Health state detection method and system based on intestinal bacterial liquid analysis

Abstract

The invention discloses a health state detection method and system based on intestinal bacterial liquid analysis, and relates to the technical field of medical health detection. The method comprises the following steps: collecting an excrement sample and obtaining an intestinal bacterial liquid sample; performing information extraction on the intestinal bacterial liquid sample to obtain microorganism information; performing biological information analysis on the microorganism information to obtain an information analysis result; evaluating the health state to obtain a health evaluation result; establishing an intestinal tract-health association model based on the information analysis result and the health assessment result; and acquiring disease information of various intestinal related diseases, and establishing an association relationship between the disease information and the intestinal-health association model to form a disease risk prediction model which is used for predicting the risk degree of the intestinal related diseases. According to the method, the intestinal health condition is comprehensively evaluated and personalized health management is provided by adopting the synergistic effect of multiple technologies such as DNA extraction, genomics analysis and machine learning, so that the accuracy and reliability of health evaluation and detection are further guaranteed.

Description

Technical Field

[0001] The present invention belongs to the field of medical health detection technology, and in particular relates to a health status detection method and system based on intestinal bacterial fluid analysis. Background Art

[0002] As an important microbial group in the human body, the intestinal flora is closely related to health status. Studies in recent years have found that changes in the composition and function of the intestinal flora are closely related to the occurrence and development of a variety of diseases, such as obesity, diabetes, cardiovascular disease, digestive system diseases, and even some neurological diseases. The intestinal flora is not only involved in the digestive process, but is also closely related to the immune system, metabolic function, and regulation of the nervous system. Therefore, the state of the intestinal flora has become an important indicator of human health.

[0003] With the continuous development of genomics and metabolomics technologies, intestinal flora analysis technology has made significant progress. Traditional intestinal flora detection mainly relies on culture methods, but this method cannot detect most of the microorganisms that cannot be cultured. Therefore, gene sequencing technology (such as 16SrRNA gene sequencing, metagenomic sequencing, etc.) has become the mainstream intestinal flora analysis technology.

[0004] Although intestinal flora analysis technology has made certain breakthroughs, it still faces many problems such as individual differences, dynamic changes, and data analysis. Therefore, a more comprehensive and accurate method of intestinal status detection is needed. Summary of the invention

[0005] The purpose of the present invention is to provide a health status detection method and system based on intestinal bacterial fluid analysis, which can be achieved through the following technical solutions: In a first aspect, the present application provides a method for detecting health status based on intestinal bacterial fluid analysis, comprising the following steps: Collect stool samples and obtain intestinal bacterial fluid samples after sample processing; Extracting information from the intestinal bacterial fluid sample to obtain microbial information; Performing biological information analysis on the microbial information to obtain information analysis results; Evaluate the health status according to the information analysis result to obtain a health evaluation result; Establishing an intestinal tract-health association model based on the information analysis results and the health assessment results; acquiring disease information of multiple intestinal tract-related diseases and establishing an association relationship between the information and the intestinal tract-health association model to form a disease risk prediction model and use it to predict the risk level of the intestinal tract-related diseases; Wherein, extracting information from the intestinal bacterial liquid sample includes: Obtaining high-throughput sequencing data from the intestinal bacterial fluid sample; Classifying the intestinal flora based on the high-throughput sequencing data and establishing an intestinal flora distribution model according to the classification results; Obtaining a bacterial species abundance table of all bacterial species types according to the intestinal flora distribution model; Screening the main components of the intestinal flora based on the bacterial species abundance table; Mining SNPs of the intestinal flora according to the main components of the intestinal flora; The microbial information includes intestinal flora types, bacterial species abundance table, main components of intestinal flora, SNPs of intestinal flora, and k groups of intestinal type difference characteristics of differential bacteria.

