CN108630312A - A kind of hypertension diagnosis rule base automatic generation method and device - Google Patents
A kind of hypertension diagnosis rule base automatic generation method and device Download PDFInfo
- Publication number
- CN108630312A CN108630312A CN201810449242.7A CN201810449242A CN108630312A CN 108630312 A CN108630312 A CN 108630312A CN 201810449242 A CN201810449242 A CN 201810449242A CN 108630312 A CN108630312 A CN 108630312A
- Authority
- CN
- China
- Prior art keywords
- data
- hypertension
- target user
- user data
- diagnosis rule
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—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
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The embodiment of the present invention discloses a kind of hypertension diagnosis rule base automatic generation method and device, wherein method includes：Target user data is obtained, target user data library is established based on acquired target user data；According to target user data library hypertension intelligent diagnostics model is built using XGBoost algorithms；It extracts hypertension diagnosis rule automatically from hypertension intelligent diagnostics model, generates hypertension diagnosis rule base.The embodiment of the present invention can automatically generate the high hypertension diagnosis rule base of accuracy rate of diagnosis, while this method for automatically generating hypertension diagnosis rule base using machine learning may replace artificial rule and arrange, and avoid human error.
Description
Technical field
The present embodiments relate to field of computer technology, and in particular to a kind of hypertension diagnosis rule base side of automatically generating
Method and device.
Background technology
Diagnosis rule base is used to store the diagnostic rule of disease, and diagnostic rule mainly describes performance and the feature of disease, table
Show the causality between disease and symptom.The diagnosis rule base of early stage is compiled according to the thought process tissue of clinician completely
Row, by generally arrive it is specific, from general character to individual character, with logicality.The foundation of usual diagnosis rule base needs to know using dedicated
Know processing language development environment to be developed, for example disease is realized using Visual (visualization) programming in logic development environment
It deducts, establish diagnosis rule base using Semantic Web rule language (SWRL), diagnostic reasoning is realized in conjunction with Jess inference engines
Deng.With universal and various Medical Equipments the application of medical information, medical data amount unprecedentedly increases, these data tool
There is the features such as missing, redundancy, do not know, it is very complicated according to doctors experience manual sorting diagnosis rule base, it takes time and effort, and advise
Generation then has certain artificial limitation, considers not enough the diversity of disease, variability and uncertain factor, may
Omit certain special rules.
The medical intelligent diagnosis system based on AI gradually demonstrated advantage, explored rank with the rise of artificial intelligence AI later stage
The AI machine learning algorithms that section uses are different, and there are commonly support vector machines, neural network, Bayesian models etc., but model is big
Part is the black-box operation for realizing intelligent diagnostics, and diagnostic rule lacks interpretation, can not generate diagnostic rule according to model
Library.A small number of methods by machine learning create-rule library is slightly short of on technical maturity and regular reasonability, practical
Accuracy rate of diagnosis is relatively low in, and there is also the larger rising spaces.
In consideration of it, how to automatically generate the high diagnosis rule base of accuracy rate of diagnosis using intelligent algorithm needs as current
Technical problems to be solved.
Invention content
Since existing method is there are the above problem, the embodiment of the present invention proposes that a kind of hypertension diagnosis rule base automatically generates
Method and device.
In a first aspect, the embodiment of the present invention proposes a kind of hypertension diagnosis rule base automatic generation method, including：
It obtains target user data and target user data library is established based on acquired target user data；
According to the target user data library hypertension intelligent diagnostics model is built using XGBoost algorithms；
It extracts hypertension diagnosis rule automatically from the hypertension intelligent diagnostics model, generates hypertension diagnosis rule
Library.
Optionally, the target user data includes at least：The essential information of target user, living habit data, the past
History data, clinical diagnosis data, inspection data and inspection data.
Optionally, based on acquired target user data, target user data library is established, including：
Data cleansing is carried out to the target user data of acquisition, retain the essential information of target user, living habit data,
Medical history data, clinical diagnosis data, inspection data and inspection data；
Based on the data retained after data cleansing, target user data library is established.
Optionally, it is extracting hypertension diagnosis rule automatically from the hypertension intelligent diagnostics model, is generating hypertension
After diagnosis rule base, the method further includes：
Update the data volume in the target user data library；
By the way of incremental learning, constructed hypertension intelligent diagnostics model is corrected；
It extracts hypertension diagnosis rule automatically from revised hypertension intelligent diagnostics model, generates updated high blood
Press diagnosis rule base.
