CN110148440A - A kind of medical information querying method - Google Patents
A kind of medical information querying method Download PDFInfo
- Publication number
- CN110148440A CN110148440A CN201910249835.3A CN201910249835A CN110148440A CN 110148440 A CN110148440 A CN 110148440A CN 201910249835 A CN201910249835 A CN 201910249835A CN 110148440 A CN110148440 A CN 110148440A
- Authority
- CN
- China
- Prior art keywords
- data
- model
- medical
- information
- analysis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
-
- 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
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Educational Administration (AREA)
- Biomedical Technology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present embodiments relate to a kind of medical information querying methods, comprising: obtains medical data；Establish platform data warehouse；Data pick-up, conversion and load are carried out to the medical data in platform data warehouse, obtain business intelligence data library；The Data Analysis Model of various dimensions is established according to the first business dimension of medical platform and the first index dimension, also, the data mining model of various dimensions is established according to the second business dimension of medical platform and the second index dimension；Repeatedly training, test and evaluation are carried out to the data model of various dimensions；Receive the query condition information of the medical information of user's input；Querying condition is parsed, key word information is obtained；Corresponding data model is called according to the model information to match；Call corresponding medical data；By medical data input data model, data model carries out data analysis to medical data, to obtain output result；Output result is shown according to the default form of expression.
Description
Technical field
The present invention relates to data processing field more particularly to a kind of medical information querying methods.
Background technique
In recent years, with the continuous development of medical technology, medical data is increased rapidly, the analysis based on medical big data
And decision support also comes into vogue.Traditional Hospital medical business is mainly by each management system such as HIS, LIS, PACS
Be supported and operate, at the same these management systems can medical profession data to hospital carry out simple query statistic.But
As the scale of hospital constantly increases, medical data volume is continuously increased, these simple service inquiry analyses cannot expire
Demand of the podiatrist institute to self-management and development.
Summary of the invention
The purpose of the present invention is in view of the drawbacks of the prior art, providing a kind of medical information querying method, use can be realized
Analysis and forecast function are realized to the multi-dimensional query of medical data in family, implement the multidimensional to the different angle of medical data
Analysis facilitates administration of health from medical personal and carries out problem analysis from different visual angles, further, it is possible to from existing data
In find out new valuable information, such as predict, describe, cluster, classification, analysis of Influential Factors, Study on Relative Factors etc., realize
Prediction is analyzed to more attribute synthesis of medical data.
In view of this, the embodiment of the invention provides a kind of medical information querying methods, comprising:
The hospital information system databases of multiple medical platforms, laboratory information system database, image is obtained respectively to return
Medical data in shelves and communication system data library；
Corresponding preset rules are obtained according to the type of database, according to the preset rules to corresponding medical number
According to Data Integration is carried out, platform data warehouse is established according to the medical data after the integration；
Data pick-up, conversion and load are carried out to the medical data in the platform data warehouse, obtain business intelligence number
According to library；
The Data Analysis Model of various dimensions is established according to the first business dimension of the medical platform and the first index dimension,
Also, the data mining model of various dimensions is established according to the second business dimension of the medical platform and the second index dimension；
Repeatedly training, test and evaluation are carried out to the data model of various dimensions；The data model includes the data point
Analyse model and the data mining model；
The incidence relation between the data model and model information is established, and according to the model information of Data Analysis Model
Analysis model list is generated, mining model list is generated according to the model information of the data mining model, and store；
Receive the query condition information of the medical information of user's input；
The querying condition is parsed, key word information is obtained；Wherein, the key word information includes version
Information, queried for items information and corresponding query context information；
According to the corresponding model list of the version acquisition of information；
The model information to match is obtained in the model list got according to the queried for items information；
Corresponding data model is called according to the model information to match；
It is called in business intelligence data library relatively according to the queried for items information and corresponding query context information
The medical data answered；
The medical data is inputted into the data model, the data model carries out data point to the medical data
Analysis, to obtain output result；
The output result is shown according to the default form of expression.
Preferably, the model information includes model name information, functional circuit information, cuit and output project.
Preferably, match in described obtained in the model list got according to the queried for items information
After model information, the method also includes:
Model selective listing is generated according to the model information to match；
Receive the model information that the user selects according to the model selective listing.
Preferably, data pick-up, conversion and load are carried out in the medical data in the platform data warehouse, obtained
To after business intelligence data library, the method also includes:
Medical control decision, medical diagnosis and scientific research demand are analyzed, first business dimension, the first finger are obtained
Mark dimension and the second business dimension, the second index dimension.
Preferably, repeatedly training, test and evaluation specifically include for the data model progress to various dimensions:
Corresponding doctor is obtained in the business intelligence data library according to first business dimension and the first index dimension
Treat data；
Repeatedly training, test and evaluation are carried out to the Data Analysis Model according to the medical data；
Repeatedly training, test and evaluation are carried out to the data mining model of the various dimensions.