[0006] Preferably, the stool sample is collected and the intestinal bacterial liquid sample is obtained by sample processing, specifically: Obtaining a stool sample from the subject and recording the time of obtaining the sample; if the time of obtaining the sample exceeds the prescribed microbial activity time, obtaining a new stool sample; Pre-processing the stool sample, including homogenization and dispersion; Extracting microorganisms from the pretreated stool sample and performing a quality inspection to obtain the intestinal bacterial liquid sample; The microbial extraction of the pretreated stool sample is specifically performed as follows: The DNA in the stool samples was extracted and all 16S rDNA therein was subjected to high-throughput sequencing.

[0007] Preferably, the classifying of intestinal flora based on the high-throughput sequencing data comprises: Bacteria classification: using a Gaussian mixture model to classify the intestinal flora and identify the proportions of beneficial bacteria, pathogenic bacteria, and harmful bacteria; Model establishment: Based on the classification results of the Gaussian mixture model, an intestinal flora distribution model of the individual subject is established to reflect the abundance of various bacterial species.

[0008] Preferably, the classifying of the intestinal flora based on the high-throughput sequencing data further includes: classifying the differential bacteria appearing in the intestinal flora, specifically: Dividing the high-throughput sequencing data into detection group data and control group data; Converting the features of each sample in the high-throughput sequencing data from absolute abundance to relative abundance, and filtering out absolute abundance features in the sample whose occurrence frequency is less than a preset value and whose relative abundance is zero; Dividing all samples in the high-throughput sequencing data into k groups of enterotypes according to the similarity of absolute abundance; The relative abundance differences between the test group data and the control group data are calculated and sorted to obtain the difference characteristics corresponding to each of the k groups of intestinal types.

[0009] Preferably, the performing biological information analysis on the microbial information includes: Obtaining the protein sequence of the SNP according to the SNP of the intestinal flora, and mapping the protein sequence to the KEGG database for comparison, and obtaining the biological pathway information involved and the dynamic changes of intestinal bacteria according to the highest comparison score result; K machine learning models are constructed based on the k groups of intestinal type difference characteristics, a group of sample data with known absolute abundance is input, the absolute abundance of the sample data is converted into relative abundance, and the k machine learning models are used to predict the unhealthy probability of the sample data.

[0010] Preferably, the performing biological information analysis on the microbial information further comprises: By comparing the established intestinal flora distribution model with the standard model of healthy flora, the imbalance of the intestinal flora of the subject is detected, and the excessive proliferation of harmful bacteria or the lack of beneficial bacteria are identified; and based on the detection results of the imbalance, a personalized regulation plan is generated for the subject.

[0011] Preferably, the detecting the imbalance of the intestinal flora of the subject comprises: Extracting the relative abundance of each flora species according to the intestinal flora distribution model, and comparing it with the corresponding flora proportion in a pre-established health standard model; The KL divergence algorithm is used to quantify the difference between the bacterial flora distribution of the subject and the healthy standard distribution; The imbalance of the bacterial flora is analyzed based on the results of the imbalance detection. When the KL divergence exceeds the set threshold, it is identified as excessive proliferation of harmful bacteria or lack of beneficial bacteria, and potential health risks are marked.

[0012] Preferably, the evaluating the health status according to the information analysis result includes: Constructing a health assessment model based on the information analysis results; Using the health assessment model to assess the health status of the subject; Wherein, constructing the health assessment model includes: Constructing a relative abundance matrix of the intestinal flora and extracting a feature matrix; Constructing a first training matrix based on the classification columns and the feature matrix and performing data set training; Selecting a number of optimal feature columns and sample classification columns in the first training matrix to construct a second training matrix; The second training matrix is ​​trained with a data set and a risk assessment model is constructed based on the training result.

[0013] Preferably, establishing the intestinal tract-health association model comprises: Screening out intestinal microbial characteristics related to health status based on the information analysis results and the health assessment results; Based on the intestinal microbial characteristics, a machine learning model is used to establish the intestinal-health association model; The intestinal tract-health association model is used to establish the association between the intestinal flora and health status, and to identify the relationship between key microorganisms and health parameters; Establishing the disease risk prediction model comprises: Integrating the recognition result of the intestinal tract-health association model with the acquired information of various intestinal tract-related diseases to obtain integrated information; Based on the integrated information, the disease risk prediction model is established using random forest; The random forest is used to analyze the relationship between intestinal characteristics and different intestinal-related diseases, and to predict the risk level of the intestinal-related diseases in combination with the identification results of the intestinal-health association model.