Second aspect, the embodiment of the present invention also propose a kind of hypertension diagnosis rule base automatically generating device, including：
Module is established, for obtaining target user data, based on acquired target user data, establishes target user's number
According to library；
Module is built, for according to the target user data library, using XGBoost algorithms, structure hypertension intelligently to be examined
Disconnected model；
First generation module, it is raw for extracting hypertension diagnosis rule automatically from the hypertension intelligent diagnostics model
At hypertension diagnosis rule base.
Optionally, the target user data includes at least：The essential information of target user, living habit data, the past
History data, clinical diagnosis data, inspection data and inspection data.
Optionally, described to establish module, it is specifically used for
Target user data is obtained, data cleansing is carried out to the target user data of acquisition, retains the basic of target user
Information, living habit data, medical history data, clinical diagnosis data, inspection data and inspection data；
Based on the data retained after data cleansing, target user data library is established.
Optionally, described device further includes：
Update module, for updating the data volume in the target user data library；
Correcting module, for by the way of incremental learning, correcting constructed hypertension intelligent diagnostics model；
Second generation module, for extracting hypertension diagnosis rule automatically from revised hypertension intelligent diagnostics model
Then, updated hypertension diagnosis rule base is generated.
The third aspect, the embodiment of the present invention also propose a kind of electronic equipment, including：Processor, memory, bus and storage
On a memory and the computer program that can run on a processor；
Wherein, the processor, memory complete mutual communication by the bus；
The processor realizes the above method when executing the computer program.
Fourth aspect, the embodiment of the present invention provide a kind of non-transient computer readable storage medium, the non-transient calculating
It is stored with computer program on machine readable storage medium storing program for executing, which realizes the above method when being executed by processor.
As shown from the above technical solution, a kind of hypertension diagnosis rule base automatic generation method provided in an embodiment of the present invention
And device, target user data library is established by the target user data based on acquisition, according to target user data library, is utilized
XGBoost algorithms build hypertension intelligent diagnostics model, extract hypertension diagnosis rule automatically from hypertension intelligent diagnostics model
Then, hypertension diagnosis rule base is generated, thereby, it is possible to automatically generate the high hypertension diagnosis rule base of accuracy rate of diagnosis, simultaneously
This method for automatically generating hypertension diagnosis rule base using machine learning may replace artificial rule and arrange, and avoid artificially accidentally
Difference.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Other attached drawings are obtained according to these figures.
Fig. 1 is a kind of flow signal for hypertension diagnosis rule base automatic generation method that one embodiment of the invention provides
Figure；
Fig. 2 is a kind of structural representation for hypertension diagnosis rule base automatically generating device that one embodiment of the invention provides
Figure；
Fig. 3 is the entity structure schematic diagram for the electronic equipment that one embodiment of the invention provides.
Specific implementation mode
Below in conjunction with the accompanying drawings, the specific implementation mode of the present invention is further described.Following embodiment is only used for more
Technical scheme of the present invention is clearly demonstrated, and not intended to limit the protection scope of the present invention.
Fig. 1 shows that a kind of flow for hypertension diagnosis rule base automatic generation method that one embodiment of the invention provides is shown
It is intended to, as shown in Figure 1, the hypertension diagnosis rule base automatic generation method of the present embodiment, including：
S1, acquisition target user data establish target user data library based on acquired target user data.
Wherein, the target user data includes at least：Essential information, living habit data, the previously disease of target user
History data, clinical diagnosis data, inspection data and inspection data.
Specifically, for example, the essential information may include：Gender and age etc., the present embodiment not to its into
Row limitation, also can include other essential informations of target user according to actual conditions.
Specifically, for example, the living habit data may include：Whether smoke/drinking/living habits such as temper
Data, the present embodiment is not limited, and also can include other living habits of target user according to actual conditions
Data.
Specifically, for example, the medical history data may include：It is diabetes, myocardial infarction, angina pectoris, primary
The data of the property medical histories such as aldosteronism and/or Cushing syndrome, the present embodiment are not limited, can basis
Actual conditions include the data of all medical histories of target user.
Specifically, for example, the clinical diagnosis data may include：Essential hypertension, secondary hypertension etc.
Clinical diagnosis data, the present embodiment are not limited.
Specifically, for example, the inspection data may include：Blood routine examination, routine urinalysis are examined, hepatic and renal function is examined
Test, myocardium protein examine etc., the present embodiment is not limited, also can include according to actual conditions target user other
Inspection data.
Specifically, for example, the inspection data may include：Systolic pressure, diastolic pressure, sickly look, gait, blood vessel are miscellaneous
Sound, arteriopalmus etc. check data, and the present embodiment is not limited, and also can include target user's according to actual conditions
Other check data.
S2, hypertension intelligent diagnostics model is built using XGBoost algorithms according to the target user data library.
S3, it extracts hypertension diagnosis rule automatically from the hypertension intelligent diagnostics model, generates hypertension diagnosis rule
Then library.
