A dietary fiber recommendation system based on intestinal flora fluctuation

Abstract

The present application belongs to the technical field of dietary fiber recommendation, and discloses a dietary fiber recommendation system based on intestinal flora fluctuation, which comprises a data collection module, a data analysis module and a dietary guidance module.The data collection module extracts the microorganism fluctuation data set under the intervention of dietary fiber; the data analysis module adopts a biological classification hierarchical weighted superposition algorithm for measuring the similarity of flora fluctuation, uses multi-level flora information to reveal the similarity between dietary fiber and diseases, and constructs a network atlas between dietary fiber and diseases with microorganism disturbance as the background; and the dietary guidance module accurately provides specific dietary intake guidance for different patients.The present application provides scientific theoretical guidance and dietary collocation for dietary intake under specific disease states, and provides strong evidence support for auxiliary drug treatment of diseases.

Description

Technical Field

[0001] This invention belongs to the field of dietary fiber recommendation technology, and in particular relates to a dietary fiber recommendation system based on gut microbiota fluctuations. Background Technology

[0002] Current research has demonstrated that adequate dietary fiber intake is crucial for maintaining healthy gut function, preventing various chronic diseases, and promoting overall health. While a close relationship exists between dietary fiber and human health, the specific mechanisms and dietary intake guidelines remain challenging. Existing techniques for studying the relationship between dietary fiber and disease can be broadly categorized as follows: epidemiological studies, clinical trials, cell and animal experiments, metabolomics and microbiome research, molecular biology, and genomics. These methods suffer from drawbacks such as long development cycles, high manpower requirements, and high costs, and also have limitations in addressing dietary intake recommendations and adjunctive drug treatments for serious diseases.

[0003] Existing machine learning-based dietary recommendation systems primarily utilize basic patient information (e.g., age, gender, weight, height) and health issues (e.g., diabetes, hypertension) to provide suggested dietary plans based on machine learning algorithms and extensive medical literature and clinical research. However, current dietary recommendation systems fail to consider the importance of gut microbiota fluctuations for personalized dietary recommendations, potentially leading to inappropriate dietary choices that exacerbate inflammatory responses, thereby increasing patient suffering and treatment duration. Technical problems with existing technologies:

[0004] 1. Neglecting the impact of gut microbiota fluctuations: While this technology can provide targeted dietary recommendations, it completely ignores the health effects of gut microbiota fluctuations. There is a close interaction between the gut microbiota and diet, and the composition and function of the gut microbiota are closely related to human health.

[0005] 2. Lack of personalization: Current technologies are mainly based on average data of physiological and biochemical changes in large populations. They cannot provide optimal dietary recommendations for individuals because each person's microbiome is unique. (This study's focus on microbiome fluctuations is also based on a large dataset; does this mean it doesn't fully support the research? Could it be modified from the perspective of dietary fiber, as follows?)

[0006] 2. Limitations of the Dataset: This technique primarily relies on traditional medical literature and clinical studies, which do not cover the increasingly important microbial community research of recent years. Furthermore, some existing disease and microbiome databases, such as HMDAD and DISBIOME, cannot accurately determine the variation spectrum of microbial differences among patients because their control groups are not entirely composed of healthy individuals. In collecting the evidence set, this study, in addition to incorporating the latest research from databases such as PubMed, also implemented a series of filtering conditions, such as ensuring the control group consisted entirely of healthy individuals and that no other drugs or antibiotics were used in the disease group. Additionally, the HMDAD and DISBIOME databases were integrated, and disease names were standardized to eliminate redundant information.

[0007] 3. Limitations of the analytical methods: Existing technologies mainly use traditional machine learning algorithms, without utilizing more advanced bioinformatics methods for in-depth data analysis. Especially in calculating the similarity between dietary fiber and diseases based on microbial fluctuations, this study employs a weighted superposition method and system for measuring the similarity of microbial community fluctuations. Leveraging the multi-level characteristics of microorganisms, this method more accurately assesses the similarity between different levels, providing scientific theoretical guidance and reasonable dietary combinations for dietary fiber intake in specific disease populations. Summary of the Invention

[0008] To address the problems existing in the prior art, this invention provides a dietary fiber recommendation system based on gut microbiota fluctuations.