It is further preferred that the data mining model to the various dimensions carries out repeatedly training, test and evaluation has
Body includes:
Cuit and output project are set according to the data mining model；The cuit includes all at the first time
Phase, the output project includes second time period；
It is obtained in the business intelligence data library according to the cuit and period first time corresponding
Medical data；
The medical data got is inputted into the data mining model, the data mining model is to the medical treatment
Data obtain prediction output data after being handled；The prediction output data includes confidence interval；
Corresponding medical data is obtained according to the output project and second time period, and carries out Macro or mass analysis, is obtained
To reality output data；
The prediction output data and the reality output data are compared, error information is obtained；
The data mining model is assessed according to multiple errors that multiple training, test obtain.
It is further preferred that the data mining model to the various dimensions carries out repeatedly training, test and evaluation has
Body includes:
Cuit and output project are set according to the data mining model；The cuit include patient information,
Check information, diagnostic message and medical expense information；The output project includes sickness influence because sublist, Analysis of prevalence arrange
Table, genius morbi list or cost impacts list of factors include project information and corresponding probabilistic information in the list；
According to obtaining corresponding medical data in business intelligence data library described in the cuit and preset quantity；
The medical data got is inputted into the data mining model, the data mining model is to the medical treatment
After data are handled, output data is exported according to the output project；
Increase the preset quantity, repeatedly training is carried out to the data mining model and test, obtains multiple output numbers
According to；
The multiple output data is compared and analyzed, the data mining model is carried out according to the analysis result
Assessment.
Preferably, the method also includes:
Update the medical platform hospital information system database, laboratory information system database and image archiving and
Medical data in communication system data library；
The Data Analysis Model and the data mining model are trained according to the updated medical data,
Test and evaluation.
Preferably, the default form of expression be line chart, bar chart, sector diagram, scatter plot, instrument board, radar map with
And one of table or a variety of.
A kind of medical information querying method provided in an embodiment of the present invention, can be realized user and looks into the multidimensional of medical data
Ask, realize analysis and forecast function, implement the multidimensional analysis to the different angle of medical data, facilitate administration of health with
Medical personal carries out problem analysis from different visual angles, further, it is possible to find out new valuable letter from existing data
Breath is such as predicted, is described, and is clustered, classification, and analysis of Influential Factors, Study on Relative Factors etc. are realized comprehensive to more attributes of medical data
Close analysis prediction.
Detailed description of the invention
Fig. 1 is a kind of medical information querying method flow chart provided in an embodiment of the present invention.
Specific embodiment
Below by drawings and examples, technical scheme of the present invention will be described in further detail.
It is applied to medical platform system for medical information querying method provided in an embodiment of the present invention, can be realized to multiple
The inquiry and analysis of the medical platform medical information of hospital.Fig. 1 is a kind of medical information issuer provided in an embodiment of the present invention
Method flow chart, as shown in Figure 1, comprising:
Step 101, hospital information system database, the laboratory information system data of multiple medical platforms are obtained respectively
Medical data in library, image archiving and communication system data library；
Hospital information system database (Hospital Information System, HIS) is covering all industry of hospital
The information management system of business and business overall process is to be provided using electronic computer and communication apparatus for component commands, hospital door
The collection of patient's medical information and administration information, storage, processing, extraction and data exchange ability and meet authorized user
Functional requirement platform.
Laboratory information system database (Laboratory Information Management System, LIS) leads to
The inspection request for crossing outpatient clinician and work station proposition in hospital, generates the chemical examination bar-code label of respective patient, is generating laboratory test report
While the essential information of patient is corresponding with testing instruments；After testing instruments generate result, system can be according to corresponding
Relationship, it is by data-interface and result approval that inspection data is automatically corresponding with patient information, to realize checking information electricity
Sonization, laboratory information management automated network system.
Communication system data library (Picture Archiving and Communication Systems, PACS), is answered
Used in the system of hospital image department, main task is exactly that (including nuclear-magnetism, CT surpass the various medical images of daily generation
Sound, various X-ray machines, the image that the equipment such as various radar stealthy materials, frequency microscope generate) pass through various interfaces (simulation, DICOM, network)
Magnanimity saves in a manner of digitized.
Specifically, obtaining the hospital information system data of each hospital respectively by the data-interface of each hospital in region
Medical data in library, laboratory information system database and image archiving and communication system data library, it should be noted that
The acquisition database of medical data include but is not limited to above-mentioned hospital information system database, laboratory information system database,
Image archiving and three kinds of communication system data library database.Those skilled in the art can according to need to the region and
The quantity of hospital is set.
Step 102, corresponding preset rules are obtained according to the type of database, according to preset rules to corresponding doctor
It treats data and carries out Data Integration, platform data warehouse is established according to the medical data after integration；
The database of each type corresponds to different preset rules, includes saving format, knot to data in preset rules
Structure and the requirement of type etc., that is to say, that return for hospital information system database, laboratory information system database, image
Medical data in shelves and communication system data library is respectively adopted corresponding preset rules and carries out Data Integration, and according to integration
Medical data afterwards establishes platform data warehouse.
Step 103, data pick-up, conversion and load are carried out to the medical data in platform data warehouse, obtains business intelligence
It can database；
Data pick-up, which refers to from platform data warehouse, extracts the data that purpose data source systems need；Data conversion refer to by
The data obtained from source data source are converted into the form of purpose data source requirement according to business demand, and to wrong, inconsistent
Data are cleaned and are processed；Data load, which refers to, is loaded into purpose data source for the data after conversion.