It is understood that XGBoost algorithms are the algorithms being improved based on GBDT (gradient boosted tree) principle, it is mesh
Preceding most fast best boosted tree (boosted tree) algorithms are, it can be achieved that concurrent operation and incremental learning, precision is fast at high speed, originally
Embodiment can be according to the target user data library, and using XGBoost algorithms, the hypertension of rapid build high-accuracy is intelligently examined
Disconnected model, and then extract hypertension diagnosis rule automatically from the hypertension intelligent diagnostics model, it is accurate to automatically generate diagnosis
The high hypertension diagnosis rule base of rate.
The hypertension diagnosis rule base automatic generation method of the present embodiment is established by the target user data based on acquisition
Target user data library builds hypertension intelligent diagnostics model, from height according to target user data library using XGBoost algorithms
Automatically hypertension diagnosis rule is extracted in blood pressure intelligent diagnostics model, generates hypertension diagnosis rule base, thereby, it is possible to give birth to automatically
It can effectively reduce and fail to pinpoint a disease in diagnosis when hypertension diagnosis rule base at the high hypertension diagnosis rule base of accuracy rate of diagnosis, described in later use
Rate, misdiagnosis rate and standardization diagnosis and treatment process, while this side that hypertension diagnosis rule base is automatically generated using machine learning
Method may replace artificial rule and arrange, and avoid human error.
Further, on the basis of the above embodiments, in the step S1 " based on acquired target user's number
According to establishing target user data library ", may include：
Data cleansing is carried out to the target user data of acquisition, retain the essential information of target user, living habit data,
Medical history data, clinical diagnosis data, inspection data and inspection data；
Based on the data retained after data cleansing, target user data library is established.
It is understood that carrying out data cleansing by the target user data to acquisition, it is possible to reduce the mesh established
The data volume in customer data base is marked, and then improves the speed for generating hypertension diagnosis rule base and accuracy.
Further, in a particular application, for example, data set target variable be whether be secondary hypertension (its
In, 1 indicates it is secondary hypertension, and 0 indicates essential hypertension), independent variable is the essential information of target user, life habit
Used, medical history, inspection data, inspection data etc., the important parameter configuration of XGBoost algorithms：Maximum decision tree quantity=
2000；Learning rate=0.15；Maximum rule layer depth=6；Minimum value=0 Gain reached needed for decision tree growth；Decision tree is multiple
Miscellaneous degree parameter of measurement=1；Sample proportion=8 of learning machine and inference machine:2, the step S2 is according to the target user data
Library, using XGBoost algorithms, the process of structure hypertension intelligent diagnostics model may include：
Extract input data set from the target user data library, by input data set be divided into learning machine data set with
Inference machine data set, division proportion=8:2；
Wherein, learning machine implementation process is as follows：
Step 1: input learning machine data set；
Step 2: objective function (including loss+regularization term)；
Wherein, the error (gradient) of loss=upper tree；The complexity of regularization term=tree.
In particular it is required that optimization object function, keeps object function prediction error as small as possible, several complexities are as far as possible
It is low.
Step 3: carrying out cut-off lookup using greedy method, decision tree is built；
Specifically, all different tree constructions can be enumerated, choose Gain (gain) value maximum and the scheme more than threshold value, such as
Fruit max (Gain) is less than threshold value, and then beta pruning terminates division.
Step 4: after decision tree structure determines, the score of leafy node is calculated；
Step 5: update decision tree sequence, preserves all decision trees built and its score；
Step 6: calculate the prediction result of each sample, i.e. the sum of the score of each tree obtains sample and belongs to each classification
Probability；
Step 7: calculating the importance score of each variable, select influences significant significant variable to model；
Specifically, can calculate Gini (Geordie) coefficient of each variable, the i.e. variable of Gini coefficients average value it is important
Property score.
Step 8: building hypertension intelligent diagnostics model using significant variable.
Correspondingly, the step S3 extracts hypertension diagnosis rule automatically from the hypertension intelligent diagnostics model, raw
Detailed process at hypertension diagnosis rule base may include：
According to the decision tree sequence in the hypertension intelligent diagnostics model, extracts all leafy node scores and be more than 0
Hypertension diagnosis sequence of rules simultaneously sorts according to score, removes all identical recurring rule of conditions for diagnostics, generates hypertension diagnosis
Rule base.
