WO2018120668A1 - Medical big data association and storage system and method - Google Patents

Medical big data association and storage system and method Download PDF

Info

Publication number
WO2018120668A1
WO2018120668A1 PCT/CN2017/088351 CN2017088351W WO2018120668A1 WO 2018120668 A1 WO2018120668 A1 WO 2018120668A1 CN 2017088351 W CN2017088351 W CN 2017088351W WO 2018120668 A1 WO2018120668 A1 WO 2018120668A1
Authority
WO
WIPO (PCT)
Prior art keywords
patient
data
medical
information table
medical data
Prior art date
Application number
PCT/CN2017/088351
Other languages
French (fr)
Chinese (zh)
Inventor
张贯京
葛新科
王海荣
高伟明
张红治
Original Assignee
深圳市易特科信息技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 深圳市易特科信息技术有限公司 filed Critical 深圳市易特科信息技术有限公司
Publication of WO2018120668A1 publication Critical patent/WO2018120668A1/en

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
    • G06F19/32—
    • 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
    • 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
    • G06F16/22—Indexing; Data structures therefor; Storage structures
    • G06F16/2282—Tablespace storage structures; Management thereof
    • 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
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2453—Query optimisation
    • 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
    • G06F16/25—Integrating or interfacing systems involving database management systems
    • G06F16/254—Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
    • 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
    • G16H40/60—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 operation of medical equipment or devices
    • G16H40/67—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 operation of medical equipment or devices for remote operation
    • 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
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS

Definitions

  • the present invention relates to the technical field of medical informationization, and in particular, to a medical big data association storage system and method.
  • the main object of the present invention is to provide a medical big data associated storage system and method, which aims to solve the problem that the existing medical data storage system performs distributed storage of massive medical data and affects the efficiency of medical data analysis and processing. Problem solution
  • the present invention provides a medical big data associative storage system, which runs in a cloud server, and the cloud server establishes a communication connection with a plurality of medical data sources through a communication network, and connects through a database and a large Data storage warehouse connection, the system includes:
  • a data collection module configured to collect raw medical data of each patient from a plurality of medical data sources
  • a data cleaning module configured to perform cleaning conversion processing on each patient's original medical data to obtain each patient's Standardize medical data
  • a data extraction module configured to extract identity information, vital sign data, and historical visit information of each patient from each patient's standardized medical data, and generate an identity for each patient according to the identity information of each patient. number;
  • a data association module configured to associate each patient's identification number with the patient's corresponding vital sign data and establish a patient vital information table, and associate each patient's identification number with the patient's respective history. Correlate the visit information and establish a patient visit information form;
  • a data storage module configured to store the patient sign information table in a first partition database in a big data storage warehouse, and store the patient visit information table in a second partition database in the big data storage warehouse in.
  • the data collection module collects the original medical data of each patient from a plurality of medical data sources by: setting a execution time and execution period of a constant script, and following the script
  • the execution of the daytime and execution cycle collects raw medical data from each patient from different medical data sources.
  • the manner in which the data cleaning module performs the cleaning conversion process on the raw medical data of each patient is: using the ETL data filtering conversion component to remove meaningless words in the original medical data, and one of the original medical data is The different forms of the word are converted to the same form, and the duplicated data in the original medical data is deleted.
  • the header field of the patient vital sign information table stores an identity identification number of each patient
  • the content field of the patient vital sign information table stores vital sign data corresponding to each patient
  • the patient visit information table The header field stores the identification number of each patient
  • the content field of the patient vital information table stores historical visit information corresponding to each patient.
  • the vital sign data includes a patient's height data, body weight data, blood pressure data, pulse data, heart rate data, blood oxygen data, and blood glucose data
  • the historical medical information includes a history of the patient, history, history Visiting hospitals, historical clinics, and historical electronic medical records.
  • the present invention also provides a medical big data association storage method, which is applied to a cloud server, wherein the cloud server establishes a communication connection with a plurality of medical data sources through a communication network, and connects with a big data storage warehouse through a database connection.
  • the medical big data association storage method includes the steps of:
  • the step of collecting raw medical data of each patient from a plurality of medical data sources comprises the following steps:
  • Raw medical data for each patient is collected from different medical data sources in accordance with the execution time and execution cycle of the programmer script.
  • the step of performing the cleaning conversion process on the raw medical data of each patient comprises the following steps: removing the meaningless words in the original medical data by using the ETL data filtering conversion component; Different forms of words are converted to the same form; delete duplicate data from raw medical data
  • the header field of the patient vital sign information table stores an identity identification number of each patient
  • the content field of the patient vital sign information table stores vital vital sign data corresponding to each patient
  • the patient is
  • the header field of the medical information table stores the identification number of each patient
  • the content field of the patient vital information table stores historical medical visit information corresponding to each patient.
  • the vital sign data includes a patient's height data, body weight data, blood pressure data, pulse data, heart rate data, blood oxygen data, and blood glucose data
  • the historical medical information includes a history of the patient, history, history Visiting hospitals, historical clinics, and historical electronic medical records.
  • the medical big data associated storage system and method of the present invention adopts the above technical solutions, and the technical effects brought by: collecting medical data in different medical data sources, and Data is cleaned and converted to obtain standardized medical data, making medical data collection more comprehensive and accurate.
  • each patient's identification number is used as a relationship between the vital information table and the medical information table, and the patient's vital information table and the medical information table are stored in different partition databases of the big data storage warehouse to reduce
  • the system load improves data processing efficiency, avoids conflicts in accessing medical data, speeds up the reading and processing of medical data, and improves medical service level and patient satisfaction.
  • FIG. 1 is a block diagram of a preferred embodiment of a medical big data associative storage system of the present invention
  • FIG. 2 is a flow chart of a preferred embodiment of the medical big data association storage method of the present invention.
  • FIG. 1 is an application environment framework of a preferred embodiment of the medical big data associative storage system of the present invention.
  • the medical big data associated storage system 10 is applied and runs in the cloud server 1, and the cloud server 1 is connected to the plurality of medical data sources 2 through the communication network 3 (two in FIG. 1 as an example).
  • Description Establish a communication connection and connect to the big data storage repository 4 via the database connection 5.
  • the communication network 3 can be a wired communication network or a wireless communication network.
  • the communication network 3 is preferably a wireless communication network, including but not limited to, a GSM network, a GPRS network, a CDMA network, a TD-SCDMA network, a WiMAX network, a TD-LTE network, an FDD-LTE network, and the like. transporting network.
  • the database connection 5 can be an Open Database Connectivity (ODBC) and a Java Data Base Connectivity (JDBC).
  • the cloud server 1 is a cloud platform or a server in the cloud platform, and the data transmission capability, the data storage capability, and the data processing capability of the cloud server 1 can be quickly collected from different medical data sources 2 Different raw medical data.
  • the medical data source 2 stores the original medical data of the patient, and may be a hospital information system that generates clinical data, such as a HIS system, an EMR, a LIS, a PACS system, or any suitable medical center, private clinic, emergency center, and the like.
  • the big data storage repository 4 includes a first partition database 41 and a second partition database 42, a first partition database 41 for storing patient sign information tables, and a second partition database 42 for storing patient visit information tables.
  • the patient sign information table is used to store vital sign data of patients collected from different medical data sources 2 for storing historical visit data of patients collected from different medical data sources 2.
  • the cloud server 1 includes, but is not limited to, a medical big data associated storage system 10, a communication unit 11, a storage unit 12, and a processing unit 13.
  • the communication unit 11 is a wired communication interface or a wireless communication interface, for example, a communication interface supporting communication technologies such as GSM, GPRS, WCDMA, CDMA, TD-S CDMA, WiMAX TD-LTE ⁇ FDD-LTE.
  • the storage unit 12 can be a read only memory unit ROM, an EEPROM, a flash memory unit F LASH or a solid hard disk.
  • the processing unit 13 may be a central processing unit (CPU), a microcontroller (MCU), a data processing chip, or an information processing unit having a data processing function.
  • the medical big data associated storage system 10 includes, but is not limited to, a data collection module 101, a data cleaning module 102, a data extraction module 103, a data association module 104, and a data storage module 105.
  • the module referred to in the present invention refers to a module that can be executed by the processing unit 13 of the cloud platform server 1 and is capable of A series of computer program instruction segments that perform fixed functions are stored in the storage unit 12 of the cloud platform server 1.