The purpose of the process is responsible for data such as relation data, flat data file will be distributed, in heterogeneous data source
It cleaned, converted, integrated etc. being drawn into after interim middle layer, be finally loaded into data warehouse or Data Mart, i.e. business intelligence
In energy database, become the basis of on-line analytical processing, data mining.
After this, described that medical control decision, medical diagnosis and scientific research demand are analyzed, obtain the first business dimension
Degree, the first index dimension and the second business dimension, the second index dimension.
Wherein, the first business dimension, the first index dimension are analyzed for data, the second business dimension, the second index dimension
For data mining, the first business dimension and the second business dimension can be the same or different, and those skilled in the art can be with
The first business dimension, the first index dimension and the second business dimension, the second index dimension are set as needed.
First business dimension refers to Analysis of Policy Making theme, can specifically include medical number quality operation management decision, manpower
Resource decision, financial decision, handling of goods and materials decision, service and decision-making, real time clinical decision, clinical path and scientific research decision,
First index dimension refers to the analysis indexes based on the first business dimension, such as medical corresponding point of operation management decision of number quality
Analysis index can accept theme, operation theme, anesthesia theme for medical treatment to be hospitalized；The analysis indexes of human resources decision can be performance master
Topic, business information, essential information theme；The analysis indexes of financial decision can be medical income theme, medical treatment cost theme；Object
The analysis indexes for providing administrative decision can be medical supplies theme, Medical Devices theme, logistical materials theme；Point of service and decision-making
Analysis index can accept prediction theme, average length of hospitalization prediction theme for medical treatment to be hospitalized；The analysis indexes of real time clinical decision can be
Real time clinical decision, clinic diagnosis theme, medical quality control theme；The analysis indexes of clinical path can for clinical path,
Common index monitor theme, clinical path and non-clinical path compare theme, Single diseases key implementation path monitor theme；Science
The analysis indexes for studying decision can be circular for confirmation medical subject, clinical research theme.
Second business dimension can specifically include service and decision-making class, medical diagnosis and scientific research class and financial management class, and second
Index refers to the analysis indexes based on the second business dimension, for example corresponding second index of service and decision-making class can be situation of registering
Prediction, medical situation are predicted, situation of paying a home visit prediction, diagnose situation prediction, discharge situation is predicted, discharge day situation is predicted, is critical
The prediction of rate situation, the prediction of invasive surgery situation, the prediction of non-invasive procedures situation, the prediction of Bed utilization rate situation, the bed turnover time of circulating funds
Situation prediction, consultation time analysis；Medical diagnosis the second index corresponding with scientific research class can be pre- for disease etiological analysis, disease
Survey analysis, patient mode's identification, concurrent disease association analysis, intelligence prescription recommendation, medication combinatory analysis, Analysis on Epidemic Surveillance,
Narco analysis, drug abnormal response analysis, state of an illness EVOLUTION ANALYSIS；Second index of medical diagnosis and scientific research class can be disease disease
Because analysis, disease forecast analysis, patient mode's identification, concurrent disease association analysis, intelligent prescription recommendation, medication combinatory analysis,
Analysis on Epidemic Surveillance, narco analysis, drug abnormal response analysis, state of an illness EVOLUTION ANALYSIS；Second index of financial management class can be with
It is pre- for cost early warning analysis, medical department cost forecast analysis, project cost forecast analysis, disease cost accounting forecast analysis, institute-level cost
Survey analysis, department's income forecast analysis, project income forecast analysis, disease income forecast analysis, institute-level income forecast analysis, doctor
Protect income forecast analysis, medical expense anomaly analysis, Analysis of The Factors Affecting Hospitalization Cost of Patients.
It should be noted that those skilled in the art can according to need to the first business dimension, the first index dimension and
Second business dimension, the second index dimension are set.
Step 104, it is analyzed according to the data that the first business dimension of medical platform and the first index dimension establish various dimensions
Model, also, establish according to the second business dimension of medical platform and the second index dimension the data mining model of various dimensions；
Specifically, each first index dimension can establish the Data Analysis Model of a dimension, thus according to medical treatment
First business dimension of platform and the first index dimension establish the OLAP data analysis model of various dimensions, and OLAP data analysis is main
Function is that data are carried out with collect statistics and is calculated, different from common static statement outside, based on the dynamic statement of OLAP technology,
Realize that the data of multi-angle analyze inquiry, convenient for the medical datas such as administration of health and medical personal administrative staff from different
Visual angle carries out inquiry and problem analysis.
Each the second index dimension can establish the data mining model of a dimension, thus according to the of medical platform
Two business dimensions and the second index dimension establish the data mining model of various dimensions, and data mining model major function is for spy
Setting analysis theme finds out new valuable information, such as using advanced data mining and statistical technique from existing data
Prediction describes, and clusters, classification, analysis of Influential Factors, Study on Relative Factors etc., and data mining provides a kind of multiattribute comprehensive
Close analysis method.