On the basis of above-mentioned learning machine implementation process, inference machine implementation process is as follows：
Step P1, inference machine data set and decision tree sequence are inputted；
Step P2, according to sample information successively from decision tree sequence each tree root node gradually to leafy node into
Row logic judgment judges that the sample belongs to left/right child node, if it is leafy node, then calculates leaf if not leafy node
Child node score simultaneously inputs next decision tree and is judged；
Step P3, the predicted value for providing all decision trees sums it up, and obtains the probability that the sample value is 1；
Step P4, judge that the final generic of the sample, threshold function table f (x) are as follows according to threshold function table：
Wherein, ctrueFor predetermined threshold value, for example, c can be takentrue=0.5.
The present embodiment utilize XGBoost algorithms, can solve medical data concentrate there are missing values, exceptional value etc. it is various often
See problem, random data can be handled, each node is optimized, can effectively be handled more on less node
Big data set is, it can be achieved that single machine parallel computation, calculating speed promotion, are conducive to large-scale promotion application, with deep learning mould
Type is compared, and the interpretation of model is stronger, is easy to adjust ginseng, can be further due to having both the ability of autonomous learning and incremental learning
Improve model accuracy.
Further, on the basis of the above embodiments, after the step S3, the present embodiment the method can be with
Include the steps that being not shown in figure：
Update the data volume in the target user data library；
By the way of incremental learning, constructed hypertension intelligent diagnostics model is corrected；
It extracts hypertension diagnosis rule automatically from revised hypertension intelligent diagnostics model, generates updated high blood
Press diagnosis rule base.
Specifically, preset quantity (such as 10%-30%) can be randomly selected from updated target user data library
Sample data, substitute into the hypertension intelligent diagnostics model that has built；Based on existing decision tree sequence, recalculate every
The Gain values of each variable on a node readjust division scheme, choose Gain value maximum schemes into line splitting, if at this time
The Gain values of all variables are respectively less than threshold value, then carry out beta pruning, if there are the division sides that Gain values are more than threshold value for leafy node
Case then continues to divide；According to updated decision tree sequence, extracts hypertension diagnosis of all leafy node scores more than 0 and advise
It then sequence and sorts according to score, removes all identical recurring rule of conditions for diagnostics, realize automatically updating for diagnosis rule base.
It is understood that after being updated to hypertension diagnosis rule base, the higher height of accuracy rate of diagnosis can be obtained
Blood pressure diagnosis rule base can more efficiently reduce rate of missed diagnosis, mistaken diagnosis described in later use when hypertension diagnosis rule base
Rate and standardization diagnosis and treatment process.
The hypertension diagnosis rule base automatic generation method of the present embodiment, can be realized by processor, can be given birth to automatically
It can effectively reduce and fail to pinpoint a disease in diagnosis when hypertension diagnosis rule base at the high hypertension diagnosis rule base of accuracy rate of diagnosis, described in later use
Rate, misdiagnosis rate and standardization diagnosis and treatment process, while this side that hypertension diagnosis rule base is automatically generated using machine learning
Method may replace artificial rule and arrange, and avoid human error.
Fig. 2 shows a kind of structures of hypertension diagnosis rule base automatically generating device of one embodiment of the invention offer to show
It is intended to, as shown in Fig. 2, the hypertension diagnosis rule base automatically generating device of the present embodiment, including：Establish module 21, structure mould
Block 22 and the first generation module 23；Wherein：
It is described to establish module 21, for obtaining target user data, based on acquired target user data, establish target
Customer data base；
The structure module 22, for building hypertension using XGBoost algorithms according to the target user data library
Intelligent diagnostics model；
First generation module 23, for extracting hypertension diagnosis rule automatically from the hypertension intelligent diagnostics model
Then, hypertension diagnosis rule base is generated.
Specifically, the acquisition target user data of module 21 of establishing establishes mesh based on acquired target user data
Mark customer data base；The structure module 22 builds hypertension according to the target user data library using XGBoost algorithms
Intelligent diagnostics model；First generation module 23 extracts hypertension diagnosis rule automatically from the hypertension intelligent diagnostics model
Then, hypertension diagnosis rule base is generated.
Wherein, the target user data includes at least：Essential information, living habit data, the previously disease of target user
History data, clinical diagnosis data, inspection data and inspection data.
Specifically, for example, the essential information may include：Gender and age etc., the present embodiment not to its into
Row limitation, also can include other essential informations of target user according to actual conditions.
Specifically, for example, the living habit data may include：Whether smoke/drinking/living habits such as temper
Data, the present embodiment is not limited, and also can include other living habits of target user according to actual conditions
Data.
Specifically, for example, the medical history data may include：It is diabetes, myocardial infarction, angina pectoris, primary
The data of the property medical histories such as aldosteronism and/or Cushing syndrome, the present embodiment are not limited, can basis
Actual conditions include the data of all medical histories of target user.
Specifically, for example, the clinical diagnosis data may include：Essential hypertension, secondary hypertension etc.