  • the data collection module 101 is configured to collect raw medical data for each patient from a plurality of different medical data sources 2.
  • the generation and collection of the patient's original medical data usually comes from the clinical data generated by the hospital information system, such as HIS system, EMR, LIS, PACS system, but with the development of the Internet of Things, the patient's original medical data can also come from Any suitable clinical business system, such as a medical center, private clinic, and emergency center.
  • the data collection module 101 is specifically configured to set an execution time and an execution period of a programmer script, and collect original medical data from different medical data sources according to execution time and execution cycle of the programmer script. .
  • the data cleaning module 102 is configured to perform a cleaning conversion process on the raw medical data of each patient to obtain standardized medical data for each patient.
  • the data cleaning module 102 needs to utilize ETL (extract, Transform (loading), loading (lo ad)
  • ETL extract, Transform (loading), loading (lo ad)
  • the data filtering and transformation component cleans and converts the collected raw medical data to obtain standardized medical data, thereby ensuring the accuracy of medical data and saving storage for medical data storage. space.
  • the manner in which the data cleaning module 102 performs the cleaning conversion process on the raw medical data of each patient is: using the ETL data filtering conversion component to remove meaningless words in the original medical data, and using a word in the original medical data.
  • the different forms are converted to the same form, and the processing of duplicate data in the original medical data is deleted.
  • the data extraction module 103 is configured to extract identity information, vital sign data, and historical visit information of each patient from the standardized medical data of each patient, and generate one for each patient according to the identity information of each patient.
  • Identification number ID
  • the vital sign data includes data such as height data, body weight data, blood pressure data, pulse data, heart rate data, blood oxygen data, blood glucose data, and the like of the patient.
  • the historical medical treatment information includes data such as a patient's historical visit, a historical hospital, a historical medical department, and a historical electronic medical record.
  • the data association module 104 is configured to associate each patient's identification number with the patient's corresponding vital sign data and establish a patient sign information table, and associate each patient's identification number with the patient.
  • the historical visit information is linked and a patient visit information form is created.
  • the header field of the patient vital sign information table stores an identification number of each patient
  • the content field of the patient vital sign information table stores vital sign data corresponding to each patient
  • the table of the patient medical information table The header field stores the identity identification number of each patient
  • the content field of the patient vital sign information table stores historical medical visit information corresponding to each patient.
  • the data storage module 105 is configured to store the patient vital information information table in the first partition database 41 in the big data storage warehouse 4, and store the patient visit information table in the second partition in the big data storage warehouse 4.
  • database 42 Since each patient's identification number is unique, each patient's identification number is used as a relationship between the patient's vital information table and the patient's medical information table, and the patient's physical information table and the patient's medical information table are stored separately.
  • the access to medical data is avoided, conflicts are generated, and the reading and processing speed of the massive medical data is accelerated, thereby improving the medical service level and patient satisfaction.
  • the present invention also provides a medical big data association storage method.
  • FIG. 2 is a flow chart of a preferred embodiment of the medical big data association storage method of the present invention.
  • the medical big data association storage method includes the following steps:
  • Step S21 Collecting raw medical data of each patient from different medical data sources; specifically, the data collecting module 101 collects raw medical data of each patient from a plurality of different medical data sources 2.
  • the generation and collection of the patient's original medical data usually comes from the clinical data generated by the hospital information system, such as HIS system, EMR, LIS, PACS system, but with the development of the Internet of Things, the patient's original medical data can also come from Any suitable clinical business system, such as a medical center, private clinic, and emergency center.
  • the step of the data acquisition module 101 performing the cleaning conversion process on the raw medical data of each patient includes the steps of: setting an execution time and an execution period of a programmer script according to the execution of the script. Inter- and execution cycles collect raw medical data from different medical data sources.
  • Step S22 performing clean conversion processing on the raw medical data of each patient to obtain standardized medical data for each patient; specifically, the data cleaning module 102 performs cleaning conversion processing on each patient's original medical data to obtain each patient. Standard medical data.
  • the data cleaning module 102 needs to utilize ETL (extract, Transformation The data filtering conversion component performs the cleaning conversion processing on the collected raw medical data to obtain the standardized medical data, thereby ensuring the accuracy of the medical data and saving the storage space for the storage of the medical data.
  • the step of performing the cleaning conversion process on the raw medical data of each patient by the data cleaning module 102 includes the steps of: removing the meaningless word in the original medical data by using the ETL data filtering conversion component, and using a word in the original medical data
  • the different forms are converted to the same form, and the processing of duplicate data in the original medical data is deleted.
  • Step S23 extracting identity information and vital sign data of each patient from the standardized medical data of each patient; specifically, the data extraction module 103 extracts identity information of each patient from the standardized medical data of each patient. , vital signs data and historical visit information.
  • the vital sign data of the patient includes data such as height data, body weight data, blood pressure data, pulse data, heart rate data, blood oxygen data, and blood glucose data of the patient.
  • the patient's historical visit information includes data such as the patient's historical visit, historical hospital, historical medical department, and historical electronic medical records.
  • step S24 generating an identity identification number for each patient according to the identity information of each patient; specifically, the data extraction module 103 generates an identity identification number for each patient according to the identity information of each patient, as each The unique identity of the patient.
  • Step S25 associating the identification number of each patient with the vital sign data of the patient and establishing a patient vital information table, and associating the identification number of each patient with the historical medical information of the patient and Establishing a patient visit information table; specifically, the data association module 104 associates each patient's identification number with the patient's respective vital sign data and establishes a patient sign information table, and identifies each patient's identification number and The patient's respective historical visit information is correlated and a patient visit information form is established.
  • the header field of the patient vital sign information table stores the identity identification number of each patient
  • the content field of the patient vital sign information table stores vital sign data corresponding to each patient
  • the patient visit information table The header field stores the identification number of each patient
  • the content field of the patient vital information table stores a historical visit corresponding to each patient.
  • step S26 storing the patient vital sign information table in the first partition database in the big data storage warehouse, and storing the patient visit information table in the second partition database in the big data storage warehouse; specifically, The data storage module 105 stores the patient vital information table in the first partition database 41 in the big data storage repository 4, and stores the patient visit information table in the second partition database 42 in the big data storage repository 4.
  • the identification number of each patient is unique, the identification number of each patient is used as a relationship between the patient's vital information table and the patient's medical information table, and the patient's vital information table and the patient's medical information are displayed.
  • the table branches are stored in different partition databases of the big data storage warehouse 4, thereby enhancing data structured storage and avoiding conflicts in accessing medical data, speeding up the reading and processing speed of the medical data by the cloud server 1 Improve medical service levels and patient satisfaction.
  • the medical big data associated storage system and method of the present invention collects medical data in different medical data sources 2, and performs medical cleaning and conversion processing to obtain standardized medical data, thereby making medical data collection more comprehensive. more precise.
  • each patient's identification number is used as a relationship between the vital information table and the medical information table, and the patient's vital information table and the medical information table are stored in different partition databases of the big data storage warehouse to reduce
  • the system load improves data processing efficiency, avoids conflicts in accessing medical data, speeds up the reading and processing of medical data, and improves medical service level and patient satisfaction.
  • the medical big data associated storage system and method of the present invention adopts the above technical solutions, and the technical effects brought by: collecting medical data in different medical data sources, and Data is cleaned and converted to obtain standardized medical data, making medical data collection more comprehensive and accurate.
  • each patient's identification number is used as a relationship between the vital information table and the medical information table, and the patient's vital information table and the medical information table are stored in different partition databases of the big data storage warehouse to reduce
  • the system load improves data processing efficiency, avoids conflicts in accessing medical data, speeds up the reading and processing of medical data, and improves medical service level and patient satisfaction.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Computational Linguistics (AREA)
  • Quality & Reliability (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Biomedical Technology (AREA)
  • Business, Economics & Management (AREA)
  • General Business, Economics & Management (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

