CN112732673A - System for realizing analysis and processing of chronic disease quality control data based on big data - Google Patents
System for realizing analysis and processing of chronic disease quality control data based on big data Download PDFInfo
- Publication number
- CN112732673A CN112732673A CN202110003039.9A CN202110003039A CN112732673A CN 112732673 A CN112732673 A CN 112732673A CN 202110003039 A CN202110003039 A CN 202110003039A CN 112732673 A CN112732673 A CN 112732673A
- Authority
- CN
- China
- Prior art keywords
- data
- chronic disease
- analysis
- information
- layer
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Quality & Reliability (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to a system for realizing analysis and processing of chronic disease quality control data based on big data, which comprises a data source layer, a data processing layer and a data processing layer, wherein the data source layer is used for constructing the big data of chronic disease health according to a service database to form a three-layer medical health data framework; the computing layer is used for performing deterministic data analysis, exploratory data analysis, predictive data analysis, data processing and conversion; the storage layer is used for storing the big data on line; and displaying the query layer, constructing a chronic disease quality control data warehouse, selecting a corresponding database to create a data source by creating an acquisition task, and completing data acquisition of the base table file by adopting a data import mode of time difference data import and incremental data import. By adopting the system for realizing the analysis and the processing of the chronic disease quality control data based on the big data, the medical and health big data are comprehensively utilized, the existing various chronic disease information is integrated, a chronic disease related data acquisition system is established, the incidence relation between the chronic disease and the medical and health big data is comprehensively and multi-dimensionally stated, and the current situation of data quality control index loss is changed.
Description
Technical Field
The invention relates to the field of big data management platforms, in particular to the field of cross-platform medical data integration, and specifically relates to a system for analyzing and processing chronic disease quality control data based on big data.
Background
Chronic diseases are a group of diseases with high morbidity, disability rate and mortality, which seriously consume social resources and harm the health of residents in an area, and mainly comprise cardiovascular and cerebrovascular diseases, diabetes, malignant tumors, chronic respiratory diseases and the like. In recent decades, public health management systems are used as supports in various regions, a series of public health management works are developed, a large amount of patient management information is obtained, however, the problem that certain problems exist in the existing community public health management information is found in the evaluation of community management effects and actual investigation, the data cannot reflect the real effect of local basic health management, and the adverse effect is brought to the healthy and high-quality development of the community health management work. Four characteristics of chronic disease service information are caused:
(1) the authenticity reliability is poor;
taking the supervision conditions of 2016 and 2017 Shanghai disease prevention and control centers on 'follow-up after death due to hypertension' as examples, the follow-up cases after death are found in a large number of cases, and the follow-up of people after death in some regions exceeds 20%. Similarly, when the chronic disease management data and the resident physical sign data, the resident diagnosis and treatment data and the resident health records are transversely compared, the condition that a lot of data are inconsistent is found, and the problems of authenticity and reliability of a large amount of basic data in the conventional basic chronic disease management process are reflected.
(2) Simple quality control method
The existing chronic disease quality control mode usually sets the overall range of a quality control individual case and a sampling scheme for quality control personnel according to actual conditions, wherein the sampling scheme comprises a data type, a quality control field, a sampling method, a weight ratio, a sampling quantity mode and the like, and the quality control process is finished in a telephone mode, a door-to-door mode and the like. And finally, the quality control personnel complete and input the quality control content according to the quality control library to generate a quality control result. The quality control in this way requires a large amount of manpower and material resources.
(3) The quality control data has single source
At present, most of domestic chronic disease data quality control result data sources are single and generally come from follow-up information such as diabetes, hypertension and the like required by national basic public health, actual chronic disease management relates to real healthy mass data of sick crowds, and if a strong database is not used as a support, the mass data cannot be summarized, cleaned, evaluated and analyzed.
(4) Relying on the service capability of quality control personnel
The management and quality control of chronic diseases are highly professional works, especially have high requirements on public health knowledge, and the development of quality control analysis on personnel or teams with insufficient data management and statistical analysis capabilities is a very difficult task. The existing chronic disease control excessively depends on the abilities of professionals, and sustainable effective supervision cannot be realized on the basis of repeated consumption of a large amount of manpower and material resources.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a system for realizing analysis and processing of chronic disease quality control data based on big data, which has the advantages of good authenticity, good reliability and wider application range.