Clinical diagnosis data, the present embodiment are not limited.
Specifically, for example, the inspection data may include：Blood routine examination, routine urinalysis are examined, hepatic and renal function is examined
Test, myocardium protein examine etc., the present embodiment is not limited, also can include according to actual conditions target user other
Inspection data.
Specifically, for example, the inspection data may include：Systolic pressure, diastolic pressure, sickly look, gait, blood vessel are miscellaneous
Sound, arteriopalmus etc. check data, and the present embodiment is not limited, and also can include target user's according to actual conditions
Other check data.
It is understood that XGBoost algorithms are the algorithms being improved based on GBDT (gradient boosted tree) principle, it is mesh
Preceding most fast best boosted tree (boosted tree) algorithms are, it can be achieved that concurrent operation and incremental learning, precision is fast at high speed, originally
Embodiment can be according to the target user data library, and using XGBoost algorithms, the hypertension of rapid build high-accuracy is intelligently examined
Disconnected model, and then extract hypertension diagnosis rule automatically from the hypertension intelligent diagnostics model, it is accurate to automatically generate diagnosis
The high hypertension diagnosis rule base of rate.
The hypertension diagnosis rule base automatically generating device of the present embodiment can automatically generate the high high blood of accuracy rate of diagnosis
Diagnosis rule base is pressed, can effectively reduce rate of missed diagnosis, misdiagnosis rate and standardization when hypertension diagnosis rule base described in later use
Diagnosis and treatment process, while to may replace artificial rule whole for this method for automatically generating hypertension diagnosis rule base using machine learning
Reason, avoids human error.
Further, on the basis of the above embodiments, described to establish module 21, it can be specifically used for
Target user data is obtained, data cleansing is carried out to the target user data of acquisition, retains the basic of target user
Information, living habit data, medical history data, clinical diagnosis data, inspection data and inspection data；
Based on the data retained after data cleansing, target user data library is established.
It is understood that carrying out data cleansing by the target user data to acquisition, it is possible to reduce the mesh established
The data volume in customer data base is marked, and then improves the speed for generating hypertension diagnosis rule base and accuracy.
In a particular application, the structure module 22 utilizes XGBoost algorithms, structure according to the target user data library
Above method embodiment can be referred to by building the process of hypertension intelligent diagnostics model.
The present embodiment described device utilizes XGBoost algorithms, and capable of solving medical data concentration, there are missing values, exceptional values
Etc. various FAQs, random data can be handled, each node is optimized, it can be effectively in less node
The data set of upper processing bigger is, it can be achieved that single machine parallel computation, calculating speed promotion, are conducive to large-scale promotion application, with depth
Degree learning model is compared, and the interpretation of model is stronger, is easy to adjust ginseng, due to having both the ability of autonomous learning and incremental learning,
It can further improve model accuracy.
Further, on the basis of the above embodiments, the present embodiment described device can also include not shown in the figure：
Update module, for updating the data volume in the target user data library；
Correcting module, for by the way of incremental learning, correcting constructed hypertension intelligent diagnostics model；
Second generation module, for extracting hypertension diagnosis rule automatically from revised hypertension intelligent diagnostics model
Then, updated hypertension diagnosis rule base is generated.
It is understood that after being updated to hypertension diagnosis rule base, the higher height of accuracy rate of diagnosis can be obtained
Blood pressure diagnosis rule base can more efficiently reduce rate of missed diagnosis, mistaken diagnosis described in later use when hypertension diagnosis rule base
Rate and standardization diagnosis and treatment process.
The hypertension diagnosis rule base automatically generating device of the present embodiment, can be applied in processor, can automatically generate
Accuracy rate of diagnosis high hypertension diagnosis rule base can be reduced effectively described in later use when hypertension diagnosis rule base and be failed to pinpoint a disease in diagnosis
Rate, misdiagnosis rate and standardization diagnosis and treatment process, while this side that hypertension diagnosis rule base is automatically generated using machine learning
Method may replace artificial rule and arrange, and avoid human error.
The hypertension diagnosis rule base automatically generating device of the present embodiment can be used for executing the skill of preceding method embodiment
Art scheme, implementing principle and technical effect are similar, and details are not described herein again.
Fig. 3 shows the entity structure schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention, as shown in figure 3, should
Electronic equipment may include：It processor 31, memory 32, bus 33 and is stored on memory 32 and can be transported on processor 31
Capable computer program；
Wherein, the processor 31, memory 32 complete mutual communication by the bus 33；
The processor 31 realizes the method that above-mentioned each method embodiment is provided when executing the computer program, such as
Including：It obtains target user data and target user data library is established based on acquired target user data；According to the mesh
Customer data base is marked, using XGBoost algorithms, builds hypertension intelligent diagnostics model；From the hypertension intelligent diagnostics model
In extract automatically hypertension diagnosis rule, generate hypertension diagnosis rule base.