A medical big data association and storage system and method. The method comprises the steps of: collecting original medical data of each patient from a plurality of different medical data sources (S21); performing cleaning and conversion processing on the original medical data to obtain standard medical data of each patient (S22); extracting identity information and vital sign data about each patient from the standard medical data of each patient (S23); generating an identity identification number for each patient according to the identity information about each patient (S24); associating the identity identification number of each patient with the vital sign data of the patient and establishing a patient sign information table, and associating the identity identification number of each patient with historical visit information about the patient and establishing a patient visit information table (S25); and storing the patient sign information table in a first partition database of a big data storage warehouse, and storing the patient visit information table in a second partition database of the big data storage warehouse (S26). By means of collecting medical data from different medical data sources and performing association and storage, the comprehensiveness and accuracy of collecting the medical data and the efficiency of processing the medical data are improved.

Description

医疗大数据关联存储系统及方法 技术领域  Medical big data associated storage system and method
[0001] 本发明涉及医疗信息化的技术领域， 尤其涉及一种医疗大数据关联存储系统及 方法。  [0001] The present invention relates to the technical field of medical informationization, and in particular, to a medical big data association storage system and method.
背景技术  Background technique
[0002] 目前， 随着我国经济持续稳定的发展和现代科技的日新月异， 人们越来越多的 关注自身健康， 在满足日常工作和生活的需求之外， 人们也迫切希望通过网络 或者手机上网就能随吋査看流行病的季节信息、 了解每种疾病下的用药情况以 及针对自身疾病获得一些个性化的推荐服务等。 对于公共卫生机构， 它们希望 各个社区居民的医疗数据能够自动汇总， 并自动对这些数据进行统计分析， 统 计的结果用来进行流行病的趋势分析和爆发预警， 从而为制定防治干预计划提 供有力的参考依据。  [0002] At present, with the continuous and stable development of China's economy and the rapid development of modern technology, people are paying more and more attention to their own health. In addition to meeting the needs of daily work and life, people also eagerly want to access the Internet through the Internet or mobile phones. You can follow the seasonal information of epidemics, understand the medications under each disease, and get some personalized recommendation services for your own diseases. For public health agencies, they hope that the medical data of residents in each community can be automatically aggregated and automatically analyzed statistically. The statistical results are used to conduct trend analysis and outbreak warning of epidemics, thus providing a powerful means for developing prevention and treatment intervention plans. Reference.
[0003] 随着国家新医改政策的颁布和实施， 与健康直接相关的医疗行业幵始迅猛发展 ， 医疗数据越来越趋于高度集中化。 在海量医疗数据的访问上， 存在大规模数 据统计分析的服务， 而且需要尽可能快的査询响应吋间。 由于医疗数据规模很 大， 医疗数据之间具有强关联性， 不同类型的用户对同一数据具有不同的观察 视角， 从而对医疗数据的存储模型有很高的要求以应付灵活多变的数据请求， 大规模数据上还存在大量已知的或者未知的数据分析需求， 査询的总类多， 需 要支持各种定制性査询。 由此可见， 用户对査询医疗数据的要求高， 对海量医 疗数据的存储与管理要求就越高， 因此现有医疗数据存储系统简单地采用传统 数据库、 商业并行数据库或者 SQL数据库对海量医疗数据进行存储已不能满足实 际情况和需求。  [0003] With the promulgation and implementation of the national new medical reform policy, the medical industry directly related to health has begun to develop rapidly, and medical data has become more and more centralized. In the access of massive medical data, there is a large-scale statistical analysis service, and it is necessary to query the response as quickly as possible. Due to the large scale of medical data and the strong correlation between medical data, different types of users have different observation angles for the same data, which has high requirements for the storage model of medical data to cope with flexible data requests. There are also a large number of known or unknown data analysis requirements on large-scale data. There are many general categories of queries, and various customized queries need to be supported. It can be seen that the user has high requirements for querying medical data, and the storage and management requirements for massive medical data are higher. Therefore, the existing medical data storage system simply uses a traditional database, a commercial parallel database or a SQL database for massive medical data. Storage has not been able to meet the actual situation and needs.
技术问题  technical problem
[0004] 本发明的主要目的在于提供一种医疗大数据关联存储系统及方法， 旨在解决现 有医疗数据存储系统对海量医疗数据进行分散存储而影响医疗数据分析处理效 率的问题。 问题的解决方案 [0004] The main object of the present invention is to provide a medical big data associated storage system and method, which aims to solve the problem that the existing medical data storage system performs distributed storage of massive medical data and affects the efficiency of medical data analysis and processing. Problem solution
技术解决方案  Technical solution
[0005] 为实现上述目的， 本发明提供了一种医疗大数据关联存储系统， 运行于云服务 器中， 所述云服务器通过通信网络与多个医疗数据源建立通信连接， 并通过数 据库连接与大数据存储仓库连接， 该系统包括：  [0005] In order to achieve the above object, the present invention provides a medical big data associative storage system, which runs in a cloud server, and the cloud server establishes a communication connection with a plurality of medical data sources through a communication network, and connects through a database and a large Data storage warehouse connection, the system includes:
[0006] 数据采集模块， 用于从多个医疗数据源收集每一个患者的原始医疗数据； [0007] 数据清洗模块， 用于对每一个患者的原始医疗数据进行清洗转换处理得到每一 个患者的规范医疗数据； [0006] a data collection module, configured to collect raw medical data of each patient from a plurality of medical data sources; [0007] a data cleaning module, configured to perform cleaning conversion processing on each patient's original medical data to obtain each patient's Standardize medical data;
[0008] 数据抽取模块， 用于从每一个患者的规范医疗数据中抽取每一个患者的身份信 息、 生命体征数据和历史就诊信息， 以及根据每一个患者的身份信息为每一个 患者产生一个身份标识号； [0008] a data extraction module, configured to extract identity information, vital sign data, and historical visit information of each patient from each patient's standardized medical data, and generate an identity for each patient according to the identity information of each patient. number;
[0009] 数据关联模块， 用于将每一个患者的身份标识号与患者各自对应的生命体征数 据进行关联并建立一个患者体征信息表， 并将每一个患者的身份标识号与患者 各自对应的历史就诊信息进行关联并建立一个患者就诊信息表； [0009] a data association module, configured to associate each patient's identification number with the patient's corresponding vital sign data and establish a patient vital information table, and associate each patient's identification number with the patient's respective history. Correlate the visit information and establish a patient visit information form;
[0010] 数据存储模块， 用于将所述患者体征信息表存储在大数据存储仓库中的第一分 区数据库中， 并将所述患者就诊信息表存储在大数据存储仓库中的第二分区数 据库中。 [0010] a data storage module, configured to store the patient sign information table in a first partition database in a big data storage warehouse, and store the patient visit information table in a second partition database in the big data storage warehouse in.
[0011] 优选的， 所述数据采集模块从多个医疗数据源收集每一个患者的原始医疗数据 的方式为： 设定一个定吋器脚本的执行吋间和执行周期， 以及按照定吋器脚本 的执行吋间和执行周期从不同的医疗数据源采集每一个患者的原始医疗数据。  [0011] Preferably, the data collection module collects the original medical data of each patient from a plurality of medical data sources by: setting a execution time and execution period of a constant script, and following the script The execution of the daytime and execution cycle collects raw medical data from each patient from different medical data sources.
[0012] 优选的， 所述数据清洗模块对每一个患者的原始医疗数据进行清洗转换处理的 方式为： 利用 ETL数据过滤转换组件移除原始医疗数据中无意义的词， 将原始医 疗数据中一个词的不同形式转换为相同形式， 以及刪除原始医疗数据中重复的 数据。  [0012] Preferably, the manner in which the data cleaning module performs the cleaning conversion process on the raw medical data of each patient is: using the ETL data filtering conversion component to remove meaningless words in the original medical data, and one of the original medical data is The different forms of the word are converted to the same form, and the duplicated data in the original medical data is deleted.
[0013] 优选的， 所述患者体征信息表的表头字段存储每一个患者的身份标识号， 所述 患者体征信息表的内容字段存储每一个患者对应的生命体征数据， 所述患者就 诊信息表的表头字段存储每一个患者的身份标识号， 所述患者体征信息表的内 容字段存储每一个患者对应的历史就诊信息。 [0014] 优选的， 所述生命体征数据包括患者的身高数据、 体重数据、 血压数据、 脉搏 数据、 心率数据、 血氧数据以及血糖数据， 所述历史就诊信息包括患者的历史 就诊吋间、 历史就诊医院、 历史就诊科室以及历史电子病历。 [0013] Preferably, the header field of the patient vital sign information table stores an identity identification number of each patient, and the content field of the patient vital sign information table stores vital sign data corresponding to each patient, and the patient visit information table The header field stores the identification number of each patient, and the content field of the patient vital information table stores historical visit information corresponding to each patient. [0014] Preferably, the vital sign data includes a patient's height data, body weight data, blood pressure data, pulse data, heart rate data, blood oxygen data, and blood glucose data, and the historical medical information includes a history of the patient, history, history Visiting hospitals, historical clinics, and historical electronic medical records.