[0014] In a second aspect, an embodiment of the present application provides a health status detection system based on intestinal bacterial fluid analysis, applying the above-mentioned health status detection method based on intestinal bacterial fluid analysis, including: Sample collection and processing module: used to collect stool samples and obtain intestinal bacterial fluid samples after sample processing; Biological information extraction module: used to extract information from the intestinal bacterial liquid sample to obtain microbial information; Bioinformatics analysis module: used to perform bioinformatics analysis on the microbial information to obtain information analysis results; Health assessment module: used to assess the health status according to the information analysis results and obtain the health assessment results; Association model building module: establish an intestinal-health association model based on the information analysis results and the health assessment results; obtain disease information of multiple intestinal-related diseases and establish an association relationship between them and the intestinal-health association model to form a disease risk prediction model and use it to predict the risk level of the intestinal-related diseases; Wherein, extracting information from the intestinal bacterial liquid sample includes: Obtaining high-throughput sequencing data from the intestinal bacterial fluid sample; Classifying the intestinal flora based on the high-throughput sequencing data and establishing an intestinal flora distribution model according to the classification results; Obtaining a bacterial species abundance table of all bacterial species types according to the intestinal flora distribution model; Screening the main components of the intestinal flora based on the bacterial species abundance table; Mining SNPs of the intestinal flora according to the main components of the intestinal flora; The microbial information includes intestinal flora types, bacterial species abundance table, main components of intestinal flora, SNPs of intestinal flora, and k groups of intestinal type difference characteristics of differential bacteria.

[0015] The beneficial effects of the present invention are as follows: the present invention provides a complete process from sample collection, DNA extraction, genomic analysis to data interpretation and health assessment, and comprehensively assesses the intestinal health status through the synergistic effect of the above steps, and provides a scientific basis for personalized health management. In addition, in the extraction and analysis of biological information, high-throughput sequencing and genome sequencing are used to comprehensively analyze the metabolic capacity and functional state of the intestinal bacterial fluid to judge the health status of the intestine. In addition, by combining machine learning or artificial intelligence algorithms for data mining, a correlation model between intestinal flora and health status is established to identify potential disease risks, thereby further ensuring the accuracy and reliability of health assessment and detection. It can also provide more accurate support for personal health management. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] For better understanding and implementation, the technical solution of the present application is described in detail below with reference to the accompanying drawings.

[0017] Figure 1 A flowchart of the steps of a health status detection method based on intestinal bacterial fluid analysis provided in an embodiment of the present application; Figure 2 A flowchart of the steps for extracting intestinal bacterial liquid sample information provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of a health status detection system based on intestinal bacterial fluid analysis provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to further explain the technical means and effects taken by the present invention to achieve the predetermined invention purpose, exemplary embodiments will be described in detail here, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are only examples of methods and systems consistent with some aspects of the present application as detailed in the attached claims.

[0019] The terms used in this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in this article refers to any or all possible combinations of one or more associated listed items.

[0020] The specific implementation methods, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0021] Example 1 See also Figure 1 The present application embodiment provides a health status detection method based on intestinal bacterial fluid analysis, comprising the following steps: Collect stool samples and obtain intestinal bacterial fluid samples after sample processing; Extracting information from the intestinal bacterial fluid sample to obtain microbial information; Performing biological information analysis on the microbial information to obtain information analysis results; Evaluate the health status according to the information analysis result to obtain a health evaluation result; Establishing an intestinal tract-health association model based on the information analysis results and the health assessment results; acquiring disease information of multiple intestinal tract-related diseases and establishing an association relationship between the information and the intestinal tract-health association model to form a disease risk prediction model and use it to predict the risk level of the intestinal tract-related diseases; The microbial information includes intestinal flora types, bacterial species abundance table, main components of intestinal flora, SNPs of intestinal flora, and k groups of intestinal type difference characteristics of differential bacteria.

