CN109599185A - Disease data processing method, device, electronic equipment and computer-readable medium - Google Patents
Disease data processing method, device, electronic equipment and computer-readable medium Download PDFInfo
- Publication number
- CN109599185A CN109599185A CN201811351658.1A CN201811351658A CN109599185A CN 109599185 A CN109599185 A CN 109599185A CN 201811351658 A CN201811351658 A CN 201811351658A CN 109599185 A CN109599185 A CN 109599185A
- Authority
- CN
- China
- Prior art keywords
- data
- disease
- diagnostic
- symptom
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- Theoretical Computer Science (AREA)
- Primary Health Care (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
This disclosure relates to a kind of disease data processing method, device, electronic equipment and computer-readable medium.It is related to medical big data processing field, includes at least one disease symptoms label in the disease data this method comprises: obtaining disease data；The disease data is subjected to word segmentation processing, generates lexical set；Symptom set is constructed by lexical set, the symptom set includes at least one disease symptoms label；And input the symptom set to obtain classification of diseases mark in diagnostic model, the diagnostic model is artificial nerve network model.This disclosure relates to disease data processing method, device, electronic equipment and computer-readable medium, can be improved disease forecasting accuracy rate, make preferably aid decision for the diagnosis of clinician.
Description
Technical field
This disclosure relates to computer information processing field, in particular to a kind of disease data processing method, device,
Electronic equipment and computer-readable medium.
Background technique
There are a large amount of disease datas in hospital clinical data, frequently include patient's disease under normal circumstances, in disease data
Sick diagnostic result and patient show symptom.Disease data can disclose the disease and disease symptoms label of patient in all its bearings
Between relationship.How using disease data progress data mining, to provide aid decision for the medical diagnosis on disease of clinician
It supports, is current popular subject under discussion.
Currently, the data digging method of common disease data is Nae Bayesianmethod: by counting extensive sample
The frequency of medical diagnosis on disease and single symptom frequency, calculate the conditional probability of diagnosis and the conditional probability of single symptom in data,
Obtain model parameter.Symptom combination is input in model, can be predicted under conditions of there is the symptom combination, medical diagnosis on disease
Distribution helps clinician to make aid decision to medical diagnosis on disease.But this medical diagnosis on disease is carried out by naive Bayesian
Method, the accuracy rate usually judged are lower.
Therefore, it is necessary to a kind of new disease data processing method, device, electronic equipment and computer-readable mediums.
Above- mentioned information are only used for reinforcing the understanding to the background of the disclosure, therefore it disclosed in the background technology part
It may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
In view of this, the disclosure provides a kind of disease data processing method, device, electronic equipment and computer-readable Jie
Matter can be improved disease forecasting accuracy rate, make preferably aid decision for the diagnosis of clinician.
Other characteristics and advantages of the disclosure will be apparent from by the following detailed description, or partially by the disclosure
Practice and acquistion.
According to the one side of the disclosure, a kind of disease data processing method is proposed, this method comprises: disease data is obtained,
It include at least one disease symptoms label in the disease data；The disease data is subjected to word segmentation processing, generates word finder
It closes；Symptom set is constructed by lexical set, the symptom set includes at least one disease symptoms label；And by the disease
To obtain classification of diseases mark in shape set input diagnostic model, the diagnostic model is artificial nerve network model.
In a kind of exemplary embodiment of the disclosure, further includes: pass through history disease data and artificial neural network mould
Type constructs the diagnostic model.
In a kind of exemplary embodiment of the disclosure, institute is constructed by history disease data and artificial nerve network model
Stating diagnostic model includes: to construct the first data pair and the second data pair by history disease data, and first data are to including
At least one disease symptoms label and diagnostic result, second data are tied to including single disease symptoms label and single diagnosis
Fruit；Vector is embedded in word is generated by second data；And by first data, second data to, institute's predicate
It is embedded in vector input artificial nerve network model, obtains diagnostic model by training.
In a kind of exemplary embodiment of the disclosure, the first data pair and the second data are constructed by history disease data
To include: by history disease data by word segmentation processing generate the first data pair；And by first data to decompose with life
At at least one the second data pair.
It include: logical to generating word to be embedded in vector by second data in a kind of exemplary embodiment of the disclosure
Second data are crossed to building diagnostic network, wherein point of the object of data centering as the diagnostic network, between object
Side of the relationship as the diagnostic network；And word is generated by internet startup disk technology and the diagnostic network and is embedded in vector.
It is in a kind of exemplary embodiment of the disclosure, first data are embedding to, institute's predicate to, second data
Incoming vector inputs in artificial nerve network model, and obtaining diagnostic model by training includes: by first data to as people
The training data of artificial neural networks model；By second data to the tally set as artificial nerve network model；It will be described
Word is embedded in parameter of the vector as artificial neural network embeding layer；And artificial nerve network model is trained by setting
To obtain the diagnostic model.
In a kind of exemplary embodiment of the disclosure, the artificial nerve network model is included at least: symptom embeding layer,
Maximum pond layer and affine transformation layer.
According to the one side of the disclosure, a kind of disease data processing unit is proposed, which includes: data module, is used for
Disease data is obtained, includes at least one disease symptoms label in the disease data；Word segmentation module is used for the disease number
According to word segmentation processing is carried out, lexical set is generated；Data are to module, for constructing symptom set, the symptom by lexical set
Set includes at least one disease symptoms label；And object module, for by the symptom set input diagnostic model in
Classification of diseases mark is obtained, the diagnostic model is artificial nerve network model.
According to the one side of the disclosure, a kind of electronic equipment is proposed, which includes: one or more processors；
Storage device, for storing one or more programs；When one or more programs are executed by one or more processors, so that one
A or multiple processors realize such as methodology above.
According to the one side of the disclosure, it proposes a kind of computer-readable medium, is stored thereon with computer program, the program
Method as mentioned in the above is realized when being executed by processor.
According to disease data processing method, device, electronic equipment and the computer-readable medium of the disclosure, artificial neural network
The conditional probability that network can directly be fitted medical diagnosis on disease under the conditions of symptom combination is differentiated；By the first data to input model
In, by carrying out maximum pondization operation to symptom combination, diagnostic model can effectively learn to symptom combination and medical diagnosis on disease it
Between association rely on, lose unreasonable conditional independence assumption；Then pass through the symptom embeding layer in disease model, Ke Yiyou
Effect captures the semantic information of symptom, to improve disease forecasting accuracy rate, makes and preferably assisting for the diagnosis of clinician
Decision.
