S1：Clinical medical data is acquired, medical data includes patient's essential information, Prescriptions for Out-patients, outpatient service electronics disease
It goes through, doctor's advice of being hospitalized, be hospitalized diagnosis, inpatient cases, inpatient record, physical signs of patient information, patient's survey report data, patient
The information such as audit report data, operation record.
These information can be obtained by retrieving clinical document database in the present embodiment, it can also be by accessing clinical number
Patient's relevant clinical medical data is obtained according to center.
Step S2：The clinical medical data of acquisition is subjected to data cleansing, in patient's holographic diagnosis and treatment information data of structure
On the basis of model, carries out Main index of patients management, timestamp management, checks data consistency, be finally completed disease that calls for specialized treatment data system
Initial data material prepare.
Following 4 aspects are mainly completed in the data cleansing of case history text：(1) character is converted：It is such as unified full-shape English words
Symbol and whole-angle figure character are converted to half-angle English and numerical character, and half-angle punctuation mark is converted to full-shape punctuation mark；(2)
Abnormality processing：Such as remove space extra in case history text, newline, bracket；(3) uniform format：Such as in case history text
Yin and yang attribute text carry out unified formatting processing, such as：(+) is formatted as the positive, and (-) is formatted as feminine gender, (+++) format
2 grades of positives are turned to, (+-) it is formatted as weakly positive etc.；(4) common-use words are converted：Such as the common abbreviation of some clinics is turned
It changes, such as 1d is formatted as 1 day, G2P1 is unified for " pregnant 2 productions 1 time ", and T is unified for " body temperature " etc..
Step S3：Non-structured medical data is handled.
It is primarily referred to as the participle technique based on Chinese case history and mode identification technology, completes the rear structuring of electronic health record,
By semantic parsing, character representation, the feature extraction of electronic health record, what Disease Clinical showed in excavation case history lapses to situation.
It is implemented as shown in Fig. 2, being the realization step further refined for step S3 below.
Step S301：In clinical application information system, structure data pick-up, cleaning, conversion and loading attachment are completed non-
The preparation material of structuring disease that calls for specialized treatment case history.
Step S302：Based on disease that calls for specialized treatment dictionary, Medical Dictionary, coordinates basic dictionary, form disease that calls for specialized treatment dictionary for word segmentation collection, pass through
Unstructured disease that calls for specialized treatment case history participle is completed in the cycle matching of disease that calls for specialized treatment dictionary for word segmentation collection.
Wherein, basic dictionary mainly include case history everyday words and its frequency of use information, such as " man ", " female ", "upper",
"lower", " preceding ", " opinion ", "available", " can and ", " appearance ", " general ", " maximum ", " function ", " multiple ", " uniform ", " consistent " etc.
Attribute word, the noun of locality, common verb, adverbial word, adjective etc., have attribute part of speech.Medical Dictionary includes mainly that clinical diagnosis is compiled
Code dictionary body part anatomy dictionary, Drug Dictionary, checks dictionary, examines the compositions such as dictionary, operation dictionary have medicine
Part of speech.Disease that calls for specialized treatment dictionary includes mainly the compositions such as index of making the rounds of the wards of the symptom dictionary of disease, the treatment dictionary of disease, disease, is had
Disease that calls for specialized treatment part of speech.
It illustrates：
Before participle：Patient's self-induction chilly, fever have intermittent cough with cerise frothy bloody phlegm, do not go to a doctor.
After participle：Patient | self-induction | chilly |, | fever | have | it is intermittent | cough | companion | cerise | foam sample | courageous and upright phlegm
|, | not | medical |.
Disease that calls for specialized treatment dictionary is formed by the self study of disease that calls for specialized treatment case history corpus, and detailed process is as shown in Figure 3.
Step S3021：After clinic information system acquisition, conversion, cleaning, the corpus of disease that calls for specialized treatment case history is generated, is generated
Case history training corpus collection.The clinical information of acquisition includes " present illness history ", " main suit ", " training inspection ", " auxiliary examination ", " preliminary
Diagnosis ", " antidiastole ", " operation record ", " seen in checking " etc..
Step S3022：Modeling learning training is carried out based on the case history language material manually marked, passes through new case history language material, root
According to context, by including hidden Markov model (Hidden Markov Model, HMM) and conditional random field models
Machine learning model including (Conditional Random Field Algorithm, CRF) etc. completes language material participle point
Analysis.
The algorithm of modeling learning training can be the sequence labelling algorithm of any type natural language, including but not limited to item
Part random field method, Hidden Markov algorithm, Recognition with Recurrent Neural Network algorithm etc..The model learnt is applied and new case history language material
It is applied, language material participle evaluation of markers work can be completed.
Step S3023：Statistical nature based on Concordance counts the frequency of tagged words.
Word frequency determines that word frequency needs to carry out normalizing according to corpus size according to the number that word occurs in entire language material
Change is handled：
Word frequency coefficient=word occurrence number/total number of word；
Can also be：
Word frequency coefficient=word occurrence number/total word number.