[0022] Specifically, due to the complexity of intestinal flora, standardization issues, individual differences, data analysis difficulties and other limitations, as well as technical cost issues, the analysis of intestinal flora and health testing have become a constraint on individual health prediction. Therefore, in order to improve the accuracy and reliability of intestinal flora analysis and health assessment, the present application provides a new health detection method that combines bioinformation extraction and analysis technology with artificial intelligence technology, specifically including: first, collecting fecal samples and obtaining intestinal flora samples after sample processing; then extracting information from the intestinal flora samples to obtain microbial information; then performing bioinformatics analysis on the microbial information to obtain information analysis results; then evaluating the health status based on the information analysis results to obtain health assessment results; finally, establishing an intestinal-health association model based on the above information analysis results and health assessment results; then, by obtaining disease information of multiple intestinal-related diseases and establishing an association relationship with the intestinal-health association model, a disease risk prediction model is formed and the model is used to predict the risk level of intestinal-related diseases.

[0023] This application provides a complete process from sample collection, DNA extraction, genomic analysis to data interpretation and health assessment. Through the synergy of the above steps, the intestinal health status is comprehensively assessed, and a scientific basis is provided for personalized health management. In addition, in the extraction and analysis of bioinformation, high-throughput sequencing and genome sequencing are used to comprehensively analyze the metabolic capacity and functional state of the intestinal bacterial fluid to judge the health status of the intestine. Data mining is also carried out by combining machine learning or artificial intelligence algorithms to establish a correlation model between intestinal flora and health status, so as to identify potential disease risks, thereby further ensuring the accuracy and reliability of health assessment and detection. It can also provide more accurate support for personal health management.

[0024] In one embodiment provided in the present application, the stool sample is collected and the intestinal bacterial liquid sample is obtained after sample processing, specifically: Obtaining a stool sample from the subject and recording the time of obtaining the sample; if the time of obtaining the sample exceeds the prescribed microbial activity time, obtaining a new stool sample; Pre-processing the stool sample, including homogenization and dispersion; Extracting microorganisms from the pretreated stool sample and performing a quality inspection to obtain the intestinal bacterial liquid sample; The microbial extraction of the pretreated stool sample is specifically performed as follows: The DNA in the stool samples was extracted and all 16S rDNA therein was subjected to high-throughput sequencing.

[0025] Specifically, this embodiment obtains a stool sample and extracts microorganisms from it to obtain an intestinal bacterial liquid sample. In this process, the time of obtaining the sample is first recorded while obtaining the stool sample. Since the time of the sample will affect the activity of the microorganisms therein, in order to prevent inactivation and contamination, the sample that exceeds the specified microorganism activity time is re-obtained by recording the sample time. In addition, the uniformity of the sample during the processing is ensured by homogenization, and the microorganisms in the sample are dispersed by dispersion treatment. Finally, this embodiment extracts microorganisms from the pretreated stool sample, analyzes the composition of intestinal microorganisms by extracting DNA of microorganisms from the sample, and uses agarose gel electrophoresis and a spectrophotometer to check the quality and concentration of the DNA after DNA extraction to ensure that the extracted DNA is complete and uncontaminated. Finally, the intestinal bacterial liquid sample is composed of the extracted microorganisms. The microorganisms in the intestinal bacterial liquid sample obtained at this time are of high quality and uniformity and are uncontaminated, which can improve the accuracy and reliability of subsequent biological information extraction and analysis.

[0026] It is understandable that microbial DNA is extracted from stool samples to ensure that subsequent analysis can accurately reflect the composition of the intestinal flora. 16S rRNA gene sequencing is to selectively amplify the bacterial 16S rRNA gene and perform high-throughput sequencing to identify the bacterial species in the intestinal microbiota.