It should be understood that the above general description and the following detailed description are merely exemplary, this can not be limited
It is open.
Detailed description of the invention
Its example embodiment is described in detail by referring to accompanying drawing, above and other target, feature and the advantage of the disclosure will
It becomes more fully apparent.Drawings discussed below is only some embodiments of the present disclosure, for the ordinary skill of this field
For personnel, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of system block diagram of disease data processing method and processing device shown according to an exemplary embodiment.
Fig. 2 is a kind of flow chart of disease data processing method shown according to an exemplary embodiment.
Fig. 3 is a kind of flow chart of the disease data processing method shown according to another exemplary embodiment.
Fig. 4 is that artificial neural network shows in a kind of disease data processing method shown according to another exemplary embodiment
It is intended to.
Fig. 5 is a kind of block diagram of disease data processing unit shown according to an exemplary embodiment.
Fig. 6 is the block diagram of a kind of electronic equipment shown according to an exemplary embodiment.
Fig. 7 is that a kind of computer readable storage medium schematic diagram is shown according to an exemplary embodiment.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be real in a variety of forms
It applies, and is not understood as limited to embodiment set forth herein；On the contrary, thesing embodiments are provided so that the disclosure will be comprehensively and complete
It is whole, and the design of example embodiment is comprehensively communicated to those skilled in the art.Identical appended drawing reference indicates in figure
Same or similar part, thus repetition thereof will be omitted.
In addition, described feature, structure or characteristic can be incorporated in one or more implementations in any suitable manner
In example.In the following description, many details are provided to provide and fully understand to embodiment of the disclosure.However,
It will be appreciated by persons skilled in the art that can with technical solution of the disclosure without one or more in specific detail,
Or it can be using other methods, constituent element, device, step etc..In other cases, it is not shown in detail or describes known side
Method, device, realization or operation are to avoid fuzzy all aspects of this disclosure.
Block diagram shown in the drawings is only functional entity, not necessarily must be corresponding with physically separate entity.
I.e., it is possible to realize these functional entitys using software form, or realized in one or more hardware modules or integrated circuit
These functional entitys, or these functional entitys are realized in heterogeneous networks and/or processor device and/or microcontroller device.
Flow chart shown in the drawings is merely illustrative, it is not necessary to including all content and operation/step,
It is not required to execute by described sequence.For example, some operation/steps can also decompose, and some operation/steps can close
And or part merge, therefore the sequence actually executed is possible to change according to the actual situation.
It should be understood that although herein various assemblies may be described using term first, second, third, etc., these groups
Part should not be limited by these terms.These terms are to distinguish a component and another component.Therefore, first group be discussed herein below
Part can be described as the second component without departing from the teaching of disclosure concept.As used herein, term " and/or " include associated
All combinations for listing any of project and one or more.
It will be understood by those skilled in the art that attached drawing is the schematic diagram of example embodiment, module or process in attached drawing
Necessary to not necessarily implementing the disclosure, therefore it cannot be used for the protection scope of the limitation disclosure.
The inventors of the present application found that naive Bayesian is a kind of statistical learning method of classics.Its Computing Principle are as follows:
P(Y|x1x2…)∝P(x1x2... | Y) * P (Y)=P (x1|Y)*P(x2|Y)*…*P(Y)
Wherein Y indicates medical diagnosis on disease, x1x2... indicate symptom combination.
Nae Bayesianmethod asks the posterior probability diagnosed under the conditions of known symptom combination solution according to Bayes principle
Topic, the prior probability for being converted to diagnosis solves and the combination condition probability of symptom combination solves.And Nae Bayesianmethod into
One step assumes existence condition independence between symptom, and it is general that the combination condition probability of symptom combination is decomposed into single symptom-conditional again
The product of rate.
By counting the frequency and single symptom frequency of medical diagnosis on disease in extensive sample data, the condition of diagnosis is calculated
The conditional probability of probability and single symptom obtains model parameter.Symptom combination is input in model, can predict the disease occur
Under conditions of shape combination, the distribution of medical diagnosis on disease.
But the medical diagnosis on disease based on naive Bayesian has following defects that
Naive Bayesian belongs to the generation model in Machine Learning Problems, calculates medical diagnosis on disease under the conditions of symptom combination indirectly
Conditional probability, model accuracy rate is usually less than discrimination model in practice；
Nae Bayesianmethod is in the combination condition probability calculation to symptom combination, it is assumed that conditional sampling between symptom.
However this conditional independence assumption is invalid, has very strong association dependence between opposite disease symptoms label；
Nae Bayesianmethod cannot learn the semantic information to disease symptoms label.
Based on the above reasons, present inventor proposes disease data processing method, utilizes magnanimity in clinical data
<symptom combination, medical diagnosis on disease>data pair modeled using artificial neural network.The model can be according to the symptom of patient
Combined prediction medical diagnosis on disease distribution, provides aid decision for clinician.
Compared to Nae Bayesianmethod, artificial neural network can directly be fitted medical diagnosis on disease under the conditions of symptom combination
Conditional probability belongs to discrimination model；Maximum pondization operation is carried out to symptom combination in model, learns model effectively to disease
Shape combination is associated with dependence between medical diagnosis on disease, loses unreasonable conditional independence assumption；Symptom insertion is added in model
Layer, can effectively capture the semantic information of symptom, greatly improve the predictive ability of model.
Below it is the detailed content of the application:
Fig. 1 is a kind of system block diagram of disease data processing method and processing device shown according to an exemplary embodiment.
As shown in Figure 1, system architecture 100 may include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 to provide the medium of communication link.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 101,102,103 and be interacted by network 104 with server 105, to receive or send out
Send message etc..Various telecommunication customer end applications can be installed, such as disease data analysis is answered on terminal device 101,102,103
With, web browser applications, searching class application, instant messaging tools etc..
Terminal device 101,102,103 can be the various electronic equipments with display screen and supported web page browsing, packet
Include but be not limited to smart phone, tablet computer, pocket computer on knee and desktop computer etc..
Server 105 can be to provide the server of various services, such as utilize terminal device 101,102,103 to user
The diseases analysis class website browsed provides the back-stage management server supported.Back-stage management server can be to the disease received
The data such as disease symptoms label analysis request are analyzed and processed, and by processing result (such as disease probability, medical diagnosis on disease analyze)
Feed back to terminal device.