[0015] 本发明还提供了一种医疗大数据关联存储方法， 应用于云服务器中， 所述云服 务器通过通信网络与多个医疗数据源建立通信连接， 并通过数据库连接与大数 据存储仓库连接， 所述医疗大数据关联存储方法包括步骤：  [0015] The present invention also provides a medical big data association storage method, which is applied to a cloud server, wherein the cloud server establishes a communication connection with a plurality of medical data sources through a communication network, and connects with a big data storage warehouse through a database connection. The medical big data association storage method includes the steps of:
[0016] 从多个医疗数据源收集每一个患者的原始医疗数据；  [0016] collecting raw medical data of each patient from a plurality of medical data sources;
[0017] 对每一个患者的原始医疗数据进行清洗转换处理得到每一个患者的规范医疗数 据；  [0017] performing a cleaning conversion process on the raw medical data of each patient to obtain standardized medical data for each patient;
[0018] 从每一个患者的规范医疗数据中抽取每一个患者的身份信息、 生命体征数据和 历史就诊信息；  [0018] extracting identity information, vital sign data, and historical visit information for each patient from each patient's standardized medical data;
[0019] 根据每一个患者的身份信息为每一个患者产生一个身份标识号；  [0019] generating an identification number for each patient based on the identity information of each patient;
[0020] 将每一个患者的身份标识号与患者各自对应的生命体征数据进行关联并建立一 个患者体征信息表， 并将每一个患者的身份标识号患者各自对应的历史就诊信 息进行关联并建立一个患者就诊信息表；  [0020] correlating each patient's identification number with the patient's corresponding vital sign data and establishing a patient sign information table, and correlating each patient's identification number with the corresponding historical medical information and establishing a Patient visit information form;
[0021] 将所述患者体征信息表存储在大数据存储仓库中的第一分区数据库中， 并将所 述患者就诊信息表存储在大数据存储仓库中的第二分区数据库中。 [0021] storing the patient sign information table in a first partition database in a big data storage repository, and storing the patient visit information table in a second partition database in the big data storage repository.
[0022] 优选的， 所述从多个医疗数据源收集每一个患者的原始医疗数据的步骤包括如 下步骤： [0022] Preferably, the step of collecting raw medical data of each patient from a plurality of medical data sources comprises the following steps:
[0023] 设定一个定吋器脚本的执行吋间和执行周期；  [0023] setting an execution time and an execution period of a timer script;
[0024] 按照定吋器脚本的执行吋间和执行周期从不同的医疗数据源采集每一个患者的 原始医疗数据。  [0024] Raw medical data for each patient is collected from different medical data sources in accordance with the execution time and execution cycle of the programmer script.
[0025] 优选的， 所述对每一个患者的原始医疗数据进行清洗转换处理的步骤包括如下 步骤： 利用 ETL数据过滤转换组件移除原始医疗数据中无意义的词； 将原始医疗 数据中的一个词的不同形式转换为相同形式； 刪除原始医疗数据中重复的数据  [0025] Preferably, the step of performing the cleaning conversion process on the raw medical data of each patient comprises the following steps: removing the meaningless words in the original medical data by using the ETL data filtering conversion component; Different forms of words are converted to the same form; delete duplicate data from raw medical data
[0026] 优选的， 所述患者体征信息表的表头字段存储每一个患者的身份标识号， 所述 患者体征信息表的内容字段存储每一个患者对应的生命体征数据， 所述患者就 诊信息表的表头字段存储每一个患者的身份标识号， 所述患者体征信息表的内 容字段存储每一个患者对应的历史就诊信息。 [0026] Preferably, the header field of the patient vital sign information table stores an identity identification number of each patient, and the content field of the patient vital sign information table stores vital vital sign data corresponding to each patient, and the patient is The header field of the medical information table stores the identification number of each patient, and the content field of the patient vital information table stores historical medical visit information corresponding to each patient.
[0027] 优选的， 所述生命体征数据包括患者的身高数据、 体重数据、 血压数据、 脉搏 数据、 心率数据、 血氧数据以及血糖数据， 所述历史就诊信息包括患者的历史 就诊吋间、 历史就诊医院、 历史就诊科室以及历史电子病历。 [0027] Preferably, the vital sign data includes a patient's height data, body weight data, blood pressure data, pulse data, heart rate data, blood oxygen data, and blood glucose data, and the historical medical information includes a history of the patient, history, history Visiting hospitals, historical clinics, and historical electronic medical records.
发明的有益效果  Advantageous effects of the invention
有益效果  Beneficial effect
[0028] 相较于现有技术， 本发明所述医疗大数据关联存储系统及方法采用上述技术方 案， 带来的技术效果为： 通过采集不同的医疗数据源中的医疗数据， 并将对医 疗数据进行清洗转换处理得到规范医疗数据， 从而使得医疗数据采集更加全面 、 更加准确。 此外， 将每个患者的身份标识号作为体征信息表与就诊信息表之 间的关联关系， 并将患者的体征信息表与就诊信息表分幵存储在大数据存储仓 库的不同分区数据库中， 减轻了系统负载， 提高了数据处理效率， 避免了访问 医疗数据吋产生冲突， 加快了对医疗数据的读取与处理速度， 从而能够提高医 疗服务水平与患者的满意度。  [0028] Compared with the prior art, the medical big data associated storage system and method of the present invention adopts the above technical solutions, and the technical effects brought by: collecting medical data in different medical data sources, and Data is cleaned and converted to obtain standardized medical data, making medical data collection more comprehensive and accurate. In addition, each patient's identification number is used as a relationship between the vital information table and the medical information table, and the patient's vital information table and the medical information table are stored in different partition databases of the big data storage warehouse to reduce The system load improves data processing efficiency, avoids conflicts in accessing medical data, speeds up the reading and processing of medical data, and improves medical service level and patient satisfaction.
对附图的简要说明  Brief description of the drawing
附图说明  DRAWINGS
[0029] 图 1是本发明医疗大数据关联存储系统优选实施例的架构图；  1 is a block diagram of a preferred embodiment of a medical big data associative storage system of the present invention;
[0030] 图 2是本发明医疗大数据关联存储方法优选实施例的流程图。 2 is a flow chart of a preferred embodiment of the medical big data association storage method of the present invention.
[0031] 本发明目的的实现、 功能特点及优点将结合实施例， 参照附图做进一步说明。 [0031] The implementation, functional features, and advantages of the present invention will be further described with reference to the accompanying drawings.
实施该发明的最佳实施例  BEST MODE FOR CARRYING OUT THE INVENTION
本发明的最佳实施方式  BEST MODE FOR CARRYING OUT THE INVENTION
[0032] 为更进一步阐述本发明为达成上述目的所采取的技术手段及功效， 以下结合附 图及优选实施例， 对本发明的具体实施方式、 结构、 特征及其功效进行详细说 明。 应当理解， 此处所描述的具体实施例仅仅用以解释本发明， 并不用于限定 本发明。 The specific embodiments, structures, features and utilities of the present invention are described in detail below in conjunction with the drawings and the preferred embodiments. It is understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
[0033] 参考图 1所示， 图 1是本发明医疗大数据关联存储系统优选实施例的应用环境架 构示意图。 在本实施例中， 所述医疗大数据关联存储系统 10应用并运行于云服 务器 1中， 所述云服务器 1通过通信网络 3与多个医疗数据源 2 (图 1中以两个为例 进行说明） 建立通信连接， 以及通过数据库连接 5与大数据存储仓库 4连接。 所 述通信网络 3可以是有线通信网络或无线通信网络。 在本实施例中， 所述通信网 络 3优选为无线通信网络， 包括但不限于， GSM网络、 GPRS网络、 CDMA网络 、 TD-SCDMA网络、 WiMAX网络、 TD-LTE网络、 FDD-LTE网络等无线传输网 络。 所述数据库连接 5可以为一种幵放数据库连接 （Open Database Connectivity ， ODBC) 以及 Java数据库连接 （Java Data Base Connectivity， JDBC) 。 [0033] Referring to FIG. 1, FIG. 1 is an application environment framework of a preferred embodiment of the medical big data associative storage system of the present invention. Schematic diagram. In this embodiment, the medical big data associated storage system 10 is applied and runs in the cloud server 1, and the cloud server 1 is connected to the plurality of medical data sources 2 through the communication network 3 (two in FIG. 1 as an example). Description) Establish a communication connection and connect to the big data storage repository 4 via the database connection 5. The communication network 3 can be a wired communication network or a wireless communication network. In this embodiment, the communication network 3 is preferably a wireless communication network, including but not limited to, a GSM network, a GPRS network, a CDMA network, a TD-SCDMA network, a WiMAX network, a TD-LTE network, an FDD-LTE network, and the like. transporting network. The database connection 5 can be an Open Database Connectivity (ODBC) and a Java Data Base Connectivity (JDBC).
[0034] 所述云服务器 1是一种云平台或云平台中的一台服务器， 通过云服务器 1的数据 传输能力、 数据存储能力及数据处理能力， 可以快速地从不同的医疗数据源 2采 集到不同的原始医疗数据。 所述医疗数据源 2存储有患者的原始医疗数据， 可以 为产生临床数据的医院信息系统， 例如 HIS系统、 EMR、 LIS、 PACS系统， 也可 以为体检中心、 私人诊所和急救中心等任何适合的临床业务系统。 所述大数据 存储仓库 4包括第一分区数据库 41以及第二分区数据库 42， 第一分区数据库 41用 于存储有患者体征信息表， 第二分区数据库 42用于存储有患者就诊信息表。 所 述患者体征信息表用于存储从不同医疗数据源 2采集的患者的生命体征数据， 所 述患者就诊信息表用于存储从不同医疗数据源 2采集的患者的历史就诊数据。  [0034] The cloud server 1 is a cloud platform or a server in the cloud platform, and the data transmission capability, the data storage capability, and the data processing capability of the cloud server 1 can be quickly collected from different medical data sources 2 Different raw medical data. The medical data source 2 stores the original medical data of the patient, and may be a hospital information system that generates clinical data, such as a HIS system, an EMR, a LIS, a PACS system, or any suitable medical center, private clinic, emergency center, and the like. Clinical business system. The big data storage repository 4 includes a first partition database 41 and a second partition database 42, a first partition database 41 for storing patient sign information tables, and a second partition database 42 for storing patient visit information tables. The patient sign information table is used to store vital sign data of patients collected from different medical data sources 2 for storing historical visit data of patients collected from different medical data sources 2.