[0027] like Figure 2 As shown, in one embodiment provided in the present application, the information extraction of the intestinal bacterial liquid sample includes: Obtaining high-throughput sequencing data from the intestinal bacterial fluid sample; Classifying the intestinal flora based on the high-throughput sequencing data and establishing an intestinal flora distribution model according to the classification results; Obtaining a bacterial species abundance table of all bacterial species types according to the intestinal flora distribution model; Screening the main components of the intestinal flora based on the bacterial species abundance table; The SNPs of the intestinal flora are mined according to the main components of the intestinal flora.

[0028] Specifically, this embodiment extracts key information from a large amount of flora data by classifying the intestinal flora, and screens the main components of the intestinal flora through the obtained bacterial species abundance table, so as to mine the SNP (Single Nucleotide Polymorphism) of the intestinal flora. Since SNP may affect the growth, metabolic function, drug resistance, etc. of microorganisms, and thus affect the health or disease state of the host, by mining the SNP in the intestinal flora, we can deeply understand the genetic diversity of intestinal microorganisms and their relationship with host health, which is helpful for individualized health intervention and disease prevention.

[0029] In one embodiment provided in the present application, the classifying of intestinal flora based on the high-throughput sequencing data includes: Bacteria classification: using a Gaussian mixture model to classify the intestinal flora and identify the proportions of beneficial bacteria, pathogenic bacteria, and harmful bacteria; Model establishment: Based on the classification results of the Gaussian mixture model, an intestinal flora distribution model of the individual subject is established to reflect the abundance of various bacterial species.

[0030] Specifically, this embodiment can effectively identify the ratio of beneficial bacteria to harmful bacteria through the above-mentioned intestinal flora classification content, and build an individualized flora distribution model, which can extract key information from a large amount of complex flora data and identify flora imbalance problems, thereby providing a scientific basis for personalized regulation solutions. At the same time, by calculating the relative abundance of flora, it can dynamically monitor the intestinal health status and provide more accurate health management and intervention measures.

[0031] It should be noted that the abundance of the above-mentioned various bacterial species includes the relative abundance and absolute abundance of each bacterial species.

[0032] In an embodiment provided in the present application, the classifying of the intestinal flora based on the high-throughput sequencing data further includes: classifying the differential bacteria appearing in the intestinal flora, specifically: Dividing the high-throughput sequencing data into detection group data and control group data; Converting the features of each sample in the high-throughput sequencing data from absolute abundance to relative abundance, and filtering out absolute abundance features in the sample whose occurrence frequency is less than a preset value and whose relative abundance is zero; Dividing all samples in the high-throughput sequencing data into k groups of enterotypes according to the similarity of absolute abundance; The relative abundance differences between the test group data and the control group data are calculated and sorted to obtain the difference characteristics corresponding to each of the k groups of intestinal types.

[0033] Specifically, this embodiment classifies the differential bacteria appearing in the intestinal flora based on the aggregation classification algorithm, and further improves the intermediate analysis process. It can not only effectively extract the sample features with high dimensions and large abundance variation range, but also has stronger anti-interference performance, which better meets the application requirements.

[0034] In an embodiment provided in the present application, the performing biological information analysis on the microbial information includes: Obtaining the protein sequence of the SNP according to the SNP of the intestinal flora, and mapping the protein sequence to the KEGG database for comparison, and obtaining the biological pathway information involved and the dynamic changes of intestinal bacteria according to the highest comparison score result; K machine learning models are constructed based on the k groups of intestinal type difference characteristics, a group of sample data with known absolute abundance is input, the absolute abundance of the sample data is converted into relative abundance, and the k machine learning models are used to predict the unhealthy probability of the sample data.

[0035] In an embodiment provided in the present application, the performing biological information analysis on the microbial information further includes: By comparing the established intestinal flora distribution model with the standard model of healthy flora, the imbalance of the intestinal flora of the subject is detected, and the excessive proliferation of harmful bacteria or the lack of beneficial bacteria are identified; and based on the detection results of the imbalance, a personalized regulation plan is generated for the subject.