Server 105 can for example obtain disease data, include at least one disease symptoms label in the disease data；Clothes
Being engaged in device 105 can be for example by disease data progress word segmentation processing, generation lexical set；Server 105 can for example pass through vocabulary
Set building symptom set, the symptom set includes at least one disease symptoms label；Server 105 can be for example by the disease
To obtain classification of diseases mark in shape set input diagnostic model, the diagnostic model is artificial nerve network model.
Server 105 can be the server of an entity, also may be, for example, multiple server compositions, needs to illustrate
It is that disease data processing method provided by the embodiment of the present disclosure can be executed by server 105, correspondingly, at disease data
Reason device can be set in server 105.And the page end for being supplied to user's progress data query is normally at terminal device
101, in 102,103.
Fig. 2 is a kind of flow chart of disease data processing method shown according to an exemplary embodiment.At disease data
Reason method 20 includes at least step S202 to S208.
It include at least one disease symptoms mark in the disease data as shown in Fig. 2, obtaining disease data in S202
Label.It can include the symptom of patient's private prosecution, disease data in disease data for example, obtain disease data by the input of doctor
It can also be for example including the symptom made a definite diagnosis after being checked by doctor.
In S204, the disease data is subjected to word segmentation processing, generates lexical set.It can be for example by doctor to be processed
It diagnoses word and carries out word segmentation processing, after " right side distal ureteral calculi is with obstruction " word segmentation processing, the lexical set of generation can example
Such as are as follows: " calculus, right side, ureter, lower section, obstruction ".
Chinese word segmentation (Chinese Word Segmentation) refers to for a chinese character sequence being cut into one by one
Individual word.Participle is exactly the process that continuous word sequence is reassembled into word sequence according to certain specification.Existing point
Word algorithm can be divided into three categories: the segmenting method based on string matching, the segmenting method based on understanding and point based on statistics
Word method.It is combined according to whether with part-of-speech tagging process, and simple segmenting method can be divided into and segmented and combined with mark
Integral method.
Character match, which is called, does mechanical segmentation method, it is the Chinese character string being analysed to according to certain strategy and one
Entry in " sufficiently big " machine dictionary is matched, if finding some character string in dictionary, successful match (identifies one
A word).According to the difference of scanning direction, String matching segmenting method can be divided into positive matching and reverse matching；According to different length
The case where spending priority match can be divided into maximum (longest) matching and minimum (most short) matching.
Understanding method, this segmenting method are to achieve the effect that identify word by allowing the understanding of computer mould personification distich.
Its basic thought is exactly to carry out syntax, semantic analysis while participle, handles ambiguity using syntactic information and semantic information
Phenomenon.It generally includes three parts: participle subsystem, syntactic-semantic subsystem, master control part.Coordination in master control part
Under, participle subsystem can obtain the syntax and semantic information in relation to word, sentence etc. to judge segmentation ambiguity, i.e. its mould
People is intended to the understanding process of sentence.This segmenting method is needed using a large amount of linguistry and information.Due to Chinese language
General, the complexity of knowledge, it is difficult to various language messages are organized into the form that machine can be directly read, therefore currently based on reason
The Words partition system of solution is also in experimental stage.
Statistic law formally sees that word is stable combinatorics on words, therefore within a context, adjacent word occurs simultaneously
Number it is more, be more possible to constitute a word.Therefore the frequency of word co-occurrence adjacent with word or probability can preferably reflect
At the confidence level of word.The frequency of each combinatorics on words of co-occurrence adjacent in corpus can be counted, calculate appearing alternatively for they
Information.The statistics Words partition system of practical application will use a basic dictionary for word segmentation (everyday words dictionary) to carry out String matching point
Word, while identifying some new words using statistical method, i.e., statistical string frequency and String matching are combined, has both played matching participle
Fast, the high-efficient feature of cutting speed, but be utilized no dictionary cutting word combination context identification new word, automatic disambiguation it is excellent
Point.
In one embodiment, word segmentation processing for example can be carried out to the disease data by string matching method, generated
Multiple participle vocabulary；And the lexical set is generated by the multiple participle vocabulary.Segmenting method in the application may be used also
Such as using the statistic method presented hereinabove or understand that participle method carries out, it can also for example pass through string matching method, reason
It solves one or more of participle method and statistical morphology and combines progress, the application is not limited.Wherein, the character string
With the standard words that the machine dictionary in method includes: in ICH International Medical dictionary；And medical speciality vocabulary.
Wherein, " ICH International Medical with dictionary (MedDRA) ", is to sponsor lower creation in ICH, is for government's pharmaceutical administration
The standard terminology collection in clinical research each stage of department and biological-pharmacy management new drug listing front and back.The terminology is supported each
Coding, retrieval and the analysis of kind clinical data, such as adverse events, medicine and social history, indication and clinical examination.It is described herein as
The background informations such as the Establish reason of MedDRA and course, the hierarchical structure of MedDRA term, MedDRA rule and habit,
The administrative requirement that application and ICH participating nation/district government of the MedDRA in data encoding and analysis use MedDRA.
In Clinical Report also referred to as " drug legislation medical terminology dictionary ".
In S206, symptom set is constructed by lexical set, the symptom set includes at least one disease symptoms mark
Label.Extract the data in lexical set, form the first data pair, the first data to may be, for example,<symptom combination, medical diagnosis on disease>
Form, wherein in symptom combination include at least one disease symptoms label.
First data to may be, for example,<(abdominal pain, vomiting, anuria), (calculus)>, wherein symptom combination are as follows: abdominal pain, vomiting,
Anuria, medical diagnosis on disease are as follows: calculus.
In S208, the symptom set is inputted in diagnostic model to obtain classification of diseases mark, the diagnostic model
For artificial nerve network model.Diagnostic model is by the model of Artificial Neural Network training, and specific training method will be
Hereinafter it is described.Can be for example, by disease symptoms label: abdominal pain, vomiting, anuria input in diagnostic model, and diagnostic model is given
Auxiliary diagnosis result out.
Wherein, artificial neural network (Artificial Neural Network, ANN) refers to by a large amount of processing unit
(neuron) interconnects and the complex network structures of formation, is, letter abstract to certain of human brain tissue structure and operating mechanism
Change and simulates.