(logarithm can be taken or converted with other monotonic functions)
Step S3024：Coefficient of frequency based on each word is compared with certain threshold value to be selected, higher than formulation threshold value
Be then selected into disease that calls for specialized treatment dictionary automatically, automatically generate disease that calls for specialized treatment dictionary.
Step S3025：The disease that calls for specialized treatment dictionary of generation and existing medical terminology dictionary are compared by algorithm, carry out disease that calls for specialized treatment word
(medicine semantic tagger includes body part, checks title, examines title, disease name, drug name the medicine part-of-speech tagging of language
Title, operation names, grammatical term for the character etc.), in conjunction with manual examination and verification, carry out the medicine part-of-speech tagging of disease that calls for specialized treatment word.
Step S3026：It closes the position for calculating medicine word context in case history text on the basis of previous step by algorithm
System is embedded in number in conjunction with existing word embedded mobile GIS, such as Word2vec, Med2vec, GloVe, fastText and open
According to library medicine semanteme dictionary library the medicine semantic tagger of disease that calls for specialized treatment word is carried out in conjunction with manual examination and verification.
Step S3027：Timing analysis diagnosis, inspection, inspection and drug dictionary library.
Step S3028：It obtains diagnosis, examine, the increment word of inspection and drug dictionary library.
Step S3029：Form disease that calls for specialized treatment dictionary.
Step S303：Pass through the medicine part of speech of disease that calls for specialized treatment dictionary and Medical Dictionary, the word word of mark case history structuring participle
Property, including symptom, diagnosis, drug, inspection project etc..
It illustrates：
After mark：Patient | P self-inductions | J chillies | S, | X generates heat | and S has | and J is intermittent | and D coughs | S companions | J cerises | D foams
Sample | D courage and uprightness phlegm | S, | X not | J is medical | A.|X
Wherein letter illustrates different parts of speech.
Step S304：By synonym, restriction dictionary etc. in disease that calls for specialized treatment dictionary, parsing medicine is semantic, after mark case history participle
Attribute part of speech, indicate the symptomatic condition of case history, such as disease symptoms aggravate or mitigate.
The results are shown in Figure 5 after illustration semantic analysis.
Step S305：By the part of speech and semantic tagger of case history, inspection, inspection, symptom, the disease that calls for specialized treatment for the treatment of and document are completed
Index parses.
It is as follows that structuring generates index：
Self-induction → chilly=>{key:Stomach cold, value:It is positive }
Self-induction → fever=>{key:Fever, value:It is positive }
Have → cough=>{key:Cough, value:It is positive }
With → courage and uprightness phlegm=>{key:Courageous and upright phlegm, value:It is positive }
Intermittence → cough=>{key:Cough, property:It is intermittent }
Cerise → courage and uprightness phlegm=>{key:Courageous and upright phlegm, property:Cerise }
Foam sample → courage and uprightness phlegm=>{key:Courageous and upright phlegm, property:Foam sample }
The specific steps of disease that calls for specialized treatment index identification are as shown in Figure 4.
Disease that calls for specialized treatment characteristic value index to be resolved is got from analysis of medical record result, and disease that calls for specialized treatment feature is obtained after targets match
Then index value carries out classification parsing.Classification include inspection as shown in the figure, laboratory assay, symptom and sign, essential information,
Index and medical record document, then by the management of timestamp, form the relevance between index and the variation tendency based on time shaft.
For checking, further comprises checking and accuse of acquisition, body part parsing and the parsing of attribute word.For experiment
Room is chemically examined, and is further comprised outer court's lab work parsing, is obtained synonym, result and unit parsing.For symptom and sign,
Further comprise parsing symptom synonym, parsing symptom with attribute word, parsing duration and unit.For essential information, packet
Include family history, past medical history basic analytical.For treatment, including the parsing of disease that calls for specialized treatment key agents, the treatment of disease that calls for specialized treatment primary operational.For disease
Document is gone through, the conventional index that further comprises making the rounds of the wards daily enters conventional index of leaving hospital.
Step S306：Ultimately form the disease that calls for specialized treatment case history of structuring.
Step S4：Based on the data to unstructured data treated data and inherently structuring, structure
Go out medical disease that calls for specialized treatment data system.
Medical disease that calls for specialized treatment data system mainly by disease that calls for specialized treatment index storehouse, disease that calls for specialized treatment dictionary library, new word library, structured electronic patient record, specially
Sick search engine, disease that calls for specialized treatment analysis platform composition.
Step S5：On the basis of medical disease that calls for specialized treatment data system, front end applications are carried out, main includes clinical aid decision
The applications such as support, disease that calls for specialized treatment analysis and research, case history retrieval, case history description, for carrying out genius morbi, prognosis of disease, therapeutic process
Analysis mining.