Step 105, repeatedly training, test and evaluation are carried out to the data model of various dimensions；
Here data model includes Data Analysis Model and data mining model two types data model, for description side
Just Data Analysis Model and data mining model are referred to as data model.
After Data Analysis Model foundation, need to be trained with model of a large amount of data to various dimensions, i.e. basis
First business dimension and the first index dimension obtain corresponding medical data in business intelligence data library；According to medical data pair
Corresponding Data Analysis Model carries out repeatedly training, test and evaluation, and according to training, test and evaluation result constantly to mould
Type optimizes, and then the Data Analysis Model of multiple various dimensions after being optimized.
After data mining model foundation, need repeatedly to be instructed with data mining model of a large amount of data to various dimensions
Practice, test and evaluation.
Data mining model has the cuit and output project of setting, not according to cuit and output item purpose
Together, different data mining model has different training test methods, and lower mask body introduces two kinds of training test appraisal procedures:
The first is to set cuit and output project according to data mining model；When including first in cuit
Between the period, include second time period in output project.In a specific example, according to the second business dimension service and decision-making
It is to register situation prediction model that the corresponding second index dimension of class, which is the data mining model that situation prediction is established of registering, and function is
Predict the situation of registering of future Y Qi Ge department, then the cuit set is the number of registering of each department of history X phase, X the
A period of time, output project are the number of registering of future Y Qi Ge department, and Y is second time period；According to cuit and
A period of time obtains corresponding medical data in business intelligence data library；The medical data input data that will acquire is dug
Model is dug, data mining model obtains prediction output data, goes back in the prediction output data after handling medical data
Including confidence interval.
After obtaining prediction output data, corresponding medical number is obtained according to output project and second time period
According to, and Macro or mass analysis is carried out, obtain reality output data；Prediction output data is compared with reality output data, is obtained
Error information；Data mining model is evaluated and optimized according to multiple errors that multiple training, test obtain.
This method is suitable for service and decision-making class data mining model, service and decision-making class data mining model table specific as follows
Shown in 1.
1 service and decision-making class data mining model of table
Second is to set cuit and output project according to data mining model；Cuit include patient information,
Check information, diagnostic message and medical expense information；Output project includes sickness influence because of sublist, Analysis of prevalence list, disease
Sick feature list or cost impacts list of factors include project information and corresponding probabilistic information in list；According to input item
Corresponding medical data is obtained in mesh and preset quantity business intelligence data library；The medical data input data that will acquire is dug
Model is dug, after data mining model handles medical data, output data is exported according to output project；Increase present count
Amount carries out repeatedly training to data mining model and tests, obtains multiple output datas；Multiple output datas are compared point
Analysis, based on the analysis results assesses data mining model.This method is suitable for medical diagnosis and the data mining of scientific research class
Shown in model, medical diagnosis and scientific research class data mining model table 2 specific as follows.
2 medical diagnosis of table and scientific research class data mining model
In addition, some use first method for financial management class data mining model, some use second of side
Method, financial management class data mining model are specifically as shown in table 3.
3 medical diagnosis of table and scientific research class data mining model
Step 106, the incidence relation between data model and model information is established, and according to the model of Data Analysis Model
Information generates analysis model list, generates mining model list according to the model information of data mining model, and store；
Wherein, model information includes model name information, functional circuit information, cuit and output project.
Data Analysis Model and data mining model generate respective model list respectively, i.e., according to Data Analysis Model
Model information generates analysis model list, generates mining model list according to the model information of data mining model, and store.
Step 107, the query condition information for receiving the medical information of user's input, parses querying condition, obtains
Key word information；
Here user can be municipal health bureau and service management department, linchpin (area) health bureau, city, in urban community health services
The heart, each hospital administrative staff, different user has different operating rights, and those skilled in the art can be according to the actual situation
The permission of user is set.
User can input the querying condition of the medical information to be inquired by user terminal, and be sent to medical platform,
Medical platform obtains the corresponding authority information of user according to user information, checks whether permission matches with querying condition, when
When matching, querying condition is parsed to obtain key word information, key word information includes version information, queried for items letter
Breath and corresponding query context information, version information here include Data Analysis Model and data mining model,
Queried for items information refers to the content to be inquired, and query context information refers to the range of inquiry content, when can be
Between range, regional scope etc..In a specific example, the querying condition of user's input can be " all hospitals in first region
The statistical conditions of equipment ", " number of registering of prediction X future, hospital phase A ", then can determine " all hospital equipments in first region
Statistical conditions " corresponding data model is Data Analysis Model, queried for items is the statistics of hospital equipment, and query context is first
All hospitals in region；" number of registering of prediction X future, hospital phase A " corresponding data model is data mining model, query term
Mesh is number of registering, and query context is the phase in A hospital future X.
Step 108, it according to the corresponding model list of version acquisition of information, is being got according to queried for items information
Model list in obtain the model information to match；
Specifically, being arranged according to the corresponding model list of version acquisition of information according to queried for items information and model
Model name, function description, cuit information corresponding with output project are matched in table, thus matched
Model information.