In order to achieve the above purpose, the system for implementing analysis and processing of chronic disease quality control data based on big data of the invention is as follows:
the system for realizing analysis and processing of chronic disease quality control data based on big data is mainly characterized by comprising the following components:
the data source layer is used for constructing the big chronic disease health data according to the business database to form a three-layer medical health data framework;
the computing layer is connected with the data source layer and is used for performing deterministic data analysis, exploratory data analysis, predictive data analysis, data processing and conversion;
the storage layer is connected with the computing layer and used for carrying out online storage on the big data;
and the display query layer is connected with the storage layer and used for constructing a chronic disease control data warehouse, selecting a corresponding database to create a data source through creating an acquisition task, and completing data acquisition of the library table file by adopting a data import mode of time difference data import and incremental data import.
Preferably, the data source layer includes:
the detail data storage library is connected with the computing layer and used for storing original data from different data sources and reducing the influence of data cleaning conversion on the basic database;
the basic database is connected with the computing layer and is used for storing the data of the basic information, the outpatient service information, the hospitalization information and the examination and examination information of the patient;
and the theme database is connected with the computing layer and used for managing information and other public health information.
Preferably, the data collected by the display query layer comprises diabetes management information, hypertension management information, stroke management information, tumor management information, clinic and diagnosis information, outpatient clinic prescriptions, hospitalization information, examination and examination information, image report information, resident electronic health file information, resident physical examination information and other public health key management information.
Preferably, the subject database is organized according to a business process, a star model is adopted, and a diabetes subject database, a hypertension subject database, a data quality subject database and other subject databases are constructed according to a fact table by a dimension modeling method.
Preferably, the system also evaluates the data quality through service attributes of different dimensions, and performs data quality management through a data quality knowledge base.
Preferably, the system assesses data quality through business attributes of business integrity, normalization, inter-table consistency, intra-table consistency, data validity, and uniqueness.
Preferably, the system also carries out encryption desensitization processing on the data, and desensitization processing on the private data is carried out through a data desensitization rule of symmetric encryption, asymmetric encryption and data bleaching.
Preferably, the system further comprises a weight data analysis library connected to the calculation layer for calculating the weight of multiple data for multiple data of a single resident.
Preferably, the weight data analysis library measures and calculates a plurality of data weights, specifically:
measuring a plurality of data weights according to the following formula:
wherein, the data are n pieces, wiWeight for each identical kind of data, wi，……，nWeights for merging n kinds of data.
Preferably, the system customizes the specific indexes of quality control analysis through four categories of data comparison, data integrity, suspicious data analysis and data distribution rationality.
By adopting the system for realizing the analysis and the processing of the chronic disease quality control data based on the big data, the factors which can be used for mining and influencing the quality of the chronic disease data are established from the two aspects of the establishment of a big data platform and the definition of a basic quality control model, and the system has important guiding effects on the establishment of a health policy, the prevention and the control of diseases, the improvement of the understanding and the attention of the chronic diseases. In application, the medical and health big data are comprehensively utilized, the existing various chronic disease information is integrated, a chronic disease related data acquisition system is established, the association relation between the chronic disease and the medical and health big data is comprehensively and multi-dimensionally stated, and the current situation of data quality control index loss is changed.
Drawings
Fig. 1 is a hardware structure diagram of a big data platform of the system for implementing analysis and processing of chronic disease control data based on big data according to the present invention.
FIG. 2 is an architecture diagram of a system for implementing analysis and processing of chronic disease control data based on big data according to the present invention.
Fig. 3 is a schematic diagram of analyzing clinical complications of a system for analyzing and processing chronic disease control data based on big data according to an embodiment.
Fig. 4 is a schematic diagram of a post-death follow-up of a system for implementing analysis and processing of chronic disease control data based on big data according to an embodiment.
Fig. 5 is a schematic diagram of clinic visit reanalysis of the system for implementing analysis and processing of chronic disease quality control data based on big data according to an embodiment.
Fig. 6 is a schematic cross-service-domain analysis diagram of a system for implementing analysis and processing of chronic disease control data based on big data according to an embodiment.
Fig. 7 is a schematic diagram of blood pressure end distribution of a system for implementing analysis and processing of chronic disease control data based on big data according to an embodiment.
