CN108614885B - Knowledge mapping analysis method and device based on medical information - Google Patents
Knowledge mapping analysis method and device based on medical information Download PDFInfo
- Publication number
- CN108614885B CN108614885B CN201810413668.7A CN201810413668A CN108614885B CN 108614885 B CN108614885 B CN 108614885B CN 201810413668 A CN201810413668 A CN 201810413668A CN 108614885 B CN108614885 B CN 108614885B
- Authority
- CN
- China
- Prior art keywords
- patient
- disease
- information
- medical
- genius morbi
- 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.)
- Active
Links
- 238000013507 mapping Methods 0.000 title claims abstract description 25
- 238000004458 analytical method Methods 0.000 title claims abstract description 22
- 201000010099 disease Diseases 0.000 claims abstract description 161
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 161
- 239000013598 vector Substances 0.000 claims abstract description 95
- 206010061818 Disease progression Diseases 0.000 claims abstract description 64
- 230000005750 disease progression Effects 0.000 claims abstract description 64
- 238000010801 machine learning Methods 0.000 claims abstract description 22
- 230000006866 deterioration Effects 0.000 claims abstract description 9
- 238000004364 calculation method Methods 0.000 claims abstract description 8
- 238000011282 treatment Methods 0.000 claims description 66
- 238000004422 calculation algorithm Methods 0.000 claims description 26
- 230000001225 therapeutic effect Effects 0.000 claims description 21
- 238000000605 extraction Methods 0.000 claims description 9
- 239000000284 extract Substances 0.000 claims description 5
- 238000005295 random walk Methods 0.000 claims description 5
- 230000008878 coupling Effects 0.000 claims description 2
- 238000010168 coupling process Methods 0.000 claims description 2
- 238000005859 coupling reaction Methods 0.000 claims description 2
- 238000000034 method Methods 0.000 abstract description 46
- 239000003814 drug Substances 0.000 description 14
- 210000000265 leukocyte Anatomy 0.000 description 12
- 230000008569 process Effects 0.000 description 12
- 230000004596 appetite loss Effects 0.000 description 9
- 235000021266 loss of appetite Nutrition 0.000 description 9
- 208000019017 loss of appetite Diseases 0.000 description 9
- 208000024891 symptom Diseases 0.000 description 9
- 238000012545 processing Methods 0.000 description 8
- 208000007882 Gastritis Diseases 0.000 description 7
- 238000004820 blood count Methods 0.000 description 6
- 239000002775 capsule Substances 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000011285 therapeutic regimen Methods 0.000 description 5
- 229940079593 drug Drugs 0.000 description 4
- 238000002651 drug therapy Methods 0.000 description 3
- 230000008030 elimination Effects 0.000 description 3
- 238000003379 elimination reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000012535 impurity Substances 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 241000894007 species Species 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 206010011224 Cough Diseases 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 208000036071 Rhinorrhea Diseases 0.000 description 1
- 206010039101 Rhinorrhoea Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000010225 co-occurrence analysis Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 208000002173 dizziness Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000010339 medical test Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 210000002784 stomach Anatomy 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
- 238000007794 visualization technique Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
Abstract
The present invention provides a kind of knowledge mapping analysis method and device based on medical information segment word included in patient medical information this method comprises: obtaining；Participle word is analyzed based on default medical knowledge base, obtains target criteria medical data corresponding to participle word；Target criteria medical data is matched with default disease knowledge map；The disease of patient is determined according to matching result；Feature vector based on the disease of patient medical information and patient building patient；Deterioration probability calculation is carried out to feature vector by disease progression machine learning model, obtains the disease progression probability of patient.This method really considers patient medical information, obtained disease outcome is more accurate, and can predict the case where disease, obtains the probability of disease progression, the technical issues of it is poor to alleviate the disease outcome accuracy that existing method obtains, and the case where disease can not be predicted.
Description
Technical field
The present invention relates to the technical fields of data processing, analyze more particularly, to a kind of knowledge mapping based on medical information
Method and device.
Background technique
Knowledge mapping is also known as mapping knowledge domains, be explicit knowledge's development process and structural relation it is a series of it is various not
With figure, knowledge resource and its carrier described with visualization technique, excavate, analysis, building, draw and explicit knowledge and they
Between connect each other.By by the theory of the subjects such as applied mathematics, graphics, Information Visualization Technology, information science and just
Method and the methods of meterological citation analysis, Co-occurrence Analysis combine, and the core of subject is visually shown using visual map
Structure, developing history, Disciplinary Frontiers and whole Knowledge framework reach the modern theory of Multidisciplinary Integration purpose.For disciplinary study
Practical, valuable reference is provided.Knowledge mapping is the semantic knowledge-base of structuring, for describing physics with sign format
Concept and its correlation in the world, basic composition unit are entity-relationship-entity triple and entity and its phase
Attribute-value pair is closed, is interconnected between entity by relationship, the webbed structure of knowledge of structure.
Currently, knowledge mapping is very widely used, in the field of medicine, construct medical knowledge map, can by illness,
Complicated relationship between disease and diagnosis and treatment means is built into database by knowledge mapping, so as to be medical staff
Good auxiliary diagnosis means are provided.Based on this, occurs the application of a large amount of online question and answer at this stage, these applications receive patient
Information description, return to the disease of a patient in conjunction with the domain knowledge map constructed in advance using Sentence analysis and related algorithm
Sick diagnostic result.
The problem of existing technical solution is generally by search question and answer library with patient's description similarity highest, returns to institute
Corresponding disease outcome.This method cannot reflect conditions of patients completely, and obtained disease outcome accuracy is poor, and can only obtain
The disease that patient is suffered from can not predict the case where disease.
Summary of the invention
In view of this, the purpose of the present invention is to provide a kind of knowledge mapping analysis method and dress based on medical information
It sets, it is poor to alleviate the disease outcome accuracy that existing method obtains, and the technology that can not be predicted the case where disease is asked
Topic.
In a first aspect, the embodiment of the invention provides a kind of knowledge mapping analysis method based on medical information, the side
Method includes:
It obtains and segments word included in patient medical information, wherein the patient medical information includes: the base of patient
This information, the state of an illness information of patient, the treatment information of patient, the social information of patient；
The participle word is analyzed based on default medical knowledge base, obtains target corresponding to the participle word
Standard medical data；
The target criteria medical data is matched with default disease knowledge map, wherein the default disease is known
Know the relevance map that map is various diseases factor associated therewith；
The disease of the patient is determined according to matching result；
Disease based on the patient medical information and the patient constructs the feature vector of the patient, wherein described
Feature vector includes: genius morbi vector, treats feature vector, relationship characteristic vector；
Deterioration probability calculation is carried out to described eigenvector by disease progression machine learning model, obtains the patient's
Disease progression probability, wherein the disease progression machine learning model is to be carried out by K-MEANS algorithm to a large amount of feature vectors
The model that training obtains.