Step 109, corresponding data model is called according to the model information to match；
When the model being matched to is one, corresponding data model is called according to the model information that matches, when
When the model being fitted on is multiple, model selective listing is generated according to the model information to match, and receive user and select according to model
The model information for selecting list selection calls corresponding data model according to the model information of user's selection.
Step 110, it is called in business intelligence data library according to queried for items information and corresponding query context information
Corresponding medical data；
Step 111, by medical data input data model, data model carries out data analysis to medical data, thus
To output result；
It is analyzed, after mining model in the data for obtaining multiple various dimensions using a large amount of data training Optimized model, area
Domain administrative staff can according to need the analysis of selection data, mining model, and selection will be analyzed, be dug in business intelligence data library
Range is excavated in the data analysis of pick, selects medical data according to data area, and is inputted selected data analysis, excavated mould
Type, to obtain data output result.
Step 112, output result is shown according to the default form of expression.
Multidimensional data analysis result and multidimensional data mining result can by trend line chart, bar chart, sector diagram, dissipate
One of point diagram, instrument board, radar map and table or it is a variety of be shown, intuitively with should be readily appreciated that.
Over time, medical platform can generate new medical data, to update the information for hospital of medical platform
Medical data in system database, laboratory information system database and image archiving and communication system data library, Jin Ergen
Data Analysis Model and data mining model are trained according to updated medical data, test and evaluation, are thus improved excellent
Change Data Analysis Model and data mining model, obtains more accurate data.
A kind of medical information querying method provided in an embodiment of the present invention, can be realized user and looks into the multidimensional of medical data
Ask, realize analysis and forecast function, implement the multidimensional analysis to the different angle of medical data, facilitate administration of health with
Medical personal carries out problem analysis from different visual angles, further, it is possible to find out new valuable letter from existing data
Breath is such as predicted, is described, and is clustered, classification, and analysis of Influential Factors, Study on Relative Factors etc. are realized comprehensive to more attributes of medical data
Close analysis prediction.
Professional should further appreciate that, described in conjunction with the examples disclosed in the embodiments of the present disclosure
Unit and algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, hard in order to clearly demonstrate
The interchangeability of part and software generally describes each exemplary composition and step according to function in the above description.
These functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.
Professional technician can use different methods to achieve the described function each specific application, but this realization
It should not be considered as beyond the scope of the present invention.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can be executed with hardware, processor
The combination of software module or the two is implemented.Software module can be placed in random access memory (RA medical information issuer
Method), memory, read-only memory (RO medical information querying method), electrically programmable RO medical information querying method, electric erasable can
Program RO medical information querying method, register, hard disk, moveable magnetic disc, CD-RO medical information querying method or technology neck
In any other form of storage medium well known in domain.
Above-described specific embodiment has carried out further the purpose of the present invention, technical scheme and beneficial effects
It is described in detail, it should be understood that being not intended to limit the present invention the foregoing is merely a specific embodiment of the invention
Protection scope, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should all include
Within protection scope of the present invention.
Claims (9)
1. a kind of medical information querying method, which is characterized in that the described method includes:
Obtain respectively the hospital information system databases of multiple medical platforms, laboratory information system database, image archiving and
Medical data in communication system data library；
Obtain corresponding preset rules according to the type of database, according to the preset rules to corresponding medical data into
Row Data Integration establishes platform data warehouse according to the medical data after the integration；
Data pick-up, conversion and load are carried out to the medical data in the platform data warehouse, obtain business intelligence data library；
The Data Analysis Model of various dimensions is established according to the first business dimension of the medical platform and the first index dimension, and
And the data mining model of various dimensions is established according to the second business dimension of the medical platform and the second index dimension；
Repeatedly training, test and evaluation are carried out to the data model of various dimensions；The data model includes the data analysis mould
Type and the data mining model；
The incidence relation between the data model and model information is established, and is generated according to the model information of Data Analysis Model
Analysis model list generates mining model list according to the model information of the data mining model, and stores；
Receive the query condition information of the medical information of user's input；
The querying condition is parsed, key word information is obtained；Wherein, the key word information includes version letter
Breath, queried for items information and corresponding query context information；
According to the corresponding model list of the version acquisition of information；
The model information to match is obtained in the model list got according to the queried for items information；
Corresponding data model is called according to the model information to match；
It is called in business intelligence data library according to the queried for items information and corresponding query context information corresponding
Medical data；
The medical data is inputted into the data model, the data model carries out data analysis to the medical data, from
And obtain output result；
The output result is shown according to the default form of expression.
2. medical information querying method according to claim 1, which is characterized in that the model information includes model name
Information, functional circuit information, cuit and output project.
3. medical information querying method according to claim 1, which is characterized in that believed described according to the queried for items
After breath obtains the model information to match in the model list got, the method also includes:
Model selective listing is generated according to the model information to match；
Receive the model information that the user selects according to the model selective listing.
4. medical information querying method according to claim 1, which is characterized in that described to the platform data warehouse
In medical data carry out data pick-up, conversion and load, after obtaining business intelligence data library, the method also includes:
Medical control decision, medical diagnosis and scientific research demand are analyzed, first business dimension, the first index dimension are obtained
Degree and the second business dimension, the second index dimension.