The embodiment of the present invention provides a kind of non-transient computer readable storage medium, is stored thereon with computer program, should
Realize the method that above-mentioned each method embodiment is provided when computer program is executed by processor, such as including：Target is obtained to use
User data establishes target user data library based on acquired target user data；According to the target user data library, profit
With XGBoost algorithms, hypertension intelligent diagnostics model is built；Hypertension is extracted automatically from the hypertension intelligent diagnostics model
Diagnostic rule generates hypertension diagnosis rule base.
It should be understood by those skilled in the art that, embodiments herein can be provided as method, apparatus or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, the application can be used in one or more wherein include computer usable program code computer
The computer program production implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The application be with reference to according to the method, apparatus of the embodiment of the present application and the flow chart of computer program product and/or
Block diagram describes.It should be understood that each flow that can be realized by computer program instructions in flowchart and/or the block diagram and/or
The combination of flow and/or box in box and flowchart and/or the block diagram.These computer program instructions can be provided to arrive
All-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices processor to generate one
Machine so that the instruction executed by computer or the processor of other programmable data processing devices generates flowing
The device/system for the function of being specified in one flow of journey figure or multiple flows and/or one box of block diagram or multiple boxes.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that instruction generation stored in the computer readable memory includes referring to
Enable the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one box of block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device so that count
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, in computer or
The instruction executed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in a box or multiple boxes.
It should be noted that herein, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also include other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.The fingers such as term "upper", "lower"
The orientation or positional relationship shown is to be based on the orientation or positional relationship shown in the drawings, and is merely for convenience of the description present invention and simplifies
Description, does not indicate or imply the indicated device or element must have a particular orientation, with specific azimuth configuration and behaviour
Make, therefore is not considered as limiting the invention.Unless otherwise clearly defined and limited, term " installation ", " connected ",
" 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；Can be
Mechanical connection can also be electrical connection；It can be directly connected, can also can be indirectly connected through an intermediary two
Connection inside element.For the ordinary skill in the art, above-mentioned term can be understood at this as the case may be
Concrete meaning in invention.
In the specification of the present invention, numerous specific details are set forth.Although it is understood that the embodiment of the present invention can
To put into practice without these specific details.In some instances, well known method, structure and skill is not been shown in detail
Art, so as not to obscure the understanding of this description.Similarly, it should be understood that disclose in order to simplify the present invention and helps to understand respectively
One or more of a inventive aspect, in the above description of the exemplary embodiment of the present invention, each spy of the invention
Sign is grouped together into sometimes in single embodiment, figure or descriptions thereof.However, should not be by the method solution of the disclosure
It releases and is intended in reflection is following：The feature that i.e. the claimed invention requirement ratio is expressly recited in each claim is more
More features.More precisely, as the following claims reflect, inventive aspect is to be less than single reality disclosed above
Apply all features of example.Therefore, it then follows thus claims of specific implementation mode are expressly incorporated in the specific implementation mode,
Wherein each claim itself is as a separate embodiment of the present invention.It should be noted that in the absence of conflict, this
The feature in embodiment and embodiment in application can be combined with each other.The invention is not limited in any single aspect,
It is not limited to any single embodiment, is also not limited to the arbitrary combination and/or displacement of these aspects and/or embodiment.And
And can be used alone of the invention each aspect and/or embodiment or with other one or more aspects and/or its implement
Example is used in combination.
Finally it should be noted that：The above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Present invention has been described in detail with reference to the aforementioned embodiments for pipe, it will be understood by those of ordinary skill in the art that：Its according to
So can with technical scheme described in the above embodiments is modified, either to which part or all technical features into
Row equivalent replacement；And these modifications or replacements, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme should all cover in the claim of the present invention and the range of specification.
Claims (10)
1. a kind of hypertension diagnosis rule base automatic generation method, which is characterized in that including：
It obtains target user data and target user data library is established based on acquired target user data；
According to the target user data library hypertension intelligent diagnostics model is built using XGBoost algorithms；
It extracts hypertension diagnosis rule automatically from the hypertension intelligent diagnostics model, generates hypertension diagnosis rule base.
2. according to the method described in claim 1, it is characterized in that, the target user data includes at least：Target user's
Essential information, living habit data, medical history data, clinical diagnosis data, inspection data and inspection data.
3. according to the method described in claim 2, it is characterized in that, based on acquired target user data, target use is established
User data library, including：
Data cleansing is carried out to the target user data of acquisition, retains the essential information, living habit data, the past of target user
History data, clinical diagnosis data, inspection data and inspection data；
Based on the data retained after data cleansing, target user data library is established.