With reference to first aspect, the embodiment of the invention provides the first possible embodiments of first aspect, wherein base
Include: in the feature vector that the disease of the patient medical information and the patient construct the patient
To the essential information of the patient, the state of an illness information of the patient and the disease of the patient are calculated, and are obtained
To the genius morbi vector；
The disease for the treatment of information and the patient to the patient calculates, and obtains the treatment feature vector；
The social information of disease and the patient to the patient calculates, and obtains the relationship characteristic vector.
With reference to first aspect, the embodiment of the invention provides second of possible embodiments of first aspect, wherein right
The essential information of the patient, the state of an illness information of the patient and the disease of the patient calculate, and obtain the disease
Feature vector includes:
Genius morbi is determined according to the disease of the patient；
The genius morbi range of disease progression crowd and the disease spy of stable disease crowd are obtained based on the genius morbi
Levy range；
The genius morbi of essential information based on the patient and patient described in the state of an illness information extraction of the patient；
In conjunction with the genius morbi range of the disease progression crowd, the genius morbi range of the stable disease crowd and
The genius morbi of the patient determines Crowds Distribute belonging to the patient；
The genius morbi vector is calculated based on Crowds Distribute belonging to the patient.
With reference to first aspect, the embodiment of the invention provides the third possible embodiments of first aspect, wherein right
The treatment information of the patient and the disease of the patient calculate, and obtain the treatment feature vector and include:
Therapeutic scheme is determined according to the disease of the patient, wherein includes multiple treatment features in the therapeutic scheme；
The treatment feature of patient described in treatment information extraction based on the patient；
The treatment feature of the patient is matched with the treatment feature in the therapeutic scheme；
The treatment feature vector of the patient is determined according to matching result.
With reference to first aspect, the embodiment of the invention provides the 4th kind of possible embodiments of first aspect, wherein right
The social information of the disease of the patient and the patient calculate, and obtain the relationship characteristic vector and include:
The social information of the disease of the patient and the patient are associated with the foundation of historical relation map, wherein described
Historical relation map is the relation map obtained according to historic patient medical information；
The historical relation map is calculated by community discovery algorithm, obtains social group belonging to the patient
Body；
The weighted value that side in the historical relation map is updated by the disease progression risk of the social groups, obtains more
Relation map after new, wherein the disease progression risk of the social groups is to be obtained according to the historic patient medical information
's；
The updated relation map is calculated by Random Walk Algorithm and node2vector, is obtained described
Relationship characteristic vector.
With reference to first aspect, the embodiment of the invention provides the 5th kind of possible embodiments of first aspect, wherein base
The participle word is analyzed in default medical knowledge base, obtains target criteria medicine number corresponding to the participle word
According to including:
It is obtained and candidate criteria medical data corresponding to the participle word based on the default medical knowledge base；
According in the incidence relation and the medical knowledge base of the participle word between each standard medical data
Topological relation, the target criteria medical data is determined from the candidate criteria medical data.
With reference to first aspect, the embodiment of the invention provides the 6th kind of possible embodiments of first aspect, wherein
After obtaining the disease progression probability of the patient, the method also includes:
It is that the patient recommends therapeutic regimen according to the disease progression probability of the patient.
With reference to first aspect, the embodiment of the invention provides the 7th kind of possible embodiments of first aspect, wherein obtains
The participle word is taken included in patient medical information to include:
Obtain the patient medical information；
The cluster probability of word and word in the patient medical information is counted using condition random field algorithm；
The patient medical information is segmented according to the cluster probability, obtains the participle word.
Second aspect, the embodiment of the invention also provides a kind of knowledge mapping analytical equipment based on medical information are described
Device includes:
Module is obtained, segments word included in patient medical information for obtaining, wherein the patient medical information
It include: the essential information of patient, the state of an illness information of patient, the treatment information of patient, the social information of patient；
Analysis module obtains the participle word for analyzing based on default medical knowledge base the participle word
Target criteria medical data corresponding to language；
Matching module, for matching the target criteria medical data with default disease knowledge map, wherein institute
State the relevance map that default disease knowledge map is various diseases factor associated therewith；
Determining module, for determining the disease of the patient according to matching result；
Construct module, for the disease based on the patient medical information and the patient construct the feature of the patient to
Amount, wherein described eigenvector includes: genius morbi vector, treats feature vector, relationship characteristic vector；
Computing module, for carrying out deterioration probability calculation to described eigenvector by disease progression machine learning model,
Obtain the disease progression probability of the patient, wherein the disease progression machine learning model is by K-MEANS algorithm to big
The model that measure feature vector is trained.
In conjunction with second aspect, the embodiment of the invention provides the first possible embodiments of second aspect, wherein institute
Stating building module includes:
First computing unit, for the essential information to the patient, the state of an illness information of the patient and the patient
Disease calculated, obtain the genius morbi vector；
Second computing unit, the disease for treatment information and the patient to the patient are calculated, are obtained
The treatment feature vector；
Third computing unit, the social information for disease and the patient to the patient calculate, and obtain institute
State relationship characteristic vector.
The embodiment of the present invention brings following the utility model has the advantages that a kind of knowledge mapping analysis method and dress based on medical information
It sets, segments word included in patient medical information this method comprises: obtaining, wherein patient medical information includes: patient's
Essential information, the state of an illness information of patient, the treatment information of patient, the social information of patient；Based on default medical knowledge base to point
Word word is analyzed, and target criteria medical data corresponding to participle word is obtained；By target criteria medical data and preset
Disease knowledge map is matched, wherein default disease knowledge map is the relevance map of various diseases factor associated therewith；
The disease of patient is determined according to matching result；The feature vector of patient is constructed based on the disease of patient medical information and patient,
In, feature vector includes: genius morbi vector, treats feature vector, relationship characteristic vector；Pass through disease progression machine learning mould
Type carries out deterioration probability calculation to feature vector, obtains the disease progression probability of patient, wherein disease progression machine learning model
For the model being trained by K-MEANS algorithm to a large amount of feature vectors.