[0009] This invention is implemented as follows: a dietary fiber recommendation system based on gut microbiota fluctuations, specifically comprising:

[0010] The data collection module collects and extracts literature on dietary fiber and microbes from PubMed, MEDLINE, Web of Science, and EMBASE databases. By setting a series of screening criteria and deduplication, it extracts a dataset of microbial fluctuations under dietary fiber intervention. Combining the HMDAD and DISBIOME databases and the PubMed database, it selects data on microbial fluctuations generated in various disease states using healthy individuals as controls for deduplication and extraction, ultimately obtaining a set of evidence for microbial fluctuations in human disease states.

[0011] The data analysis module employs a weighted overlay algorithm based on biological classification levels to measure the similarity of microbial community fluctuations. It utilizes multi-level microbial community information to reveal the similarities between dietary fiber and diseases, and constructs a network map of dietary fiber and diseases against the background of microbial disturbance.

[0012] The dietary guidance module provides precise dietary intake guidance for different patients based on network graphs.

[0013] Furthermore, the data collection module uses the following criteria for screening dietary fiber literature: only randomized controlled clinical trials (RCTs) are selected; healthy individuals are used as research subjects; the interference condition is dietary fiber intake; the control group can be a normal diet, a placebo, or a low dose of the same dietary fiber; and the measured result is the fluctuation of microbial activity.

[0014] Furthermore, the disease literature screening criteria in the data collection module are as follows: healthy individuals serve as the control group, and the disease group serves as the experimental group; there are no significant differences in dietary patterns between the two groups, and no significant differences in physical signs between the groups; the disease group did not take any topical medications or experience a washout period; the final measurement result is the fluctuation of microorganisms.

[0015] Furthermore, the data analysis module's network includes 122 diseases and 32 types of dietary fiber.

[0016] Furthermore, in the dietary guidance module, the gut microbiota fluctuations introduced by dietary fiber are generally opposite to those introduced by disease occurrence. If the total similarity of gut microbiota fluctuations is less than 0 and statistically significant, then the dietary fiber helps improve the disease state. Conversely, if the gut microbiota fluctuations introduced by dietary fiber are generally similar to those introduced by disease occurrence, and the total similarity of gut microbiota fluctuations is greater than 0 and statistically significant, then the dietary fiber is not conducive to improving the disease state.

[0017] Furthermore, in the dietary guidance module, under 122 specific disease states, it is recommended to consume dietary fiber that has significant and negative similarity, and to reduce the intake of dietary fiber that has positive similarity.

[0018] Another objective of this invention is to provide a dietary fiber recommendation system based on gut microbiota fluctuations and a method for recommending dietary fiber based on gut microbiota fluctuations, the method comprising the following steps:

[0019] Step 1: Using the data collection module, literature on dietary fiber and microbiome was collected and extracted from PubMed, MEDLINE, Web of Science, and EMBASE databases. By setting a series of screening criteria and deduplication, a dataset of microbiome fluctuations under dietary fiber intervention was extracted. Combining the HMDAD and DISBIOME databases and the PubMed database, data on microbiome fluctuations generated in various disease states using healthy individuals as controls were selected and deduplicated to obtain a set of evidence on microbiome fluctuations in human disease states.

[0020] Step 2: Using the data analysis module, a weighted superposition algorithm based on the biological classification hierarchy is adopted to measure the similarity of microbial community fluctuations. Multi-level microbial community information is used to reveal the similarity between dietary fiber and diseases, and a network map between dietary fiber and diseases with microbial disturbance as the background is constructed.

[0021] Step 3: Using the dietary guidance module, specific dietary intake guidance is provided precisely to different patients based on the network graph.

[0022] Another objective of this invention is to provide an application of a dietary fiber recommendation system based on gut microbiota fluctuations to provide specific dietary fiber recommendations for different patients.

[0023] Furthermore, for patients with ulcerative colitis, inulin-based substances are not recommended; AXOS, WG, RS2, and Walnut can be used.

[0024] Furthermore, for diseases with high prevalence in the population, such as hypertension, diabetes (type 1 and type 2 diabetes), gout, rheumatoid arthritis, and colitis, we recommend the following lists of the most suitable and least suitable diets:

[0025]

[0026] Based on the above technical solutions and the technical problems solved, the advantages and positive effects of the technical solution to be protected by this invention are as follows:

[0027] First, this invention utilizes text mining and statistical analysis of scientific literature to collect relevant literature from multiple literature databases on how dietary fiber intake leads to fluctuations in the human gut microbiota and how disease occurrence leads to these fluctuations. The aim is to construct an indirect causal inference network between dietary fiber and disease based on the similarity of gut microbiota fluctuations, analyze complex relationships, and provide support for dietary intake matching and adjuvant drug treatment for specific populations.

