Standardized model construction method and system for medical scientific research data

Abstract

The invention provides a standardized model construction method and system for medical scientific research data, and belongs to the technical field of medical data processing, and the method comprises the steps: determining the data type of to-be-collected medical scientific research data; defining a data field of the medical scientific research data; constructing a data variable of the medical scientific research data, and determining point location information of the medical scientific research data to be collected based on the data field and the data variable; splicing the point location information to obtain a plurality of different sequences, and combining based on the plurality of different sequences to form a standardized data model; the system comprises a data type determination module, a data field definition module, a data variable construction module, a data point location information determination module and a data model establishment module. According to the unified standardized data model constructed by the invention, the medical scientific research data of different sources and different business lines can be better interactively integrated, data sharing is facilitated, and the utilization rate of the data is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and particularly to a method and system for constructing a standardized model of medical research data. Background Art

[0002] At present, in medical research, due to the improvement of research level and the rapid development of informatization, a large amount or even a vast amount of medical-related data has been generated, including clinical data, experimental data, environmental data, test specimen data, etc. These generated and collected data are undoubtedly valuable information resources for promoting the further research work of researchers, and the results obtained after analyzing and utilizing them can provide more research support for researchers.

[0003] However, there are still problems and challenges in the management and application of these data. Medical research data has diversity and complexity, and different types of data have different formats, structures and characteristics. For example, some clinical data is structured, while medical records or imaging data is unstructured. Due to the differences in the sources and formats of different data, it is difficult to integrate, compare and analyze the data. Therefore, it is necessary to standardize and normalize medical research data. Summary of the Invention

[0004] In view of the above problems, the present invention provides a method and system for constructing a standardized model of medical research data, which can uniformly express and process medical research data from different sources and formats by establishing a unified data model and standard, so as to better meet the requirements of subsequent applications such as data transformation and analysis in medical research.

[0005] On the one hand, the present invention provides a method for constructing a standardized model of medical research data, the method comprising:

[0006] Determine the data type of the medical research data to be collected according to the preset requirements of data standardization;

[0007] Define the data domain of the medical research data based on the medical research objective and the determined data type;

[0008] Construct data variables of the medical research data, and associate the data variables with the data domain to obtain the data domain corresponding to different data variables;

[0009] Determine the point position information of the medical research data to be collected based on the data domain and the data variables;

[0010] Assemble the point position information belonging to the same data domain to obtain multiple different sequences, and aggregate the multiple different sequences to form a standardized data model.

[0011] Further, before determining the point information, it also includes standardizing the controlled terms of medical research data.

[0012] Further, the controlled terms include one or more of SNOMED CT, LOINC, and MedDRA.

[0013] Further, the point information includes single points, point groups, and point sets. Multiple single points are assembled to form a point group, and multiple point groups and / or single points are assembled to form a point set. The single points, point groups, and / or point sets are assembled to form a sequence.

[0014] Further, the data domain attribute includes domain classification, and the domain classification includes CDASH domain and SDTM domain.

[0015] Further, the point information is obtained by converting the data variables.

[0016] Further, it also includes verifying the data model and publishing the model when the data model meets the requirements.

[0017] On the other hand, the present invention provides a standardized construction system for medical research data, including:

[0018] A data type determination module for determining the data type of the medical research data to be collected to meet the requirements of data processing;

[0019] A data domain definition module for defining and managing the data domain based on the medical research objective and the data type determined by the data type determination module;

[0020] A data variable construction module for constructing and managing data variables;

[0021] A data point information determination module for determining and managing the data point information based on the data domain defined by the data domain definition module and the data variables constructed by the data variable construction module;

[0022] A data model establishment module for assembling and combining the point information determined by the data point information determination module into a sequence, and aggregating the sequences with the same data domain to obtain the required standardized data model.

[0023] Further, it also includes a controlled term specification module for standardizing the terms of medical research data using a standard controlled term system.

[0024] Furthermore, it also includes a model verification module, which is used to check whether the model meets the standards and research requirements after the data model is established, and release the data model if the data model established according to the data model establishment module meets the requirements.