5. medical information querying method according to claim 1, which is characterized in that the data model to various dimensions into
The multiple training of row, test and evaluation specifically include:
Corresponding medical number is obtained in the business intelligence data library according to first business dimension and the first index dimension
According to；
Repeatedly training, test and evaluation are carried out to the Data Analysis Model according to the medical data；
Repeatedly training, test and evaluation are carried out to the data mining model of the various dimensions.
6. medical information querying method according to claim 5, which is characterized in that the data to the various dimensions are dug
Pick model carries out repeatedly training, test and evaluation and specifically includes:
Cuit and output project are set according to the data mining model；The cuit includes period first time,
The output project includes second time period；
Corresponding medical treatment is obtained in the business intelligence data library according to the cuit and period first time
Data；
The medical data got is inputted into the data mining model, the data mining model is to the medical data
Prediction output data is obtained after being handled；The prediction output data includes confidence interval；
Corresponding medical data is obtained according to the output project and second time period, and carries out Macro or mass analysis, obtains reality
Border output data；
The prediction output data and the reality output data are compared, error information is obtained；
The data mining model is assessed according to multiple errors that multiple training, test obtain.
7. medical information querying method according to claim 5, which is characterized in that the data to the various dimensions are dug
Pick model carries out repeatedly training, test and evaluation and specifically includes:
Cuit and output project are set according to the data mining model；The cuit includes patient information, checks
Information, diagnostic message and medical expense information；The output project includes sickness influence because of sublist, Analysis of prevalence list, disease
Sick feature list or cost impacts list of factors include project information and corresponding probabilistic information in the list；
According to obtaining corresponding medical data in business intelligence data library described in the cuit and preset quantity；
The medical data got is inputted into the data mining model, the data mining model is to the medical data
After being handled, output data is exported according to the output project；
Increase the preset quantity, repeatedly training is carried out to the data mining model and test, obtains multiple output datas；
The multiple output data is compared and analyzed, the data mining model is commented according to the analysis result
Estimate.
8. medical information querying method according to claim 1, which is characterized in that the method also includes:
Update hospital information system database, laboratory information system database and image archiving and the communication of the medical platform
Medical data in system database；
The Data Analysis Model and the data mining model are trained according to the updated medical data, tested
With assessment.
9. medical information querying method according to claim 1, which is characterized in that the default form of expression is broken line
One of figure, bar chart, sector diagram, scatter plot, instrument board, radar map and table are a variety of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910249835.3A CN110148440B (en) | 2019-03-29 | 2019-03-29 | Medical information query method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910249835.3A CN110148440B (en) | 2019-03-29 | 2019-03-29 | Medical information query method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110148440A true CN110148440A (en) | 2019-08-20 |
| CN110148440B CN110148440B (en) | 2023-06-30 |
Family
ID=67588722
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910249835.3A Active CN110148440B (en) | 2019-03-29 | 2019-03-29 | Medical information query method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110148440B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111223534A (en) * | 2020-01-03 | 2020-06-02 | 首都医科大学附属北京儿童医院 | Fine management system for industry and finance integration |
| CN111899822A (en) * | 2020-06-28 | 2020-11-06 | 广州万孚生物技术股份有限公司 | Medical institution database construction method, query method, device, equipment and medium |
| CN111914011A (en) * | 2020-08-06 | 2020-11-10 | 上海智众医疗科技有限公司 | Cross-platform data conversion method and system |
| CN111933241A (en) * | 2020-08-31 | 2020-11-13 | 平安国际智慧城市科技股份有限公司 | Medical data analysis method, medical data analysis device, electronic device, and storage medium |
| CN114334103A (en) * | 2020-09-30 | 2022-04-12 | 西门子医疗有限公司 | Medical data processing system and method |
| CN114334092A (en) * | 2021-12-22 | 2022-04-12 | 四川大学华西医院 | Medical image AI model management method and equipment |
| CN114334111A (en) * | 2019-01-21 | 2022-04-12 | 四川大学华西医院 | Medical information management method, device, server and readable storage medium |