[0028] Secondly, the network of this invention utilizes evidence from existing literature databases to construct a network between dietary fiber and disease based on microbial fluctuation patterns, revealing the complex relationship between the two. This provides scientific theoretical guidance and dietary matching for dietary intake in specific disease states, and also offers strong evidence support for adjuvant drug treatment of diseases.

[0029] The personalized dietary guidance of this invention helps optimize patients' nutritional intake, maintain gut health, alleviate disease symptoms, and improve treatment outcomes. Simultaneously, by reducing the intake of inappropriate dietary fiber, it can also lower the risk of adverse reactions in patients.

[0030] Third, the technical solution of this invention fills a technological gap in the industry both domestically and internationally:

[0031] Current research on constructing networks between diet and disease generally follows these approaches: Based on the physicochemical properties and chemical structures of small molecules abundant in food, similar structural units can be used to infer their function in relation to the disease, as seen in the InChI database. Alternatively, the overlap between small molecules abundant in food and the target proteins of corresponding therapeutic drugs can be used to identify drug analogues, thus inferring their therapeutic effects, as seen in the NutriChem 2.0 and FooDisNet databases. Some studies directly collect evidence from the literature to construct associations between food and disease, such as the NutriFD database. However, these databases have a relatively broad definition of diet, lacking focus on specific dietary types. Furthermore, current research often analyzes from the perspectives of physicochemical properties, gene expression, and proteomics, with less exploration from the perspective of the microbiome.

[0032] This invention utilizes text mining and statistical analysis of scientific literature to focus on specific substances such as dietary fiber in multiple literature databases, collecting evidence of how its intake causes fluctuations in the human gut microbiota, as well as relevant literature on how disease causes these fluctuations. From the perspective of microbial perturbation, the connection between dietary fiber and disease is determined, and a correlation map is constructed to provide scientific theoretical guidance for dietary planning for specific patients, helping to improve their microbial community status and contributing to disease management and treatment.

[0033] Fourth, significant technological advancements in dietary fiber recommendation systems based on gut microbiota fluctuations include the following aspects:

[0034] 1. Data Collection and Preprocessing: During the collection and extraction of literature on the relationship between dietary fiber and microbiota, this system employs a series of screening criteria and deduplication processes to more accurately obtain microbial fluctuation datasets under dietary fiber intervention. Furthermore, by combining the HMDAD and DISBIOME databases with the PubMed database, the system can comprehensively collect microbial fluctuation data under various disease states, thus providing a reliable data source for subsequent analysis.

[0035] 2. In-depth Analysis and Algorithm Application: This system employs a weighted overlay algorithm based on biological classification levels to measure the similarity of gut microbiota fluctuations. This algorithm enables in-depth analysis and quantification of the similarity of microbial fluctuations across different disease states at the microbial classification level. The application of this algorithm helps the system better understand the complex relationship between dietary fiber, gut microbiota, and human health, providing individuals with more precise dietary fiber intake recommendations.

[0036] 3. Personalized Dietary Guidance: Based on the above analysis, the system can provide specific dietary intake guidance for different patients. This guidance, based on network mapping, can more accurately reflect the association between dietary fiber and different disease states. Through this personalized guidance, the system can help individuals adjust their diet to improve gut microbiota fluctuations, thereby promoting gut health or assisting in disease treatment.

[0037] 4. System Integration and Automation: This system integrates multiple modules, including data collection, preprocessing, in-depth analysis, and personalized dietary guidance, enabling it to automate a series of processes. This not only improves work efficiency but also reduces human error, enhancing the accuracy and reliability of recommendations.

[0038] These significant technological advancements have enabled dietary fiber recommendation systems based on gut microbiota fluctuations to provide individuals with more accurate dietary fiber intake advice, helping them improve gut health and support disease treatment. Attached Figure Description

[0039] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a structural diagram of the dietary fiber recommendation system based on gut microbiota fluctuations provided in an embodiment of the present invention;

[0041] Figure 2 This is a flowchart of a dietary fiber recommendation method based on gut microbiota fluctuations provided in an embodiment of the present invention. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0043] To address the problems existing in the prior art, this invention provides a dietary fiber recommendation system based on gut microbiota fluctuations.

