Automatic reporting system based on data driving

Abstract

The invention relates to an automatic reporting system based on data driving, and the system comprises a template configuration module which is used for generating a corresponding template file according to a target statistical analysis process; the data management module is used for managing the project data and the literature data; the statistical analysis engine module is used for providing a corresponding statistical analysis model; the statistical analysis visualization module is used for providing an interactive statistical analysis panel so as to screen data to be analyzed, determine a statistical analysis model and visually display a statistical analysis result; the automatic report engine module is used for carrying out statistical analysis on the to-be-analyzed data and generating a structured report data object; the report parameter adjusting module is used for configuring, adjusting and storing corresponding parameters; and the report generation and export module is used for generating a final statistical analysis report and previewing and exporting the final statistical analysis report. The method can be widely applied to the technical field of data analysis.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a data-driven automated reporting system for clinical data-assisted statistical analysis and automated report analysis. Background Art

[0002] Statistical analysis plays a vital role in clinical research. By applying statistical principles and methods, researchers can objectively and scientifically analyze clinical data to obtain accurate conclusions and decisions.

[0003] Common statistical analysis methods in clinical research include: descriptive statistical analysis, parametric tests, nonparametric tests, correlation analysis, regression analysis, classification models, survival analysis and other methods. In actual clinical research, researchers should choose appropriate statistical analysis methods according to the research design and data characteristics, and follow scientific and standardized data analysis processes. However, in current practice, there is still a considerable amount of misuse of statistical methods in research, which is often due to the lack of sufficient understanding of data analysis methods in clinical research by researchers, thus affecting the scientificity and reliability of research conclusions. On the other hand, the use of commonly used statistical software (including SAS, SPSS, R, etc.) is relatively complicated and unfamiliar to medical researchers who are not statistical professionals. Using these software for statistical analysis requires additional learning costs.

[0004] In order to solve the above problems, researchers usually need to spend a lot of time and energy to learn complex statistical analysis knowledge, or seek help from professional statisticians. However, this method is not only inefficient but also costly, especially for researchers who are not statistical professionals, it is a huge challenge. Therefore, the market is increasingly in need of a tool that can simplify the data analysis operation process in clinical research and ensure that the data analysis conclusions are accurate and reliable.

[0005] There are some existing methods related to automated statistical analysis and generating statistical analysis reports, but these methods have the following problems: 1. The statistical analysis methods used are relatively simple. Existing patents cannot cover most of the commonly used statistical analysis methods in clinical research. For example, Chinese patent CN117851481A only supports simple descriptive statistical analysis of data and lacks support for complex statistical models and methods. However, with the increase in the amount of data in clinical research and the deepening of research, the use of simple descriptions and inferences is far from sufficient to meet the needs of statistical analysis methods in clinical research. It is urgent to adopt more complex statistical models and methods for data analysis and in-depth mining.

[0006] 2. Lack of an easy-to-use interactive statistical analysis interface. Currently, there are two main ways to implement statistical analysis in clinical research: one is to use official toolkits through special software such as SAS and SPSS; the other is for analysts to use languages ​​such as R and Python, relying on a large number of third-party software packages and self-written programs to perform statistical analysis. In fact, the above two methods have a high threshold for use for most researchers. A simple and easy-to-use interactive statistical analysis interface can lower the threshold and learning cost for researchers, and to a certain extent, it can also reduce statistical analysis errors caused by incorrect use of statistical software.

[0007] 3. There is a lack of a one-stop solution for repeatable research applicable to clinical data analysis research paths. The process of clinical data analysis is relatively standard, but the requirements for statistical analysis models and methods are relatively in-depth. Usually, the research results will be published in academic papers. The part of the paper involving analysis methods and empirical research often contains a large number of charts and conclusions. If traditional software is used for analysis, it is easy to make mistakes in the process of pasting the analysis results into the paper document, especially when it involves multiple model adjustments. Some minor mistakes caused by pasting charts may cause misunderstandings of academic misconduct. A repeatable research system that automatically generates reports directly from analysis models and standard data can fundamentally solve this problem. Summary of the invention

[0008] In view of the above problems, the purpose of the present invention is to provide a data-driven automated reporting system for assisting the automation of data analysis in clinical research, performing data analysis and generating analysis reports.

[0009] To achieve the above object, the present invention adopts the following technical solutions: A data-driven automated reporting system, including: Template configuration module, used to generate corresponding template files according to the target statistical analysis process; Data management module, used to manage project data and literature data; The statistical analysis engine module is used to pre-store several statistical analysis models and provide an interface for users to create custom statistical analysis models according to actual needs; The statistical analysis visualization module is used to provide an interactive statistical analysis panel to screen the data to be analyzed, determine the target statistical analysis model, and perform visual exploratory analysis; The automatic report engine module is used to call the target statistical analysis model to perform statistical analysis on the data to be analyzed and generate structured report data objects; A report parameter adjustment module is used to configure and adjust the configurable parameters of the template file and the model parameters of the target statistical analysis model, and to uniformly store the parameter configuration information; The report generation and export module is used to import structured report data objects and parameter configuration information into the template file, generate the final statistical analysis report and perform real-time preview or export.

[0010] Further, the template configuration module includes a template import module, a template update module, a template customization module and a template library module; The template import module is used for the user to import a preset analysis report template from the template library module as an initial analysis report template according to the target statistical analysis process; The template update module is used for users to customize and modify the initial analysis report template according to actual needs, and generate an analysis report template file corresponding to the target statistical analysis process; The template customization module is used for users to create and generate new analysis report templates corresponding to the target statistical analysis process according to actual needs; The template library module is used to pre-generate and store a number of analysis report templates corresponding to different statistical analysis processes.

[0011] Further, the analysis report template pre-generated in the template library module includes a text part and an R language code part; The text part is written in Markdown format to control the text content in the generated analysis report template and the structure of the analysis report template; The R language code part is used to implement the statistical analysis process in the analysis report template, including using the R language to call the system's built-in statistical analysis model or a custom statistical analysis model to perform statistical analysis, and inserting the statistical analysis results into the text part.

[0012] Further, the data management module includes a project data management module, a literature data management module, a data import module and a data interaction module; The project data management module and the document data management module are used to manage project data and document data respectively, and generate standard format data sets; The data import module is used to provide a data import interface, so that users can import the data used in the research project into the system; The data interaction module is used to provide a database interaction interface to enable the statistical analysis engine module to call a standard format data set.

[0013] Furthermore, the project data management module and the document data management module use SQL databases to manage project data and document data respectively.

[0014] Further, the statistical analysis engine module includes a statistical analysis module, a clinical analysis module, a model customization module and a model interface module; Several statistical analysis models are arranged in the statistical analysis module; The clinical analysis module is provided with several statistical and machine learning models; The model customization module is used by the user to customize the statistical analysis methods and processes used according to actual needs and generate a customized statistical analysis model; The model interface module is used to provide an interface in the form of an R language function to call the standard format data set in the data management module and input the corresponding statistical analysis model to realize automatic statistical analysis.

[0015] Furthermore, the statistical analysis visualization module includes a data screening module, a model parameter configuration module and a visualization exploration analysis module; The data screening module is used for the user to screen the required data to be analyzed from the data management module according to the target statistical analysis process; The model parameter configuration module is used for the user to determine the target statistical analysis model according to actual needs and configure the model parameters of the target statistical analysis model; The visual exploratory analysis module is used to perform exploratory analysis based on statistical analysis results.

[0016] Further, the automatic reporting engine module includes a template parsing module, a model calling module and a report generating module; The template parsing module is used to parse the template file generated by the template configuration module to obtain the text part and R language code block of the template file; The model calling module is used to call the target statistical analysis model from the statistical analysis engine module according to the R language code block to perform statistical analysis; The report generation module is used to mix the statistical analysis results and the report format in the template file to generate a structured report data object and store it in the Markdown format.

[0017] Further, the report parameter adjustment module includes a template parameter configuration interface, a model parameter reading interface and a parameter storage module; The template parameter configuration interface is used to manually adjust the configurable parameters according to the configuration in the template file; The model parameter reading interface is used to read the model parameters configured in the statistical analysis visualization module; The parameter storage module is used to uniformly store template parameters and model parameters for generating a final analysis report.

[0018] Further, the report generation and export module includes a report rendering module, a format conversion module, a report adjustment module and a report export module; The report rendering module is used to set the format or select different document styles through interactive pages, automatically adjust format-related parameters, modify the corresponding content of the template file, and obtain a rendered Markdown file; The format conversion module is used to convert the Markdown file into the required target format using Pandoc according to the output format of the final report selected by the user, so as to obtain an automated analysis report; The report adjustment module is used to edit or modify the automated analysis report according to user needs; The report export module is used to export the final statistical analysis report.

[0019] The present invention adopts the above technical solution, which has the following advantages: 1. The present invention sets a template configuration module, so that users can easily configure different report templates. Combined with the statistical analysis engine module and the report generation and export module, different statistical analysis processes can be quickly applied to a project data to generate an analysis report. At the same time, the template configuration module also supports users to customize the template file. The module used in this system is designed based on the general style of literary programming, which is convenient for users to modify and maintain the report template.

[0020] 2. By setting up a statistical analysis engine module, the present invention enables users to easily analyze project data using a variety of built-in statistical methods or customized statistical analysis methods and processes in the template, thereby simplifying the statistical analysis process and effectively lowering the usage threshold for researchers.

[0021] 3. The present invention can realize the automatic generation of statistical analysis reports of clinical research project data by setting up report generation and export modules, thereby improving the efficiency of data analysis work and report quality in clinical research.

[0022] In short, the present invention can simply realize the automation of statistical analysis process and analysis report generation in clinical research. The invention can assist researchers to perform statistical analysis more standardized and accurately, thereby improving the scientificity and reliability of the research and helping to improve the quality of clinical medical research; on the other hand, the invention realizes the automation of the statistical analysis part of clinical research, which helps to save researchers' time and energy and improve the efficiency of research. Therefore, the present invention can be widely used in the field of data analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Throughout the accompanying drawings, the same reference numerals are used to represent the same components. In the accompanying drawings: Figure 1 It is a structural diagram of a data-driven automated reporting system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0025] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0026] In some embodiments of the present invention, a data-driven automated reporting system is provided, which can provide an interactive statistical analysis interface based on a pre-given and modified data analysis template, and automatically generate a statistical analysis report of a target clinical study according to the data analysis template. The present invention simplifies the operational process of data analysis in clinical research, lowers the threshold for use by clinical researchers, and avoids erroneous conclusions caused by misuse of statistical analysis methods in clinical research.

[0027] Example 1 like Figure 1 As shown, the present invention provides a data-driven automated reporting system, which includes: Template configuration module, used to generate corresponding template files according to the target statistical analysis process; Data management module, used to manage project data and literature data; The statistical analysis engine module is used to pre-store commonly used standard statistical analysis models and provide an interface for users to create custom statistical analysis models according to actual needs; The statistical analysis visualization module is used to provide an interactive statistical analysis panel to screen the data to be analyzed, determine the target statistical analysis model, and perform visual exploratory analysis; Automatic report engine module, used to call standard statistical analysis model or custom statistical analysis model to perform statistical analysis on the data to be analyzed and generate structured report data objects; A report parameter adjustment module is used to configure and adjust the configurable parameters of the template file and the model parameters of the statistical analysis model, and to store the parameter configuration information in a unified manner; The report generation and export module is used to import structured report data objects and parameter configuration information into the template file, generate the final statistical analysis report and perform real-time preview or export.

[0028] Furthermore, the template configuration module includes a template import module, a template update module, a template customization module and a template library module. Among them, the template import module is used for the user to import a preset analysis report template from the template library module as an initial analysis report template according to the target statistical analysis process; the template update module is used for the user to customize and modify the initial analysis report template according to actual needs, and generate an analysis report template corresponding to the target statistical analysis process; the template customization module is used for the user to create and generate a new analysis report template corresponding to the target statistical analysis process according to actual needs; the template library module is used to pre-generate and store a number of analysis report templates corresponding to different statistical analysis processes.

[0029] Furthermore, the analysis report templates pre-generated in the template library module are stored in the R Markdown format. R Markdown is based on the idea of ​​literary programming and integrates R language code and text.

[0030] Specifically, the analysis report template includes a text part and an R language code part. The text part is written in Markdown format and is used to control the text content and structure of the analysis report template; the R language code part is used to implement the statistical analysis process in the analysis report template. For example, you can use R language to call the system's built-in statistical methods, or write your own program for statistical analysis. At the same time, you also need to use the R code embedded in the text part to insert the statistical analysis results into the text part.

[0031] Since the present invention pre-stores analysis report templates in the template library module, it can be used by users without R language basics, and can also be used by users with a certain R language basics to write analysis report templates for use; at the same time, only a simple R language basics are required, and the user can also manually modify the existing analysis report template, or directly select the automatic modification plan recommended by the system for the template with the assistance of the large language model without the need for R language basics.

[0032] Furthermore, the data management module includes a project data management module, a literature data management module, a data import module and a data interaction module. Among them, the project data management module and the literature data management module are used to manage project data and literature data respectively, and generate standard format data sets; the data import module is used to provide a data import interface, which is convenient for users to import the data used in the research project into the system for management and subsequent analysis; the data interaction module is used to provide a database interaction interface to enable the statistical analysis engine module to call the standard format data set in the system.

[0033] Furthermore, the project data management module and the document data management module use SQL database to manage project data and document data.

[0034] Furthermore, in the data interaction module, the data interaction interface can use the default RSQLite package or other database interfaces to realize the interaction between R code and SQL database.

[0035] Furthermore, in the data import module, the data import interface can be implemented by a function for reading data files in the R language, such as read.xlsx, etc. The user only needs to prepare the data file according to the required fields, such as an Excel spreadsheet file, etc., and upload it to the system for import.

[0036] Furthermore, the statistical analysis engine module includes a statistical analysis module, a clinical analysis module, a model customization module and a model interface module. Among them, the statistical analysis module is provided with commonly used statistical analysis models for descriptive statistics, hypothesis testing and other analyses; the clinical analysis module is provided with commonly used statistical and machine learning models for clinical data analysis, including but not limited to regression analysis, multivariate linear models, classification models, survival analysis models, etc.; the model customization module is used for users to customize the statistical analysis methods and processes used according to actual needs and generate customized statistical analysis models; the model interface module is used to provide an interface in the form of R language functions to call the standard format data set in the data management module and input the corresponding statistical analysis model to realize automatic statistical analysis.

[0037] In this embodiment, the statistical analysis engine serves as a system background engine and is not directly exposed to the user. The user can call the interface of the statistical analysis engine when configuring the template file through the template configuration module to generate an automated report; the user can also explore using an interactive method in the statistical analysis visualization module and call the statistical analysis engine.

[0038] Furthermore, the statistical analysis visualization module is used to provide an interactive statistical analysis panel, which is written in RShiny. Specifically, it includes a data screening module, a model parameter configuration module and a visualization output module. Among them, the data screening module is used for users to filter the required project data from the data management module according to the target statistical analysis process; the model parameter configuration module is used for users to determine the target statistical analysis model according to actual needs and configure the model parameters of the target statistical analysis model; the visualization output module is used for users to conduct exploratory analysis based on the statistical analysis results.

[0039] In this embodiment, when the user performs exploratory analysis in the statistical analysis visualization module, the user may directly confirm certain parameters, such as age range, treatment method, etc., and may also modify the parameters as needed. The model parameters of the model parameter configuration module can be automatically brought into the parameter storage module. The user can directly store them if there is no question, and can modify them in the parameter storage module if there is any question.

[0040] Furthermore, the automatic report engine module includes a template parsing module, a model calling module and a report generating module. The template parsing module is used to parse the template file generated by the template configuration module to obtain the text part and the R language code block of the template file; the model calling module is used to call the corresponding statistical analysis model or the user-defined statistical analysis model from the statistical analysis engine module according to the R language code block to perform statistical analysis; the report generating module is used to mix the statistical analysis results and the report format in the template file to generate a structured report data object and store it in the Markdown format.

[0041] Furthermore, the report parameter adjustment module includes a template parameter configuration interface, a model parameter reading interface and a parameter storage module. The template parameter configuration interface is used to manually adjust the configurable parameters such as date, institution, reference address, etc. according to the configuration in the analysis report template file; the model parameter reading interface is used to read the statistical model parameters configured in the statistical analysis visualization module; the parameter storage module is used to uniformly store the template parameters and model parameters, and the user can confirm the storage of the parameters obtained by the model parameter reading interface, or modify the parameters and then store them for the generation of the final analysis report.

[0042] Furthermore, the report generation and export module includes a report rendering module, a format conversion module, a report adjustment module and a report export module. Among them, the report rendering module is used to call R language Bookdown, officer and other packages, set the format through the interactive page, or select different document styles, automatically adjust the format-related parameters, such as font size, chart format, etc., modify the corresponding content of the template file, and thus obtain the rendered Markdown file; the format conversion module is used to use Pandoc to convert the Markdown file into the required target format according to the output format of the final report selected by the user, where the target format can be HTML, Docx, PDF format, etc.; the report adjustment module is used to further edit or modify the automatically generated report according to user needs; the report export module is used to export the final statistical analysis report.

[0043] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A data-driven automated reporting system, characterized in that: include: Template configuration module, used to generate corresponding template files according to the target statistical analysis process; Data management module, used to manage project data and literature data; The statistical analysis engine module is used to pre-store several statistical analysis models and provide an interface for users to create custom statistical analysis models according to actual needs; The statistical analysis visualization module is used to provide an interactive statistical analysis panel to screen the data to be analyzed, determine the target statistical analysis model, and perform visual exploratory analysis; The automatic report engine module is used to call the target statistical analysis model to perform statistical analysis on the data to be analyzed and generate structured report data objects; A report parameter adjustment module is used to configure and adjust the configurable parameters of the template file and the model parameters of the target statistical analysis model, and to uniformly store the parameter configuration information; The report generation and export module is used to import structured report data objects and parameter configuration information into the template file, generate the final statistical analysis report and perform real-time preview or export.

2. A data-driven automated reporting system as claimed in claim 1, characterized in that: The template configuration module includes a template import module, a template update module, a template customization module and a template library module; The template import module is used for the user to import a preset analysis report template from the template library module as an initial analysis report template according to the target statistical analysis process; The template update module is used for users to customize and modify the initial analysis report template according to actual needs, and generate an analysis report template file corresponding to the target statistical analysis process; The template customization module is used for users to create and generate new analysis report templates corresponding to the target statistical analysis process according to actual needs; The template library module is used to pre-generate and store a number of analysis report templates corresponding to different statistical analysis processes.

3. A data-driven automated reporting system as claimed in claim 2, characterized in that: The analysis report template pre-generated in the template library module includes a text part and an R language code part; The text part is written in Markdown format to control the text content in the generated analysis report template and the structure of the analysis report template; The R language code part is used to implement the statistical analysis process in the analysis report template, including using the R language to call the system's built-in statistical analysis model or a custom statistical analysis model to perform statistical analysis, and inserting the statistical analysis results into the text part.

4. The data-driven automated reporting system according to claim 1, characterized in that: The data management module includes a project data management module, a literature data management module, a data import module and a data interaction module; The project data management module and the document data management module are used to manage project data and document data respectively, and generate standard format data sets; The data import module is used to provide a data import interface, so that users can import the data used in the research project into the system; The data interaction module is used to provide a database interaction interface to enable the statistical analysis engine module to call a standard format data set.

5. A data-driven automated reporting system as claimed in claim 4, characterized in that: The project data management module and the document data management module use SQL database to manage project data and document data respectively.

6. The data-driven automated reporting system according to claim 1, characterized in that: The statistical analysis engine module includes a statistical analysis module, a clinical analysis module, a model customization module and a model interface module; Several statistical analysis models are arranged in the statistical analysis module; The clinical analysis module is provided with several statistical and machine learning models; The model customization module is used by the user to customize the statistical analysis methods and processes used according to actual needs and generate a customized statistical analysis model; The model interface module is used to provide an interface in the form of an R language function to call the standard format data set in the data management module and input the corresponding statistical analysis model to realize automatic statistical analysis.

7. The data-driven automated reporting system according to claim 1, characterized in that: The statistical analysis visualization module includes a data screening module, a model parameter configuration module and a visualization exploration analysis module; The data screening module is used for the user to screen the required data to be analyzed from the data management module according to the target statistical analysis process; The model parameter configuration module is used for the user to determine the target statistical analysis model according to actual needs and configure the model parameters of the target statistical analysis model; The visual exploratory analysis module is used to perform exploratory analysis based on statistical analysis results.

8. The data-driven automated reporting system according to claim 3, characterized in that: The automatic reporting engine module includes a template parsing module, a model calling module and a report generating module; The template parsing module is used to parse the template file generated by the template configuration module to obtain the text part and R language code block of the template file; The model calling module is used to call the target statistical analysis model from the statistical analysis engine module according to the R language code block to perform statistical analysis; The report generation module is used to mix the statistical analysis results and the report format in the template file to generate a structured report data object and store it in the Markdown format.

9. The data-driven automated reporting system according to claim 1, characterized in that: The report parameter adjustment module includes a template parameter configuration interface, a model parameter reading interface and a parameter storage module; The template parameter configuration interface is used to manually adjust the configurable parameters according to the configuration in the template file; The model parameter reading interface is used to read the model parameters configured in the statistical analysis visualization module; The parameter storage module is used to uniformly store template parameters and model parameters for generating a final analysis report.

10. The data-driven automated reporting system according to claim 1, characterized in that: The report generation and export module includes a report rendering module, a format conversion module, a report adjustment module and a report export module; The report rendering module is used to set the format or select different document styles through interactive pages, automatically adjust format-related parameters, modify the corresponding content of the template file, and obtain a rendered Markdown file; The format conversion module is used to convert the Markdown file into the required target format using Pandoc according to the output format of the final report selected by the user, so as to obtain an automated analysis report; The report adjustment module is used to edit or modify the automated analysis report according to user needs; The report export module is used to export the final statistical analysis report.

Images