Fig. 8 is a schematic diagram of a blood pressure end distribution of a system for implementing analysis and processing of chronic disease control data based on big data according to another embodiment.
Fig. 9 is a schematic diagram of a blood pressure end distribution of a system for implementing analysis and processing of chronic disease control data based on big data according to another embodiment.
Fig. 10 is a schematic diagram of a blood pressure end distribution of a system for implementing analysis and processing of chronic disease control data based on big data according to another embodiment.
Detailed Description
In order to more clearly describe the technical contents of the present invention, the following further description is given in conjunction with specific embodiments.
The invention relates to a system for realizing analysis and processing of chronic disease control data based on big data, which comprises:
the data source layer is used for constructing the big chronic disease health data according to the business database to form a three-layer medical health data framework;
the computing layer is connected with the data source layer and is used for performing deterministic data analysis, exploratory data analysis, predictive data analysis, data processing and conversion;
the storage layer is connected with the computing layer and used for carrying out online storage on the big data;
and the display query layer is connected with the storage layer and used for constructing a chronic disease control data warehouse, selecting a corresponding database to create a data source through creating an acquisition task, and completing data acquisition of the library table file by adopting a data import mode of time difference data import and incremental data import.
As a preferred embodiment of the present invention, the data source layer includes:
the detail data storage library is connected with the computing layer and used for storing original data from different data sources and reducing the influence of data cleaning conversion on the basic database;
the basic database is connected with the computing layer and is used for storing the data of the basic information, the outpatient service information, the hospitalization information and the examination and examination information of the patient;
and the theme database is connected with the computing layer and used for managing information and other public health information.
As a preferred embodiment of the present invention, the data collected by the presentation query layer includes diabetes management information, hypertension management information, stroke management information, tumor management information, clinic and diagnosis information, outpatient clinic prescription, hospitalization information, examination and examination information, image report information, resident electronic health record information, resident physical examination information, and other public health key management information.
As a preferred embodiment of the present invention, the topic database is organized according to a business process, and a diabetes topic database, a hypertension topic database, a data quality topic database, and other topic databases are constructed according to a fact table by a dimension modeling method using a star model.
As a preferred embodiment of the invention, the system also evaluates the data quality through service attributes of different dimensions and performs data quality management through a data quality knowledge base.
As a preferred embodiment of the invention, the system evaluates data quality through business attributes of business integrity, normalization, inter-table consistency, intra-table consistency, data validity, and uniqueness.
As a preferred embodiment of the present invention, the system further performs encryption desensitization processing on the data, and desensitizes the private data through a data desensitization rule of symmetric encryption, asymmetric encryption, and data bleaching.
In a preferred embodiment of the present invention, the system further comprises a weight data analysis library connected to the calculation layer for calculating the weight of the plurality of data for the plurality of data of the single resident.
As a preferred embodiment of the present invention, the weight data analysis library measures a plurality of data weights, specifically:
measuring a plurality of data weights according to the following formula:
wherein, the data are n pieces, wiWeight for each identical kind of data, wi，……，nWeights for merging n kinds of data.
As a preferred embodiment of the invention, the system customizes the concrete indexes of quality control analysis through four categories of data comparison, data integrity, suspicious data analysis and data distribution rationality.
In a specific implementation mode, the invention relates to cross-platform intelligent integration of medical, health and crowd health measurement big data, a quality control platform based on big data technology is established by combining the requirements of a basic medical institution and a disease prevention control institution, a data intelligent analysis platform is established by carrying out procedures of logic check, deficiency check, data noise reduction, data coding standardization and the like on massive heterogeneous data to form multidimensional quality control information data, the integrity, accuracy, uniqueness and logic relation of the data are comprehensively evaluated, problems in basic chronic disease management are discovered in time, and the improvement of the chronic disease management level of the public health institution is promoted.
The system and the method are based on an electronic health file platform of regional residents, and are supported by an innovatively constructed big data management platform, and multisource systematic chronic disease service and data monitoring and quality control are performed by using a plurality of big data means.
The method is mainly aimed at establishing a big data system through an informatization approach under the existing informatization condition, integrating massive population medical and health big data in a cross-platform manner, taking the individuals of residents with chronic diseases as data clues and data main bodies, and forming a continuous, complete and credible data system through data management and an advanced data architecture; and establishing a data resource catalog, and classifying, cleaning, standardizing, splitting and reconstructing the data on the basis to form a multi-class main database.