[0044] like Figure 1 As shown in the figure, an embodiment of the present invention provides a dietary fiber recommendation system based on gut microbiota fluctuations. The dietary fiber recommendation system based on gut microbiota fluctuations specifically includes:

[0045] The data collection module collects and extracts literature on dietary fiber and microbes from PubMed, MEDLINE, Web of Science, and EMBASE databases. By setting a series of screening criteria and deduplication, it extracts a dataset of microbial fluctuations under dietary fiber intervention. Combining the HMDAD and DISBIOME databases and the PubMed database, it selects data on microbial fluctuations generated in various disease states using healthy individuals as controls for deduplication and extraction, ultimately obtaining a set of evidence on microbial fluctuations in human disease states.

[0046] The data analysis module employs a weighted overlay algorithm based on biological classification levels to measure the similarity of microbial community fluctuations. It utilizes multi-level microbial community information to reveal the similarities between dietary fiber and diseases, and constructs a network map of dietary fiber and diseases against the background of microbial disturbance.

[0047] The dietary guidance module provides precise dietary intake guidance for different patients based on network graphs.

[0048] The working principle of a dietary fiber recommendation system based on gut microbiota fluctuations mainly includes the following steps:

[0049] 1. Data Collection: First, the data collection module gathers and extracts literature on the relationship between dietary fiber and microbes from databases such as PubMed, MEDLINE, Web of Science, and EMBASE. Through a series of screening criteria and deduplication, a dataset of microbial fluctuations under dietary fiber intervention is extracted. Furthermore, combining the HMDAD and DISBIOME databases and the PubMed database, data on microbial fluctuations generated in various disease states using healthy individuals as controls are selected and deduplicated, ultimately yielding an evidence set of microbial fluctuations in human disease states.

[0050] 2. Data Analysis: The data analysis module employs a hierarchical weighted overlay algorithm for measuring the similarity of microbial community fluctuations, utilizing multi-level microbial community information to reveal the similarities between dietary fiber and diseases. First, the collected microbial fluctuation data is preprocessed and standardized to eliminate differences between various experimental conditions and data sources. Then, the hierarchical weighted overlay algorithm is used for in-depth analysis of the microbial fluctuation data, calculating the similarity of microbial fluctuations under different disease states. This algorithm can quantify microbial community fluctuations under different disease states at the microbial classification level, thereby discovering the potential association between dietary fiber and disease.

[0051] 3. Dietary Guidance: Based on the above analysis, the dietary guidance module provides specific dietary intake guidance for different patients. This guidance is based on network graphs, which illustrate the association between dietary fiber and different disease states. By analyzing these network graphs, the system can provide personalized dietary recommendations to different patients, helping them adjust their diets to improve gut microbiota fluctuations, thereby promoting health or assisting in disease treatment.

[0052] This system works by collecting and deeply analyzing data from a large amount of literature and databases. It utilizes a weighted overlay algorithm based on biological taxonomy to reveal the potential association between dietary fiber and gut microbiota fluctuations, and then provides precise dietary fiber intake recommendations to individuals based on these associations. This approach helps people better understand the complex relationship between dietary fiber, gut microbiota, and human health, and provides personalized guidance for improving gut health and assisting in disease treatment.

[0053] Furthermore, the data collection module uses the following criteria for screening dietary fiber literature: only randomized controlled clinical trials (RCTs) are selected; healthy individuals are used as research subjects; the interference condition is dietary fiber intake; the control group can be a normal diet, a placebo, or a low dose of the same dietary fiber; and the measured result is the fluctuation of microbial activity.

[0054] Furthermore, the disease literature screening criteria in the data collection module are as follows: healthy individuals serve as the control group, and the disease group serves as the experimental group; there are no significant differences in dietary patterns between the two groups, and no significant differences in physical signs between the groups; the disease group did not take any topical medications or experience a washout period; the final measurement result is the fluctuation of microorganisms.

[0055] Furthermore, the data analysis module's network includes 122 diseases and 32 types of dietary fiber.