Artificial neural network is divided into multilayer and single layer, and each layer includes several neurons, can with band between each neuron
The directed arc of variable weight connects, and network changes neuron company by the repetition learning training to Given information, by gradually adjusting
The method for connecing weight achievees the purpose that handle relationship between information, simulation input output.It is required no knowledge about between input and output
Definite relationship, be not required to quantity of parameters, it is only necessary to know the non-constant factor for causing output to change, i.e. non-constant parameter.Cause
This is compared with traditional data processing method, and nerual network technique is in processing fuzzy data, random data, nonlinear data side
Mask has a clear superiority, big to scale, structure is complicated, the indefinite system of information is especially suitable.
The medical diagnosis on disease scene being directed in the embodiment of the present application, artificial neural network can directly be fitted symptom combination item
The conditional probability of medical diagnosis on disease is differentiated under part；It is maximum by being carried out to symptom combination by the first data in input model
Pondization operation, diagnostic model can effectively learn to be associated with dependence between symptom combination and medical diagnosis on disease, lose unreasonable
Conditional independence assumption；Then by the symptom embeding layer in disease model, the semantic information of symptom can be effectively captured, greatly
The predictive ability of width raising model.
According to the disease data processing method of the disclosure, disease forecasting accuracy rate can be improved, be the diagnosis of clinician
Make preferably aid decision.
It will be clearly understood that the present disclosure describes how to form and use particular example, but the principle of the disclosure is not limited to
These exemplary any details.On the contrary, the introduction based on disclosure disclosure, these principles can be applied to many other
Embodiment.
In a kind of exemplary embodiment of the disclosure, further includes: pass through history disease data and artificial neural network mould
Type constructs the diagnostic model.
Fig. 3 is a kind of flow chart of the disease data processing method shown according to another exemplary embodiment.
As shown in figure 3, in S302, the first data pair and the second data pair are constructed by history disease data, described the
One data are to including at least one disease symptoms label and diagnostic result, and second data are to including single disease symptoms label
With single diagnostic result.For example, history disease data is generated the first data pair by word segmentation processing；And described first is counted
According to decompose to generate at least one second data pair.
As described above, patient disease's diagnostic result is frequently included in disease data and patient shows symptom.Disease data
The relationship between the disease of patient and disease symptoms label can be disclosed in all its bearings.It can be for example by being obtained in electronic health record
Disease data is taken, it can also be for example by obtaining diagnostic data in diagnosis report.
Wherein, electronic health record data are directly acquired from clinic diagnosis behavior, and collection process with clinic diagnosis process
Fusion, does not constitute added burden to medical staff.Pathogeneticing characteristic, the diagnosis and treatment method spy of a large amount of diseases are analyzed using these data
Sign, will can greatly promote the working efficiency of associated medical person, more efficient, inexpensive promotion disease prevention, therapeutic efficiency
Progress.
In one embodiment, by present in hospital's historical clinical data<symptom combination, medical diagnosis on disease>data are to logical
The mode for crossing word segmentation processing extracts, and constructs the first data pair, form of multiple first data to composable data set A.It mentions
Take the data in lexical set, form the first data pair, the first data to may be, for example,<symptom combination, medical diagnosis on disease>shape
Formula wherein includes at least one disease symptoms label in symptom combination.
First data to may be, for example,<(abdominal pain, vomiting, anuria), (calculus)>, wherein symptom combination are as follows: abdominal pain, vomiting,
Anuria, medical diagnosis on disease are as follows: calculus.
Wherein each first data is to being further decomposed into multiple<monosymptom, medical diagnosis on disease>data pair, construction the
Two data pair, form of multiple second data to composable data set B.
The second data corresponding to the first data pair are to being three:<abdominal pain, calculus>；<vomiting, calculus>；< anuria, calculus
>。
In S304, vector is embedded in word is generated by second data.It include: by second data to building
Diagnostic network, wherein point of the object of data centering as the diagnostic network, the relationship between object is as the diagnosis net
The side of network；And word is generated by internet startup disk technology and the diagnostic network and is embedded in vector.
In one embodiment, using data set B, monosymptom and medical diagnosis on disease figure are constructed, wherein vertex set is all lists
Symptom and medical diagnosis on disease, the association of all monosymptoms occurred in Bian Jiwei data set B and corresponding medical diagnosis on disease.Using existing
Internet startup disk technology (such as LINE) learns monosymptomatic word and is embedded in vector.
Word embedded space (vector) is the general name of feature learning technology in one group of language model and natural language processing, word
Word in remittance is mapped to the real vector of the lower dimensional space for the size of vocabulary.
Internet startup disk: being a kind of word embedded technology, learns it by the connection relationship between word and is embedded in vector.
Wherein, LINE is the algorithm that an extensive information network is embedded among a low-dimensional vector space, this calculation
Method is visualizing, node-classification, and many fields of link prediction etc. are all largely effective.This method is suitable for handling any class
The information network of type, it is whether oriented, it is undirected, if to have weight.This method uses a target optimized
Function, for retaining global and local network structure simultaneously.
Algorithm with a kind of sampling of side in LINE, solves the limitation of classical stochastic gradient descent, improves reasoning
Validity and efficiency.Experiments have shown that validity of the LINE algorithm for various information networks in the real world, including language
Network, community network and citation network.The algorithm is largely effective, can learn within several hours on single machine out one have
The insertion vector of the network on million vertex and upper 1,000,000,000 sides.
Wherein, there are many kinds of the technologies of internet startup disk, and also in lasting optimization.This programme uses LINE conduct
The method of internet startup disk, other methods can also substitute the initial work for completing artificial neural network.
In S306, first data, second data are inputted into artificial neural network to, institute's predicate insertion vector
In model, diagnostic model is obtained by training.It include: by first data to the training number as artificial nerve network model
According to；By second data to the tally set as artificial nerve network model；Using institute's predicate insertion vector as artificial neuron
The parameter of internet startup disk layer；And artificial nerve network model is trained by setting to obtain the diagnostic model.
Vector is embedded in using internet startup disk method study symptom word, and the vector is used to be embedded in as artificial neural network symptom
The initial value of layer parameter.
As shown in figure 4, the artificial nerve network model in the present embodiment includes at least: symptom embeding layer, maximum pond layer,
And affine transformation layer.