In the prior art, generally by search question and answer library with patient's description similarity highest the problem of, it is right to return to institute
The disease outcome answered, the disease outcome accuracy that this method obtains is poor, and can not predict the case where disease.With it is existing
Method is compared, can be according to patient medical information in the knowledge mapping analysis method based on medical information of the embodiment of the present invention
In participle word determine its corresponding target criteria medical data, then target criteria medical data and default disease are known again
Know map to be matched, the disease of patient is determined, after obtaining disease outcome, additionally it is possible to disease and patient doctor based on patient
The feature vector for learning information architecture patient carries out feature vector eventually by disease progression machine learning model to deteriorate probability meter
It calculates, obtains the disease progression probability of patient.This method really considers patient medical information, and obtained disease outcome is more quasi-
Really, and the case where disease, can be predicted, obtains the probability of disease progression, alleviate the disease that existing method obtains
As a result accuracy is poor, and the technical issues of can not predict the case where disease.
Other features and advantages of the present invention will illustrate in the following description, also, partly become from specification
It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention are in specification, claims
And specifically noted structure is achieved and obtained in attached drawing.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor
It puts, is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of flow chart of the knowledge mapping analysis method based on medical information provided in an embodiment of the present invention；
Fig. 2 is the flow chart that word is segmented included in acquisition patient medical information provided in an embodiment of the present invention；
Fig. 3 is the feature vector provided in an embodiment of the present invention that patient is constructed based on the disease of patient medical information and patient
Flow chart；
Fig. 4 is the essential information provided in an embodiment of the present invention to patient, the state of an illness information of patient and the disease of patient
It is calculated, obtains the flow chart of genius morbi vector；
Fig. 5 calculates the treatment information of patient and the disease of patient to be provided in an embodiment of the present invention, is controlled
Treat the flow chart of feature vector；
Fig. 6 calculates the disease of patient and the social information of patient to be provided in an embodiment of the present invention, obtains relationship
The flow chart of feature vector；
Fig. 7 is a kind of structural block diagram of the knowledge mapping analytical equipment based on medical information provided in an embodiment of the present invention.
Icon:
11- obtains module；12- analysis module；13- matching module；14- determining module；15- constructs module；16- calculates mould
Block.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with attached drawing to the present invention
Technical solution be clearly and completely described, it is clear that described embodiments are some of the embodiments of the present invention, rather than
Whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise
Under every other embodiment obtained, shall fall within the protection scope of the present invention.
For convenient for understanding the present embodiment, first to a kind of based on medical information disclosed in the embodiment of the present invention
Knowledge mapping analysis method describes in detail.
Embodiment one:
A kind of knowledge mapping analysis method based on medical information, with reference to Fig. 1, this method comprises:
Word is segmented included in S102, acquisition patient medical information, wherein patient medical information includes: patient's
Essential information, the state of an illness information of patient, the treatment information of patient, the social information of patient；
In embodiments of the present invention, the executing subject for being somebody's turn to do the knowledge mapping analysis method based on medical information is server,
Server can obtain and segment word included in patient medical information.Specifically, patient medical data includes: the basic of patient
Information, the state of an illness information of patient, the treatment information of patient, the social information of patient.
The essential information of patient includes: the name of patient, the gender of patient, the age of patient, the identification card number etc. of patient
Deng the embodiment of the present invention is to it without concrete restriction.
The state of an illness information of patient includes: the symptom of patient, the medical history of patient, the duration of symptom, and cause symptom can
The event of doubting etc., the embodiment of the present invention is to it without concrete restriction.
The treatment information of patient includes: the time for the treatment of patients, mode (such as drug therapy, the treatment of needle liquid, gastroscope
Etc.), therapeutic scheme (such as drug noun eaten in drug therapy, dosage etc.) etc., the embodiment of the present invention to its not into
Row concrete restriction.
Content is again described in detail the process for obtaining participle word included in patient medical information below, herein
It repeats no more.
S104, participle word is analyzed based on default medical knowledge base, obtains target mark corresponding to participle word
Quasi- medical data；
After obtaining participle word included in patient medical information, inventor is not special in view of certain participle words
The medical terminology of industry, in order to which disease is more accurately determined and predicted, so needing based on default medical knowledge base pair
Participle word is analyzed, and target criteria medical data corresponding to participle word is obtained.Hereinafter the process is carried out again detailed
Thin description, details are not described herein.
S106, target criteria medical data is matched with default disease knowledge map, wherein default disease knowledge figure
Spectrum is the relevance map of various diseases factor associated therewith；
After obtaining target criteria medical data, by target criteria medical data and the progress of default disease knowledge map
Match, wherein default disease knowledge map is the relevance map of various diseases factor associated therewith.
S108, the disease that patient is determined according to matching result；
After the completion of matching, the disease of patient is determined according to matching result.Specifically, the target criteria medicine number such as obtained
According to being dizzy, rhinorrhea, cough is had a throat-ache, by these target criteria medical datas and the progress of default disease knowledge map
Match, is given a mark according to matched matching degree to possible disease, disease corresponding to score highest is determined as patient's
Disease, the disease as determined by above-mentioned target criteria medical data are flu.The embodiment of the present invention is only carried out with a citing
Explanation, does not limit the method in the present invention.
S110, the feature vector based on the disease of patient medical information and patient building patient, wherein feature vector packet
Include: genius morbi vector treats feature vector, relationship characteristic vector；
After obtaining the disease of patient, be based further on the feature of the disease building patient of patient medical information and patient to
Amount.Since the social information of the essential information of patient, the state of an illness information of patient, the treatment information of patient, patient is not structure
Change data, be not used to the computation in later period, so needing these non-structured data carrying out structuring, obtains patient
Feature vector, specifically included genius morbi vector, treated feature vector, relationship characteristic vector.Hereinafter again to the process
It describes in detail.
S112, deterioration probability calculation is carried out to feature vector by disease progression machine learning model, obtains the disease of patient
Disease deteriorates probability, wherein disease progression machine learning model is to be trained by K-MEANS algorithm to a large amount of feature vectors
The model arrived.
After obtaining the feature vector of patient, deterioration probability is carried out to feature vector by disease progression machine learning model
It calculates, it will be able to obtain the disease progression probability of patient.
Disease progression machine learning model in the embodiment of the present invention be first pass through in advance K-MEANS algorithm to big measure feature to
The model being trained is measured, K-MEANS algorithm is one of unsupervised machine learning algorithm, is using K- in the present invention
When MEANS algorithm, K therein is obtained after being analyzed by Gaussian function a large amount of historic patient medical informations.
After the completion of the disease progression machine learning model is established, it will be able to carry out online real-time learning, be carried out to the model
Continuous iteration optimization.