[0056] Furthermore, in the dietary guidance module, the gut microbiota fluctuations introduced by dietary fiber are generally opposite to those introduced by disease occurrence. If the total similarity of gut microbiota fluctuations is less than 0 and statistically significant, then the dietary fiber helps improve the disease state. Conversely, if the gut microbiota fluctuations introduced by dietary fiber are generally similar to those introduced by disease occurrence, and the total similarity of gut microbiota fluctuations is greater than 0 and statistically significant, then the dietary fiber is not conducive to improving the disease state.

[0057] Furthermore, in the dietary guidance module, under 122 specific disease states, it is recommended to consume dietary fiber that has significant and negative similarity, and to reduce the intake of dietary fiber that has positive similarity.

[0058] The network includes 122 diseases (such as hypertension, diabetes (type 1 and type 2), gout, rheumatoid arthritis, Crohn's disease, ulcerative colitis, chronic obstructive pulmonary disease, Alzheimer's disease, asthma, lung cancer, breast cancer, etc.) and 32 types of dietary fiber (such as arabinoxylan, resistant starch, inulin, galactooligosaccharides, fructooligosaccharides, resistant maltodextrin, polydextrose, etc.), providing precise dietary intake guidance for different patients (a total of 1667 dietary intake recommendations; please see the appendix for the full names of dietary fibers). This includes diseases with relatively high prevalence such as hypertension, diabetes (type 1 and type 2), gout, rheumatoid arthritis, and colitis. For example, based on the results of the gut microbiota fluctuation similarity network for ulcerative colitis, the use of inulin-like substances is not recommended because the gut microbiota fluctuation pattern caused by this dietary fiber is similar to that caused by Crohn's disease and ulcerative colitis, which will aggravate intestinal inflammation, increase patient suffering, and prolong the treatment period. Conversely, these two types of patients can use substances such as AXOS, WG, RS2, and Walnut, which are dietary fibers that can reduce the inflammatory response in patients with inflammatory bowel disease. Furthermore, in a mouse model of inflammatory bowel disease, it has been demonstrated that AXOS can indeed reduce the inflammatory response caused by Crohn's disease and ulcerative colitis, which also strongly supports the accuracy of the network.

[0059] This invention demonstrates the association between 122 diseases and 32 types of dietary fiber. If the gut microbiota fluctuations introduced by dietary fiber are generally opposite to those introduced by disease (i.e., the total similarity of gut microbiota fluctuations is less than 0 and statistically significant), then the dietary fiber will help improve the disease state; conversely, if the gut microbiota fluctuations introduced by dietary fiber are generally similar to those introduced by disease (i.e., the total similarity of gut microbiota fluctuations is greater than 0 and statistically significant), then the dietary fiber will be detrimental to the improvement of the disease state. For specific disease states (122 diseases), it is recommended to consume dietary fiber with significant negative similarity, while minimizing the intake of dietary fiber with positive similarity to avoid increasing inflammatory responses in the body. These include hypertension, diabetes (type 1 and type 2 diabetes), gout, rheumatoid arthritis, Crohn's disease, and ulcerative colitis. Based on the significant relationships, the recommended and unrecommended dietary intakes for the 122 diseases are presented in Table 1 below:

[0060] Table 1

[0061]

[0062]

[0063]

[0064]

[0065]

[0066]

[0067]

[0068]

[0069]

[0070]

[0071]

[0072]

[0073]

[0074]

[0075]

[0076]

[0077]

[0078]

[0079]

[0080]

[0081]

[0082]

[0083]

[0084]

[0085]

[0086] Based on information from the network graph, personalized dietary fiber intake recommendations are made for patients to suit their disease state.

[0087] The online recommendation list provides a candidate list of foods with a certain scientific basis for their evaluation. It is important to note that individual differences, other nutritional factors, and disease complexity can affect the effectiveness of dietary fiber. Therefore, when applying these research findings to clinical practice, the overall patient condition should be considered, and personalized guidance should be provided based on the specific disease and individual characteristics.

[0088] like Figure 2 As shown, this embodiment of the invention provides a dietary fiber recommendation system based on gut microbiota fluctuations and a dietary fiber recommendation method based on gut microbiota fluctuations. The method includes the following steps:

[0089] S101 utilizes the data collection module to collect and extract literature on dietary fiber and microbes from PubMed, MEDLINE, Web of Science, and EMBASE databases. By setting a series of screening criteria and deduplication, a dataset of microbial fluctuations under dietary fiber intervention is extracted. Combining the HMDAD and DISBIOME databases and the PubMed database, data on microbial fluctuations generated in various disease states using healthy individuals as controls are selected and deduplicated to obtain a set of evidence on microbial fluctuations in human disease states.