The method have the characteristics that optimizing the structure flow of medical disease that calls for specialized treatment data system, it is proposed that disease that calls for specialized treatment dictionary for word segmentation
Collection optimizes participle dictionary library, forms the professional part of speech library in medical field, is not to be divided into name as general participle library
Word, verb, adjective etc., but part of speech is divided into diagnosis, drug, symptom, inspection item etc., and form medical treatment by automating
Dictionary.And the genius morbi key point in case history text is obtained by the model of pattern match according to the characteristic index of disease that calls for specialized treatment, then
By the management of timestamp, the association sexual intercourse and the variation tendency based on time shaft, integrated structure that are formed between index are faced
Bed information ultimately forms comprehensive medical disease that calls for specialized treatment data system.
Although to simplify explanation to illustrate the above method and being described as a series of actions, it should be understood that and understand,
The order that these methods are not acted is limited, because according to one or more embodiments, some actions can occur in different order
And/or with from it is depicted and described herein or herein it is not shown and describe but it will be appreciated by those skilled in the art that other
Action concomitantly occurs.
Those skilled in the art will further appreciate that, the various illustratives described in conjunction with the embodiments described herein
Logic plate, module, circuit and algorithm steps can be realized as electronic hardware, computer software or combination of the two.It is clear
Explain to Chu this interchangeability of hardware and software, various illustrative components, frame, module, circuit and step be above with
Its functional form makees generalization description.Such functionality be implemented as hardware or software depend on concrete application and
It is applied to the design constraint of total system.Technical staff can realize each specific application described with different modes
Functionality, but such realization decision should not be interpreted to cause departing from the scope of the present invention.
General place can be used in conjunction with various illustrative logic plates, module and the circuit that presently disclosed embodiment describes
Reason device, digital signal processor (DSP), application-specific integrated circuit (ASIC), field programmable gate array (FPGA) other are compiled
Journey logical device, discrete door or transistor logic, discrete hardware component or its be designed to carry out function described herein
Any combinations are realized or are executed.General processor can be microprocessor, but in alternative, which can appoint
What conventional processor, controller, microcontroller or state machine.Processor is also implemented as the combination of computing device, example
Such as DSP and the combination of microprocessor, multi-microprocessor, one or more microprocessors to cooperate with DSP core or any
Other such configurations.
It can be embodied directly in hardware, in by processor in conjunction with the step of method or algorithm that embodiment disclosed herein describes
It is embodied in the software module of execution or in combination of the two.Software module can reside in RAM memories, flash memory, ROM and deposit
Reservoir, eprom memory, eeprom memory, register, hard disk, removable disk, CD-ROM or known in the art appoint
In the storage medium of what other forms.Exemplary storage medium is coupled to processor so that the processor can be from/to the storage
Medium reads and writees information.In alternative, storage medium can be integrated into processor.Pocessor and storage media can
It resides in ASIC.ASIC can reside in user terminal.In alternative, pocessor and storage media can be used as discrete sets
Part is resident in the user terminal.
In one or more exemplary embodiments, described function can be in hardware, software, firmware, or any combination thereof
Middle realization.If being embodied as computer program product in software, each function can be used as the instruction of one or more items or generation
Code may be stored on the computer-readable medium or is transmitted by it.Computer-readable medium includes computer storage media and communication
Both media comprising any medium for facilitating computer program to shift from one place to another.Storage medium can be can quilt
Any usable medium that computer accesses.It is non-limiting as example, such computer-readable medium may include RAM, ROM,
EEPROM, CD-ROM or other optical disc storage, disk storage or other magnetic storage apparatus can be used to carry or store to refer to
The desirable program code of order or data structure form and any other medium that can be accessed by a computer.Any connection is also proper
Ground is known as computer-readable medium.For example, if software is using coaxial cable, fiber optic cables, twisted-pair feeder, digital subscriber line
(DSL) or the wireless technology of such as infrared, radio and microwave etc is passed from web site, server or other remote sources
It send, then the coaxial cable, fiber optic cables, twisted-pair feeder, DSL or such as infrared, radio and microwave etc is wireless
Technology is just included among the definition of medium.Disk (disk) and dish (disc) as used herein include compression dish
(CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and blu-ray disc, which disk (disk) are often reproduced in a manner of magnetic
Data, and dish (disc) with laser reproduce data optically.Combinations of the above should also be included in computer-readable medium
In the range of.
Offer is that can make or use this public affairs to make any person skilled in the art all to the previous description of the disclosure
It opens.The various modifications of the disclosure all will be apparent for a person skilled in the art, and as defined herein general
Suitable principle can be applied to spirit or scope of other variants without departing from the disclosure.The disclosure is not intended to be limited as a result,
Due to example described herein and design, but should be awarded and principle disclosed herein and novel features phase one
The widest scope of cause.
Claims (10)
1. a kind of construction method of general medical disease that calls for specialized treatment data system, which is characterized in that including：
Step 1：Acquire clinical medical data；
Step 2：Collected clinical medical data is subjected to data cleansing；
Step 3：Non-structured medical data is handled, process content includes participle technique and mould based on Chinese case history
Formula identification technology completes the structuring of electronic health record, by semantic parsing, character representation, the feature extraction of electronic health record, excavates
What Disease Clinical showed in case history lapses to situation；
Step 4：Unstructured data treated clinical medical data is integrated, the medical data of integrated structure forms full dimension
The medical disease that calls for specialized treatment data of degree, construct medical disease that calls for specialized treatment data system.