[0035] 在本实施例中， 所述云服务器 1包括， 但不仅限于， 医疗大数据关联存储系统 1 0、 通信单元 11、 存储单元 12以及处理单元 13。 所述通信单元 11为一种有线通讯 接口或者为无线通讯接口， 例如， 支持 GSM、 GPRS、 WCDMA、 CDMA、 TD-S CDMA、 WiMAX TD-LTE ^ FDD-LTE等通讯技术的通讯接口。 所述存储单元 1 2可以为一种只读存储单元 ROM, 电可擦写存储单元 EEPROM、 快闪存储单元 F LASH或固体硬盘等。 所述的处理单元 13可以为一种中央处理器 （Central Processing Unit, CPU) 、 微控制器 （MCU) 、 数据处理芯片、 或者具有数据处 理功能的信息处理单元。  [0035] In this embodiment, the cloud server 1 includes, but is not limited to, a medical big data associated storage system 10, a communication unit 11, a storage unit 12, and a processing unit 13. The communication unit 11 is a wired communication interface or a wireless communication interface, for example, a communication interface supporting communication technologies such as GSM, GPRS, WCDMA, CDMA, TD-S CDMA, WiMAX TD-LTE ^ FDD-LTE. The storage unit 12 can be a read only memory unit ROM, an EEPROM, a flash memory unit F LASH or a solid hard disk. The processing unit 13 may be a central processing unit (CPU), a microcontroller (MCU), a data processing chip, or an information processing unit having a data processing function.
[0036] 所述医疗大数据关联存储系统 10， 包括但不仅限于， 数据采集模块 101、 数据 清洗模块 102、 数据抽取模块 103、 数据关联模块 104以及数据存储模块 105。 本 发明所称的模块是指一种能够被所述云平台服务器 1的处理单元 13执行并且能够 完成固定功能的一系列计算机程序指令段， 其存储在所述云平台服务器 1的存储 单元 12中。 [0036] The medical big data associated storage system 10 includes, but is not limited to, a data collection module 101, a data cleaning module 102, a data extraction module 103, a data association module 104, and a data storage module 105. The module referred to in the present invention refers to a module that can be executed by the processing unit 13 of the cloud platform server 1 and is capable of A series of computer program instruction segments that perform fixed functions are stored in the storage unit 12 of the cloud platform server 1.
[0037] 所述数据采集模块 101用于从多个不同的医疗数据源 2收集每一个患者的原始医 疗数据。 一般地， 患者的原始医疗数据的生成和采集通常来自于医院信息系统 所产生的临床数据， 例如 HIS系统、 EMR、 LIS、 PACS系统， 但是随着物联网的 发展， 患者的原始医疗数据还可以来自于体检中心、 私人诊所和急救中心等任 何适合的临床业务系统。 具体地， 所述数据采集模块 101具体用于设定一个定吋 器脚本的执行吋间和执行周期， 以及按照定吋器脚本的执行吋间和执行周期从 不同的医疗数据源采集原始医疗数据。  [0037] The data collection module 101 is configured to collect raw medical data for each patient from a plurality of different medical data sources 2. Generally, the generation and collection of the patient's original medical data usually comes from the clinical data generated by the hospital information system, such as HIS system, EMR, LIS, PACS system, but with the development of the Internet of Things, the patient's original medical data can also come from Any suitable clinical business system, such as a medical center, private clinic, and emergency center. Specifically, the data collection module 101 is specifically configured to set an execution time and an execution period of a programmer script, and collect original medical data from different medical data sources according to execution time and execution cycle of the programmer script. .
[0038] 所述数据清洗模块 102用于对每一个患者的原始医疗数据进行清洗转换处理得 到每一个患者的规范医疗数据。 在本实施例中， 由于从不同的医疗数据源 2收集 上来的原始医疗数据可能有坏数据、 不合理的数据或者是重复的数据等， 因此 数据清洗模块 102需要利用 ETL (抽取 （extract) 、 转换 （transform) 、 加载 （lo ad) ) 数据过滤转换组件对所收集的原始医疗数据进行清洗转换处理得到规范医 疗数据， 从而并保证了医疗数据的准确性， 并为医疗数据的存储节省了存储空 间。 具体地， 所述数据清洗模块 102对每一个患者的原始医疗数据进行清洗转换 处理的方式为： 利用 ETL数据过滤转换组件移除原始医疗数据中无意义的词， 将 原始医疗数据中一个词的不同形式转换为相同形式， 以及刪除原始医疗数据中 重复的数据等处理。  [0038] The data cleaning module 102 is configured to perform a cleaning conversion process on the raw medical data of each patient to obtain standardized medical data for each patient. In this embodiment, since the original medical data collected from different medical data sources 2 may have bad data, unreasonable data, or repeated data, etc., the data cleaning module 102 needs to utilize ETL (extract, Transform (loading), loading (lo ad) The data filtering and transformation component cleans and converts the collected raw medical data to obtain standardized medical data, thereby ensuring the accuracy of medical data and saving storage for medical data storage. space. Specifically, the manner in which the data cleaning module 102 performs the cleaning conversion process on the raw medical data of each patient is: using the ETL data filtering conversion component to remove meaningless words in the original medical data, and using a word in the original medical data. The different forms are converted to the same form, and the processing of duplicate data in the original medical data is deleted.
[0039] 所述数据抽取模块 103用于从每一个患者的规范医疗数据中抽取每一个患者的 身份信息、 生命体征数据和历史就诊信息， 以及根据每一个患者的身份信息为 每一个患者产生一个身份标识号 （ID) 。 在本实施例中， 所述生命体征数据包 括患者的身高数据、 体重数据、 血压数据、 脉搏数据、 心率数据、 血氧数据、 血糖数据等数据信息。 所述历史就诊信息包括患者的历史就诊吋间、 历史就诊 医院、 历史就诊科室以及历史电子病历等数据信息。  [0039] The data extraction module 103 is configured to extract identity information, vital sign data, and historical visit information of each patient from the standardized medical data of each patient, and generate one for each patient according to the identity information of each patient. Identification number (ID). In this embodiment, the vital sign data includes data such as height data, body weight data, blood pressure data, pulse data, heart rate data, blood oxygen data, blood glucose data, and the like of the patient. The historical medical treatment information includes data such as a patient's historical visit, a historical hospital, a historical medical department, and a historical electronic medical record.
[0040] 所述数据关联模块 104用于将每一个患者的身份标识号与患者各自对应的生命 体征数据进行关联并建立一个患者体征信息表， 并将每一个患者的身份标识号 与患者各自对应的历史就诊信息进行关联并建立一个患者就诊信息表。 在本实 施例中， 所述患者体征信息表的表头字段存储每一个患者的身份标识号， 所述 患者体征信息表的内容字段存储每一个患者对应的生命体征数据， 所述患者就 诊信息表的表头字段存储每一个患者的身份标识号， 所述患者体征信息表的内 容字段存储每一个患者对应的历史就诊信息。 [0040] The data association module 104 is configured to associate each patient's identification number with the patient's corresponding vital sign data and establish a patient sign information table, and associate each patient's identification number with the patient. The historical visit information is linked and a patient visit information form is created. In this reality In an embodiment, the header field of the patient vital sign information table stores an identification number of each patient, and the content field of the patient vital sign information table stores vital sign data corresponding to each patient, and the table of the patient medical information table The header field stores the identity identification number of each patient, and the content field of the patient vital sign information table stores historical medical visit information corresponding to each patient.
[0041] 所述数据存储模块 105用于将患者体征信息表存储在大数据存储仓库 4中的第一 分区数据库 41中， 并将患者就诊信息表存储在大数据存储仓库 4中的第二分区数 据库 42中。 由于每个患者的身份标识号是唯一， 因此将每个患者的身份标识号 作为患者体征信息表与患者就诊信息表之间的关联关系， 并将患者体征信息表 与患者就诊信息表分幵存储在大数据存储仓库 4的不同分区数据库中， 避免了访 问医疗数据吋产生冲突， 加快了对海量医疗数据的读取与处理速度， 从而能够 提高医疗服务水平与患者的满意度。 [0041] The data storage module 105 is configured to store the patient vital information information table in the first partition database 41 in the big data storage warehouse 4, and store the patient visit information table in the second partition in the big data storage warehouse 4. In database 42. Since each patient's identification number is unique, each patient's identification number is used as a relationship between the patient's vital information table and the patient's medical information table, and the patient's physical information table and the patient's medical information table are stored separately. In the different partition databases of the big data storage warehouse 4, the access to medical data is avoided, conflicts are generated, and the reading and processing speed of the massive medical data is accelerated, thereby improving the medical service level and patient satisfaction.
[0042] 为实现本发明目的， 本发明还提供了一种医疗大数据关联存储方法。 如图 2所 示， 图 2是本发明医疗大数据关联存储方法优选实施例的流程图。 在本实施例中 ， 所述的医疗大数据关联存储方法包括如下步骤：  [0042] In order to achieve the object of the present invention, the present invention also provides a medical big data association storage method. As shown in FIG. 2, FIG. 2 is a flow chart of a preferred embodiment of the medical big data association storage method of the present invention. In this embodiment, the medical big data association storage method includes the following steps:
[0043] 步骤 S21， 从不同的医疗数据源收集每一个患者的原始医疗数据； 具体地， 数 据采集模块 101从多个不同的医疗数据源 2收集每一个患者的原始医疗数据。 一 般地， 患者的原始医疗数据的生成和采集通常来自于医院信息系统所产生的临 床数据， 例如 HIS系统、 EMR、 LIS、 PACS系统， 但是随着物联网的发展， 患者 的原始医疗数据还可以来自于体检中心、 私人诊所和急救中心等任何适合的临 床业务系统。 在本实施例中， 数据采集模块 101对每一个患者的原始医疗数据进 行清洗转换处理的步骤包括步骤： 设定一个定吋器脚本的执行吋间和执行周期 ， 按照定吋器脚本的执行吋间和执行周期从不同的医疗数据源采集原始医疗数 据。  [0043] Step S21: Collecting raw medical data of each patient from different medical data sources; specifically, the data collecting module 101 collects raw medical data of each patient from a plurality of different medical data sources 2. Generally, the generation and collection of the patient's original medical data usually comes from the clinical data generated by the hospital information system, such as HIS system, EMR, LIS, PACS system, but with the development of the Internet of Things, the patient's original medical data can also come from Any suitable clinical business system, such as a medical center, private clinic, and emergency center. In this embodiment, the step of the data acquisition module 101 performing the cleaning conversion process on the raw medical data of each patient includes the steps of: setting an execution time and an execution period of a programmer script according to the execution of the script. Inter- and execution cycles collect raw medical data from different medical data sources.