[0090] S102 utilizes the data analysis module and employs a weighted superposition algorithm based on the biological classification hierarchy to measure the similarity of microbial community fluctuations. It uses multi-level microbial community information to reveal the similarity between dietary fiber and diseases, and constructs a network map between dietary fiber and diseases against the background of microbial disturbance.

[0091] S103 utilizes a dietary guidance module to provide precise dietary intake guidance for different patients based on network graphs.

[0092] The dietary fiber and disease network constructed in this invention can provide dietary guidance for any disease within the network, and can also assist in drug treatment, regulate the gut microbiota microenvironment of patients, alleviate patient suffering, and shorten treatment duration. It should be noted that these research results still require further validation and evaluation in clinical practice. Individual differences, other nutritional factors, and disease complexity affect the effectiveness of dietary fiber. Therefore, when applying these research results to clinical practice, the overall condition of the patient should be comprehensively considered, and personalized guidance should be provided based on the specific disease and individual characteristics.

[0093] In 2022, Nature published a study on the effects of inulin on gut microbiota composition, bacterial metabolites, and subsequent immune responses. While regulating T-cell proliferation to combat inflammation, it also increased eosinophils, indicating that inulin simultaneously promotes type 2 inflammatory responses. Previous experiments have demonstrated that arabinoxylan can effectively inhibit the expression and protein levels of inflammatory factors in patients with inflammatory bowel disease. This evidence effectively supports the validity and accuracy of dietary fiber and key nodes in disease networks.

[0094] Example 1:

[0095] 1. Data Collection Module: This module utilizes an automated web crawler technique to search and extract relevant literature on dietary fiber and microbiome from databases such as PubMed, MEDLINE, Web of Science, and EMBASE. Screening criteria can include study type (e.g., randomized controlled trials, observational studies), study quality (e.g., scoring based on methodological design and execution), and sample size. This data is then cleaned and deduplicated to obtain a dataset on microbiome fluctuations under dietary fiber intervention. Simultaneously, data on microbiome fluctuations in various disease states, with healthy individuals as controls, are selected and deduplicated from HMDAD, DISBIOME, and PubMed databases, ultimately yielding an evidence set of microbiome fluctuations in human disease states.

[0096] 2. Data Analysis Module: An algorithm called "Biological Taxonomy Hierarchical Weighted Overlay" is employed, which measures the similarity of microbial community fluctuations. This algorithm utilizes multi-level microbial community information to reveal the similarities between dietary fiber and diseases, constructing a network map of dietary fiber and diseases against the backdrop of microbial disturbance.

[0097] 3. Dietary Guidance Module: Based on the network map, precise and specific dietary intake guidance is provided for each patient. This includes specific types of dietary fiber, intake amounts, and intake frequencies.

[0098] Example 2:

[0099] 1. Data Collection Module: In addition to the database search and data extraction mentioned above, this module can also directly obtain patients' medical records and microbiome sample data through cooperation with hospitals and clinics. This will add more direct and personalized data to the dataset.

[0100] 2. Data Analysis Module: In addition to using the weighted overlay algorithm based on biological classification hierarchy, machine learning and artificial intelligence technologies, such as deep learning algorithms, can be utilized to further optimize the construction of the network graph and the measurement of community fluctuations.

[0101] 3. Dietary Guidance Module: When providing dietary intake guidance to patients, more personalized factors can be considered, such as the patient's age, gender, weight, lifestyle, and genetic factors. Furthermore, an interactive online platform can be created where patients can access dietary guidance and provide feedback, allowing the system to continuously optimize and personalize dietary recommendations.

[0102] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications, equivalent substitutions, and improvements made by those skilled in the art within the scope of the technology disclosed in the present invention, and within the spirit and principles of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A dietary fiber recommendation system based on gut microbiota fluctuations, characterized in that, Specifically, it includes: The data collection module collects and extracts literature on dietary fiber and microbes from PubMed, MEDLINE, Web of Science, and EMBASE databases. By setting a series of screening criteria and deduplication, it extracts a dataset of microbial fluctuations under dietary fiber intervention. Combining the HMDAD and DISBIOME databases and the PubMed database, it selects data on microbial fluctuations generated in various disease states using healthy individuals as controls for deduplication and extraction, ultimately obtaining a set of evidence on microbial fluctuations in human disease states. The data analysis module employs a weighted overlay algorithm based on biological classification levels to measure the similarity of microbial community fluctuations. It utilizes multi-level microbial community information to reveal the similarities between dietary fiber and diseases, and constructs a network map of dietary fiber and diseases against the background of microbial disturbance. The dietary guidance module provides precise dietary intake guidance for different patients based on network graphs.