4. according to the method described in claim 1, it is characterized in that, being extracted automatically from the hypertension intelligent diagnostics model
Hypertension diagnosis rule, after generating hypertension diagnosis rule base, the method further includes：
Update the data volume in the target user data library；
By the way of incremental learning, constructed hypertension intelligent diagnostics model is corrected；
It extracts hypertension diagnosis rule automatically from revised hypertension intelligent diagnostics model, generates updated hypertension and examine
Disconnected rule base.
5. a kind of hypertension diagnosis rule base automatically generating device, which is characterized in that including：
Module is established, for obtaining target user data, based on acquired target user data, establishes target user data
Library；
Module is built, for building hypertension intelligent diagnostics mould using XGBoost algorithms according to the target user data library
Type；
First generation module generates high for extracting hypertension diagnosis rule automatically from the hypertension intelligent diagnostics model
Blood pressure diagnosis rule base.
6. device according to claim 5, which is characterized in that the target user data includes at least：Target user's
Essential information, living habit data, medical history data, clinical diagnosis data, inspection data and inspection data.
7. device according to claim 6, which is characterized in that it is described to establish module, it is specifically used for
Obtain target user data, data cleansing carried out to the target user data of acquisition, retain target user essential information,
Living habit data, medical history data, clinical diagnosis data, inspection data and inspection data；
Based on the data retained after data cleansing, target user data library is established.
8. device according to claim 5, which is characterized in that described device further includes：
Update module, for updating the data volume in the target user data library；
Correcting module, for by the way of incremental learning, correcting constructed hypertension intelligent diagnostics model；
Second generation module, it is raw for extracting hypertension diagnosis rule automatically from revised hypertension intelligent diagnostics model
At updated hypertension diagnosis rule base.
9. a kind of electronic equipment, which is characterized in that including：Processor, memory, bus and storage on a memory and can located
The computer program run on reason device；
Wherein, the processor, memory complete mutual communication by the bus；
The processor realizes the method as described in any one of claim 1-4 when executing the computer program.
10. a kind of non-transient computer readable storage medium, which is characterized in that in the non-transient computer readable storage medium
It is stored with computer program, the side as described in any one of claim 1-4 is realized when which is executed by processor
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810449242.7A CN108630312A (en) | 2018-05-11 | 2018-05-11 | A kind of hypertension diagnosis rule base automatic generation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810449242.7A CN108630312A (en) | 2018-05-11 | 2018-05-11 | A kind of hypertension diagnosis rule base automatic generation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108630312A true CN108630312A (en) | 2018-10-09 |
Family
ID=63692662
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810449242.7A Pending CN108630312A (en) | 2018-05-11 | 2018-05-11 | A kind of hypertension diagnosis rule base automatic generation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108630312A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109359850A (en) * | 2018-10-10 | 2019-02-19 | 大连诺道认知医学技术有限公司 | A kind of method and device generating risk assessment scale |
| CN109493966A (en) * | 2018-10-27 | 2019-03-19 | 平安医疗健康管理股份有限公司 | A kind of hypertension authentication method and relevant device based on data processing |
| CN109599179A (en) * | 2018-11-30 | 2019-04-09 | 平安医疗健康管理股份有限公司 | Peritoneal dialysis manages method, apparatus, equipment and storage medium |
| CN110111886A (en) * | 2019-05-16 | 2019-08-09 | 闻康集团股份有限公司 | A kind of intelligent interrogation system and method based on XGBoost disease forecasting |
| CN111176623A (en) * | 2019-12-31 | 2020-05-19 | 中山大学 | C + + abstract information recovery method based on graph convolution neural network |
| CN113470774A (en) * | 2021-07-15 | 2021-10-01 | 杭州康晟健康管理咨询有限公司 | Chronic disease archive management system based on big data |
| CN115099355A (en) * | 2022-07-08 | 2022-09-23 | 中山大学孙逸仙纪念医院 | XGboost algorithm-based vertigo cause diagnosis model construction method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101485569A (en) * | 2008-09-26 | 2009-07-22 | 厦门大学 | Traditional Chinese medicine multifunctional intelligent diagnostic apparatus based on self-adapting fuzzy logic |