[0036] In one embodiment provided in the present application, the detecting the imbalance of the intestinal flora of the subject includes: Extracting the relative abundance of each flora species according to the intestinal flora distribution model, and comparing it with the corresponding flora proportion in a pre-established health standard model; The KL divergence algorithm is used to quantify the difference between the bacterial flora distribution of the subject and the healthy standard distribution; The imbalance of the bacterial flora is analyzed based on the results of the imbalance detection. When the KL divergence exceeds the set threshold, it is identified as excessive proliferation of harmful bacteria or lack of beneficial bacteria, and potential health risks are marked.

[0037] Specifically, this embodiment realizes personalized monitoring and dynamic adjustment of the health status of the subject through intestinal microecological regulation, health status assessment and personalized regulation schemes. Based on intestinal flora classification and imbalance detection, health problems of the subject can be discovered in time and dynamic adjustments can be made.

[0038] In an embodiment provided in the present application, the evaluating the health status according to the information analysis result includes: Constructing a health assessment model based on the information analysis results; Using the health assessment model to assess the health status of the subject; Wherein, constructing the health assessment model includes: Constructing a relative abundance matrix of the intestinal flora and extracting a feature matrix; Constructing a first training matrix based on the classification columns and the feature matrix and performing data set training; Selecting a number of optimal feature columns and sample classification columns in the first training matrix to construct a second training matrix; The second training matrix is ​​trained with a data set and a risk assessment model is constructed based on the training result.

[0039] Specifically, this embodiment uses machine learning and other algorithms to construct a health assessment model, which has greatly improved the accuracy of disease health assessment and can be used for risk warning and health monitoring of various intestinal diseases.

[0040] In one embodiment provided in the present application, establishing the intestinal tract-health association model includes: Screening out intestinal microbial characteristics related to health status based on the information analysis results and the health assessment results; Based on the intestinal microbial characteristics, a machine learning model is used to establish the intestinal-health association model; The intestinal tract-health association model is used to establish the association between the intestinal flora and health status, and to identify the relationship between key microorganisms and health parameters; Establishing the disease risk prediction model comprises: Integrating the recognition result of the intestinal tract-health association model with the acquired information of various intestinal tract-related diseases to obtain integrated information; Based on the integrated information, the disease risk prediction model is established using random forest; The random forest is used to analyze the relationship between intestinal characteristics and different intestinal-related diseases, and to predict the risk level of the intestinal-related diseases in combination with the identification results of the intestinal-health association model.

[0041] Specifically, this embodiment establishes a gut-health association model and builds a disease risk prediction model based on it, which can not only help identify individual health risks but also promote personalized medicine and preventive health management.

[0042] Example 2 See also Figure 3 The embodiment of the present application provides a health status detection system based on intestinal bacterial fluid analysis, which uses the above-mentioned health status detection method based on intestinal bacterial fluid analysis, including: Sample collection and processing module: used to collect stool samples and obtain intestinal bacterial fluid samples after sample processing; Biological information extraction module: used to extract information from the intestinal bacterial liquid sample to obtain microbial information; Bioinformatics analysis module: used to perform bioinformatics analysis on the microbial information to obtain information analysis results; Health assessment module: used to assess the health status according to the information analysis results and obtain the health assessment results; Association model building module: establish an intestinal-health association model based on the information analysis results and the health assessment results; obtain disease information of multiple intestinal-related diseases and establish an association relationship between them and the intestinal-health association model to form a disease risk prediction model and use it to predict the risk level of the intestinal-related diseases; Wherein, extracting information from the intestinal bacterial liquid sample includes: Obtaining high-throughput sequencing data from the intestinal bacterial fluid sample; Classifying the intestinal flora based on the high-throughput sequencing data and establishing an intestinal flora distribution model according to the classification results; Obtaining a bacterial species abundance table of all bacterial species types according to the intestinal flora distribution model; Screening the main components of the intestinal flora based on the bacterial species abundance table; Mining SNPs of the intestinal flora according to the main components of the intestinal flora; The microbial information includes intestinal flora types, bacterial species abundance table, main components of intestinal flora, SNPs of intestinal flora, and k groups of intestinal type difference characteristics of differential bacteria.