2. the construction method of general medical disease that calls for specialized treatment data system according to claim 1, which is characterized in that in step 1
The medical data of acquisition includes patient's essential information, Prescriptions for Out-patients, clinic electronic medical recorder, doctor's advice of being hospitalized, diagnosis of being hospitalized, disease of being hospitalized
It goes through, inpatient record, physical signs of patient information, patient's survey report data, patient's audit report data, operation record data exist
Interior clinical medical data, acquisition means include being obtained or by retrieving clinical document database by accessing in clinical data
The heart obtains the relevant clinical medical data of patient.
3. the construction method of general medical disease that calls for specialized treatment data system according to claim 2, which is characterized in that in step 2
Data cleansing be to carry out Main index of patients management, timestamp on the basis of patient's holographic diagnosis and treatment Information Data model of structure
Management checks data consistency, and the initial data material for completing disease that calls for specialized treatment data system prepares.
4. the construction method of general medical disease that calls for specialized treatment data system according to claim 3, which is characterized in that in step 2
Data cleansing include four aspect action, be respectively：(1) character is converted：Including it is unified full-shape English character with
Whole-angle figure character is converted to half-angle English and numerical character, and half-angle punctuation mark is converted to full-shape punctuation mark；(2) abnormal
Processing：The extra symbol including space, newline, bracket in removal case history text；(3) uniform format：Including
Unified formatting processing is carried out to the yin and yang attribute text in case history text；(4) common-use words are converted：Including to the common abbreviation of clinic
It is converted.
5. the construction method of general medical disease that calls for specialized treatment data system according to claim 4, which is characterized in that step 3 into
One step includes：
Prepare material：Prepare the unstructured disease that calls for specialized treatment case history material cleaned；
Word segmentation processing：Based on disease that calls for specialized treatment dictionary, Medical Dictionary, coordinates basic dictionary, form disease that calls for specialized treatment dictionary for word segmentation collection, pass through disease that calls for specialized treatment
Unstructured disease that calls for specialized treatment case history participle is completed in the cycle matching of dictionary for word segmentation collection；
Medicine part-of-speech tagging：Pass through the medicine part of speech of disease that calls for specialized treatment dictionary and basic medical dictionary, the word of mark case history structuring participle
Words and phrases, part of speech include symptom, diagnosis, drug, inspection project；
Medicine semantic tagger：By synonym, the restriction dictionary in disease that calls for specialized treatment dictionary, parsing medicine is semantic, after mark case history participle
Attribute part of speech, indicate the symptomatic condition of case history；
Disease that calls for specialized treatment index identifies：By the part of speech and semantic tagger of case history, inspection, inspection, symptom, the disease that calls for specialized treatment for the treatment of and document are completed
Index parses；
Data structured：Form the disease that calls for specialized treatment medical record data collection of structuring.
6. the construction method of general medical disease that calls for specialized treatment data system according to claim 5, which is characterized in that basic dictionary
Include mainly case history everyday words and its frequency of use information, there is attribute part of speech；Medical Dictionary includes mainly that clinical diagnosis encodes
Dictionary body part anatomy dictionary, Drug Dictionary, checks dictionary, examines dictionary, operation dictionary have medicine part of speech；Disease that calls for specialized treatment
Dictionary includes mainly the index of making the rounds of the wards of the symptom dictionary of disease, the treatment dictionary of disease, disease, has disease that calls for specialized treatment part of speech.
7. the construction method of general medical disease that calls for specialized treatment data system according to claim 6, which is characterized in that disease that calls for specialized treatment dictionary
It is to be formed by the self study of disease that calls for specialized treatment case history corpus, formation includes the combination that two aspects are handled,
The processing of one side includes：
After clinic information system acquisition, conversion, cleaning, the corpus of disease that calls for specialized treatment case history is generated, generates case history training corpus collection；
Modeling learning training is carried out based on the case history language material manually marked, by new case history language material, based on context, passes through packet
The machine learning model including hidden Markov model and conditional random field models is included, language material participle analysis is completed；
Statistical nature based on Concordance counts the frequency of tagged words, and wherein word frequency is gone out in entire language material according to word
Existing number determines that word frequency needs are normalized according to corpus size；
Coefficient of frequency based on each word is compared selection with certain threshold value, and disease that calls for specialized treatment dictionary is then selected into automatically higher than threshold value,
Automatically generate disease that calls for specialized treatment dictionary；
The medicine part-of-speech tagging that the disease that calls for specialized treatment dictionary of generation is carried out to disease that calls for specialized treatment word carries out the medicine word of disease that calls for specialized treatment word in conjunction with manual examination and verification
Property mark；
Calculate the position relationship of medicine word context in case history text, bluebeard compound embedded mobile GIS and open embedding data
Library medicine semanteme dictionary library carries out the medicine semantic tagger of disease that calls for specialized treatment word in conjunction with manual examination and verification；
The processing of another aspect includes：
Timing analysis diagnosis, inspection, inspection and drug dictionary library；
It obtains diagnosis, examine, the increment word of inspection and drug dictionary library；
Disease that calls for specialized treatment dictionary is ultimately formed in conjunction with the handling result of two aspects.