For multiple first data in data set A to being entered in neural network model, this batch training can accelerate net
Network training process.It wherein, further include occupy-place processing during the first data are to input neural network model, it is therefore an objective to be used for
Alignment of data in the batch training process of artificial neural network.
By in the embeding layer of word insertion vector input neural network, multiple first data in data set A are to by being embedded in
The calculating of layer generates intermediate data set.
Intermediate data set generates symptom using the calculating of maximum pond layer in artificial neural network and is embedded in vector.
Symptom insertion vector exports different medical diagnosis on disease classifications by affine transformation.
According to the disease data processing method of the disclosure, the disease with semantic information arrived using internet startup disk technological learning
Shape is embedded in vector initialising artificial neural network.
Wherein, the structure of the artificial neural network in the application can also be but basic according to the adjusting and optimizing that needs of calculating
Frame and the presently disclosed content of the application are almost the same.
According to the disease data processing method of the disclosure, using artificial neural network to symptom combined prediction medical diagnosis on disease point
Cloth.And word insertion vector is advanced optimized, preferably capture the semantic information of symptom.To improve model prediction ability, to face
Bed doctor makes diagnosis and provides better aid decision.
There are a large amount of patient disease diagnosis and symptom combination data in hospital clinical data.At the disease data of the disclosure
Reason method
Using it is this with many-one mapping relations<symptom combination, medical diagnosis on disease>data pair, using artificial neural network
Network carries out mathematical modeling, enables symptom combination predictive disease diagnosis distribution of the model according to patient, to be clinician
Medical diagnosis on disease provides aid decision and helps.
It will be appreciated by those skilled in the art that realizing that all or part of the steps of above-described embodiment is implemented as being executed by CPU
Computer program.When the computer program is executed by CPU, above-mentioned function defined by the above method that the disclosure provides is executed
Energy.The program can store in a kind of computer readable storage medium, which can be read-only memory, magnetic
Disk or CD etc..
Further, it should be noted that above-mentioned attached drawing is only the place according to included by the method for disclosure exemplary embodiment
Reason schematically illustrates, rather than limits purpose.It can be readily appreciated that above-mentioned processing shown in the drawings is not indicated or is limited at these
The time sequencing of reason.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
Following is embodiment of the present disclosure, can be used for executing embodiments of the present disclosure.It is real for disclosure device
Undisclosed details in example is applied, embodiments of the present disclosure is please referred to.
Fig. 5 is a kind of block diagram of disease data processing unit shown according to an exemplary embodiment.Disease data processing
Device 50 includes: data module 502, and word segmentation module 504, data are to module 506 and object module 508.
Data module 502 include at least one disease symptoms label for obtaining disease data, in the disease data with
Diagnostic result；As described above, patient disease's diagnostic result is frequently included in disease data and patient shows symptom.Disease data
The relationship between the disease of patient and disease symptoms label can be disclosed in all its bearings.It can be for example by being obtained in electronic health record
Disease data is taken, it can also be for example by obtaining diagnostic data in diagnosis report.
Word segmentation module 504 is used to the disease data carrying out word segmentation processing, generates lexical set；Character can for example be passed through
String matching method carries out word segmentation processing to the disease data, generates multiple participle vocabulary；And pass through the multiple participle vocabulary
Generate the lexical set.
Data are used to module 506 construct the first data pair by lexical set, and first data are to including at least one
A disease symptoms label and diagnostic result；The data in lexical set are extracted, the first data pair are formed, the first data are to can be such as
For<symptom combination, medical diagnosis on disease>form, wherein include at least one disease symptoms label in symptom combination.First data pair
May be, for example,<(abdominal pain, vomiting, anuria), (calculus)>, wherein symptom combination are as follows: abdominal pain, vomiting, anuria, medical diagnosis on disease are as follows: knot
Stone.
Object module 508 be used for by first data to input diagnostic model in obtain medical diagnosis on disease as a result, described
Diagnosing model is artificial nerve network model.
According to the disease data processing unit of the disclosure, disease forecasting accuracy rate can be improved, be the diagnosis of clinician
Make preferably aid decision.
Fig. 6 is the block diagram of a kind of electronic equipment shown according to an exemplary embodiment.
The electronic equipment 200 of this embodiment according to the disclosure is described referring to Fig. 6.The electronics that Fig. 6 is shown
Equipment 200 is only an example, should not function to the embodiment of the present disclosure and use scope bring any restrictions.
As shown in fig. 6, electronic equipment 200 is showed in the form of universal computing device.The component of electronic equipment 200 can wrap
It includes but is not limited to: at least one processing unit 210, at least one storage unit 220, (including the storage of the different system components of connection
Unit 220 and processing unit 210) bus 230, display unit 240 etc..
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 210
Row, so that the processing unit 210 executes described in this specification above-mentioned electronic prescription circulation processing method part according to this
The step of disclosing various illustrative embodiments.For example, the processing unit 210 can be executed such as Fig. 2, walked shown in Fig. 3
Suddenly.
The storage unit 220 may include the readable medium of volatile memory cell form, such as random access memory
Unit (RAM) 2201 and/or cache memory unit 2202 can further include read-only memory unit (ROM) 2203.
The storage unit 220 can also include program/practical work with one group of (at least one) program module 2205
Tool 2204, such program module 2205 includes but is not limited to: operating system, one or more application program, other programs
It may include the realization of network environment in module and program data, each of these examples or certain combination.
Bus 230 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 200 can also be with one or more external equipments 300 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 200 communicate, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 200 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 250.Also, electronic equipment 200 can be with
By network adapter 260 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.Network adapter 260 can be communicated by bus 230 with other modules of electronic equipment 200.It should
Understand, although not shown in the drawings, other hardware and/or software module can be used in conjunction with electronic equipment 200, including but unlimited
In: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and number
According to backup storage system etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server or network equipment etc.) executes the above method according to disclosure embodiment.
Fig. 7 schematically shows a kind of computer readable storage medium schematic diagram in disclosure exemplary embodiment.