[0044] 步骤 S22， 对每一个患者的原始医疗数据进行清洗转换处理得到每一个患者的 规范医疗数据； 具体地， 数据清洗模块 102对每一个患者的原始医疗数据进行清 洗转换处理得到每一个患者的规范医疗数据。 在本实施例中， 由于从不同的医 疗数据源 2收集上来的原始医疗数据可能有坏数据、 不合理的数据或者是重复的 数据等， 因此数据清洗模块 102需要利用 ETL (抽取 （extract) 、 转换 （transform ) 、 加载 （load) 数据过滤转换组件对所收集的原始医疗数据进行清洗转换处理 得到规范医疗数据， 从而并保证了医疗数据的准确性， 并为医疗数据的存储节 省了存储空间。 具体地， 数据清洗模块 102对每一个患者的原始医疗数据进行清 洗转换处理的步骤包括步骤： 利用利用 ETL数据过滤转换组件移除原始医疗数据 中无意义的词， 将原始医疗数据中一个词的不同形式转换为相同形式， 以及刪 除原始医疗数据中重复的数据等处理。 [0044] Step S22, performing clean conversion processing on the raw medical data of each patient to obtain standardized medical data for each patient; specifically, the data cleaning module 102 performs cleaning conversion processing on each patient's original medical data to obtain each patient. Standard medical data. In this embodiment, since the original medical data collected from different medical data sources 2 may have bad data, unreasonable data, or repeated data, etc., the data cleaning module 102 needs to utilize ETL (extract, Transformation The data filtering conversion component performs the cleaning conversion processing on the collected raw medical data to obtain the standardized medical data, thereby ensuring the accuracy of the medical data and saving the storage space for the storage of the medical data. Specifically, the step of performing the cleaning conversion process on the raw medical data of each patient by the data cleaning module 102 includes the steps of: removing the meaningless word in the original medical data by using the ETL data filtering conversion component, and using a word in the original medical data The different forms are converted to the same form, and the processing of duplicate data in the original medical data is deleted.
[0045] 步骤 S23， 从每一个患者的规范医疗数据中抽取每一个患者的身份信息和生命 体征数据； 具体地， 数据抽取模块 103从每一个患者的规范医疗数据中抽取每一 个患者的身份信息、 生命体征数据和历史就诊信息。 在本实施例中， 所述患者 的生命体征数据包括患者的身高数据、 体重数据、 血压数据、 脉搏数据、 心率 数据、 血氧数据以及血糖数据等数据信息。 所述患者的历史就诊信息包括患者 的历史就诊吋间、 历史就诊医院、 历史就诊科室以及历史电子病历等数据信息 [0045] Step S23, extracting identity information and vital sign data of each patient from the standardized medical data of each patient; specifically, the data extraction module 103 extracts identity information of each patient from the standardized medical data of each patient. , vital signs data and historical visit information. In this embodiment, the vital sign data of the patient includes data such as height data, body weight data, blood pressure data, pulse data, heart rate data, blood oxygen data, and blood glucose data of the patient. The patient's historical visit information includes data such as the patient's historical visit, historical hospital, historical medical department, and historical electronic medical records.
[0046] 步骤 S24， 根据每一个患者的身份信息为每一个患者产生一个身份标识号； 具 体地， 数据抽取模块 103根据每一个患者的身份信息为每一个患者产生一个身份 标识号， 作为每一个患者唯一的身份标识。 [0046] step S24, generating an identity identification number for each patient according to the identity information of each patient; specifically, the data extraction module 103 generates an identity identification number for each patient according to the identity information of each patient, as each The unique identity of the patient.
[0047] 步骤 S25， 将每一个患者的身份标识号与该患者的生命体征数据进行关联并建 立一个患者体征信息表， 并将每一个患者的身份标识号与该患者的历史就诊信 息进行关联并建立一个患者就诊信息表； 具体地， 数据关联模块 104将每一个患 者的身份标识号与患者各自对应的生命体征数据进行关联并建立一个患者体征 信息表， 并将每一个患者的身份标识号与患者各自对应的历史就诊信息进行关 联并建立一个患者就诊信息表。 在本实施例中， 所述患者体征信息表的表头字 段存储每一个患者的身份标识号， 所述患者体征信息表的内容字段存储每一个 患者对应的生命体征数据， 所述患者就诊信息表的表头字段存储每一个患者的 身份标识号， 所述患者体征信息表的内容字段存储每一个患者对应的历史就诊 f π息。  [0047] Step S25, associating the identification number of each patient with the vital sign data of the patient and establishing a patient vital information table, and associating the identification number of each patient with the historical medical information of the patient and Establishing a patient visit information table; specifically, the data association module 104 associates each patient's identification number with the patient's respective vital sign data and establishes a patient sign information table, and identifies each patient's identification number and The patient's respective historical visit information is correlated and a patient visit information form is established. In this embodiment, the header field of the patient vital sign information table stores the identity identification number of each patient, and the content field of the patient vital sign information table stores vital sign data corresponding to each patient, and the patient visit information table The header field stores the identification number of each patient, and the content field of the patient vital information table stores a historical visit corresponding to each patient.
[0048] 步骤 S26， 将患者体征信息表存储在大数据存储仓库中的第一分区数据库中， 并将患者就诊信息表存储在大数据存储仓库中的第二分区数据库中； 具体地， 数据存储模块 105将患者体征信息表存储在大数据存储仓库 4中的第一分区数据 库 41中， 并将患者就诊信息表存储在大数据存储仓库 4中的第二分区数据库 42中[0048] step S26, storing the patient vital sign information table in the first partition database in the big data storage warehouse, and storing the patient visit information table in the second partition database in the big data storage warehouse; specifically, The data storage module 105 stores the patient vital information table in the first partition database 41 in the big data storage repository 4, and stores the patient visit information table in the second partition database 42 in the big data storage repository 4.
。 在本实施例中， 由于每个患者的身份标识号是唯一， 每个患者的身份标识号 作为患者体征信息表与患者就诊信息表之间的关联关系， 并将患者体征信息表 与患者就诊信息表分幵存储在大数据存储仓库 4的不同分区数据库中， 因此增强 了数据结构化存储以及避免了访问医疗数据吋产生冲突， 加快了云服务器 1对医 疗数据的读取与处理速度， 从而能够提高医疗服务水平与患者的满意度。 . In this embodiment, since the identification number of each patient is unique, the identification number of each patient is used as a relationship between the patient's vital information table and the patient's medical information table, and the patient's vital information table and the patient's medical information are displayed. The table branches are stored in different partition databases of the big data storage warehouse 4, thereby enhancing data structured storage and avoiding conflicts in accessing medical data, speeding up the reading and processing speed of the medical data by the cloud server 1 Improve medical service levels and patient satisfaction.
[0049] 本发明所述医疗大数据关联存储系统及方法通过采集不同的医疗数据源 2中的 医疗数据， 并将对医疗数据进行清洗转换处理得到规范医疗数据， 从而使得医 疗数据采集更加全面、 更加准确。 此外， 将每个患者的身份标识号作为体征信 息表与就诊信息表之间的关联关系， 并将患者的体征信息表与就诊信息表分幵 存储在大数据存储仓库的不同分区数据库中， 减轻了系统负载， 提高了数据处 理效率， 避免了访问医疗数据吋产生冲突， 加快了对医疗数据的读取与处理速 度， 从而能够提高医疗服务水平与患者的满意度。 [0049] The medical big data associated storage system and method of the present invention collects medical data in different medical data sources 2, and performs medical cleaning and conversion processing to obtain standardized medical data, thereby making medical data collection more comprehensive. more precise. In addition, each patient's identification number is used as a relationship between the vital information table and the medical information table, and the patient's vital information table and the medical information table are stored in different partition databases of the big data storage warehouse to reduce The system load improves data processing efficiency, avoids conflicts in accessing medical data, speeds up the reading and processing of medical data, and improves medical service level and patient satisfaction.
[0050] 以上仅为本发明的优选实施例， 并非因此限制本发明的专利范围， 凡是利用本 发明说明书及附图内容所作的等效结构或等效功能变换， 或直接或间接运用在 其他相关的技术领域， 均同理包括在本发明的专利保护范围内。 The above are only the preferred embodiments of the present invention, and are not intended to limit the scope of the invention, and the equivalent structure or equivalent function changes made by the description of the present invention and the contents of the drawings, or directly or indirectly applied to other related The technical field is equally included in the scope of patent protection of the present invention.
工业实用性  Industrial applicability
[0051] 相较于现有技术， 本发明所述医疗大数据关联存储系统及方法采用上述技术方 案， 带来的技术效果为： 通过采集不同的医疗数据源中的医疗数据， 并将对医 疗数据进行清洗转换处理得到规范医疗数据， 从而使得医疗数据采集更加全面 、 更加准确。 此外， 将每个患者的身份标识号作为体征信息表与就诊信息表之 间的关联关系， 并将患者的体征信息表与就诊信息表分幵存储在大数据存储仓 库的不同分区数据库中， 减轻了系统负载， 提高了数据处理效率， 避免了访问 医疗数据吋产生冲突， 加快了对医疗数据的读取与处理速度， 从而能够提高医 疗服务水平与患者的满意度。  Compared with the prior art, the medical big data associated storage system and method of the present invention adopts the above technical solutions, and the technical effects brought by: collecting medical data in different medical data sources, and Data is cleaned and converted to obtain standardized medical data, making medical data collection more comprehensive and accurate. In addition, each patient's identification number is used as a relationship between the vital information table and the medical information table, and the patient's vital information table and the medical information table are stored in different partition databases of the big data storage warehouse to reduce The system load improves data processing efficiency, avoids conflicts in accessing medical data, speeds up the reading and processing of medical data, and improves medical service level and patient satisfaction.