In the prior art, generally by search question and answer library with patient's description similarity highest the problem of, it is right to return to institute
The disease outcome answered, the disease outcome accuracy that this method obtains is poor, and can not predict the case where disease.With it is existing
Method is compared, can be according to patient medical information in the knowledge mapping analysis method based on medical information of the embodiment of the present invention
In participle word determine its corresponding target criteria medical data, then target criteria medical data and default disease are known again
Know map to be matched, the disease of patient is determined, after obtaining disease outcome, additionally it is possible to disease and patient doctor based on patient
The feature vector for learning information architecture patient carries out feature vector eventually by disease progression machine learning model to deteriorate probability meter
It calculates, obtains the disease progression probability of patient.This method really considers patient medical information, and obtained disease outcome is more quasi-
Really, and the case where disease, can be predicted, obtains the probability of disease progression, alleviate the disease that existing method obtains
As a result accuracy is poor, and the technical issues of can not predict the case where disease.
In embodiments of the present invention, after obtaining the disease progression probability of patient, this method further include:
It is that patient recommends therapeutic regimen according to the disease progression probability of patient.
Specifically, be directed to different diseases, different disease progression probability there are corresponding therapeutic regimen,
After obtaining disease progression probability, it will be able to according to therapeutic regimen of the deterioration determine the probability corresponding to it, by the treatment side
Case is pushed to corresponding patient.
The brief introduction that above content carries out the method in the present invention below carries out the particular content being directed to
It is discussed in detail.
Optionally, with reference to Fig. 2, obtaining participle word included in patient medical information includes:
S201, patient medical information is obtained；
In embodiments of the present invention, patient medical information can be text information, or voice messaging, when for voice
When information, first voice messaging is identified, the text information corresponding to voice messaging is obtained, then carries out subsequent mistake again
Journey.
The essential information of patient is mainly that patient is defeated in such a way that voice input or text input when this method is used
The information entered, the state of an illness information of patient include the history state of an illness information and current state of an illness information of patient, and current state of an illness information is
The information that patient states in such a way that voice describes, or with the information etc. of graphic form publication, the history state of an illness of patient
Information is the history state of an illness information (such as passing case) relevant to current state of an illness information acquired automatically by interface,
Similarly, the treatment information of patient also includes the Current therapeutic information of patient, also includes the historical therapeutic information of patient, obtains
Mode is similar to above-mentioned mode, and details are not described herein.
The social information of patient is the information crawled by way of web crawlers, certainly, the embodiment of the present invention pair
It is without concrete restriction.
S202, the cluster probability that word and word in patient medical information are counted using condition random field algorithm；
It after obtaining patient medical information, needs first to pre-process patient medical information, specifically, pretreatment packet
Include: impurity elimination processing, classification processing, impurity elimination processing do not meet the information of preset field requirement to remove in patient medical information, point
Impurity elimination treated information is is classified by class processing according to classification belonging to information, such as symptom class, time class, medicine
Species etc..
There are many kinds of the methods segmented to patient medical information, and condition random field algorithm is used in the embodiment of the present invention
Segmented, count patient medical information in word and word cluster probability, then according to when join together probability be less than predetermined probabilities when,
Word segmentation processing is carried out between two words.
S203, patient medical information is segmented according to cluster probability, obtains participle word.
After obtaining participle word, participle word is analyzed based on default medical knowledge base.
In one optionally embodiment, participle word is analyzed based on default medical knowledge base, is segmented
Target criteria medical data corresponding to word includes:
(1) it obtains based on default medical knowledge base and segments candidate criteria medical data corresponding to word；
Specifically, the preparatory manual sorting of medical profession can be asked to go out or sort out by artificial intelligence technology various
Standard medical data in first input database, are then established search index, and relevant knowledge entry cluster is got up, are obtained
Medical knowledge base.It is, being stored with various standard medical data and its topological relation in medical knowledge base, group reticulates knot
Structure facilitates storage and calling.For the ease of inquiry, medical knowledge base can also increase intelligent word processing and search function.Its
In, generally there are two source, the clinical experiences of medical literature and a certain domain expert for medical knowledge.
Medical knowledge base can be understood as a primary medical knowledge map by putting and side forms, wherein point is used to
Each standard medical data in medical knowledge base are described, for example various symptoms, various organs and tissue etc.；Side is used to describe each mark
Relationship between quasi- medical data, such as " being located at ", "comprising" and " quantity ".
With the continuous development of the medical technologies such as medical test, medical image, clinical diagnosis and rehabilitation, medicine is known
Knowing constantly to enrich, and in order to give full play to the effect of medical knowledge base, can constantly acquire newborn medical knowledge, update medicine
Knowledge base.
Participle word is calculated at a distance from word in default medical knowledge base using distance metric method, when distance is less than in advance
If when value, extracting corresponding candidate criteria medical data (i.e. data of the distance less than preset value).The candidate criteria medicine number
According to quantity may be one, can also be able to be multiple.
It should be noted that the distance metric method includes but is not limited to COS distance, Euclidean distance or other distances
Measure.
(2) it is closed according to the topology in the incidence relation and medical knowledge base of participle word between each standard medical data
System determines target criteria medical data from candidate criteria medical data.
After obtaining candidate criteria medical data, further according in the incidence relation and medical knowledge base of participle word
Topological relation between each standard medical data determines target criteria medical data from candidate criteria medical data.
It is that the cooccurrence relation of statistical medicine word is realized when specific implementation.Assuming that the participle word in patient medical information
Both occurred symptom word " loss of appetite " in language, and disease word " gastritis " also occurred, and laboratory indexes " white blood cell count(WBC) is exceeded ",
With drug " sanjiu weitai capsules ", then it represents that " loss of appetite " and " gastritis " has cooccurrence relation, and " loss of appetite " and " white blood cell count(WBC) is super
Mark " has cooccurrence relation, and " loss of appetite " and " sanjiu weitai capsules " has cooccurrence relation.
Further, if " loss of appetite " and the co-occurrence quantity of " gastritis " are very high, " loss of appetite " and " stomach can be indicated
It is scorching " there is very strong cooccurrence relation.The very strong keyword of cooccurrence relation, referred to as neighbours.In this embodiment, the neighbours of " loss of appetite "
It is " gastritis ", " white blood cell count(WBC) is exceeded ", " sanjiu weitai capsules ".