[0025] By providing a method and system for constructing a standardized model of medical research data, the present invention has at least the following beneficial effects: on the one hand, by using the constructed unified standardized data model, medical data from different sources and different business lines can be better interactively integrated, facilitating data sharing and improving the utilization rate of data; on the other hand, by determining unified data formats and specifications, errors and distortions in the process of data processing and use can be reduced or prevented, improving the quality and credibility of data. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 is a flowchart of the method for constructing a standardized model of medical research data in Embodiment 1 of the present invention.

[0027] Figure 2 is a flowchart of point information processing of the method for constructing a standardized model of medical research data in Embodiment 1 of the present invention.

[0028] Figure 3 is a schematic diagram of the data types determined in the method for constructing a standardized model of medical research data in Embodiment 2 of the present invention.

[0029] Figure 4 is a schematic diagram of the data domains defined in the method for constructing a standardized model of medical research data in Embodiment 2 of the present invention.

[0030] Figure 5 is a schematic diagram of the data variables constructed in the method for constructing a standardized model of medical research data in Embodiment 2 of the present invention.

[0031] Figure 6 is a single-point schematic diagram of the point information determined in the method for constructing a standardized model of medical research data in Embodiment 2 of the present invention.

[0032] Figure 7 is a point group schematic diagram of the point information determined in the method for constructing a standardized model of medical research data in Embodiment 2 of the present invention.

[0033] Figure 8 is a schematic diagram of the relationship between the point group ID and the single-point ID of the point information determined in the method for constructing a standardized model of medical research data in Embodiment 2 of the present invention.

[0034] Figure 9 is a point set schematic diagram of the point information determined in the method for constructing a standardized model of medical research data in Embodiment 2 of the present invention.

[0035] Figure 10 It is a schematic diagram of the relationship among the single-point ID, point-group ID, and point-set ID of the point position information determined in the method for constructing a standardized model of medical research data in the second embodiment of the present invention.

[0036] Figure 11 It is a schematic diagram of the basic information for establishing data model entry in the method for constructing a standardized model of medical research data in the second embodiment of the present invention.

[0037] Figure 12 It is a schematic diagram of the sequence generated by establishing a data model in the method for constructing a standardized model of medical research data in the second embodiment of the present invention.

[0038] Figure 13 It is a schematic diagram of the data model established in the method for constructing a standardized model of medical research data in the second embodiment of the present invention.

[0039] Figure 14 It is a schematic diagram of the structure of the standardized construction system for medical research data in the third embodiment of the present invention. Detailed implementation manners

[0040] In order to enable those skilled in the art to more clearly and completely understand the technical solution of the present invention, the present invention will be described in detail below with reference to the embodiments and the accompanying drawings.

[0041] The present invention provides a method and a system for constructing a standardized model of medical research data, and establishes a unified data model and standard, so that medical data from different sources can be uniformly expressed and processed.

[0042] Embodiment 1

[0043] As a specific embodiment of the present invention, this embodiment provides a method for constructing a standardized model of medical research data. Referring to Figure 1 , including:

[0044] S100. Determine the data type of the medical research data to be collected

[0045] According to the preset requirements for the standardization of medical research data, extract and select the data type of the medical research data to be collected. The determined data type includes one or more of numbers, texts, and enumerations. In other embodiments, the determined data type is not limited to numbers, texts, and enumerations, and may also be other types of data to meet the preset requirements.

[0046] S200. Define the data domain of the medical research data

[0047] Based on the medical research objectives and the data types of the medical research data determined in S100, a data domain is defined, wherein the data domain refers to a logical organization unit of medical research data, such as patient information, disease diagnosis, and drug treatment. The data domain attributes include at least a domain name and a coding attribute.

[0048] S300, constructing data variables for medical research data

[0049] Construct data variables of the medical research data to be collected, wherein the data variables refer to the summary data items to be collected, such as the planned time and the execution time. The data variable attributes at least include the summary description and the role attributes, and associate the data variables with the data domains defined in S200.

[0050] S400, Standardized controlled terminology for medical research data

[0051] Standard controlled terminology system definitions are used as terminology specifications for medical research data to ensure that the same terms are used in different studies to describe similar data, making the data consistent and interoperable.

[0052] S500: Determine the specific location information of the medical research data to be collected

[0053] Based on the data domain defined in S200 and the data variables constructed in S300, in each domain, the point information of the medical research data to be collected is determined, wherein the point refers to the specific data item to be collected. The point attributes include at least identification information, business specific description and role attributes.

[0054] The point information is obtained through the data variable constructed by S300. More specifically, the point is obtained by assigning specific business meanings to the data variable. For example, the sampling time of the inspection order is a point, which is obtained through the data variable of execution time.

[0055] Reference Figure 2 ,The point information includes single point, point group and point set, where multiple single points are assembled to form a point group, and multiple single points and point groups are assembled to form a point set.

[0056] S600, Establishing Medical Research Data Model

[0057] According to business requirements, single points, point groups and / or point sets are assembled into multiple different sequences, and then multiple sequences are aggregated to obtain a complete standardized data model including the target business domain. Among them, the single points, point groups and / or point sets assembled in the same sequence belong to the same data domain, and the data domains of the aggregated multiple sequences are the same.

[0058] After aggregating single points, point groups, and / or point sets into a sequence, ensure the consistency of the data structure of the data in the obtained data model, achieve the effect of standardizing medical research data, and enable the model to be applicable to all sequences; and after aggregating multiple sequences, the obtained data model can contain more data information, with higher usability, providing more comprehensive data support for subsequent data processing and analysis.

[0059] Since the single points, point groups, and / or point sets assembled in the same sequence belong to the same data domain, it helps to ensure the consistency of the data domain, thereby simplifying the complexity of data processing and analysis.

[0060] To ensure the accuracy and effectiveness of the data model, after S600, it also includes S700:

[0061] Verify the data model. The verification process involves checking whether the model meets the standards and research requirements, and when the data model meets the requirements, release the model.

[0062] The method for constructing a standardized data model of medical research data according to the present invention can construct a unified data model and standards through processing, and can convert all medical research data from different sources and different formats collected into standardized data, thereby improving data interoperability.

[0063] Embodiment 2

[0064] As a specific embodiment of the present invention, this embodiment provides a method for constructing a standardized model of medical research data, referring to Figure 1 , including:

[0065] S100. Determine the data types of the medical research data to be collected

[0066] According to the preset requirements of medical research data standardization, extract and select the data types of the medical research data to be collected. The determined data types include one or more of numbers, texts, and enumerations. In other embodiments, the determined data types are not limited to numbers, texts, and enumerations, and can also be other types of data to meet the preset requirements.

[0067] Specifically, referring to Figure 3 , in this embodiment, by building a dictionary table in the PostgreSQL database to store the basic data types of metadata. This dictionary table records the IDs of the data types to be collected and the input format attributes, and the input formats are such as text, data, and time.

[0068] In this embodiment, the dictionary table can be used as a document of data types, providing a clear description of the data types, which helps to better understand the data structure and specifications. Storing the basic data types of metadata in the dictionary table can ensure the consistency, standardization, and accuracy of the data types, helping to avoid inconsistent data type definitions and improving data quality.

[0069] Storing data type information in the dictionary table is conducive to the subsequent maintenance of data types. When it is necessary to modify or update the definition of a data type, only one modification needs to be made in the dictionary table, instead of searching for and updating multiple definitions.

[0070] In addition, by using the predefined data types of metadata, it is convenient to understand the data and improve the readability of the data. Through the built-in dictionary table, it is more convenient to query and analyze metadata using the correct data types, which helps to optimize the data query performance, especially in the case where metadata information needs to be frequently queried.

[0071] S200. Define the data domains of medical research data

[0072] Based on the medical research objectives and the data types of medical research data determined in S100, define the data domains, where the data domain refers to the logical organizational unit of medical research data, such as patient information, disease diagnosis, and drug treatment. The data domain attributes at least include the domain name and the coding attribute.

[0073] Specifically, referring to Figure 4 , in this embodiment, different data domains are defined and the corresponding IDs, names, and codes are given to the data domains, and the classification of the data domains is given. In this embodiment, the data domains are divided into two categories: CDASH and SDTM according to different business scenarios. For example, the domain code of demographic data is DM, which respectively corresponds to the two categories of CDASH and SDTM in the domain classification.

[0074] The standardization objective of this embodiment is docked with the international common CDISC standard and split into the construction of medical data models for different business scenarios based on CDASH and SDTM.

[0075] S300. Construct the data variables of medical research data

[0076] Construct the data variables of the medical research data to be collected, where the data variable refers to the summary data item to be collected, such as the planned time and the execution time. The data variable attributes at least include the summary description and the role attribute, and the data variable is associated with the data domain defined in S200.

[0077] Specifically, referring to Figure 5, in this embodiment, the constructed data variable attributes include variable ID, variable code, variable label, and variable role attribute. The data domain defined in S200 is associated with the data variable using the domain ID to determine the data domain to which the data variable belongs, and the data type determined in S100 is associated with the data variable using the meta ID to determine the input format of the data variable. For example, for a data variable with the variable code "bedtime", its corresponding variable label is "sleep time", the corresponding variable role is "timing", the corresponding CDASH domain is "PS Sleep Quality Index", and the input format is "time".

[0078] By setting the data variable as described above, the data format of the data variable is fixed. The final standardized model has a stronger sense of boundary and more accurate data, enabling the upper-layer application to be clearer when using the standardized model.

[0079] For the constructed data variable, based on the basic information attributes, match the input format of the data domain defined in S200 and the data type determined in S100 to which it belongs.

[0080] S400, Standardize the controlled terms of medical research data

[0081] Adopt the definition of a standard controlled term system as the term specification for medical research data to ensure that the same terms are used to describe similar data in different studies, making the data consistent and interoperable.

[0082] Specifically, in this embodiment, the controlled term system can be one or more of Clinical Terms (SNOMED CT), Logical Observation Identifiers Names and Codes (LOINC), and Medical Dictionary for Regulatory Activities (MedDRA).

[0083] S500, Determine the specific point information of the medical research data to be collected

[0084] Based on the data domain defined in S200 and the data variable constructed in S300, in each domain, determine the points of the medical research data to be collected, where the point refers to the specific data item to be collected. The point attributes at least include identification information, specific business description, and role attribute.

[0085] By determining the points to be collected in each data domain, as well as the identification information, specific business description, and role attribute of each point, the consistency and standardization of the data in the entire system can be ensured, the data quality can be better managed, the identification information and specific business description can help users understand the meaning of the data, and the role attribute can guide the correct use and analysis of the data.

[0086] In another embodiment, the acquisition of point information can be achieved through the form of a questionnaire, and each questionnaire can obtain multiple point information.

[0087] The point information is obtained from the data variables constructed by S300. More specifically, the points are obtained by assigning specific business meanings to the data variables. For example, the sampling time of the inspection form is a point, and this point is obtained through the data variable of the execution time.

[0088] Refer to Figure 2 , the point information includes single points, point groups, and point sets. Among them, multiple single points are assembled to form a point group, and multiple single points and point groups are assembled to form a point set.

[0089] To more conveniently construct a standardized model, the single points are further assembled into point groups and point sets to combine different single points. In one example, there are three single points, namely the LBTESTTEXT inspection sub-item name, the LBORRESNUM inspection result value, and the LBORRESU unit. The three single points form a point group to describe a problem, such as for a certain inspection, the value and unit of the inspection result.

[0090] By assembling relevant single points into point groups and point sets, the data can be better structured. After assembly, it can better describe a problem, which helps to establish the association between data, enabling relevant data to be processed and analyzed together.

[0091] In addition, assembling single points into point groups and point sets helps to standardize data management and reduce data redundancy and duplication.

[0092] Specifically, refer to Figure 6 , in this embodiment, the point attributes include point description, point code, and controlled content attribute. The data variables constructed in S300 are associated with the points using the variable ID, and the data domains defined in S200 are associated with the points using the domain ID. For example, for a point with the point description of sleeping time, the corresponding point code is PSbedtime, the corresponding controlled content is empty, the corresponding variable label is sleeping time, and the corresponding CDASH domain is the PS sleep quality index.

[0093] When associating a single point with a data variable and a data domain, first select the data variable for association, and then select the data domain for association. The selected data domain must be the data domain that the selected data variable acts on.

[0094] Refer to Figure 7, the point group attributes include point group ID, point group name, and combined content attributes. Since a point group is composed of multiple single points, the combined content of a point group contains at least two single point contents. For example, for the point group with the point group name cGFR, the corresponding combined content is "test sub-item name; test result name; unit", that is, the point group with the point group name cGFR is composed of three single points with point descriptions of test sub-item name, test result name, and unit. The point group and the single point are associated through the point group ID and the single point ID. Refer to Figure 8 , the IDs of the single points corresponding to the point group with ID 3154 are 11, 13, and 14 respectively.

[0095] The point group is associated with one of the data domains defined in S200, and the single points that make up the point group belong to the data domain associated with the point group.

[0096] Refer to Figure 9 , the point set attributes include point set ID, point set name, and set content attributes. A point set is composed of multiple point groups and / or single points, and a single point is packaged as a point group in the point set. Therefore, the set content of the point set includes at least two point groups. For example, for the point set with the point set name actual sleep time, the corresponding combined content is "point group: actual sleep time; point: questionnaire question", that is, the point set with the point set name actual sleep time is composed of the point group with the point group name actual sleep time and the single point with the point description of questionnaire question. Refer to Figure 10 , the ID of the point set is 3028, and the IDs of the corresponding point groups are 3121 and 3153. Among them, 3121 is the ID of the point group with the point group name actual sleep time, and 3153 is the ID of the point group formed by packaging the single point with ID 6111 and the point description of questionnaire question.

[0097] All the unit groups and / or single points that make up the point set belong to the same data domain.

[0098] S600. Establishing a medical research data model

[0099] According to the business requirements, single points, point groups, and / or point sets are assembled in multiple different sequences, and then the multiple sequences are aggregated to obtain a complete standardized data model including the target business domain. Among them, the single points, point groups, and / or point sets assembled in the same sequence belong to the same data domain. The multiple sequences for aggregation belong to the same data domain.

[0100] Specifically, in this embodiment, taking the creation of a disease model as an example, it includes:

[0101] S601. Basic information entry

[0102] Refer toFigure 11 , the basic information includes one or more of the creation time, creator, model ID, disease name, disease code, and model introduction.

[0103] S602. Sequence Generation

[0104] As needed, the required single points, point groups, and point sets are assembled and combined into sequences. Each sequence belongs to a specific domain, and the assembled and combined sequences and the single points, point groups, and point sets required for assembly belong to the same data domain. At least one sequence belongs to the same data domain.

[0105] Among them, the point information, point group information, and point set information required for each assembled sequence are saved in the database. The point information includes the ID and the data type of the variable corresponding to the point. The point group information includes the point information that makes up the point group.

[0106] Refer to Figure 12 , in this embodiment, multiple sequences including sociodemographics, physical sign monitoring, and laboratory tests are obtained through assembly and combination. After obtaining all the sequences that need to be configured, proceed to the next step.

[0107] S603. Model Establishment

[0108] According to the domain code corresponding to each sequence, sequences with the same data domain are aggregated, and the union of all used points is taken to form the required standardized data model. For example, sequences with the domain code LB in all sequences are aggregated, and sequences with the domain code SU are aggregated.

[0109] Finally, the data format of the obtained data model is simply exemplified as follows:

[0110] {"domainName":"Laboratory","domainCode":"LB","pointList":[{"pointCode":"LBSEQ",

[0111] "pointName":"Test Form Code","inputFormat":"text","basedTable":"Y","keyType":1}]}。

[0112] It means that there are multiple points in the domain where the code is LB: the LBSEQ point, the name of the point is the test form code, and the data type that can be stored is text. Since there are multiple points, the information of other points is omitted and not shown.

[0113] The formed model is as Figure 13As shown in the figure. Among them, laboratory, hobby use, and demographic data are domain names, representing domains, and LBCLMS, SUTRTA, and DMADDR are point codes, representing points.

[0114] To ensure the accuracy and effectiveness of the data model, after S600, it also includes S700:

[0115] Verify the data model. The verification process involves checking whether the model meets the standards and research requirements, and releasing the model when the data model meets the requirements.

[0116] The method for constructing a standardized model of medical research data of the present invention constructs a standardized mathematical model for scientific research data processing, which can improve data interoperability, and reduce errors and distortions in the data processing process by defining a unified data format and specifications, improve the quality and credibility of the data, so that medical research personnel can use the data more conveniently, quickly, and standardly for interaction. Standardize and normalize the underlying data using the constructed basic data model to meet the data application requirements under different medical research business scenarios.

[0117] Embodiment III

[0118] As a specific embodiment of the present invention, this embodiment provides a system for constructing a standardized model of medical research data, referring to Figure 14 , for implementing the method for constructing a data standardization model in Embodiment 1 and / or Embodiment 2, including:

[0119] The data type determination module 10 is used to determine the data type of the medical research data to be collected to meet the requirements of data processing;

[0120] The data domain definition module 20 is used to define and manage the data domain based on the medical research objective and the data type determined by the data type determination module. The data domain refers to the logical organization unit of medical science and technology data, including patient information, disease diagnosis, and drug treatment;

[0121] The data variable construction module 30 is used to construct and manage data variables. The variable is a summary data item to be collected, such as planned time and execution time;

[0122] The data point information determination module 50 is used to determine and manage the data point information based on the data domain defined by the data domain definition module and the data variables constructed by the data variable construction module. The point refers to the specific data item to be collected, including identification information, business specific description, and role attributes.

[0123] The data model establishment module 60 is used to establish and manage the standardized data model. Based on business requirements, it assembles the point location information determined by the module according to the data point location information into a sequence, and aggregates the sequences with the same data domain to obtain the required standardized data model.

[0124] In other embodiments, the system further includes a data controlled term specification module 40, which is used to standardize the terms of medical research data by adopting a standard controlled term system, so that the medical research data has consistency and interoperability.

[0125] In a more optimal embodiment, the system may further include a model verification module 70, which is used to check whether the model meets the standards and research requirements after the data model is established. If the data model established according to the data model establishment module meets the requirements, the data model is published.

[0126] By establishing a unified standardized data model through the standardized model construction system of this embodiment, it can meet the standardized requirements in the subsequent data usage processes such as medical data conversion and analysis. When data processing is carried out, medical research data from different sources and different businesses can be more easily interactively integrated, facilitating data sharing.

[0127] It should be noted that the above description is only a preferred embodiment of the present invention and does not impose any other form of limitation on the present invention. Any modification or equivalent change made based on the technical essence of the present invention still falls within the scope of protection required by the present invention.

Claims

1. A method for constructing a standardized model of medical research data, characterized in that, The method includes: Determine the data type of the medical research data to be collected according to the preset requirements of data standardization; Define the data domain of the medical research data based on the medical research objective and the determined data type; Construct the data variables of the medical research data, and associate the data variables with the data domain to obtain the data domain corresponding to different data variables; Based on the data domain and the data variables, determine the point location information of the medical research data to be collected; Assemble the point location information belonging to the same data domain to obtain multiple different sequences, and aggregate the multiple different sequences to form a standardized data model.

2. The method for constructing a standardized model of medical research data according to claim 1, wherein Before determining the point location information, it also includes standardizing the controlled terms of the medical research data.

3. The method for constructing a standardization model of medical research data according to claim 2, characterized in that, The controlled terms include one or more of SNOMED CT, LOINC, and MedDRA.

4. The method for constructing a standardization model of medical research data according to claim 1, wherein The point location information includes single points, point groups, and point sets. Assemble multiple single points to form a point group, and assemble multiple point groups and / or single points to form a point set. The single points, point groups, and / or point sets are assembled to form a sequence.

5. The method for constructing a standardized model of medical research data according to claim 1, wherein The data domain attribute includes domain classification, and the domain classification includes CDASH domain and SDTM domain.

6. The method for constructing a standardized model of medical research data according to claim 1, characterized in that, The point location information is obtained through the conversion of the data variables.

7. The method for constructing a standardized model of medical research data according to claim 1, wherein It also includes verifying the data model and publishing the model when the data model meets the requirements.

8. A standardized construction system for medical research data, used to implement the method described in any one of claims 1-7, characterized in that, It includes: A data type determination module, which is used to determine the data type of the medical research data to be collected to meet the requirements of data processing; A data domain definition module, which is used to define the data domain and manage the data domain based on the medical research objective and the data type determined by the data type determination module; A data variable construction module, which is used to construct and manage the data variables; A data point location information determination module, which is used to determine and manage the data point location information based on the data domain defined by the data domain definition module and the data variables constructed by the data variable construction module; A data model establishment module, which is used to assemble and combine the point location information determined by the data point location information determination module into a sequence, and aggregate the sequences with the same data domain to obtain the required standardized data model.

9. The standardized construction system for medical research data according to claim 8, wherein It also includes a controlled term specification module, which is used to standardize the terms of the medical research data using a standard controlled term system.

10. The standardized construction system for medical research data according to claim 8, characterized in that, It also includes a model verification module, which is used to check whether the model meets the standards and research requirements after the data model is established. If the data model established by the data model establishment module meets the requirements, the data model is published.

Images