Claims

权利要求书  Claim
[权利要求 1] 一种医疗大数据关联存储系统， 运行于云服务器中， 所述云服务器通 过通信网络与多个医疗数据源建立通信连接， 并通过数据库连接与大 数据存储仓库连接， 其特征在于， 所述医疗大数据关联存储系统包括 ： 数据采集模块， 用于从多个医疗数据源收集每一个患者的原始医疗 数据； 数据清洗模块， 用于对每一个患者的原始医疗数据进行清洗转 换处理得到每一个患者的规范医疗数据； 数据抽取模块， 用于从每一 个患者的规范医疗数据中抽取每一个患者的身份信息、 生命体征数据 和历史就诊信息， 以及根据每一个患者的身份信息为每一个患者产生 一个身份标识号； 数据关联模块， 用于将每一个患者的身份标识号与 患者各自对应的生命体征数据进行关联并建立一个患者体征信息表， 并将每一个患者的身份标识号与患者各自对应的历史就诊信息进行关 联并建立一个患者就诊信息表； 数据存储模块， 用于将所述患者体征 信息表存储在大数据存储仓库中的第一分区数据库中， 并将所述患者 就诊信息表存储在大数据存储仓库中的第二分区数据库中。  [Claim 1] A medical big data associative storage system, running in a cloud server, the cloud server establishing a communication connection with a plurality of medical data sources through a communication network, and connecting to a big data storage warehouse through a database connection, and the characteristics thereof The medical big data associated storage system includes: a data collection module, configured to collect raw medical data of each patient from a plurality of medical data sources; and a data cleaning module, configured to perform cleaning conversion on each patient's original medical data Processing the standardized medical data of each patient; the data extraction module is configured to extract identity information, vital sign data and historical medical information of each patient from the standardized medical data of each patient, and according to the identity information of each patient Each patient generates an identification number; a data association module is configured to associate each patient's identification number with the patient's corresponding vital sign data and establish a patient vital information table, and identify each patient's identification number With the patient The historical medical information is associated and a patient medical information table is established; a data storage module is configured to store the patient vital information information table in a first partition database in the big data storage warehouse, and store the patient medical information table In the second partition database in the big data storage repository.
[权利要求 2] 如权利要求 1所述的医疗大数据关联存储系统， 其特征在于， 所述数 据采集模块从多个医疗数据源收集每一个患者的原始医疗数据的方式 为： 设定一个定吋器脚本的执行吋间和执行周期， 以及按照定吋器脚 本的执行吋间和执行周期从不同的医疗数据源采集每一个患者的原始 医疗数据。  [Claim 2] The medical big data associative storage system according to claim 1, wherein the data collection module collects raw medical data of each patient from a plurality of medical data sources in the following manner: The execution time and execution cycle of the buffer script, and the raw medical data of each patient are collected from different medical data sources according to the execution time and execution cycle of the programmer script.
[权利要求 3] 如权利要求 1所述的医疗大数据关联存储系统， 其特征在于， 所述数 据清洗模块对每一个患者的原始医疗数据进行清洗转换处理的方式为 ： 利用 ETL数据过滤转换组件移除原始医疗数据中无意义的词， 将原 始医疗数据中一个词的不同形式转换为相同形式， 以及刪除原始医疗 数据中重复的数据。  [Claim 3] The medical big data associative storage system according to claim 1, wherein the data cleaning module performs a cleaning conversion process on the original medical data of each patient: using ETL data filtering conversion component Remove meaningless words from the original medical data, convert different forms of a word in the original medical data into the same form, and delete duplicate data from the original medical data.
[权利要求 4] 如权利要求 1所述的医疗大数据关联存储系统， 其特征在于， 所述患 者体征信息表的表头字段存储每一个患者的身份标识号， 所述患者体 征信息表的内容字段存储每一个患者对应的生命体征数据， 所述患者 就诊信息表的表头字段存储每一个患者的身份标识号， 所述患者体征 信息表的内容字段存储每一个患者对应的历史就诊信息。 [Claim 4] The medical big data associative storage system according to claim 1, wherein a header field of the patient vital sign information table stores an identification number of each patient, and a content of the patient vital information table The field stores vital sign data corresponding to each patient, the patient The header field of the medical information table stores the identification number of each patient, and the content field of the patient vital information table stores historical medical information corresponding to each patient.
如权利要求 1所述的医疗大数据关联存储系统， 其特征在于， 所述生 命体征数据包括患者的身高数据、 体重数据、 血压数据、 脉搏数据、 心率数据、 血氧数据以及血糖数据， 所述历史就诊信息包括患者的历 史就诊吋间、 历史就诊医院、 历史就诊科室以及历史电子病历。 一种医疗大数据关联存储方法， 应用于云服务器中， 所述云服务器通 过通信网络与多个医疗数据源建立通信连接， 并通过数据库连接与大 数据存储仓库连接， 其特征在于， 所述医疗大数据关联存储方法包括 步骤： 从多个医疗数据源收集每一个患者的原始医疗数据； 对每一个 患者的原始医疗数据进行清洗转换处理得到每一个患者的规范医疗数 据； 从每一个患者的规范医疗数据中抽取每一个患者的身份信息、 生 命体征数据和历史就诊信息； 根据每一个患者的身份信息为每一个患 者产生一个身份标识号； 将每一个患者的身份标识号与患者各自对应 的生命体征数据进行关联并建立一个患者体征信息表， 并将每一个患 者的身份标识号与患者各自对应的历史就诊信息进行关联并建立一个 患者就诊信息表； 将所述患者体征信息表存储在大数据存储仓库中的 第一分区数据库中， 并将所述患者就诊信息表存储在大数据存储仓库 中的第二分区数据库中。 The medical big data associative storage system according to claim 1, wherein the vital sign data includes a patient's height data, body weight data, blood pressure data, pulse data, heart rate data, blood oxygen data, and blood glucose data, Historical visit information includes the patient's history visits, historical hospitals, historical visits, and historical electronic medical records. A medical big data association storage method is applied to a cloud server, wherein the cloud server establishes a communication connection with a plurality of medical data sources through a communication network, and is connected to the big data storage warehouse through a database connection, wherein the medical server The big data associative storage method comprises the steps of: collecting raw medical data of each patient from a plurality of medical data sources; performing a cleaning conversion process on each patient's original medical data to obtain standardized medical data for each patient; from each patient's specification The medical data extracts identity information, vital sign data and historical medical information of each patient; generates an identification number for each patient according to the identity information of each patient; and identifies each patient's identification number with the patient's respective life The vital signs data are correlated and a patient sign information table is established, and each patient's identification number is associated with the patient's corresponding historical medical information and a patient medical information table is established; the patient vital information information table is stored in the big data. Save Warehouse database in the first partition, the second partition and the patient treatment information database table stored in large data storage in the warehouse.
如权利要求 6所述的医疗大数据关联存储方法， 其特征在于， 所述从 多个医疗数据源收集每一个患者的原始医疗数据的步骤包括如下步骤 ： 设定一个定吋器脚本的执行吋间和执行周期； 按照定吋器脚本的执 行吋间和执行周期从不同的医疗数据源采集每一个患者的原始医疗数 据。 The medical big data association storage method according to claim 6, wherein the step of collecting raw medical data of each patient from a plurality of medical data sources comprises the steps of: setting an execution of a programmer script吋Inter- and execution cycles; Raw medical data for each patient is collected from different medical data sources according to the execution time and execution cycle of the programmer script.
如权利要求 6所述的医疗大数据关联存储方法， 其特征在于， 所述对 每一个患者的原始医疗数据进行清洗转换处理的步骤包括如下步骤： 利用 ETL数据过滤转换组件移除原始医疗数据中无意义的词； 将原始 医疗数据中的一个词的不同形式转换为相同形式； 刪除原始医疗数据 中重复的数据。 The medical big data association storage method according to claim 6, wherein the step of performing a cleaning conversion process on the raw medical data of each patient comprises the following steps: removing the original medical data by using the ETL data filtering conversion component Meaningless words; convert different forms of a word in raw medical data into the same form; delete original medical data Duplicate data.
[权利要求 9] 如权利要求 6所述的医疗大数据关联存储方法， 其特征在于， 所述患 者体征信息表的表头字段存储每一个患者的身份标识号， 所述患者体 征信息表的内容字段存储每一个患者对应的生命体征数据， 所述患者 就诊信息表的表头字段存储每一个患者的身份标识号， 所述患者体征 信息表的内容字段存储每一个患者对应的历史就诊信息。  [Claim 9] The medical big data association storage method according to claim 6, wherein the header field of the patient vital sign information table stores an identification number of each patient, and the content of the patient vital information table The field stores vital sign data corresponding to each patient, the head field of the patient visit information table stores the identification number of each patient, and the content field of the patient sign information table stores historical visit information corresponding to each patient.
[权利要求 10] 如权利要求 6所述的医疗大数据关联存储方法， 其特征在于， 所述生 命体征数据包括患者的身高数据、 体重数据、 血压数据、 脉搏数据、 心率数据、 血氧数据以及血糖数据， 所述历史就诊信息包括患者的历 史就诊吋间、 历史就诊医院、 历史就诊科室以及历史电子病历。  [Claim 10] The medical big data association storage method according to claim 6, wherein the vital sign data includes a patient's height data, body weight data, blood pressure data, pulse data, heart rate data, blood oxygen data, and Blood glucose data, the historical visit information includes a patient's historical visit, a historical hospital, a history clinic, and a historical electronic medical record.
PCT/CN2017/088351 2016-12-31 2017-06-15 Medical big data association and storage system and method WO2018120668A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201611267777.XA CN106815337A (en) 2016-12-31 2016-12-31 Medical big data associated storage system and method
CN201611267777.X 2016-12-31