8. the construction method of general medical disease that calls for specialized treatment data system according to claim 7, which is characterized in that disease that calls for specialized treatment feature
The step of value index identifies further comprises：
Disease that calls for specialized treatment characteristic value index to be resolved is got from analysis of medical record result, and disease that calls for specialized treatment characteristic index is obtained after targets match
Then value carries out classification parsing, classification includes inspection, laboratory assay, symptom and sign, essential information, index and medical record document,
Again by the management of timestamp, the association sexual intercourse between index and the variation tendency based on time shaft are formed.
9. the construction method of general medical disease that calls for specialized treatment data system according to claim 8, which is characterized in that in step 4
Medical disease that calls for specialized treatment data system mainly by disease that calls for specialized treatment index storehouse, disease that calls for specialized treatment dictionary library, new word library, structured electronic patient record, disease that calls for specialized treatment search for
Engine, disease that calls for specialized treatment analysis platform composition.
10. the construction method of general medical disease that calls for specialized treatment data system according to any one of claim 1 to 9, feature
It is, method further includes the step 5 after step 4：
Carry out front end applications on the basis of medical disease that calls for specialized treatment data system, front end applications include mainly clinical aid decision support,
Disease that calls for specialized treatment analysis and research, case history retrieval, case history are described, the analysis mining for carrying out genius morbi, prognosis of disease, therapeutic process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810282025.3A CN108538395A (en) | 2018-04-02 | 2018-04-02 | A kind of construction method of general medical disease that calls for specialized treatment data system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810282025.3A CN108538395A (en) | 2018-04-02 | 2018-04-02 | A kind of construction method of general medical disease that calls for specialized treatment data system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108538395A true CN108538395A (en) | 2018-09-14 |
Family
ID=63482236
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810282025.3A Pending CN108538395A (en) | 2018-04-02 | 2018-04-02 | A kind of construction method of general medical disease that calls for specialized treatment data system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108538395A (en) |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109166608A (en) * | 2018-09-17 | 2019-01-08 | 新华三大数据技术有限公司 | Electronic health record information extracting method, device and equipment |
| CN109299472A (en) * | 2018-11-09 | 2019-02-01 | 天津开心生活科技有限公司 | Text data processing method, device, electronic equipment and computer-readable medium |
| CN109446191A (en) * | 2018-11-09 | 2019-03-08 | 医渡云（北京）技术有限公司 | Medical treatment data processing system and method, storage medium and electronic equipment |
| CN109493977A (en) * | 2018-11-09 | 2019-03-19 | 天津新开心生活科技有限公司 | Text data processing method, device, electronic equipment and computer-readable medium |
| CN109524121A (en) * | 2018-11-09 | 2019-03-26 | 贵州医渡云技术有限公司 | Medical records processing method and device |
| CN109710670A (en) * | 2018-12-11 | 2019-05-03 | 河南通域医疗科技有限公司 | A method of case history text is converted into structural metadata from natural language |
| CN109785927A (en) * | 2019-02-01 | 2019-05-21 | 上海众恒信息产业股份有限公司 | Clinical document structuring processing method based on internet integration medical platform |
| CN109961828A (en) * | 2019-03-06 | 2019-07-02 | 卫宁健康科技集团股份有限公司 | Multimodal medical image and data reporting management method and system |
| CN110033834A (en) * | 2019-03-01 | 2019-07-19 | 医利捷(上海)信息科技有限公司 | Clinical research big data service platform and method |
| CN110263168A (en) * | 2019-06-20 | 2019-09-20 | 北京百度网讯科技有限公司 | Symptom word classification method, device and terminal |
| CN110289058A (en) * | 2019-06-06 | 2019-09-27 | 北京市天元网络技术股份有限公司 | A kind of electronic health record standardization matching process and device |
| CN110444261A (en) * | 2019-07-11 | 2019-11-12 | 新华三大数据技术有限公司 | Sequence labelling network training method, electronic health record processing method and relevant apparatus |
| CN110459282A (en) * | 2019-07-11 | 2019-11-15 | 新华三大数据技术有限公司 | Sequence labelling model training method, electronic health record processing method and relevant apparatus |