Topological relation between each standard medical data can be inquired from default medical knowledge base.If it was found that symptom
Word " receive difference " and disease " gastritis ", symptom word " receive difference " and laboratory indexes " white blood cell count(WBC) is exceeded ", symptom word " receive difference " and medicine
Product " sanjiu weitai capsules ", between have direct or indirect company side, then can be determined as " receive difference " and " gastritis " has topological relation, " receives
Difference " has topological relation with " white blood cell count(WBC) is exceeded ", and " receive difference " has topological relation with " sanjiu weitai capsules ".
Point in each medical knowledge base for having topological relation is also referred to as neighbours.In the example above, medical knowledge base
In the neighbours of " receive difference " be " gastritis ", " white blood cell count(WBC) is exceeded ", " sanjiu weitai capsules ".
Thus judge, " receive difference " is much like with the neighbours of " loss of appetite ", so, " receive difference " and " loss of appetite " have compared with
Strong replacement possibility.
Why above-mentioned process is carried out, be because if when patient is described using voice, it is possible to the language recognized
Message breath is incorrect.For example word wrong in the example above " receive difference " is recognized, it can analyze to obtain by this way correct
Word.
The process of building patient characteristic vector is described below:
In one optionally embodiment, with reference to Fig. 3, based on the disease of patient medical information and patient building patient's
Feature vector includes:
S301, the essential information to patient, the state of an illness information of patient and the disease of patient calculate, and obtain disease spy
Levy vector；
Specifically, genius morbi vector is the essential information according to patient, the state of an illness information of patient and the disease of patient
It is calculated, hereinafter specific calculating process is described in detail again, details are not described herein.
S302, the treatment information of patient and the disease of patient are calculated, obtain medical treatment feature vector；
Specifically, treatment feature vector is calculated according to the treatment information of patient and the disease of patient, hereafter
In specific calculating process is described in detail again, details are not described herein.
S303, the disease of patient and the social information of patient are calculated, obtains relationship characteristic vector.
Specifically, relationship characteristic vector is calculated according to the disease of patient and the social information of patient, under same
The process is described in detail in Wen Zhongzai, and details are not described herein.
Optionally, with reference to Fig. 4, to the essential information of patient, the state of an illness information of patient and the disease of patient are calculated,
Obtaining genius morbi vector includes:
S401, genius morbi is determined according to the disease of patient；
Specifically, corresponding genius morbi is also different for different diseases, these genius morbis are specially medical expert
By the representative feature that the medical practice of many years is summarized, these genius morbis can be one, or
It is multiple, it is no longer illustrated in embodiments of the present invention.
The disease of S402, the genius morbi range that disease progression crowd is obtained based on genius morbi and stable disease crowd are special
Levy range；
After obtaining genius morbi, it is based further on genius morbi and obtains corresponding disease progression human diseases characteristic range
With the genius morbi range of stable disease crowd.These ranges are also that expert obtains by the summary of experience of many years.Certainly, also
It may include the genius morbi range of disease improvement crowd, be also no longer illustrated here.
The genius morbi of the state of an illness information extraction patient of S403, the essential information based on patient and patient；
After obtaining the genius morbi range of genius morbi range and stable disease crowd of above-mentioned disease progression crowd,
Extract the genius morbi of patient.
S404, the genius morbi range in conjunction with disease progression crowd, the genius morbi range of stable disease crowd and trouble
The genius morbi of person determines Crowds Distribute belonging to patient；
After obtaining the genius morbi of patient, by the genius morbi range of the genius morbi of patient and disease progression crowd,
The genius morbi range of stable disease crowd matches, and determines Crowds Distribute belonging to patient.
S405, genius morbi vector is calculated based on Crowds Distribute belonging to patient.
Specifically, point patient belonging to after Crowds Distribute, it will be able to obtain genius morbi vector.Specifically, patient
Genius morbi in the genius morbi range of disease progression crowd, the position of the genius morbi range of stable disease crowd is different,
Obtained numerical value is not also identical, which is genius morbi vector.
Optionally, with reference to Fig. 5, the disease for the treatment of information and patient to patient is calculated, the feature that obtains medical treatment to
Amount includes:
S501, therapeutic scheme is determined according to the disease of patient, wherein include multiple treatment features in therapeutic scheme；
In embodiments of the present invention, therapeutic scheme is determined according to the disease of patient, includes multiple treatments spies in therapeutic scheme
Sign.
S502, the treatment feature for treating information extraction patient based on patient；
After the treatment feature for the scheme of obtaining medical treatment, the treatment feature of the treatment information extraction patient based on patient.Specifically
, treatment feature include at least: treatment time, therapeutic modality and with treatment-related other information.For example, therapeutic modality is
Drug therapy, then just including the species characteristic of drug, the dose characteristics of drug in treatment feature.
S503, the treatment feature of patient is matched with the treatment feature in therapeutic scheme；
After the treatment feature for the scheme that obtains medical treatment and the treatment feature of patient, by the treatment feature and therapeutic scheme of patient
In treatment feature matched.
S504, the treatment feature vector that patient is determined according to matching result.
Optionally, with reference to Fig. 6, the social information of disease and patient to patient is calculated, and obtains relationship characteristic vector
Include:
S601, the social information of the disease of patient and patient are associated with the foundation of historical relation map, wherein historical relation
Map is the relation map obtained according to historic patient medical information；
In embodiments of the present invention, historic patient medical information is stored in server, so, it is corresponding that there is also history
Relation map.After the social information of the disease and patient that obtain patient, those information are associated with the foundation of historical relation map.
For example, there are a user A, also having a user A in the social information of patient in historical relation map, just capable of establishing trouble
The disease of person, the social information of patient and being associated with for historical relation map.
S602, historical relation map is calculated by community discovery algorithm, obtains social groups belonging to patient；
Establish with after being associated with of historical relation map, by community discovery algorithm to the historical relation figure established after being associated with
Spectrum is calculated, and social groups belonging to patient are obtained.
S603, the weighted value that side in historical relation map is updated by the disease progression risk of social groups, are updated
Relation map afterwards, wherein the disease progression risk of social groups is to be obtained according to historic patient medical information；
The weighted value that side in historical relation map is updated by the disease progression risk of social groups, obtains updated pass
It is map.Wherein, known to the disease progression risk of social groups.
S604, updated relation map is calculated by Random Walk Algorithm and node2vector, obtains relationship
Feature vector.
After obtaining updated relation map, by Random Walk Algorithm and node2vector to updated relationship
Map is calculated, and relationship characteristic vector is obtained.
Why such calculating is carried out, be because some diseases are group's bursty natures, which (closes
It is feature vector) it is also required to account for.