| WO2022142748A1 (en) * | 2020-12-31 | 2022-07-07 | 天津开心生活科技有限公司 | Method and apparatus for time-series analysis of clinical trial data, electronic device, and medium |
| CN116126976A (en) * | 2023-04-06 | 2023-05-16 | 之江实验室 | Data synchronization method and device, storage medium and electronic equipment |
| CN116798590A (en) * | 2023-08-17 | 2023-09-22 | 北京大学第三医院（北京大学第三临床医学院） | Processing method, device, equipment and medium for constructing medicine management prediction model |
| CN117370426A (en) * | 2023-12-04 | 2024-01-09 | 畅捷通信息技术股份有限公司 | Report data generation method, system and storage medium based on artificial intelligence |
| CN118193759A (en) * | 2024-04-16 | 2024-06-14 | 中南大学湘雅医院 | Medical scientific research data interactive guiding index method and system based on large model |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040143567A1 (en) * | 2003-01-16 | 2004-07-22 | International Business Machines Corporation | Framework for dynamic analysis of varying structured data using multiple analysis techniques |
| US20050060191A1 (en) * | 2003-08-28 | 2005-03-17 | Parkins Kent D. | System and method for multi-dimensional extension of database information |
| US20050071349A1 (en) * | 2003-08-11 | 2005-03-31 | Jordan Philip Martin | Method and apparatus for accessing multidimensional data |
| US20090006349A1 (en) * | 2007-06-29 | 2009-01-01 | International Business Machines Corporation | Entity-based business intelligence |
| CN102682118A (en) * | 2012-05-15 | 2012-09-19 | 北京久其软件股份有限公司 | Multidimensional data model access method and device |
| US20140046696A1 (en) * | 2012-08-10 | 2014-02-13 | Assurerx Health, Inc. | Systems and Methods for Pharmacogenomic Decision Support in Psychiatry |
| US20170124176A1 (en) * | 2015-10-30 | 2017-05-04 | Vladislav Michael Beznos | Universal analytical data mart and data structure for same |
| CN107122464A (en) * | 2017-04-27 | 2017-09-01 | 国信优易数据有限公司 | A kind of aid decision-making system and method |
| CN107169070A (en) * | 2017-05-08 | 2017-09-15 | 山大地纬软件股份有限公司 | The constructing system and its method in a kind of social security index warehouse based on big data |
| CN107766574A (en) * | 2017-11-13 | 2018-03-06 | 天津开心生活科技有限公司 | Data query method and device, date storage method and device |
| CN108536826A (en) * | 2018-04-10 | 2018-09-14 | 口口相传(北京)网络技术有限公司 | Data analysing method and device |
| CN108615560A (en) * | 2018-03-19 | 2018-10-02 | 安徽锐欧赛智能科技有限公司 | A kind of clinical medical data analysis method based on data mining |
| CN208207819U (en) * | 2018-07-17 | 2018-12-07 | 于果鑫 | A kind of big data analysis processing system based on extended node cluster |
| CN109086354A (en) * | 2018-07-17 | 2018-12-25 | 于果鑫 | A kind of big data analysis processing system based on extended node cluster |
-
2019
- 2019-03-29 CN CN201910249835.3A patent/CN110148440B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040143567A1 (en) * | 2003-01-16 | 2004-07-22 | International Business Machines Corporation | Framework for dynamic analysis of varying structured data using multiple analysis techniques |
| US20050071349A1 (en) * | 2003-08-11 | 2005-03-31 | Jordan Philip Martin | Method and apparatus for accessing multidimensional data |
| US20050060191A1 (en) * | 2003-08-28 | 2005-03-17 | Parkins Kent D. | System and method for multi-dimensional extension of database information |
| US20090006349A1 (en) * | 2007-06-29 | 2009-01-01 | International Business Machines Corporation | Entity-based business intelligence |
| CN102682118A (en) * | 2012-05-15 | 2012-09-19 | 北京久其软件股份有限公司 | Multidimensional data model access method and device |
| US20140046696A1 (en) * | 2012-08-10 | 2014-02-13 | Assurerx Health, Inc. | Systems and Methods for Pharmacogenomic Decision Support in Psychiatry |
| US20170124176A1 (en) * | 2015-10-30 | 2017-05-04 | Vladislav Michael Beznos | Universal analytical data mart and data structure for same |
| CN107122464A (en) * | 2017-04-27 | 2017-09-01 | 国信优易数据有限公司 | A kind of aid decision-making system and method |
| CN107169070A (en) * | 2017-05-08 | 2017-09-15 | 山大地纬软件股份有限公司 | The constructing system and its method in a kind of social security index warehouse based on big data |
| CN107766574A (en) * | 2017-11-13 | 2018-03-06 | 天津开心生活科技有限公司 | Data query method and device, date storage method and device |
| CN108615560A (en) * | 2018-03-19 | 2018-10-02 | 安徽锐欧赛智能科技有限公司 | A kind of clinical medical data analysis method based on data mining |
| CN108536826A (en) * | 2018-04-10 | 2018-09-14 | 口口相传(北京)网络技术有限公司 | Data analysing method and device |
| CN208207819U (en) * | 2018-07-17 | 2018-12-07 | 于果鑫 | A kind of big data analysis processing system based on extended node cluster |
| CN109086354A (en) * | 2018-07-17 | 2018-12-25 | 于果鑫 | A kind of big data analysis processing system based on extended node cluster |
Non-Patent Citations (6)
| Title |
|---|
| 宁维塞: "商业智能在医院辅助决策系统中的应用", CNKI优秀硕士学位论文全文库, no. 8 * |
| 李晓华;张晓祥;: "住院病人医疗信息商业智能系统开发应用", 医学信息学杂志, no. 09 * |
| 王冬冬;叶枫;吕旭东;闵令通;王利;: "基于openEHR的临床医疗数据仓库构建方法", 中国生物医学工程学报, no. 02 * |
| 王徐冬;杨希武;: "数据仓库与数据挖掘在医院信息系统中的应用", 医疗卫生装备, no. 08 * |