Publications (1)

Publication Number Publication Date
WO2018120668A1 true WO2018120668A1 (en) 2018-07-05

Family

ID=59110605

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/088351 WO2018120668A1 (en) 2016-12-31 2017-06-15 Medical big data association and storage system and method

Country Status (2)

Country Link
CN (1) CN106815337A (en)
WO (1) WO2018120668A1 (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112582056A (en) * 2020-12-21 2021-03-30 曙光星云信息技术（北京）有限公司 Regional medical information management platform based on big data technology
CN112863626A (en) * 2021-03-08 2021-05-28 北京冠新医卫软件科技有限公司 Multi-platform similar medical data removing method, device and equipment
CN114974565A (en) * 2022-05-17 2022-08-30 上海市第四人民医院 Refined management and control method and system for diagnosis and treatment stages of new coronary patients
CN117272395A (en) * 2023-11-21 2023-12-22 江西曼荼罗软件有限公司 Patient medical data processing method and system

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106815337A (en) * 2016-12-31 2017-06-09 深圳市易特科信息技术有限公司 Medical big data associated storage system and method
CN106815336A (en) * 2016-12-31 2017-06-09 深圳市易特科信息技术有限公司 Medical data inquiry system and method based on big data associated storage
CN107704600B (en) * 2017-10-16 2018-11-16 上海康云科技有限公司 A kind of tuberculosis detection cloud data management and analysis system
CN108847274B (en) * 2018-05-16 2021-07-06 上海术木医疗科技有限公司 Vital sign data processing method and system based on cloud platform
CN108922607A (en) * 2018-05-31 2018-11-30 康键信息技术（深圳）有限公司 Server, the method for data processing and storage medium
CN109119138A (en) * 2018-09-19 2019-01-01 广州视源电子科技股份有限公司 Sign data acquisition system
CN109471863B (en) * 2018-11-12 2021-07-20 北京懿医云科技有限公司 Information query method and device based on distributed database and electronic equipment
CN109597801A (en) * 2018-11-14 2019-04-09 金色熊猫有限公司 Medical data standardized management method and system, electronic equipment, storage medium
CN109710682A (en) 2018-12-31 2019-05-03 深圳市道通科技股份有限公司 A kind of diagnostic data processing method, device, diagnostic device and server
CN109935285A (en) * 2019-01-30 2019-06-25 杭州脉兴医疗科技有限公司 A kind of the structuring processing method and processing system of ICU nursing forms data
CN110085326A (en) * 2019-04-30 2019-08-02 上海复繁信息科技有限公司 A kind of atrial fibrillation multidimensional big data analysis system based on MySQL database
CN110442638A (en) * 2019-07-23 2019-11-12 万达信息股份有限公司 A kind of the visual information generation method and system of medical data
CN113537529A (en) * 2021-07-30 2021-10-22 国能铁路装备有限责任公司 Truck bearing associated data generation method and device and computer equipment
CN113938539B (en) * 2021-12-17 2022-03-04 中国人民解放军总医院 Tracing method and system for medical data
CN114417033A (en) * 2022-01-14 2022-04-29 联仁健康医疗大数据科技股份有限公司 Image data processing system, method, electronic terminal and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050158767A1 (en) * 2003-12-19 2005-07-21 Haskell Robert E. System for managing healthcare data including genomic and other patient specific information
CN1845115A (en) * 2006-05-15 2006-10-11 赵达 Medical treatment data processing system and processing method
CN101782935A (en) * 2009-01-19 2010-07-21 中国人民解放军第二军医大学 Electronic medical record system and medical record data parsing and processing method for traditional Chinese medical science
CN102054032A (en) * 2010-12-22 2011-05-11 广州市慧通计算机有限公司 Medical data information processing method and system
CN104392132A (en) * 2014-11-24 2015-03-04 蔡志明 Medical data storage system based on cloud computing
CN106815337A (en) * 2016-12-31 2017-06-09 深圳市易特科信息技术有限公司 Medical big data associated storage system and method

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050158767A1 (en) * 2003-12-19 2005-07-21 Haskell Robert E. System for managing healthcare data including genomic and other patient specific information
CN1845115A (en) * 2006-05-15 2006-10-11 赵达 Medical treatment data processing system and processing method
CN101782935A (en) * 2009-01-19 2010-07-21 中国人民解放军第二军医大学 Electronic medical record system and medical record data parsing and processing method for traditional Chinese medical science
CN102054032A (en) * 2010-12-22 2011-05-11 广州市慧通计算机有限公司 Medical data information processing method and system
CN104392132A (en) * 2014-11-24 2015-03-04 蔡志明 Medical data storage system based on cloud computing
CN106815337A (en) * 2016-12-31 2017-06-09 深圳市易特科信息技术有限公司 Medical big data associated storage system and method

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112582056A (en) * 2020-12-21 2021-03-30 曙光星云信息技术（北京）有限公司 Regional medical information management platform based on big data technology
CN112863626A (en) * 2021-03-08 2021-05-28 北京冠新医卫软件科技有限公司 Multi-platform similar medical data removing method, device and equipment
CN114974565A (en) * 2022-05-17 2022-08-30 上海市第四人民医院 Refined management and control method and system for diagnosis and treatment stages of new coronary patients
CN117272395A (en) * 2023-11-21 2023-12-22 江西曼荼罗软件有限公司 Patient medical data processing method and system
CN117272395B (en) * 2023-11-21 2024-01-26 江西曼荼罗软件有限公司 Patient medical data processing method and system

Also Published As

Publication number Publication date
CN106815337A (en) 2017-06-09

Similar Documents

Publication Publication Date Title
WO2018120668A1 (en) Medical big data association and storage system and method
WO2018121044A1 (en) Medical treatment information management system and method
WO2018120669A1 (en) Medical data query system and method based on big data association and storage
CN104361221B (en) Medical data acquisition system and method based on heterogeneous system data mapping template
WO2021227511A1 (en) Complication onset risk prediction method and system based on electronic medical record big data, and terminal and storage medium
Mustapha et al. Impact of industry 4.0 on healthcare: a systematic literature review (SLR) from the last decade
WO2019006920A1 (en) Chronic disease patient health examination system and method based on doctor inquiry
CN105723366A (en) Method for preparing a system for searching databases and system and method for executing queries to a connected data source
CN110600092A (en) Method and system for generating personnel main index applied to medical field
CN105718732A (en) Medical data collection and analysis method and system
US20190108264A1 (en) System prototype of intelligent regional mobile healthcare integrated data center based on metadata
CN105160155A (en) Medical information network sharing system
CN101546418A (en) Clinic doctor check evaluating system and evaluating process
CN112199425A (en) Medical big data center based on mixed database structure and construction method thereof
CN105279389A (en) Intelligent medical physical examination system and information processing method thereof
US20130290022A1 (en) System and method for creating metadata-based natural language processing capabilities
KR20160125543A (en) User-oriented healthcare big data service method, computer program and system
CN106327396A (en) Hospital business data management platform and method
CN110070929A (en) A kind of acquisition and cleaning method for atrial fibrillation Single diseases data
CN106250691A (en) A kind of medicinal data processing method
CN113643814A (en) Health management scheme recommendation method, device, equipment and storage medium
CN107610783A (en) A kind of brain tumor information platform
Hu Research on monitoring system of daily statistical indexes through big data
CN206301336U (en) A kind of _ based Patient Records Management Systems for wisdom endowment
Gomes et al. A Proposal to Incorporate Digital Auscultation and Its Processing into an Existing Electronic Health Record.

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17886351

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17886351

Country of ref document: EP

Kind code of ref document: A1