Refering to what is shown in Fig. 7, describing the program product for realizing the above method according to embodiment of the present disclosure
400, can using portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device,
Such as it is run on PC.However, the program product of the disclosure is without being limited thereto, in this document, readable storage medium storing program for executing can be with
To be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
It is in connection.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
The computer readable storage medium may include in a base band or the data as the propagation of carrier wave a part are believed
Number, wherein carrying readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetism
Signal, optical signal or above-mentioned any appropriate combination.Readable storage medium storing program for executing can also be any other than readable storage medium storing program for executing
Readable medium, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or
Person's program in connection.The program code for including on readable storage medium storing program for executing can transmit with any suitable medium, packet
Include but be not limited to wireless, wired, optical cable, RF etc. or above-mentioned any appropriate combination.
Can with any combination of one or more programming languages come write for execute the disclosure operation program
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
Above-mentioned computer-readable medium carries one or more program, when said one or multiple programs are by one
When the equipment executes, so that the computer-readable medium implements function such as: obtaining disease data, include in the disease data
At least one disease symptoms label and diagnostic result；The disease data is subjected to word segmentation processing, generates lexical set；Pass through word
Collect conjunction the first data pair of building, first data are to including at least one disease symptoms label and diagnostic result；And it will
First data to input diagnostic model in obtain medical diagnosis on disease as a result, the diagnostic model is artificial neural network mould
Type.
It will be appreciated by those skilled in the art that above-mentioned each module can be distributed in device according to the description of embodiment, it can also
Uniquely it is different from one or more devices of the present embodiment with carrying out corresponding change.The module of above-described embodiment can be merged into
One module, can also be further split into multiple submodule.
By the description of above embodiment, those skilled in the art is it can be readily appreciated that example embodiment described herein
It can also be realized in such a way that software is in conjunction with necessary hardware by software realization.Therefore, implemented according to the disclosure
The technical solution of example can be embodied in the form of software products, which can store in a non-volatile memories
In medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) or on network, including some instructions are so that a calculating equipment (can
To be personal computer, server, mobile terminal or network equipment etc.) it executes according to the method for the embodiment of the present disclosure.
It is particularly shown and described the exemplary embodiment of the disclosure above.It should be appreciated that the present disclosure is not limited to
Detailed construction, set-up mode or implementation method described herein；On the contrary, disclosure intention covers included in appended claims
Various modifications and equivalence setting in spirit and scope.
In addition, structure shown by this specification Figure of description, ratio, size etc., only to cooperate specification institute
Disclosure, for skilled in the art realises that be not limited to the enforceable qualifications of the disclosure with reading, therefore
Do not have technical essential meaning, the modification of any structure, the change of proportionate relationship or the adjustment of size are not influencing the disclosure
Under the technical effect and achieved purpose that can be generated, it should all still fall in technology contents disclosed in the disclosure and obtain and can cover
In the range of.Meanwhile cited such as "upper" in this specification, " first ", " second " and " one " term, be also only and be convenient for
Narration is illustrated, rather than to limit the enforceable range of the disclosure, relativeness is altered or modified, without substantive change
Under technology contents, when being also considered as the enforceable scope of the disclosure.
Claims (10)
1. a kind of disease data processing method characterized by comprising
Disease data is obtained, includes at least one disease symptoms label in the disease data；
The disease data is subjected to word segmentation processing, generates lexical set；
Symptom set is constructed by lexical set, the symptom set includes at least one disease symptoms label；And
The symptom set is inputted to obtain classification of diseases mark in diagnostic model, the diagnostic model is artificial neural network
Model.
2. the method as described in claim 1, which is characterized in that further include:
The diagnostic model is constructed by history disease data and artificial nerve network model.
3. method according to claim 2, which is characterized in that constructed by history disease data and artificial nerve network model
The diagnostic model includes:
The first data pair and the second data pair are constructed by history disease data, first data are to including at least one disease
Symptom label and diagnostic result, second data are to including single disease symptoms label and single diagnostic result；
Vector is embedded in word is generated by second data；And
First data pass through, second data in, institute's predicate insertion vector input artificial nerve network model
Training obtains diagnostic model.
4. method as claimed in claim 3, which is characterized in that construct the first data pair and the second number by history disease data
According to including:
History disease data is subjected to word segmentation processing with dictionary according to International Medical and generates the first data pair；And
First data are generated at least one second data pair to decomposing according to disease symptoms label.
5. method as claimed in claim 3, which is characterized in that include: to word insertion vector is generated by second data
By second data to building diagnostic network, wherein point of the object of data centering as the diagnostic network, right
Side of the relationship as the diagnostic network as between；And
Word, which is generated, by internet startup disk technology and the diagnostic network is embedded in vector.
6. method as claimed in claim 3, which is characterized in that by first data to, second data to, institute's predicate
It is embedded in vector input artificial nerve network model, obtaining diagnostic model by training includes:
By first data to the training data as artificial nerve network model；
By second data to the tally set as artificial nerve network model；
Using institute's predicate insertion vector as the parameter of artificial neural network embeding layer；And
Artificial nerve network model is trained by setting to obtain the diagnostic model.
7. method as claimed in claim 3, which is characterized in that the artificial nerve network model includes at least: symptom insertion
Layer, maximum pond layer and affine transformation layer.
8. a kind of disease data processing unit characterized by comprising
Data module includes at least one disease symptoms label in the disease data for obtaining disease data；
Word segmentation module generates lexical set for the disease data to be carried out word segmentation processing；
Data are to module, and for constructing symptom set by lexical set, the symptom set includes at least one disease symptoms
Label；And
Object module, for inputting in diagnostic model the symptom set to obtain classification of diseases mark, the diagnostic model
For artificial nerve network model.
9. a kind of electronic equipment characterized by comprising
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now method as described in any in claim 1-7.
10. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that described program is held by processor
The method as described in any in claim 1-7 is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811351658.1A CN109599185B (en) | 2018-11-14 | 2018-11-14 | Disease data processing method and device, electronic equipment and computer readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811351658.1A CN109599185B (en) | 2018-11-14 | 2018-11-14 | Disease data processing method and device, electronic equipment and computer readable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109599185A true CN109599185A (en) | 2019-04-09 |
| CN109599185B CN109599185B (en) | 2021-05-25 |
Family
ID=65958487
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811351658.1A Active CN109599185B (en) | 2018-11-14 | 2018-11-14 | Disease data processing method and device, electronic equipment and computer readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109599185B (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110534203A (en) * | 2019-08-26 | 2019-12-03 | 腾讯科技（深圳）有限公司 | The monitoring method and device of regional disease, storage medium |
| CN110570945A (en) * | 2019-11-06 | 2019-12-13 | 常州糖族部落云健康科技有限公司 | AI chronic disease management method, computer storage medium and electronic device |
| CN110851595A (en) * | 2019-10-08 | 2020-02-28 | 云知声智能科技股份有限公司 | Identification method and device for disease term core vocabulary |
| CN110928922A (en) * | 2019-11-27 | 2020-03-27 | 开普云信息科技股份有限公司 | Public policy analysis model deployment method and system based on big data mining |
| CN111063446A (en) * | 2019-12-17 | 2020-04-24 | 医渡云（北京）技术有限公司 | Method, apparatus, device and storage medium for standardizing medical text data |
| CN111180064A (en) * | 2019-12-25 | 2020-05-19 | 北京亚信数据有限公司 | Evaluation method and device for auxiliary diagnosis model and computing equipment |
| CN111209387A (en) * | 2019-12-31 | 2020-05-29 | 嘉兴太美医疗科技有限公司 | Retrieval analysis method and system based on MedDRA |
| CN111681755A (en) * | 2020-04-28 | 2020-09-18 | 北京农业信息技术研究中心 | Pig disease diagnosis and treatment system and method |
| CN111785369A (en) * | 2020-06-30 | 2020-10-16 | 安徽科大讯飞医疗信息技术有限公司 | Diagnostic prediction method, related device and readable storage medium |
| CN112259229A (en) * | 2020-06-10 | 2021-01-22 | 北京小白世纪网络科技有限公司 | Method, system and equipment for realizing traditional Chinese medicine diagnosis and treatment based on neural network |
| CN112509691A (en) * | 2020-11-30 | 2021-03-16 | 北京百度网讯科技有限公司 | Prompting method and device for differential diagnosis, electronic equipment and storage medium |
| WO2021051496A1 (en) * | 2019-09-18 | 2021-03-25 | 平安科技（深圳）有限公司 | Diagnosis result identification and model training method, computer device, and storage medium |
| CN112885457A (en) * | 2021-01-25 | 2021-06-01 | 武汉大学 | Post-structured processing method, system and storage medium of medical big data |
| CN113077892A (en) * | 2021-04-21 | 2021-07-06 | 大连医科大学附属第二医院 | Thyroid disease data collection management system |
| CN113096817A (en) * | 2021-04-13 | 2021-07-09 | 北京大学 | Method, apparatus, computer device and storage medium for disease prediction |
| CN114334065A (en) * | 2022-03-07 | 2022-04-12 | 阿里巴巴达摩院(杭州)科技有限公司 | Medical record processing method, computer readable storage medium and computer device |
| WO2022141923A1 (en) * | 2020-12-31 | 2022-07-07 | 上海明品医学数据科技有限公司 | Intelligent medical brain model establishment system and method, and service system and medium |
| CN114783597A (en) * | 2022-06-23 | 2022-07-22 | 瀚依科技(杭州)有限公司 | Method and device for diagnosing multi-class diseases, electronic equipment and storage medium |
| CN114822865A (en) * | 2022-06-27 | 2022-07-29 | 天津幸福生命科技有限公司 | Diagnostic data identification method and device, electronic equipment and storage medium |
| CN115497616A (en) * | 2022-10-25 | 2022-12-20 | 杭州杏林信息科技有限公司 | Method, system, equipment and storage medium for aid decision making of infectious diseases |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1194045A (en) * | 1995-07-25 | 1998-09-23 | 好乐思治疗公司 | Computer assisted methods for diagnosing diseases |
| CN106951719A (en) * | 2017-04-10 | 2017-07-14 | 荣科科技股份有限公司 | The construction method and constructing system of clinical diagnosis model, clinical diagnosing system |
| CN107785075A (en) * | 2017-11-01 | 2018-03-09 | 杭州依图医疗技术有限公司 | Fever in children disease deep learning assistant diagnosis system based on text case history |
| CN107833629A (en) * | 2017-10-25 | 2018-03-23 | 厦门大学 | Aided diagnosis method and system based on deep learning |
| CN107863147A (en) * | 2017-10-24 | 2018-03-30 | 清华大学 | The method of medical diagnosis based on depth convolutional neural networks |
| US20180204644A1 (en) * | 2011-03-28 | 2018-07-19 | Canon Kabushiki Kaisha | Medical diagnosis support apparatus and medical diagnosis support method |
-
2018
- 2018-11-14 CN CN201811351658.1A patent/CN109599185B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1194045A (en) * | 1995-07-25 | 1998-09-23 | 好乐思治疗公司 | Computer assisted methods for diagnosing diseases |
| US20180204644A1 (en) * | 2011-03-28 | 2018-07-19 | Canon Kabushiki Kaisha | Medical diagnosis support apparatus and medical diagnosis support method |
| CN106951719A (en) * | 2017-04-10 | 2017-07-14 | 荣科科技股份有限公司 | The construction method and constructing system of clinical diagnosis model, clinical diagnosing system |
| CN107863147A (en) * | 2017-10-24 | 2018-03-30 | 清华大学 | The method of medical diagnosis based on depth convolutional neural networks |
| CN107833629A (en) * | 2017-10-25 | 2018-03-23 | 厦门大学 | Aided diagnosis method and system based on deep learning |
| CN107785075A (en) * | 2017-11-01 | 2018-03-09 | 杭州依图医疗技术有限公司 | Fever in children disease deep learning assistant diagnosis system based on text case history |
Non-Patent Citations (2)
| Title |
|---|
| RICCARDO MIOTTO等: "《Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records》", 《SCIENTIFIC REPORTS》 * |
| 宋红等: "《用于医学辅助诊断的神经网络方法的应用研究》", 《生物医学工程学杂志》 * |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110534203A (en) * | 2019-08-26 | 2019-12-03 | 腾讯科技（深圳）有限公司 | The monitoring method and device of regional disease, storage medium |
| WO2021051496A1 (en) * | 2019-09-18 | 2021-03-25 | 平安科技（深圳）有限公司 | Diagnosis result identification and model training method, computer device, and storage medium |