Based on a big data architecture, a multi-dimensional space-time analysis and presentation is realized by heuristically establishing a thematic analysis and calculation model of mass data; and a data system related to chronic disease management indexes is established, a basis is provided for making a health policy and implementing preventive measures, the comprehensive utilization efficiency of health and medical data is improved, and the efficiency of health assessment and performance evaluation decision is improved.
The invention aims to solve the technical limitation of the traditional chronic disease quality control, fully utilizes the big data technology, develops a whole set of chronic disease data quality control model of the medical and health big data, integrates various medical and health informationized data, particularly can represent various data related to chronic disease crowd management, adopts advanced big data information analysis and mining algorithm to carry out data multidimensional analysis and mining, establishes an index system capable of comprehensively reflecting regional chronic disease management water quality, and provides decision basis for regional chronic disease comprehensive evaluation and effective utilization of basic public health resources.
In order to solve the technical problems, the technical scheme of the invention is as follows:
EHR (Enterprise energy reactor) regional health platform-based expansion big data base platform
Construction of big data platform
As shown in fig. 1, the project is physically supported by underlying big data formed by more than 6 servers, and 2 are management servers; more than 4 servers are dataode servers.
The HDFS is stored by using a distributed file on the architecture, and the CDH architecture is adopted to realize the persistence and safe storage of mass diagnosis and treatment and disease control data; the YARN provides uniform resource management scheduling on the uniform distributed storage, complete authority management control is provided by combining LDAP, different users can create a computing cluster to access authorization data of the computing cluster according to needs, and the computing cluster comprises SQL type statistical analysis application and data mining type application based on a Spark computing framework and application based on a MapReduce computing framework.
As shown in fig. 2, in particular, the main responsibilities of the various layers are:
the data source layer mainly refers to the fact that chronic disease hygiene big data are constructed on the basis of a traditional business database of an electronic health archive of residents on a traditional regional hygiene platform, three layers of medical hygiene data architectures such as detail data storage, a basic database and a subject database are formed, the detail data storage is used for storing original data from different data sources, and the influence of data cleaning conversion on the basic database is reduced; the basic database comprises data such as basic information of patients, outpatient service information, hospitalization information, examination and examination information, chronic disease management information and other public health information.
One of the differences of the big data-based chronic disease control computing layer is the idea of 'single platform and multiple applications'. The traditional database quality control bottom layer only has one database engine and only processes relational logic, so that the system is a single platform and single application; while big data is a "multi-platform multi-application" schema. Deterministic data analysis, exploratory data analysis, predictive data analysis, data processing, and transformation are supported.
HDFS has become a de facto standard for large data storage, for online storage of large volumes of large files. Through the development of the years, the basic solidification of the architecture and the functions of the HDFS is realized, and important characteristics such as HA, heterogeneous storage, local data short-circuit access and the like are realized, so that the storage requirement of medical and health big data is sufficiently supported.
Acquisition of (II) chronic disease quality control basic data
As a basis for quality control analysis of chronic disease data, data required to be collected by a model at least comprises the following information, and a new data warehouse realizes collection of library table files in various databases such as Oracle, Db2, Sysbase and the like. And selecting a corresponding database creation data source by creating a collection task, and adopting a data import mode of time difference data import and incremental data import so as to finish the data collection work of the library table file.
(1) Diabetes management information:
basic information of diabetes high risk population, basic information of diabetes patients, basic information of diabetes pre-stage population, information of diabetes patient management card, follow-up information of diabetes patients, evaluation information of diabetes patients and management information of diabetes patient complications.
(2) Hypertension management information:
basic information of hypertension susceptible population, basic information of hypertension patients, management card information of hypertension patients, follow-up visit information of hypertension patients, evaluation information of hypertension patients and coexisting clinical symptoms of hypertension patients.
(3) Stroke management information:
the system comprises basic information of stroke high risk population, follow-up visit information of stroke high risk population and information of a new brain report card.
(4) Tumor management information:
tumor crowd registration information, tumor crowd follow-up visit information and tumor early discovery information.
(5) Visit and diagnosis information:
the resident sees the resident basic information, outpatient service registration, main diagnosis and secondary diagnosis information in all levels of medical institutions.