| CN110517788A (en) * | 2019-08-30 | 2019-11-29 | 山东健康医疗大数据有限公司 | A kind of method of Chinese electronic health record information extraction |
| CN110853745A (en) * | 2019-09-23 | 2020-02-28 | 陈翔 | Skin disease patient standardization system |
| CN111063455A (en) * | 2019-11-28 | 2020-04-24 | 北京紫冬认知科技有限公司 | Human-computer interaction method and device for telemedicine |
| CN111161881A (en) * | 2019-06-13 | 2020-05-15 | 南京医基云医疗数据研究院有限公司 | Method and device for identifying disease co-occurrence relationship and storage medium |
| CN111180026A (en) * | 2019-12-23 | 2020-05-19 | 卫宁健康科技集团股份有限公司 | Special diagnosis and treatment view system and method |
| CN111696666A (en) * | 2020-06-10 | 2020-09-22 | 杭州联众医疗科技股份有限公司 | Intelligent chronic disease management system based on time coding |
| CN111985246A (en) * | 2020-08-27 | 2020-11-24 | 武汉东湖大数据交易中心股份有限公司 | Disease cognitive system based on main symptoms and accompanying symptom words |
| CN112289398A (en) * | 2020-08-17 | 2021-01-29 | 上海柯林布瑞信息技术有限公司 | Pathological report analysis method and device, storage medium and terminal |
| CN112365939A (en) * | 2020-10-14 | 2021-02-12 | 山东大学 | Data management method and system based on medical health big data |
| CN112712118A (en) * | 2020-12-29 | 2021-04-27 | 银江股份有限公司 | Medical text data oriented filtering method and system |
| CN112749545A (en) * | 2020-12-30 | 2021-05-04 | 杭州依图医疗技术有限公司 | Medical data processing method and device and storage medium |
| CN113111048A (en) * | 2021-03-31 | 2021-07-13 | 宁波金唐软件有限公司 | Clinical scientific research special disease database construction method based on big data technology |
| CN113129180A (en) * | 2021-05-13 | 2021-07-16 | 贵阳业勤中小企业促进中心有限公司 | Method for building intellectual property data analysis system |
| CN113284628A (en) * | 2021-06-02 | 2021-08-20 | 山东健康医疗大数据有限公司 | Method for realizing standardization of dictionary data for medical institution inspection |
| CN113674867A (en) * | 2021-07-27 | 2021-11-19 | 上海药慧信息技术有限公司 | Clinical data mining method and device, electronic equipment and storage medium |
| CN113688632A (en) * | 2021-08-17 | 2021-11-23 | 中国人民解放军海军军医大学 | Method and system for extracting structured data of disease prognosis covariates |
| CN113871025A (en) * | 2021-09-08 | 2021-12-31 | 四川大学华西医院 | Dermatological clinical special disease database construction method and system |
| CN114067976A (en) * | 2021-11-23 | 2022-02-18 | 南京理工大学 | Information cascade processing method and system suitable for medical treatment extrusion |
| CN114610748A (en) * | 2022-03-16 | 2022-06-10 | 云南升玥信息技术有限公司 | Safe, rapid, accurate and effective medical disease data management system based on artificial intelligence and application |
| CN116166698A (en) * | 2023-01-12 | 2023-05-26 | 之江实验室 | Method and system for quickly constructing queues based on general medical terms |
| CN116226362A (en) * | 2023-05-06 | 2023-06-06 | 湖南德雅曼达科技有限公司 | Word segmentation method for improving accuracy of searching hospital names |
| CN116453640A (en) * | 2023-06-15 | 2023-07-18 | 北京四海汇智科技有限公司 | Method and device for constructing clinical special disease library based on multi-label screening and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030105638A1 (en) * | 2001-11-27 | 2003-06-05 | Taira Rick K. | Method and system for creating computer-understandable structured medical data from natural language reports |
| CN103020453A (en) * | 2012-12-15 | 2013-04-03 | 中国科学院深圳先进技术研究院 | Generation method of structured electronic medical record based on ontology technology |
| US20140006013A1 (en) * | 2012-05-24 | 2014-01-02 | International Business Machines Corporation | Text mining for large medical text datasets and corresponding medical text classification using informative feature selection |
| CN104766259A (en) * | 2015-03-31 | 2015-07-08 | 华据医疗评估信息技术（北京）有限公司 | Medical clinical quality monitoring and evaluation system based on single-disease model |
| CN106383853A (en) * | 2016-08-30 | 2017-02-08 | 刘勇 | Realization method and system for electronic medical record post-structuring and auxiliary diagnosis |
-
2018
- 2018-04-02 CN CN201810282025.3A patent/CN108538395A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030105638A1 (en) * | 2001-11-27 | 2003-06-05 | Taira Rick K. | Method and system for creating computer-understandable structured medical data from natural language reports |
| US20140006013A1 (en) * | 2012-05-24 | 2014-01-02 | International Business Machines Corporation | Text mining for large medical text datasets and corresponding medical text classification using informative feature selection |
| CN103020453A (en) * | 2012-12-15 | 2013-04-03 | 中国科学院深圳先进技术研究院 | Generation method of structured electronic medical record based on ontology technology |