The invention discloses a kind of knowledge mapping analysis method and device based on medical information, to unsupervised machine learning
The technological innovation of model is applied in medical data processing, by the essential information to patient, the state of an illness information of patient, patient's
Information is treated, the vectorization of the social information of patient calculates, disease progression machine learning model is constructed by K-MEANS algorithm,
Disease progression probability can be determined in real time, patient and medical staff are carried out to the disease event of patient deep
Solution improves cure rate to take effective therapeutic scheme in time.
Embodiment two:
A kind of knowledge mapping analytical equipment based on medical information, with reference to Fig. 7, which includes:
Module 11 is obtained, segments word included in patient medical information for obtaining, wherein patient medical information's packet
It includes: the essential information of patient, the state of an illness information of patient, the treatment information of patient, the social information of patient；
It is right to obtain participle word institute for analyzing based on default medical knowledge base participle word for analysis module 12
The target criteria medical data answered；
Matching module 13, for matching target criteria medical data with default disease knowledge map, wherein default
Disease knowledge map is the relevance map of various diseases factor associated therewith；
Determining module 14, for determining the disease of patient according to matching result；
Module 15 is constructed, the feature vector for the disease building patient based on patient medical information and patient, wherein special
Levying vector includes: genius morbi vector, treats feature vector, relationship characteristic vector；
Computing module 16 is obtained for carrying out deterioration probability calculation to feature vector by disease progression machine learning model
To the disease progression probability of patient, wherein disease progression machine learning model is by K-MEANS algorithm to a large amount of feature vectors
The model being trained.
It, can be according in patient medical information in the knowledge mapping analytical equipment based on medical information of the embodiment of the present invention
Participle word determine its corresponding target criteria medical data, then again by target criteria medical data and default disease knowledge
Map is matched, and the disease of patient is determined, after obtaining disease outcome, additionally it is possible to disease and patient medical based on patient
The feature vector of information architecture patient carries out feature vector eventually by disease progression machine learning model to deteriorate probability meter
It calculates, obtains the disease progression probability of patient.The device really considers patient medical information, and obtained disease outcome is more quasi-
Really, and the case where disease, can be predicted, obtains the probability of disease progression, alleviate the disease that existing method obtains
As a result accuracy is poor, and the technical issues of can not predict the case where disease.
Optionally, building module includes:
First computing unit, for the essential information to patient, the state of an illness information of patient and the disease of patient are counted
It calculates, obtains genius morbi vector；
Second computing unit, the disease for treatment information and patient to patient calculate, and obtain medical treatment feature
Vector；
Third computing unit, the social information for disease and patient to patient calculate, obtain relationship characteristic to
Amount.
Optionally, the first computing unit includes:
First determines subelement, for determining genius morbi according to the disease of patient；
Subelement is obtained, for obtaining genius morbi range and the stable disease people of disease progression crowd based on genius morbi
The genius morbi range of group；
First extracts subelement, and the disease of the state of an illness information extraction patient for essential information and patient based on patient is special
Sign；
Second determines subelement, for combining the genius morbi range of disease progression crowd, the disease of stable disease crowd
Characteristic range and the genius morbi of patient, determine Crowds Distribute belonging to patient；
First computation subunit, for calculating genius morbi vector based on Crowds Distribute belonging to patient.
Optionally, the second computing unit includes:
Third determines subelement, for determining therapeutic scheme according to the disease of patient, wherein comprising multiple in therapeutic scheme
Treat feature；
Second extracts subelement, the treatment feature for the treatment information extraction patient based on patient；
Coupling subelement, for matching the treatment feature of patient with the treatment feature in therapeutic scheme；
4th determines subelement, for determining the treatment feature vector of patient according to matching result.
Optionally, third computing unit includes:
Association subelement is established, is closed for establishing the social information of the disease of patient and patient and historical relation map
Connection, wherein historical relation map is the relation map obtained according to historic patient medical information；
Second computation subunit obtains patient institute for calculating by community discovery algorithm historical relation map
The social groups of category；
Subelement is updated, the weight on side in historical relation map is updated for the disease progression risk by social groups
Value, obtains updated relation map, wherein the disease progression risk of social groups is to be obtained according to historic patient medical information
's；
Third computation subunit, for by Random Walk Algorithm and node2vector to updated relation map into
Row calculates, and obtains relationship characteristic vector.
Optionally, analysis module includes:
First acquisition unit, for obtaining based on default medical knowledge base and segmenting candidate criteria medicine corresponding to word
Data；
Determination unit, between each standard medical data in the incidence relation and medical knowledge base according to participle word
Topological relation, from candidate criteria medical data determine target criteria medical data.
Optionally, device further include:
Recommending module, for being that patient recommends therapeutic regimen according to the disease progression probability of patient.
Optionally, obtaining module includes:
Second acquisition unit, for obtaining patient medical information；
Statistic unit, for the cluster probability using word and word in condition random field algorithm statistics patient medical information；
Participle unit obtains participle word for segmenting according to cluster probability to patient medical information.
Specifically describing in the embodiment two can be with reference to the detailed content in above-described embodiment one, and details are not described herein.
The computer program of knowledge mapping analysis method and device based on medical information provided by the embodiment of the present invention
Product, the computer readable storage medium including storing program code, the instruction that said program code includes can be used for executing
Previous methods method as described in the examples, specific implementation can be found in embodiment of the method, and details are not described herein.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description
It with the specific work process of device, can refer to corresponding processes in the foregoing method embodiment, details are not described herein.
In addition, in the description of the embodiment of the present invention unless specifically defined or limited otherwise, term " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected；It can
To be mechanical connection, it is also possible to be electrically connected；It can be directly connected, can also can be indirectly connected through an intermediary
Connection inside two elements.For the ordinary skill in the art, above-mentioned term can be understood at this with concrete condition
Concrete meaning in invention.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
In the description of the present invention, it should be noted that term " center ", "upper", "lower", "left", "right", "vertical",
The orientation or positional relationship of the instructions such as "horizontal", "inner", "outside" be based on the orientation or positional relationship shown in the drawings, merely to
Convenient for description the present invention and simplify description, rather than the device or element of indication or suggestion meaning must have a particular orientation,
It is constructed and operated in a specific orientation, therefore is not considered as limiting the invention.In addition, term " first ", " second ",
" third " is used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance.