| 贝乾: "数据仓库技术在医院系统集成中的应用", CNKI优秀硕士学位论文全文库, no. 11 * |
| 陈晓明;刘海林;: "基于商业智能技术的医院经营决策分析平台的开发与应用", 中国医学教育技术, no. 04 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114334111A (en) * | 2019-01-21 | 2022-04-12 | 四川大学华西医院 | Medical information management method, device, server and readable storage medium |
| CN114334111B (en) * | 2019-01-21 | 2023-08-18 | 四川大学华西医院 | Medical information management method, device, server and readable storage medium |
| CN111223534A (en) * | 2020-01-03 | 2020-06-02 | 首都医科大学附属北京儿童医院 | Fine management system for industry and finance integration |
| CN111223534B (en) * | 2020-01-03 | 2023-08-18 | 首都医科大学附属北京儿童医院 | Industry and financial fusion fine management system |
| CN111899822B (en) * | 2020-06-28 | 2024-01-30 | 广州万孚生物技术股份有限公司 | Medical institution database construction method, query method, device, equipment and medium |
| CN111899822A (en) * | 2020-06-28 | 2020-11-06 | 广州万孚生物技术股份有限公司 | Medical institution database construction method, query method, device, equipment and medium |
| CN111914011A (en) * | 2020-08-06 | 2020-11-10 | 上海智众医疗科技有限公司 | Cross-platform data conversion method and system |
| CN111933241A (en) * | 2020-08-31 | 2020-11-13 | 平安国际智慧城市科技股份有限公司 | Medical data analysis method, medical data analysis device, electronic device, and storage medium |
| CN111933241B (en) * | 2020-08-31 | 2023-06-20 | 深圳平安智慧医健科技有限公司 | Medical data analysis method, device, electronic equipment and storage medium |
| CN114334103A (en) * | 2020-09-30 | 2022-04-12 | 西门子医疗有限公司 | Medical data processing system and method |
| WO2022142748A1 (en) * | 2020-12-31 | 2022-07-07 | 天津开心生活科技有限公司 | Method and apparatus for time-series analysis of clinical trial data, electronic device, and medium |
| CN114334092A (en) * | 2021-12-22 | 2022-04-12 | 四川大学华西医院 | Medical image AI model management method and equipment |
| CN116126976A (en) * | 2023-04-06 | 2023-05-16 | 之江实验室 | Data synchronization method and device, storage medium and electronic equipment |
| CN116798590A (en) * | 2023-08-17 | 2023-09-22 | 北京大学第三医院（北京大学第三临床医学院） | Processing method, device, equipment and medium for constructing medicine management prediction model |
| CN116798590B (en) * | 2023-08-17 | 2024-09-10 | 北京大学第三医院（北京大学第三临床医学院） | Processing method, device, equipment and medium for constructing medicine management prediction model |
| CN117370426A (en) * | 2023-12-04 | 2024-01-09 | 畅捷通信息技术股份有限公司 | Report data generation method, system and storage medium based on artificial intelligence |
| CN117370426B (en) * | 2023-12-04 | 2024-03-26 | 畅捷通信息技术股份有限公司 | Report data generation method, system and storage medium based on artificial intelligence |
| CN118193759A (en) * | 2024-04-16 | 2024-06-14 | 中南大学湘雅医院 | Medical scientific research data interactive guiding index method and system based on large model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110148440B (en) | 2023-06-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110148440A (en) | A kind of medical information querying method | |
| CN110136837A (en) | A kind of medical data processing platform | |
| US7490085B2 (en) | Computer-assisted data processing system and method incorporating automated learning | |
| US6826578B2 (en) | Method, system, and computer product for collecting and distributing clinical data for data mining | |
| Tang et al. | Electronic health record systems | |
| US20070088559A1 (en) | Method for computerising and standardizing medical information | |
| US20070118399A1 (en) | System and method for integrated learning and understanding of healthcare informatics | |
| CN110119432A (en) | A kind of data processing method for medical platform | |
| US20040122709A1 (en) | Medical procedure prioritization system and method utilizing integrated knowledge base | |
| US20040122706A1 (en) | Patient data acquisition system and method | |
| US20060136259A1 (en) | Multi-dimensional analysis of medical data | |
| US20040122707A1 (en) | Patient-driven medical data processing system and method | |
| US20040120557A1 (en) | Data processing and feedback method and system | |
| US20040122703A1 (en) | Medical data operating model development system and method | |
| US20040122704A1 (en) | Integrated medical knowledge base interface system and method | |
| EP1994484A1 (en) | Platform for interoperable healthcare data exchange | |
| WO2004061744A2 (en) | Enhanced computer-assisted medical data processing system and method | |
| EP1576527A2 (en) | Medical data analysis method and apparatus incorporating in vitro test data | |
| US7505867B2 (en) | System and method for predicting medical condition | |
| CN109427420A (en) | Diagnose validity tool | |
| US20230178189A1 (en) | System and method for phenotype vector manipulation of medical data | |
| CN109411036A (en) | A kind of cloud platform system and method monitoring various disease surgery complication | |
| Weiner et al. | Electronic health records: high-quality electronic data for higher-quality clinical research. | |
| Bansal et al. | Introduction to computational health informatics | |
| MXPA06011525A (en) | System and methods for patient data and treatment management. |
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 |