| CN104766259A (en) * | 2015-03-31 | 2015-07-08 | 华据医疗评估信息技术（北京）有限公司 | Medical clinical quality monitoring and evaluation system based on single-disease model |
| CN106383853A (en) * | 2016-08-30 | 2017-02-08 | 刘勇 | Realization method and system for electronic medical record post-structuring and auxiliary diagnosis |
Non-Patent Citations (2)
| Title |
|---|
| 王淑 等: "基于临床数据中心的专病研究系统建设与实践", 《中国医院》 * |
| 翟菊叶 等: "基于CＲF 与规则相结合的中文电子病历命名实体识别研究", 《包头医学院学报》 * |
Cited By (43)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109166608A (en) * | 2018-09-17 | 2019-01-08 | 新华三大数据技术有限公司 | Electronic health record information extracting method, device and equipment |
| CN109524121B (en) * | 2018-11-09 | 2020-11-10 | 贵州医渡云技术有限公司 | Medical file processing method and device |
| CN109446191A (en) * | 2018-11-09 | 2019-03-08 | 医渡云（北京）技术有限公司 | Medical treatment data processing system and method, storage medium and electronic equipment |
| CN109493977A (en) * | 2018-11-09 | 2019-03-19 | 天津新开心生活科技有限公司 | Text data processing method, device, electronic equipment and computer-readable medium |
| CN109524121A (en) * | 2018-11-09 | 2019-03-26 | 贵州医渡云技术有限公司 | Medical records processing method and device |
| CN109299472A (en) * | 2018-11-09 | 2019-02-01 | 天津开心生活科技有限公司 | Text data processing method, device, electronic equipment and computer-readable medium |
| CN109493977B (en) * | 2018-11-09 | 2020-07-31 | 天津新开心生活科技有限公司 | Text data processing method and device, electronic equipment and computer readable medium |
| CN109710670A (en) * | 2018-12-11 | 2019-05-03 | 河南通域医疗科技有限公司 | A method of case history text is converted into structural metadata from natural language |
| CN109710670B (en) * | 2018-12-11 | 2020-04-28 | 萱闱(河南)生命科学研究院有限公司 | Method for converting medical record text from natural language into structured metadata |
| CN109785927A (en) * | 2019-02-01 | 2019-05-21 | 上海众恒信息产业股份有限公司 | Clinical document structuring processing method based on internet integration medical platform |
| CN110033834A (en) * | 2019-03-01 | 2019-07-19 | 医利捷(上海)信息科技有限公司 | Clinical research big data service platform and method |
| CN110033834B (en) * | 2019-03-01 | 2023-12-01 | 医利捷(上海)信息科技有限公司 | Clinical scientific research big data service platform and method |
| CN109961828A (en) * | 2019-03-06 | 2019-07-02 | 卫宁健康科技集团股份有限公司 | Multimodal medical image and data reporting management method and system |
| CN110289058A (en) * | 2019-06-06 | 2019-09-27 | 北京市天元网络技术股份有限公司 | A kind of electronic health record standardization matching process and device |
| CN111161881A (en) * | 2019-06-13 | 2020-05-15 | 南京医基云医疗数据研究院有限公司 | Method and device for identifying disease co-occurrence relationship and storage medium |
| CN110263168A (en) * | 2019-06-20 | 2019-09-20 | 北京百度网讯科技有限公司 | Symptom word classification method, device and terminal |
| CN110459282A (en) * | 2019-07-11 | 2019-11-15 | 新华三大数据技术有限公司 | Sequence labelling model training method, electronic health record processing method and relevant apparatus |
| CN110444261A (en) * | 2019-07-11 | 2019-11-12 | 新华三大数据技术有限公司 | Sequence labelling network training method, electronic health record processing method and relevant apparatus |
| CN110517788A (en) * | 2019-08-30 | 2019-11-29 | 山东健康医疗大数据有限公司 | A kind of method of Chinese electronic health record information extraction |
| CN110853745A (en) * | 2019-09-23 | 2020-02-28 | 陈翔 | Skin disease patient standardization system |
| CN111063455A (en) * | 2019-11-28 | 2020-04-24 | 北京紫冬认知科技有限公司 | Human-computer interaction method and device for telemedicine |
| CN111180026A (en) * | 2019-12-23 | 2020-05-19 | 卫宁健康科技集团股份有限公司 | Special diagnosis and treatment view system and method |
| CN111696666A (en) * | 2020-06-10 | 2020-09-22 | 杭州联众医疗科技股份有限公司 | Intelligent chronic disease management system based on time coding |
| CN112289398A (en) * | 2020-08-17 | 2021-01-29 | 上海柯林布瑞信息技术有限公司 | Pathological report analysis method and device, storage medium and terminal |
| CN111985246B (en) * | 2020-08-27 | 2023-08-15 | 武汉东湖大数据交易中心股份有限公司 | Disease cognitive system based on main symptoms and accompanying symptom words |
| CN111985246A (en) * | 2020-08-27 | 2020-11-24 | 武汉东湖大数据交易中心股份有限公司 | Disease cognitive system based on main symptoms and accompanying symptom words |
| CN112365939A (en) * | 2020-10-14 | 2021-02-12 | 山东大学 | Data management method and system based on medical health big data |
| CN112712118A (en) * | 2020-12-29 | 2021-04-27 | 银江股份有限公司 | Medical text data oriented filtering method and system |
| CN112749545A (en) * | 2020-12-30 | 2021-05-04 | 杭州依图医疗技术有限公司 | Medical data processing method and device and storage medium |
| CN113111048A (en) * | 2021-03-31 | 2021-07-13 | 宁波金唐软件有限公司 | Clinical scientific research special disease database construction method based on big data technology |