Finally, it should be noted that embodiment described above, only a specific embodiment of the invention, to illustrate the present invention
Technical solution, rather than its limitations, scope of protection of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, those skilled in the art should understand that: anyone skilled in the art
In the technical scope disclosed by the present invention, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features；And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of technical solution of the embodiment of the present invention, should all cover in protection of the invention
Within the scope of.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (1)
1. a kind of knowledge mapping analytical equipment based on medical information, which is characterized in that described device includes:
Module is obtained, segments word included in patient medical information for obtaining, wherein patient medical information's packet
It includes: the essential information of patient, the state of an illness information of patient, the treatment information of patient, the social information of patient；
Analysis module obtains participle word institute for analyzing based on default medical knowledge base the participle word
Corresponding target criteria medical data；
Matching module, for matching the target criteria medical data with default disease knowledge map, wherein described pre-
If disease knowledge map is the relevance map of various diseases factor associated therewith；
Determining module, for determining the disease of the patient according to matching result；
Module is constructed, the feature vector of the patient is constructed for the disease based on the patient medical information and the patient,
Wherein, described eigenvector includes: genius morbi vector, treats feature vector, relationship characteristic vector；
Computing module is obtained for carrying out deterioration probability calculation to described eigenvector by disease progression machine learning model
The disease progression probability of the patient, wherein the disease progression machine learning model is by K-MEANS algorithm to a large amount of spies
The model that sign vector is trained；
Wherein, the building module includes:
First computing unit, for the essential information to the patient, the state of an illness information of the patient and the disease of the patient
Disease is calculated, and the genius morbi vector is obtained；
Second computing unit, the disease for treatment information and the patient to the patient calculate, and obtain described
Treat feature vector；
Third computing unit, the social information for disease and the patient to the patient calculate, and obtain the pass
It is feature vector；
First computing unit includes:
First determines subelement, for determining genius morbi according to the disease of patient；
Subelement is obtained, for obtaining genius morbi range and the stable disease crowd of disease progression crowd based on genius morbi
Genius morbi range；
First extracts subelement, the genius morbi of the state of an illness information extraction patient for essential information and patient based on patient；
Second determines subelement, for combining the genius morbi range of disease progression crowd, the genius morbi of stable disease crowd
The genius morbi of range and patient determine Crowds Distribute belonging to patient；
First computation subunit, for calculating genius morbi vector based on Crowds Distribute belonging to patient；
Second computing unit includes:
Third determines subelement, for determining therapeutic scheme according to the disease of patient, wherein includes multiple treatments in therapeutic scheme
Feature；
Second extracts subelement, the treatment feature for the treatment information extraction patient based on patient；
Coupling subelement, for matching the treatment feature of patient with the treatment feature in therapeutic scheme；
4th determines subelement, for determining the treatment feature vector of patient according to matching result；
The third computing unit includes:
Association subelement is established, for the social information of the disease of patient and patient to be associated with the foundation of historical relation map,
In, historical relation map is the relation map obtained according to historic patient medical information；
Second computation subunit obtains belonging to patient for being calculated by community discovery algorithm historical relation map
Social groups；
Subelement is updated, the weighted value on side in historical relation map is updated for the disease progression risk by social groups, is obtained
To updated relation map, wherein the disease progression risk of social groups is to be obtained according to historic patient medical information；
Third computation subunit, based on being carried out by Random Walk Algorithm and node2vector to updated relation map
It calculates, obtains relationship characteristic vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810413668.7A CN108614885B (en) | 2018-05-03 | 2018-05-03 | Knowledge mapping analysis method and device based on medical information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810413668.7A CN108614885B (en) | 2018-05-03 | 2018-05-03 | Knowledge mapping analysis method and device based on medical information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108614885A CN108614885A (en) | 2018-10-02 |
| CN108614885B true CN108614885B (en) | 2019-04-30 |
Family
ID=63661692
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810413668.7A Active CN108614885B (en) | 2018-05-03 | 2018-05-03 | Knowledge mapping analysis method and device based on medical information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108614885B (en) |
Families Citing this family (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109559820A (en) * | 2018-10-27 | 2019-04-02 | 平安医疗健康管理股份有限公司 | Coronary heart disease quality certification method, equipment and server based on data processing |
| CN109559822A (en) * | 2018-11-12 | 2019-04-02 | 平安科技（深圳）有限公司 | Intelligent first visit method, apparatus, computer equipment and storage medium |
| CN110147878B (en) * | 2018-11-28 | 2023-01-31 | 腾讯科技（深圳）有限公司 | Data processing method, device and equipment |
| CN109767842B (en) * | 2018-12-13 | 2023-08-22 | 平安科技（深圳）有限公司 | Disease early warning method, disease early warning device and computer readable storage medium |
| CN109616169B (en) * | 2018-12-24 | 2020-11-13 | 广州天鹏计算机科技有限公司 | Similar patient mining method, similar patient mining device, computer equipment and storage medium |
| WO2020132793A1 (en) * | 2018-12-24 | 2020-07-02 | Beijing Didi Infinity Technology And Development Co., Ltd. | Artificial intelligence medical symptom recognition system based on span searching |
| CN111383773B (en) * | 2018-12-28 | 2023-04-28 | 医渡云（北京）技术有限公司 | Medical entity information processing method and device, storage medium and electronic equipment |
| CN109887596A (en) * | 2019-02-18 | 2019-06-14 | 广州天鹏计算机科技有限公司 | Chronic obstructive disease of lung diagnostic method, device and the computer equipment of knowledge based map |
| CN109979589B (en) * | 2019-02-21 | 2023-04-25 | 歌尔科技有限公司 | Cure rate analysis method, cure rate analysis device and computer readable storage medium |
| CN110379507B (en) * | 2019-06-27 | 2023-03-14 | 南京市卫生信息中心 | Auxiliary diagnosis method based on patient vector image |