(6) Prescription for clinic visit:
prescription details, drug specifications, usage and dosage of clinic prescriptions and medical advice.
(7) Hospitalization information:
and the sum of the hospital entrance and the hospital discharge of the resident at the clinic.
(8) Checking the checking information:
laboratory examination information of resident's treatment, including all inspection index codes, inspection results and reference ranges.
(9) Image report information:
the resident sees the image inspection method, inspection name, clinical diagnosis and examination seeing, inspection diagnosis.
(10) Resident electronic health record information:
the resident basic information, family history, disease history and other information in the resident electronic health record.
(12) Resident physical examination:
basic characteristics and inspection result information acquired in the process of resident basic public health physical examination.
(13) Other public health key management information:
the key management information in the health care of pregnant and lying-in women, the health care of children, the health care of the old and the management of traditional Chinese medicine is particularly important residents.
(III) multisource data governance
(1) Establishment of data resource pool
The detail data storage is designed for storing original health-related data from a data source system, the original data serve as objects of data processing, the content of the original data is kept unchanged in the detail data storage, and the detail data storage only merges data tables with the same attribute, but the data table structure of the original data is not changed.
(2) Creation of analysis topic library
The subject database is around chronic disease analysis application, and is integrated into human-based analysis subject database. The theme database is constructed according to the business theme and is oriented to a specific data set, and the data model of the hierarchy is opened for business personnel to use for data mining and business analysis. The method is characterized in that the method is organized according to business processes, a star model is adopted, a dimensionality modeling method is used for constructing topic databases such as a diabetes topic library, a hypertension topic library, a data quality topic library and the like according to fact tables and dimension tables, each fact table represents an independent business process, and direct dependency relationship does not exist among the fact tables, so that business personnel can easily correspond analysis requirements to the fact tables, simple SQL is written out by using tools or by hand, statistical data are extracted and analyzed, and the calculation and display efficiency of upper-layer analysis application is improved.
The subject database includes:
(3) data quality assessment
The data quality evaluation method and the data quality evaluation device realize the data quality evaluation of 6-dimensional service attributes such as service integrity, normalization, consistency among tables, consistency in tables, data effectiveness, uniqueness and the like, and provide a data quality knowledge base to help data managers to carry out data quality management work.
Service integrity: and detecting whether field name content in the chronic disease data table is missing or not, wherein the data of the master table and the slave table have an association relation. And displaying the data of the main table and the data which cannot be associated with the main table in the slave table. For example: the patient basic information table (main table) and the doctor card information table (auxiliary table) are subjected to primary key association through a field PERSONID, and the field IDCARD has an association relation. The user can find out the data which can not be matched in the field IDCARD of the patient basic information table (main table) from the field IDCARD of the visit card information table (auxiliary table) through the service integrity rule.
Standardization: normative evaluation is carried out on some special fields, and record rows with non-normative data are displayed; for example: the patient basic information table field IDCARD is the patient identification number. The identity card number meets certain rules.
In-table consistency: carrying out consistency evaluation on data items in the same data table, and displaying all inconsistent record rows in the same table;
consistency between tables: carrying out consistency evaluation on data items in different data tables, and splicing inconsistent columns among different tables into one table for display; for example: the user can find out the data which can not be matched in the basic information table (main table) field BITHDAY of the patient through a conversion formula from the field IDCARD of the information table (auxiliary table) of the clinic card through the consistency rule among tables.
Data validity: and evaluating the ratio of valid fields in one record, regarding some fields in each record which are possibly missing or the filling is not in accordance with the requirement as invalid data, displaying the filled record lines, and allowing the user to manually fill blank fields.
Uniqueness: and evaluating whether the record value of a certain key field in the data table is unique or not, and displaying repeated record rows to allow the repeated data to be deleted. For example: the field IDCARD and the field NAME of each record of the patient basic information table have uniqueness. The user can find out the repeatedly recorded line data from the basic information table of the patient through the uniqueness rule.
(4) Data encryption desensitization
The medical and health data gathered in the platform contains part of private data, in order to guarantee the use safety of the data, desensitization processing capability to the private data needs to be provided, and data desensitization rules such as symmetric encryption, asymmetric encryption, data bleaching and the like are provided.
(5) Weight data analysis library
For the condition of multiple kinds of data of a single resident, the weight of the multiple data is measured and calculated by adopting the following model, and a weight database is established.