2. The dietary fiber recommendation system based on gut microbiota fluctuations as described in claim 1, characterized in that, The data collection module's criteria for screening dietary fiber literature were as follows: only randomized controlled clinical trials (RCTs) were selected; healthy individuals were used as research subjects; and dietary fiber intake was the interference condition. The control group could be a normal diet, a placebo, or a low dose of the same dietary fiber; the results measured were fluctuations in the microbiome.

3. The dietary fiber recommendation system based on gut microbiota fluctuations as described in claim 1, characterized in that, The disease literature screening criteria in the data collection module are as follows: healthy people serve as the control group and disease groups serve as the experimental group; there are no significant differences in dietary patterns between the two groups, and no significant differences in physical signs between the groups; the disease group did not take any topical medications or experience a washout period; the final measurement result is the fluctuation of microorganisms.

4. The dietary fiber recommendation system based on gut microbiota fluctuations as described in claim 1, characterized in that, The data analysis module's network includes 122 diseases and 32 types of dietary fiber.

5. The dietary fiber recommendation system based on gut microbiota fluctuations as described in claim 1, characterized in that, In the dietary guidance module, the gut microbiota fluctuations introduced by dietary fiber are generally opposite to those introduced by disease occurrence. If the total similarity of gut microbiota fluctuations is less than 0 and statistically significant, then the dietary fiber helps to improve the disease state. If the gut microbiota fluctuations introduced by dietary fiber are generally similar to those introduced by disease, and the overall similarity of gut microbiota fluctuations is greater than 0 and statistically significant, then the dietary fiber is not conducive to improving the disease state.

6. The dietary fiber recommendation system based on gut microbiota fluctuations as described in claim 1, characterized in that, In the dietary guidance module, under 122 specific disease states, it is recommended to consume dietary fiber that has significant and negative similarity, and to reduce the intake of dietary fiber that has positive similarity.

7. The dietary fiber recommendation system based on gut microbiota fluctuations and the dietary fiber recommendation method based on gut microbiota fluctuations as described in any one of claims 1 to 6, characterized in that, The method includes the following steps: Step 1: Using the data collection module, literature on dietary fiber and microbiome was collected and extracted from PubMed, MEDLINE, Web of Science, and EMBASE databases. By setting a series of screening criteria and deduplication, a dataset of microbiome fluctuations under dietary fiber intervention was extracted. Combining the HMDAD and DISBIOME databases and the PubMed database, data on microbiome fluctuations generated in various disease states using healthy individuals as controls were selected and deduplicated to obtain a set of evidence on microbiome fluctuations in human disease states. Step 2: Using the data analysis module, a weighted superposition algorithm based on the biological classification hierarchy is adopted to measure the similarity of microbial community fluctuations. Multi-level microbial community information is used to reveal the similarity between dietary fiber and diseases, and a network map between dietary fiber and diseases with microbial disturbance as the background is constructed. Step 3: Using the dietary guidance module, specific dietary intake guidance is provided precisely to different patients based on the network graph.

8. An application of a dietary fiber recommendation system based on gut microbiota fluctuations as described in any one of claims 1 to 6, providing specific dietary fiber recommendations for different patients.

9. The application of the dietary fiber recommendation system based on gut microbiota fluctuations as described in claim 8, which provides specific dietary fiber recommendations for different patients, is characterized in that... For patients with ulcerative colitis, inulin-based substances are not recommended; AXOS, WG, RS2, and Walnut can be used.

10. The application of the dietary fiber recommendation system based on gut microbiota fluctuations as described in claim 8, which provides specific dietary fiber recommendations for different patients, is characterized in that... For people with hypertension, it is recommended to consume more resistant starches such as RS, β-glucan, and FOS, while consuming less PDX and SCF. Type 1 diabetics can consume more FOS, JA, and CH inulin-based substances. However, patients with ulcerative colitis and Crohn's disease are not advised to use inulin-based substances; they can consume AXOS, WG, RS2, and Walnut.

Images