| CN102354283A (en) * | 2011-09-20 | 2012-02-15 | 天津智康医疗科技有限公司 | Method for constructing rule base and method for checking data by utilizing rule base |
| CN107066791A (en) * | 2016-12-19 | 2017-08-18 | 银江股份有限公司 | A kind of aided disease diagnosis method based on patient's assay |
| CN107835201A (en) * | 2017-12-14 | 2018-03-23 | 华中师范大学 | Network attack detecting method and device |
-
2018
- 2018-05-11 CN CN201810449242.7A patent/CN108630312A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101485569A (en) * | 2008-09-26 | 2009-07-22 | 厦门大学 | Traditional Chinese medicine multifunctional intelligent diagnostic apparatus based on self-adapting fuzzy logic |
| CN102354283A (en) * | 2011-09-20 | 2012-02-15 | 天津智康医疗科技有限公司 | Method for constructing rule base and method for checking data by utilizing rule base |
| CN107066791A (en) * | 2016-12-19 | 2017-08-18 | 银江股份有限公司 | A kind of aided disease diagnosis method based on patient's assay |
| CN107835201A (en) * | 2017-12-14 | 2018-03-23 | 华中师范大学 | Network attack detecting method and device |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109359850A (en) * | 2018-10-10 | 2019-02-19 | 大连诺道认知医学技术有限公司 | A kind of method and device generating risk assessment scale |
| CN109493966A (en) * | 2018-10-27 | 2019-03-19 | 平安医疗健康管理股份有限公司 | A kind of hypertension authentication method and relevant device based on data processing |
| CN109599179A (en) * | 2018-11-30 | 2019-04-09 | 平安医疗健康管理股份有限公司 | Peritoneal dialysis manages method, apparatus, equipment and storage medium |
| CN109599179B (en) * | 2018-11-30 | 2022-09-23 | 深圳平安医疗健康科技服务有限公司 | Peritoneal dialysis management method, device, equipment and storage medium |
| CN110111886A (en) * | 2019-05-16 | 2019-08-09 | 闻康集团股份有限公司 | A kind of intelligent interrogation system and method based on XGBoost disease forecasting |
| CN111176623A (en) * | 2019-12-31 | 2020-05-19 | 中山大学 | C + + abstract information recovery method based on graph convolution neural network |
| CN113470774A (en) * | 2021-07-15 | 2021-10-01 | 杭州康晟健康管理咨询有限公司 | Chronic disease archive management system based on big data |
| CN115099355A (en) * | 2022-07-08 | 2022-09-23 | 中山大学孙逸仙纪念医院 | XGboost algorithm-based vertigo cause diagnosis model construction method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108630312A (en) | A kind of hypertension diagnosis rule base automatic generation method and device | |
| Akter et al. | Comprehensive performance assessment of deep learning models in early prediction and risk identification of chronic kidney disease | |
| Patil | Causal representation of patient illness for electrolyte and acid-base diagnosis | |
| US9672326B2 (en) | Determining disease state of a patient by mapping a topological module representing the disease, and using a weighted average of node data | |
| US9558324B2 (en) | Artificial general intelligence system/medical reasoning system (MRS) for determining a disease state using graphs | |
| JP2018067266A (en) | Program for forecasting onset risk or recurrence risk of disease | |
| CN117877763A (en) | Communication system and method for nursing based on intelligent wristband | |
| Du et al. | The effects of deep network topology on mortality prediction | |
| EP3874514A2 (en) | Patient treatment resource utilization predictor | |
| CN111897857A (en) | ICU (intensive care unit) duration prediction method after aortic dissection cardiac surgery | |
| CN118280579A (en) | Sepsis patient condition assessment method and system based on multi-mode data fusion | |
| Rana et al. | Comparative Study of Supervised Machine Learning Methods for Prediction of Heart Disease | |
| CN115547502B (en) | Hemodialysis patient risk prediction device based on time sequence data | |
| US20220083720A1 (en) | Electrical circuit design | |
| Kuperwajs et al. | Heuristics for meta-planning from a normative model of information search | |
| US9881134B2 (en) | Artificial general intelligence method for determining a disease state using a general graph and an individualized graph | |
| CN114330859A (en) | Optimization method, system and equipment for real-time quality control | |
| Wu et al. | OA-MedSQL: Order-Aware Medical Sequence Learning for Clinical Outcome Prediction | |
| JPH064292A (en) | Decision rule generating device | |
| Pavlič et al. | NiaNet: A framework for constructing Autoencoder architectures using nature-inspired algorithms | |
| EP4235683A1 (en) | Health improvement path search device and health improvement path search method | |
| Muyama et al. | Step-by-Step Guidance to Differential Anemia Diagnosis with Real-World Data and Deep Reinforcement Learning | |
| CN114091671B (en) | Disease risk prediction method for improving random forest similarity measurement | |
| KR102559883B1 (en) | Dosage Strategy Generation Method Using Markov Decision Process | |
| CN110211701B (en) | Model generation method, data processing method and corresponding device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181009 |
|
| RJ01 | Rejection of invention patent application after publication |