Suppose a person has n pieces of data, and the weight of each piece of data of the same kind is wi(i-1 … … n), the weight of merging n kinds of data is: .
Secondly, establishing a basic quality control analysis model
And (3) by depending on the established quality control big data subject database, developing formation evaluation aiming at basic data quality and effect expectation, defining a quality control design idea, determining a big model classification, and designing a specific quality control index based on the data dimension of a resource pool. The basic data quality control model including but not limited to the following major categories and specific indexes is preliminarily established and is specifically divided into four categories of 'data comparison', 'data integrity', 'suspicious data analysis' and 'data distribution rationality', and each category can customize the corresponding specific indexes according to permission requirements.
Some embodiments of the present invention take the following design ideas of some quality control indexes as examples:
(I) analysis of clinical complications
As shown in fig. 3, management and diagnosis and treatment information is integrated by using the unique identification of residents, the diagnosis and management conditions of the chronic disease complications of the residents are obtained by comparing the diagnosis conditions of the chronic disease crowd in the region, and the diagnosis and management conditions, the data quality and the management service quality of the chronic disease are monitored by using the ICD diagnosis codes.
(II) post-mortem follow-up
As shown in fig. 4, the identity card index uniquely associates the chronic disease system and the death system, finds out the dead patients with hypertension and diabetes, checks whether the follow-up time, the evaluation time and the like are later than the death date, and controls the authenticity of the data traffic of hypertension and diabetes.
(III) reasonable analysis of clinic visit
As shown in fig. 5, the system is compared with the outpatient service situation of the residents with chronic diseases, and the follow-up mode of each basic medical institution in the designated interval in the quality control chronic disease system is the recorded situation of outpatient follow-up visit without diagnosis and treatment information, and the situation that the follow-up visit is managed without related diagnosis and medicine dispensing information. Meanwhile, the consistency and the relevance of information such as prescriptions, inspection reports, diagnoses and the like in an outpatient service and chronic disease information are determined.
(IV) Cross-Business Domain analysis
As shown in fig. 6, the managed population specifies the blood pressure control condition, blood sugar control condition, and glycated hemoglobin control condition in the designated interval during diagnosis and treatment, and compares the consistency and relevance of data in the system for maternal and child health care and disease prevention control.
(V) analysis of data such as tail distribution
As shown in fig. 7 to 10, the statistical value of the distribution of the health information data is mined, and the final distribution of the data such as blood pressure, blood sugar, glycosylated hemoglobin, height, weight and the like formed by each basic medical institution is evaluated; the distribution of the terminal blood pressure under different follow-up modes/different patient stratification/different follow-up doctor dimensions; blood sugar, terminal distribution of glycosylated hemoglobin, etc. under different follow-up modes/different follow-up doctor dimensions.
By adopting the system for realizing the analysis and the processing of the chronic disease quality control data based on the big data, the factors which can be used for mining and influencing the quality of the chronic disease data are established from the two aspects of the establishment of a big data platform and the definition of a basic quality control model, and the system has important guiding effects on the establishment of a health policy, the prevention and the control of diseases, the improvement of the understanding and the attention of the chronic diseases. In application, the medical and health big data are comprehensively utilized, the existing various chronic disease information is integrated, a chronic disease related data acquisition system is established, the association relation between the chronic disease and the medical and health big data is comprehensively and multi-dimensionally stated, and the current situation of data quality control index loss is changed.
In this specification, the invention has been described with reference to specific embodiments thereof. It will, however, be evident that various modifications and changes may be made thereto without departing from the broader spirit and scope of the invention. The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense.
Claims (10)
1. A system for realizing analysis and processing of chronic disease quality control data based on big data is characterized by comprising:
the data source layer is used for constructing the big chronic disease health data according to the business database to form a three-layer medical health data framework;
the computing layer is connected with the data source layer and is used for performing deterministic data analysis, exploratory data analysis, predictive data analysis, data processing and conversion;
the storage layer is connected with the computing layer and used for carrying out online storage on the big data;
and the display query layer is connected with the storage layer and used for constructing a chronic disease control data warehouse, selecting a corresponding database to create a data source through creating an acquisition task, and completing data acquisition of the library table file by adopting a data import mode of time difference data import and incremental data import.
2. The system for implementing analysis and processing of chronic disease control data based on big data as claimed in claim 1, wherein said data source layer comprises:
the detail data storage library is connected with the computing layer and used for storing original data from different data sources and reducing the influence of data cleaning conversion on the basic database;
the basic database is connected with the computing layer and is used for storing the data of the basic information, the outpatient service information, the hospitalization information and the examination and examination information of the patient;
and the theme database is connected with the computing layer and used for managing information and other public health information.
3. The big data based system for analyzing and processing chronic disease control data according to claim 1, wherein the data collected by the display query layer comprises diabetes management information, hypertension management information, stroke management information, tumor management information, clinic and diagnosis information, outpatient prescriptions, hospitalization information, examination and examination information, image report information, resident electronic health record information, resident physical examination information, and other public health key management information.
4. The system of claim 2, wherein the topic database is organized according to business process, and a star model is used to construct a diabetes topic database, a hypertension topic database, a data quality topic database and other topic databases according to fact table by dimension modeling.
5. The system for implementing analysis and processing of chronic disease control data based on big data as claimed in claim 1, wherein said system further evaluates data quality by service attributes of different dimensions and manages data quality by data quality knowledge base.
6. The system for implementing analysis and processing of chronic disease control data based on big data as claimed in claim 5, wherein said system evaluates data quality by business attributes of business integrity, normalization, inter-table consistency, intra-table consistency, data validity and uniqueness.
7. The system for implementing analysis and processing of chronic disease control data based on big data as claimed in claim 1, wherein said system further performs encryption desensitization processing on the data, and desensitizes the private data through data desensitization rules of symmetric encryption, asymmetric encryption, and data bleaching.
8. The system for analyzing and processing chronic disease control data based on big data as claimed in claim 1, further comprising a weight data analysis library connected to said computation layer for calculating a plurality of data weights for a single resident.
9. The big data based system for analyzing and processing chronic disease control data according to claim 8, wherein the weight data analysis library calculates a plurality of data weights, specifically:
measuring a plurality of data weights according to the following formula:
wherein, the data are n pieces, wiWeight for each identical kind of data, wi，……，nWeights for merging n kinds of data.
10. The big data-based system for analyzing and processing chronic disease quality control data according to claim 1, wherein the system customizes the concrete indexes of quality control analysis through four categories of data comparison, data integrity, suspicious data analysis and data distribution rationality.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110003039.9A CN112732673A (en) | 2021-01-04 | 2021-01-04 | System for realizing analysis and processing of chronic disease quality control data based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110003039.9A CN112732673A (en) | 2021-01-04 | 2021-01-04 | System for realizing analysis and processing of chronic disease quality control data based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112732673A true CN112732673A (en) | 2021-04-30 |
Family
ID=75589523
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110003039.9A Pending CN112732673A (en) | 2021-01-04 | 2021-01-04 | System for realizing analysis and processing of chronic disease quality control data based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112732673A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114911861A (en) * | 2022-07-15 | 2022-08-16 | 山东中联佳裕软件股份有限公司 | Public health service project data quality control system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0917078A1 (en) * | 1996-09-30 | 1999-05-19 | Smithkline Beecham Corporation | Disease management method and system |
| WO2009061514A1 (en) * | 2007-11-08 | 2009-05-14 | 32 Mott Street Acquisition I, Llc, D/B/A | Automated systems and methods for obtaining, storing, processing and utilizing immunologic and other information of an individual and population for various uses |
| CN108062973A (en) * | 2017-11-30 | 2018-05-22 | 江西洪都航空工业集团有限责任公司 | A kind of health care data analysing method |
| CN109935319A (en) * | 2019-03-15 | 2019-06-25 | 南京邮电大学 | Chronic disease systematic management system |
| CN110415831A (en) * | 2019-07-18 | 2019-11-05 | 天宜(天津)信息科技有限公司 | A kind of medical treatment big data cloud service analysis platform |
| CN111125061A (en) * | 2019-12-18 | 2020-05-08 | 甘肃省卫生健康统计信息中心(西北人口信息中心) | Method for standardizing and promoting health medical big data |
-
2021
- 2021-01-04 CN CN202110003039.9A patent/CN112732673A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0917078A1 (en) * | 1996-09-30 | 1999-05-19 | Smithkline Beecham Corporation | Disease management method and system |
| WO2009061514A1 (en) * | 2007-11-08 | 2009-05-14 | 32 Mott Street Acquisition I, Llc, D/B/A | Automated systems and methods for obtaining, storing, processing and utilizing immunologic and other information of an individual and population for various uses |
| CN108062973A (en) * | 2017-11-30 | 2018-05-22 | 江西洪都航空工业集团有限责任公司 | A kind of health care data analysing method |
| CN109935319A (en) * | 2019-03-15 | 2019-06-25 | 南京邮电大学 | Chronic disease systematic management system |
| CN110415831A (en) * | 2019-07-18 | 2019-11-05 | 天宜(天津)信息科技有限公司 | A kind of medical treatment big data cloud service analysis platform |
| CN111125061A (en) * | 2019-12-18 | 2020-05-08 | 甘肃省卫生健康统计信息中心(西北人口信息中心) | Method for standardizing and promoting health medical big data |
Non-Patent Citations (7)
| Title |
|---|
| LAURA SEBASTIAN-COLEMAN: "《穿越数据的迷宫 数据管理执行指南》", 30 April 2020, pages: 136 - 138 * |
| 肖良武等: "《大数据与城市经济发展研究》", 30 May 2019, pages: 64 * |
| 苏逸飞等: "基于大数据的区域慢病综合管理平台的设计与应用实践", 《网络空间安全》, no. 01, 25 January 2020 (2020-01-25) * |
| 谢威 * |
| 邓先明: "基于西安市矿产资源规划关系数据库的数据质量控制研究", 《中国优秀硕士学位论文数据库》, 15 June 2016 (2016-06-15) * |
| 邱航: "慢性病大数据分析平台设计", 《中国卫生信息管理杂志 》, 20 April 2017 (2017-04-20) * |
| 黄晓琴等: "基于区域卫生信息平台的医疗卫生大数据研究", 《中国卫生信息管理杂志》, no. 06, 20 December 2016 (2016-12-20) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114911861A (en) * | 2022-07-15 | 2022-08-16 | 山东中联佳裕软件股份有限公司 | Public health service project data quality control system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110415831B (en) | Medical big data cloud service analysis platform | |
| Kaur et al. | Managing data in healthcare information systems: many models, one solution | |
| FitzHenry et al. | Creating a common data model for comparative effectiveness with the observational medical outcomes partnership | |
| CN105528529B (en) | The data processing method of tcm clinical practice technical ability appraisement system based on big data analysis | |
| US20070005154A1 (en) | System and method for multidimensional extension of database information using inferred groupings | |
| CN107833595A (en) | Medical big data multicenter integration platform and method | |
| Wolfson et al. | Sickle‐cell disease in California: A population‐based description of emergency department utilization | |
| CN109785927A (en) | Clinical document structuring processing method based on internet integration medical platform | |
| CN108962394B (en) | Medical data decision support method and system | |
| CN113345583A (en) | Method and system for constructing full life cycle resident intelligent health file | |
| CN101986333A (en) | Auxiliary decision supporting system of hospital | |
| CN114639479A (en) | Intelligent diagnosis auxiliary system based on medical knowledge map | |
| CN115497631A (en) | Clinical scientific research big data analysis system | |
| CN116434899A (en) | Health record information platform establishment method based on multi-source data | |
| CN112732673A (en) | System for realizing analysis and processing of chronic disease quality control data based on big data | |
| Liu et al. | [Retracted] Prediction Method of Gestational Diabetes Based on Electronic Medical Record Data | |
| Parmanto et al. | A framework for designing a healthcare outcome data warehouse | |
| CN118152385B (en) | Medical-based data quality verification method | |
| CN109411094A (en) | Health life expectancy in life expectancy application support information system and method based on hygiene medical treatment big data | |
| CN113903423A (en) | Medication scheme recommendation method, device, equipment and medium | |
| Chondrogiannis et al. | A novel approach for clinical data harmonization | |
| CN116665860A (en) | Wisdom research ward management and service platform | |
| CN110853745A (en) | Skin disease patient standardization system | |
| CN113468138A (en) | Method, system and computer medium for perfecting medical database rules | |
| Li et al. | TCM Constitution Analysis Method Based on Parallel FP‐Growth Algorithm in Hadoop Framework |
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 |