| CN110851595A (en) * | 2019-10-08 | 2020-02-28 | 云知声智能科技股份有限公司 | Identification method and device for disease term core vocabulary |
| CN110570945A (en) * | 2019-11-06 | 2019-12-13 | 常州糖族部落云健康科技有限公司 | AI chronic disease management method, computer storage medium and electronic device |
| CN110570945B (en) * | 2019-11-06 | 2020-02-14 | 常州糖族部落云健康科技有限公司 | AI chronic disease management method, computer storage medium and electronic device |
| CN110928922A (en) * | 2019-11-27 | 2020-03-27 | 开普云信息科技股份有限公司 | Public policy analysis model deployment method and system based on big data mining |
| CN111063446A (en) * | 2019-12-17 | 2020-04-24 | 医渡云（北京）技术有限公司 | Method, apparatus, device and storage medium for standardizing medical text data |
| CN111180064A (en) * | 2019-12-25 | 2020-05-19 | 北京亚信数据有限公司 | Evaluation method and device for auxiliary diagnosis model and computing equipment |
| CN111209387B (en) * | 2019-12-31 | 2022-02-18 | 上海亿锎智能科技有限公司 | Retrieval analysis method and system based on MedDRA |
| CN111209387A (en) * | 2019-12-31 | 2020-05-29 | 嘉兴太美医疗科技有限公司 | Retrieval analysis method and system based on MedDRA |
| CN111681755A (en) * | 2020-04-28 | 2020-09-18 | 北京农业信息技术研究中心 | Pig disease diagnosis and treatment system and method |
| CN112259229A (en) * | 2020-06-10 | 2021-01-22 | 北京小白世纪网络科技有限公司 | Method, system and equipment for realizing traditional Chinese medicine diagnosis and treatment based on neural network |
| CN111785369B (en) * | 2020-06-30 | 2024-04-05 | 讯飞医疗科技股份有限公司 | Diagnostic prediction method, related device, and readable storage medium |
| CN111785369A (en) * | 2020-06-30 | 2020-10-16 | 安徽科大讯飞医疗信息技术有限公司 | Diagnostic prediction method, related device and readable storage medium |
| CN112509691A (en) * | 2020-11-30 | 2021-03-16 | 北京百度网讯科技有限公司 | Prompting method and device for differential diagnosis, electronic equipment and storage medium |
| CN112509691B (en) * | 2020-11-30 | 2024-04-19 | 北京百度网讯科技有限公司 | Method and device for prompting differential diagnosis, electronic equipment and storage medium |
| WO2022141923A1 (en) * | 2020-12-31 | 2022-07-07 | 上海明品医学数据科技有限公司 | Intelligent medical brain model establishment system and method, and service system and medium |
| CN112885457A (en) * | 2021-01-25 | 2021-06-01 | 武汉大学 | Post-structured processing method, system and storage medium of medical big data |
| CN113096817A (en) * | 2021-04-13 | 2021-07-09 | 北京大学 | Method, apparatus, computer device and storage medium for disease prediction |
| CN113077892A (en) * | 2021-04-21 | 2021-07-06 | 大连医科大学附属第二医院 | Thyroid disease data collection management system |
| CN114334065B (en) * | 2022-03-07 | 2022-06-28 | 阿里巴巴达摩院(杭州)科技有限公司 | Medical record processing method, computer readable storage medium and computer device |
| CN114334065A (en) * | 2022-03-07 | 2022-04-12 | 阿里巴巴达摩院(杭州)科技有限公司 | Medical record processing method, computer readable storage medium and computer device |
| CN114783597A (en) * | 2022-06-23 | 2022-07-22 | 瀚依科技(杭州)有限公司 | Method and device for diagnosing multi-class diseases, electronic equipment and storage medium |
| CN114783597B (en) * | 2022-06-23 | 2022-11-29 | 瀚依科技(杭州)有限公司 | Method and device for diagnosing multi-class diseases, electronic equipment and storage medium |
| CN114822865A (en) * | 2022-06-27 | 2022-07-29 | 天津幸福生命科技有限公司 | Diagnostic data identification method and device, electronic equipment and storage medium |
| CN115497616A (en) * | 2022-10-25 | 2022-12-20 | 杭州杏林信息科技有限公司 | Method, system, equipment and storage medium for aid decision making of infectious diseases |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109599185B (en) | 2021-05-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109599185A (en) | Disease data processing method, device, electronic equipment and computer-readable medium | |
| Fan et al. | Adverse drug event detection and extraction from open data: A deep learning approach | |
| Dharwadkar et al. | A medical chatbot | |
| Degoulet et al. | Introduction to clinical informatics | |
| CN109509556A (en) | Knowledge mapping generation method, device, electronic equipment and computer-readable medium | |
| CN111666477B (en) | Data processing method, device, intelligent equipment and medium | |
| Lee et al. | Machine learning in relation to emergency medicine clinical and operational scenarios: an overview | |
| CN113707299A (en) | Auxiliary diagnosis method and device based on inquiry session and computer equipment | |
| CN108231146A (en) | A kind of medical records model building method, system and device based on deep learning | |
| Gudivada et al. | A literature review on machine learning based medical information retrieval systems | |
| CN113657105A (en) | Medical entity extraction method, device, equipment and medium based on vocabulary enhancement | |
| RU2699607C2 (en) | High efficiency and reduced frequency of subsequent radiation studies by predicting base for next study | |
| CN114175173A (en) | Learning platform for patient history mapping | |
| Li et al. | Dynamic assessment of the COVID-19 vaccine acceptance leveraging social media data | |
| Varshney et al. | Knowledge grounded medical dialogue generation using augmented graphs | |
| Swarupa et al. | Disease prediction: smart disease prediction system using random forest algorithm | |
| Guo et al. | PaCAR: COVID-19 pandemic control decision making via large-scale agent-based modeling and deep reinforcement learning | |
| An | Construction and application of Chinese breast cancer knowledge graph based on multi-source heterogeneous data | |
| Vu et al. | Identifying patients with pain in emergency departments using conventional machine learning and deep learning | |
| Khanam et al. | Joint knowledge-powered topic level attention for a convolutional text summarization model | |
| US11281855B1 (en) | Reinforcement learning approach to decode sentence ambiguity | |
| Wang et al. | Accelerating epidemiological investigation analysis by using NLP and knowledge reasoning: a case study on COVID-19 | |
| Al-Smadi | DeBERTa-BiLSTM: A multi-label classification model of Arabic medical questions using pre-trained models and deep learning | |
| CN114743647A (en) | Medical data processing method, device, equipment and storage medium | |
| Wang et al. | Automatic ICD-10 coding based on multi-head attention mechanism and gated residual network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |