Intelligent data analysis assistant based on mesh meta analysis

Abstract

The invention is suitable for the technical field of intelligent medical treatment, and provides an intelligent data analysis assistant based on mesh meta analysis, which comprises a processor, a data acquisition module, a preprocessing module, an analysis modeling module, a statistical analysis module, a visualization module, a generation module, an AI auxiliary analysis module and a storage module are arranged in the processor; the analysis modeling module is used for automatically constructing a treatment network diagram on the basis of multi-element mesh Meta analysis and in combination with a Bayesian multi-level analysis model and a mixed linear model, displaying direct and indirect comparison relationships among different treatments and providing selection of a fixed effect model and a random effect model; the assistant helps a user to quickly understand complex data by automatically constructing a treatment network diagram, displaying direct and indirect comparison relationships among different treatments, providing selection of a fixed effect model and a random effect model, automatically calculating direct comparison and indirect comparison results of treatment effects, providing consistency check, improving retrieval analysis ability and helping the user to quickly understand the complex data.

Description

Technical Field

[0001] The present invention relates to the field of intelligent medical technology, and more specifically, to an intelligent data analysis assistant based on network meta-analysis. Background Art

[0002] Traditional data analysis methods mainly target structured data, such as relational databases and tabular data, and can use SQL query language and statistical analysis methods to extract and analyze data. However, these methods have certain limitations in processing unstructured data and cannot fully mine the information contained in unstructured data such as text, images, and audio.

[0003] Meta-analysis, also known as "Meta-analysis", Meta means something that appeared later and is more comprehensive, and is usually used to name a new related discipline that comments on the original discipline. It includes not only data combination, but also epidemiological exploration and evaluation of results. It replaces individuals as analysis entities with the findings of original research, and through quantitative synthesis of multiple independent studies, it improves statistical power and draws more reliable and general conclusions.

[0004] Existing intelligent data analysis assistants lack advanced search and analysis capabilities when using large model data analysis. At the same time, due to the massive amount of irrelevant data in the database, they are unable to help doctors quickly understand complex data, resulting in output results that do not meet requirements. Summary of the invention

[0005] In view of the shortcomings of the prior art, the purpose of the present invention is to provide an intelligent data analysis assistant based on network meta-analysis, which automatically constructs a treatment network diagram, displays the direct and indirect comparison relationships between different treatments, provides fixed effect model and random effect model selection, automatically calculates the direct and indirect comparison results of treatment effects, provides consistency test, supports heterogeneity analysis to provide ranking probability, improves retrieval and analysis capabilities, and helps users quickly understand complex data; saves time through automated data processing and analysis, helps users quickly understand complex data through visualization, supports multiple data formats and analysis requirements, can integrate AI models and more advanced analysis functions, and further improves retrieval and analysis capabilities.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An intelligent data analysis assistant based on network meta-analysis includes a processor; the processor is internally provided with a data acquisition module, a preprocessing module, an analysis modeling module, a statistical analysis module, a visualization module, a generation module, an AI-assisted analysis module and a storage module; the analysis modeling module is based on multivariate network Meta-analysis and combines a Bayesian multi-level analysis model with a mixed linear model, analyzes and calculates the data obtained by comparison, automatically constructs a treatment network diagram, displays the direct and indirect comparison relationship between different treatments, and provides a fixed effect model and a random effect model selection; the statistical analysis module automatically calculates the direct and indirect comparison results of the treatment effect, provides consistency testing, and provides sorting probability and ranking diagrams; the AI-assisted analysis module provides data insight suggestions by integrating an AI model, and at the same time, provides automatic result interpretation to help users understand the analysis results.

[0008] The present invention is further configured as follows: the data acquisition module extracts the retrieved keywords based on artificial intelligence and supplements the keywords.

[0009] The present invention is further configured as follows: the analysis and modeling module performs Meta analysis based on the supplemented keywords to obtain an initial document set, and performs topic evaluation and self-checking for duplicates based on all the documents therein to obtain a final document set, and performs data extraction, indexing and query on the obtained reference set through the statistical analysis module.

[0010] The present invention is further configured such that: the visualization module can be used to generate a treatment network diagram, a forest diagram, a ranking diagram, a funnel diagram and an interactive chart.

[0011] The present invention is further configured as follows: the treatment network diagram is used to display the relationship between different treatments; the forest diagram is used to compare the effects of different treatments; the ranking diagram is used to display the ranking probability of each treatment; the funnel diagram is used to evaluate publication bias; and the interactive chart supports zooming, filtering, and hovering to view data points.

[0012] The present invention is further configured as follows: the generation module is used to automatically generate an analysis report, including methods, results and charts, and at the same time, provides a customizable template to facilitate users to quickly generate a report that meets their needs.

[0013] The present invention is further configured as follows: the statistical analysis module is composed of a word vector model, a pre-trained risk prediction model, and model selection and tuning; the visualization module is composed of result presentation and interpretation as well as visualization and analysis tools.

[0014] The present invention is further configured as follows: the word vector model converts text data into numerical representation, and at the same time, the pre-trained risk prediction model is trained according to the classification prediction result data and the actual result data in the disease risk prediction model for predicting disease risk, and the model selection and tuning select the best model and perform parameter tuning through cross-validation and grid search technology, and then the results generated by the trained model are visualized so as to intuitively observe and understand the output of the model.

[0015] The advantages of the present invention are:

[0016] 1. The present invention automatically constructs a treatment network diagram to display the direct and indirect comparison relationships between different treatments, provides a choice of fixed effect models and random effect models, automatically calculates the direct and indirect comparison results of treatment effects, provides consistency tests, supports heterogeneity analysis to provide ranking probabilities, improves retrieval and analysis capabilities, and helps users quickly understand complex data.

[0017] 2. The present invention saves time by automating data processing and analysis, helps users quickly understand complex data through visualization, supports multiple data formats and analysis requirements, can integrate AI models and more advanced analysis functions, and further improves retrieval and analysis capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a framework diagram of an intelligent data analysis assistant system based on network meta-analysis of the present invention.

[0019] Figure 2 Generate a framework diagram for the visualization module of the present invention.

[0020] Figure 3 It is a composition framework diagram of the statistical analysis module of the present invention. DETAILED DESCRIPTION

[0021] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application may be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0022] It should be noted that, unless otherwise specified, all technical and scientific terms used in this application have the same meanings as commonly understood by ordinary technicians in the technical field to which this application belongs.

[0023] In the present invention, unless otherwise specified, the directions used, such as "up" and "down", usually refer to the directions shown in the drawings, or to the vertical, perpendicular or gravity directions; similarly, for ease of understanding and description, "left" and "right" usually refer to the left and right shown in the drawings; "inside" and "outside" refer to the inside and outside relative to the outline of each component itself, but the above-mentioned directions are not used to limit the present invention.

[0024] For example, see Figure 1-3 , the present invention provides the following technical solutions:

[0025] An intelligent data analysis assistant based on network meta-analysis, specifically, includes a processor; the processor is internally provided with a data acquisition module, a preprocessing module, an analysis modeling module, a statistical analysis module, a visualization module, a generation module, an AI-assisted analysis module and a storage module; the analysis modeling module is based on multivariate network Meta-analysis and combines a Bayesian multi-level analysis model with a mixed linear model, analyzes and calculates the data obtained by comparison, automatically constructs a treatment network diagram, displays the direct and indirect comparison relationship between different treatments, and provides a fixed effect model and a random effect model selection; the statistical analysis module automatically calculates the direct and indirect comparison results of the treatment effect, provides consistency testing, and provides sorting probability and ranking diagrams; the AI-assisted analysis module provides data insight suggestions by integrating an AI model, and at the same time, provides automatic result interpretation to help users understand the analysis results.

[0026] The working principle of the first embodiment of the present invention is as follows: by automatically constructing a treatment network diagram, displaying the direct and indirect comparison relationships between different treatments, providing a choice of a fixed effect model and a random effect model, automatically calculating the direct and indirect comparison results of the treatment effects, providing a consistency test, supporting heterogeneity analysis to provide a ranking probability, improving the retrieval and analysis capabilities, and helping users to quickly understand complex data; by automating data processing and analysis, saving time, helping users to quickly understand complex data through visualization, supporting a variety of data formats and analysis requirements, and being able to integrate AI models and more advanced analysis functions, further improving the retrieval and analysis capabilities.

[0027] For example 2, please refer to Figure 1-3 ,This second embodiment makes the following improvements on the basis of the first embodiment. Specifically, the data acquisition module extracts the searched keywords based on artificial intelligence and supplements the keywords.

[0028] The analysis and modeling module conducts Meta-analysis based on the supplemented keywords to obtain the initial literature set, and conducts topic evaluation and self-checking based on all the literature therein to obtain the final literature set. The statistical analysis module then extracts data, indexes, and queries the obtained reference set.

[0029] The visualization module can be used to generate treatment network diagrams, forest plots, ordination plots, funnel plots, and interactive charts.

[0030] The treatment network diagram is used to show the relationship between different treatments; the forest plot is used to compare the effects of different treatments; the ranking diagram is used to show the ranking probability of each treatment; the funnel plot is used to evaluate publication bias; the interactive chart supports zooming, filtering, and hovering to view the data points.

[0031] The generation module is used to automatically generate analysis reports, including methods, results and charts. At the same time, it provides customizable templates to facilitate users to quickly generate reports that meet their needs.

[0032] Working principle of the second embodiment:

[0033] Meta-analysis based on artificial intelligence can complete the retrieval of all databases in a very short time, improve the efficiency of literature retrieval, and increase the number of literature samples in each meta-analysis, ensuring the accuracy and authority of the analysis.

[0034] The data acquisition module and preprocessing module support multiple data formats such as CSV, Excel, and RevMan formats, automatically clean data such as processing missing values, outliers, and duplicate data, and support data standardization such as unifying effect size units.

[0035] Network meta-analysis modeling is used to automatically construct treatment network diagrams to display direct and indirect comparative relationships between different treatments. It supports multiple effect size models such as risk ratio (RR), odds ratio (OR), mean difference (MD), provides fixed effect model and random effect model selection, and supports Bayesian and frequentist methods.

[0036] The statistical analysis module is used to automatically calculate the direct and indirect comparison results of treatment effects, provide consistency tests such as node splitting method and global consistency test, support heterogeneity analysis such as I² statistics, and provide ranking probabilities such as SUCRA values ​​and ranking graphs.

[0037] The generation module supports exporting to PDF, PPT or HTML formats; it integrates AI models to provide data insight suggestions such as outlier detection and trend analysis.

[0038] For example 3, please refer to Figure 1-3 , this embodiment three makes the following improvements on the basis of embodiment two. Specifically, the statistical analysis module consists of a word vector model, a pre-trained risk prediction model, and model selection and tuning; the visualization module consists of result presentation and interpretation as well as visualization and analysis tools.

[0039] The word vector model converts text data into numerical representation. At the same time, the pre-trained risk prediction model is trained based on the classification prediction result data and actual result data in the disease risk prediction model to predict disease risk. Model selection and tuning select the best model and perform parameter tuning through cross-validation and grid search technology. The results generated by the trained model are then visualized to intuitively observe and understand the output of the model.

[0040] Working principle of the third embodiment:

[0041] The pre-trained risk prediction model is used to show the contribution of each data feature to the prediction result. The SHAP (SHapley Additive exPlanations) value is used to explain the impact of each feature on the individual prediction result. At the same time, local interpretability analysis is provided for the prediction results of a single patient.

[0042] The advantages of the present invention are:

[0043] 1. Efficiency: Automated data processing and analysis, saving time.

[0044] 2. Intuitiveness: Help users quickly understand complex data through visualization.

[0045] 3. Flexibility: Supports multiple data formats and analysis requirements.

[0046] 4. Scalability: AI models and more advanced analytical functions can be integrated.

[0047] Obviously, the above-described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0048] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. 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 "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0049] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein.

[0050] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0051] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. An intelligent data analysis assistant based on network meta-analysis, comprising a processor; characterized in that: The processor is internally provided with a data acquisition module, a preprocessing module, an analysis and modeling module, a statistical analysis module, a visualization module, a generation module, an AI-assisted analysis module and a storage module; The analysis and modeling module is based on multivariate network meta-analysis combined with Bayesian multi-level analysis model and mixed linear model. It analyzes and calculates the data obtained by comparison, automatically constructs a treatment network diagram, displays the direct and indirect comparison relationship between different treatments, and provides fixed effect model and random effect model selection; The statistical analysis module automatically calculates the direct and indirect comparison results of the treatment effects, provides consistency checks, and provides ranking probabilities and ranking graphs; The AI-assisted analysis module provides data insight suggestions by integrating AI models, and at the same time, provides automated result interpretation to help users understand the analysis results.

2. The intelligent data analysis assistant based on network meta-analysis according to claim 1, characterized in that: The data acquisition module extracts the searched keywords based on artificial intelligence and supplements the keywords.

3. The intelligent data analysis assistant based on network meta-analysis according to claim 2, characterized in that: The analysis and modeling module performs Meta-analysis based on the supplemented keywords to obtain an initial document set, and performs topic evaluation and self-checking based on all the documents therein to obtain a final document set, and uses the statistical analysis module to extract data, index and query the obtained reference set.

4. The intelligent data analysis assistant based on network meta-analysis according to claim 3, characterized in that: The visualization module can be used to generate treatment network diagrams, forest plots, ordination plots, funnel plots, and interactive charts.

5. The intelligent data analysis assistant based on network meta-analysis according to claim 4, characterized in that: The treatment network diagram is used to show the relationship between different treatments; the forest plot is used to compare the effects of different treatments; the ranking diagram is used to show the ranking probability of each treatment; the funnel plot is used to evaluate publication bias; the interactive chart supports zooming, filtering, and hovering to view data points.

6. The intelligent data analysis assistant based on network meta-analysis according to claim 5, characterized in that: The generation module is used to automatically generate analysis reports, including methods, results and charts. At the same time, it provides customizable templates to facilitate users to quickly generate reports that meet their needs.

7. The intelligent data analysis assistant based on network meta-analysis according to claim 6, characterized in that: The statistical analysis module consists of a word vector model, a pre-trained risk prediction model, and model selection and tuning; the visualization module consists of result presentation and interpretation as well as visualization and analysis tools.

8. The intelligent data analysis assistant based on network meta-analysis according to claim 7, characterized in that: The word vector model converts text data into numerical representation. At the same time, the pre-trained risk prediction model is trained according to the classification prediction result data and the actual result data in the disease risk prediction model to predict disease risk. Model selection and tuning select the best model and perform parameter tuning through cross-validation and grid search technology, and then visualize the results generated by the trained model to intuitively observe and understand the output of the model.

Images