| CN113129180A (en) * | 2021-05-13 | 2021-07-16 | 贵阳业勤中小企业促进中心有限公司 | Method for building intellectual property data analysis system |
| CN113284628A (en) * | 2021-06-02 | 2021-08-20 | 山东健康医疗大数据有限公司 | Method for realizing standardization of dictionary data for medical institution inspection |
| CN113674867A (en) * | 2021-07-27 | 2021-11-19 | 上海药慧信息技术有限公司 | Clinical data mining method and device, electronic equipment and storage medium |
| CN113688632A (en) * | 2021-08-17 | 2021-11-23 | 中国人民解放军海军军医大学 | Method and system for extracting structured data of disease prognosis covariates |
| CN113871025A (en) * | 2021-09-08 | 2021-12-31 | 四川大学华西医院 | Dermatological clinical special disease database construction method and system |
| CN114067976A (en) * | 2021-11-23 | 2022-02-18 | 南京理工大学 | Information cascade processing method and system suitable for medical treatment extrusion |
| CN114610748B (en) * | 2022-03-16 | 2022-09-09 | 云南升玥信息技术有限公司 | Medical disease data safe, rapid, accurate and effective management system based on artificial intelligence and application |
| CN114610748A (en) * | 2022-03-16 | 2022-06-10 | 云南升玥信息技术有限公司 | Safe, rapid, accurate and effective medical disease data management system based on artificial intelligence and application |
| CN116166698A (en) * | 2023-01-12 | 2023-05-26 | 之江实验室 | Method and system for quickly constructing queues based on general medical terms |
| CN116166698B (en) * | 2023-01-12 | 2023-09-01 | 之江实验室 | Method and system for quickly constructing queues based on general medical terms |
| CN116226362A (en) * | 2023-05-06 | 2023-06-06 | 湖南德雅曼达科技有限公司 | Word segmentation method for improving accuracy of searching hospital names |
| CN116453640A (en) * | 2023-06-15 | 2023-07-18 | 北京四海汇智科技有限公司 | Method and device for constructing clinical special disease library based on multi-label screening and electronic equipment |
| CN116453640B (en) * | 2023-06-15 | 2023-09-22 | 北京四海汇智科技有限公司 | Method and device for constructing clinical special disease library based on multi-label screening and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108538395A (en) | A kind of construction method of general medical disease that calls for specialized treatment data system | |
| Pezoulas et al. | Medical data quality assessment: On the development of an automated framework for medical data curation | |
| CN109299239B (en) | ES-based electronic medical record retrieval method | |
| CN113871003B (en) | Disease auxiliary differential diagnosis system based on causal medical knowledge graph | |
| CN104516942B (en) | The automatic merogenesis mark of Concept-driven test | |
| Doing-Harris et al. | Computer-assisted update of a consumer health vocabulary through mining of social network data | |
| Dalianis et al. | HEALTH BANK-A Workbench for Data Science Applications in Healthcare. | |
| Meystre et al. | Automation of a problem list using natural language processing | |
| CN110277149A (en) | Processing method, device and the equipment of electronic health record | |
| US20080228769A1 (en) | Medical Entity Extraction From Patient Data | |
| CN112597774B (en) | Chinese medical named entity recognition method, system, storage medium and equipment | |
| Masarie Jr et al. | An interlingua for electronic interchange of medical information: using frames to map between clinical vocabularies | |
| US20140181128A1 (en) | Systems and Methods for Processing Patient Data History | |
| CN110069779B (en) | Symptom entity identification method of medical text and related device | |
| WO2003040965A2 (en) | Patient data mining | |
| US20210183526A1 (en) | Unsupervised taxonomy extraction from medical clinical trials | |
| CN113688255A (en) | Knowledge graph construction method based on Chinese electronic medical record | |
| Travers et al. | Using nurses’ natural language entries to build a concept-oriented terminology for patients’ chief complaints in the emergency department | |
| Becker et al. | Extraction of UMLS® concepts using Apache cTAKES™ for German language | |
| Friedman | Semantic text parsing for patient records | |
| Dalianis | Clinical text retrieval-an overview of basic building blocks and applications | |
| CN116383413B (en) | Knowledge graph updating method and system based on medical data extraction | |
| Yaiprasert et al. | Artificial intelligence for target symptoms of Thai herbal medicine by web scraping | |
| Batool et al. | Automatic extraction and mapping of discharge summary’s concepts into SNOMED CT | |
| Lamy et al. | Formalization of the semantics of iconic languages: An ontology-based method and four semantic-powered applications |
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 |
Application publication date: 20180914 |
|
| RJ01 | Rejection of invention patent application after publication |