| CN110289101A (en) * | 2019-07-02 | 2019-09-27 | 京东方科技集团股份有限公司 | A kind of computer equipment, system and readable storage medium storing program for executing |
| CN110335676A (en) * | 2019-07-09 | 2019-10-15 | 泰康保险集团股份有限公司 | Data processing method, device, medium and electronic equipment |
| CN110675954A (en) * | 2019-10-11 | 2020-01-10 | 北京百度网讯科技有限公司 | Information processing method and device, electronic equipment and storage medium |
| CN111507827A (en) * | 2020-04-20 | 2020-08-07 | 上海商涌网络科技有限公司 | Health risk assessment method, terminal and computer storage medium |
| CN111816280A (en) * | 2020-07-10 | 2020-10-23 | 吾征智能技术(北京)有限公司 | Disease prediction model construction method and system based on eating behavior |
| CN111813874B (en) * | 2020-09-03 | 2023-09-15 | 中国传媒大学 | Terahertz knowledge graph construction method and system |
| CN112349423A (en) * | 2020-11-04 | 2021-02-09 | 吾征智能技术(北京)有限公司 | Stem of mouth information matching system based on BiMPM method |
| CN113160964A (en) * | 2020-12-31 | 2021-07-23 | 上海明品医学数据科技有限公司 | Intelligent medical brain model establishing system, method, service system and medium |
| CN112992317B (en) * | 2021-05-10 | 2021-11-02 | 明品云(北京)数据科技有限公司 | Medical data processing method, system, equipment and medium |
| CN113704555B (en) * | 2021-07-16 | 2023-11-07 | 杭州医康慧联科技股份有限公司 | Feature management method based on medical direction federal learning |
| CN113434626B (en) * | 2021-08-27 | 2021-12-07 | 之江实验室 | Multi-center medical diagnosis knowledge map representation learning method and system |
| CN114707615B (en) * | 2022-04-28 | 2023-07-25 | 吉林大学 | Ancient character similarity quantification method based on duration Chinese character knowledge graph |
| CN117838510A (en) * | 2024-03-08 | 2024-04-09 | 深圳市艾利特医疗科技有限公司 | External counterpulsation device and external counterpulsation signal control method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102971755A (en) * | 2010-01-21 | 2013-03-13 | 阿斯玛西格诺斯公司 | Early warning method and system for chronic disease management |
| CN102999686A (en) * | 2011-09-19 | 2013-03-27 | 上海煜策信息科技有限公司 | Health management system and implementation method thereof |
| CN107145744A (en) * | 2017-05-08 | 2017-09-08 | 合肥工业大学 | Construction method, device and the aided diagnosis method of medical knowledge collection of illustrative plates |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7774143B2 (en) * | 2002-04-25 | 2010-08-10 | The United States Of America As Represented By The Secretary, Department Of Health And Human Services | Methods for analyzing high dimensional data for classifying, diagnosing, prognosticating, and/or predicting diseases and other biological states |
| WO2005086068A2 (en) * | 2004-02-27 | 2005-09-15 | Aureon Laboratories, Inc. | Methods and systems for predicting occurrence of an event |
| CN102324001A (en) * | 2010-11-15 | 2012-01-18 | 上海聚类生物科技有限公司 | Method for predicting gastric cancer on the basis of high performance liquid chromatography/mass spectrometry (HPLC/MS) metabonomics data analysis |
| CN106874643B (en) * | 2016-12-27 | 2020-02-28 | 中国科学院自动化研究所 | Method and system for automatically constructing knowledge base to realize auxiliary diagnosis and treatment based on word vectors |
-
2018
- 2018-05-03 CN CN201810413668.7A patent/CN108614885B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102971755A (en) * | 2010-01-21 | 2013-03-13 | 阿斯玛西格诺斯公司 | Early warning method and system for chronic disease management |
| CN102999686A (en) * | 2011-09-19 | 2013-03-27 | 上海煜策信息科技有限公司 | Health management system and implementation method thereof |
| CN107145744A (en) * | 2017-05-08 | 2017-09-08 | 合肥工业大学 | Construction method, device and the aided diagnosis method of medical knowledge collection of illustrative plates |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108614885A (en) | 2018-10-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108614885B (en) | Knowledge mapping analysis method and device based on medical information | |
| CN110993081B (en) | Doctor online recommendation method and system | |
| CN106874643B (en) | Method and system for automatically constructing knowledge base to realize auxiliary diagnosis and treatment based on word vectors | |
| CN109670179A (en) | Case history text based on iteration expansion convolutional neural networks names entity recognition method | |
| US11670420B2 (en) | Drawing conclusions from free form texts with deep reinforcement learning | |
| CN110222201A (en) | A kind of disease that calls for specialized treatment knowledge mapping construction method and device | |
| CN108628824A (en) | A kind of entity recognition method based on Chinese electronic health record | |
| CN110675944A (en) | Triage method and device, computer equipment and medium | |
| CN106934235A (en) | Patient's similarity measurement migratory system between a kind of disease areas based on transfer learning | |
| CN108389614A (en) | The method for building medical image collection of illustrative plates based on image segmentation and convolutional neural networks | |
| CN109378066A (en) | A kind of control method and control device for realizing disease forecasting based on feature vector | |
| Ejegwa et al. | Intuitionistic fuzzzy sets in career determination | |
| Gharehchopogh et al. | Neural network application in diagnosis of patient: a case study | |
| CN109686441A (en) | A kind of big data medical data feature extraction and intellectual analysis prediction technique | |
| CN111048167A (en) | Hierarchical case structuring method and system | |
| CN110069779A (en) | The symptom entity recognition method and relevant apparatus of medical text | |
| CN110097975A (en) | A kind of nosocomial infection intelligent diagnosing method and system based on multi-model fusion | |
| CN116364299B (en) | Disease diagnosis and treatment path clustering method and system based on heterogeneous information network | |
| CN111191456B (en) | Method for identifying text segments by using sequence labels | |
| WO2020224433A1 (en) | Target object attribute prediction method based on machine learning and related device | |
| He et al. | A consensus reaching model for hesitant information with different preference structures | |
| Shen et al. | Constructing node embeddings for human phenotype ontology to assist phenotypic similarity measurement | |
| CN112071431B (en) | Clinical path automatic generation method and system based on deep learning and knowledge graph | |
| Abaho et al. | Detect and Classify--Joint Span Detection and Classification for Health Outcomes | |
| CN112259232A (en) | VTE risk automatic evaluation system based on deep learning |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230301 Address after: 311100 1-14, Floor 3-1, No. 999 (Angel Village), Jingxing Road, Cangqian Street, Yuhang District, Hangzhou City, Zhejiang Province Patentee after: Zhejiang Cognition Technology Co.,Ltd. Address before: Room 107, Building 1, No. 1818-2, Wenyi West Road, Yuhang District, Hangzhou City, Zhejiang Province, 310000 Patentee before: HANGZHOU RENSHI TECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240222 Address after: 215000 Suzhou Free Trade Zone Suzhou Area Suzhou Industrial Park, No. 88 Jinjihu Avenue, Artificial Intelligence Industrial Park G4-1101-007 Patentee after: Jiangsu Zhizhi Intelligent Technology Co.,Ltd. Country or region after: China Address before: 311100 1-14, Floor 3-1, No. 999 (Angel Village), Jingxing Road, Cangqian Street, Yuhang District, Hangzhou City, Zhejiang Province Patentee before: Zhejiang Cognition Technology Co.,Ltd. Country or region before: China |