[0043] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0044] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0045] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0046] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A health status detection method based on intestinal bacterial fluid analysis, characterized in that: The steps include: Collect stool samples and obtain intestinal bacterial fluid samples after sample processing; Extracting information from the intestinal bacterial fluid sample to obtain microbial information; Performing biological information analysis on the microbial information to obtain information analysis results; Evaluate the health status according to the information analysis result to obtain a health evaluation result; Establishing an intestinal-health association model based on the information analysis results and the health assessment results; Obtaining disease information of multiple intestinal diseases and establishing an association relationship between the information and the intestinal health association model to form a disease risk prediction model and use it to predict the risk level of the intestinal diseases; Wherein, extracting information from the intestinal bacterial liquid sample includes: Obtaining high-throughput sequencing data from the intestinal bacterial fluid sample; Classifying the intestinal flora based on the high-throughput sequencing data and establishing an intestinal flora distribution model according to the classification results; Obtaining a bacterial species abundance table of all bacterial species types according to the intestinal flora distribution model; Screening the main components of the intestinal flora based on the bacterial species abundance table; Mining SNPs of the intestinal flora according to the main components of the intestinal flora; The microbial information includes intestinal flora types, bacterial species abundance table, main components of intestinal flora, SNPs of intestinal flora, and k groups of intestinal type difference characteristics of differential bacteria.

2. A health status detection method based on intestinal bacterial liquid analysis according to claim 1, characterized in that: The stool sample is collected and the intestinal bacterial liquid sample is obtained after sample processing, specifically: Obtaining a stool sample from the subject and recording the time of obtaining the sample; if the time of obtaining the sample exceeds the prescribed microbial activity time, obtaining a new stool sample; Pre-processing the stool sample, including homogenization and dispersion; Extracting microorganisms from the pretreated stool sample and performing a quality inspection to obtain the intestinal bacterial liquid sample; The microbial extraction of the pretreated stool sample is specifically performed as follows: The DNA in the stool samples was extracted and all 16S rDNA therein was subjected to high-throughput sequencing.

3. A health status detection method based on intestinal bacterial liquid analysis according to claim 1, characterized in that: The classifying of intestinal flora based on the high-throughput sequencing data comprises: Bacteria classification: using a Gaussian mixture model to classify the intestinal flora and identify the proportions of beneficial bacteria, pathogenic bacteria, and harmful bacteria; Model establishment: Based on the classification results of the Gaussian mixture model, an intestinal flora distribution model of the individual subject is established to reflect the abundance of various bacterial species.

4. A health status detection method based on intestinal bacterial liquid analysis according to claim 1, characterized in that: The classifying of the intestinal flora based on the high-throughput sequencing data further includes: classifying the differential bacteria appearing in the intestinal flora, specifically: Dividing the high-throughput sequencing data into detection group data and control group data; Converting the features of each sample in the high-throughput sequencing data from absolute abundance to relative abundance, and filtering out absolute abundance features in the sample whose occurrence frequency is less than a preset value and whose relative abundance is zero; Dividing all samples in the high-throughput sequencing data into k groups of enterotypes according to the similarity of absolute abundance; The relative abundance differences between the test group data and the control group data are calculated and sorted to obtain the difference characteristics corresponding to each of the k groups of intestinal types.

5. The method for detecting health status based on intestinal bacterial fluid analysis according to claim 1, characterized in that: The performing biological information analysis on the microbial information includes: Obtaining the protein sequence of the SNP according to the SNP of the intestinal flora, and mapping the protein sequence to the KEGG database for comparison, and obtaining the biological pathway information involved and the dynamic changes of intestinal bacteria according to the highest comparison score result; K machine learning models are constructed based on the k groups of intestinal type difference characteristics, a group of sample data with known absolute abundance is input, the absolute abundance of the sample data is converted into relative abundance, and the k machine learning models are used to predict the unhealthy probability of the sample data.

6. A health status detection method based on intestinal bacterial liquid analysis according to claim 1, characterized in that: The performing biological information analysis on the microbial information further includes: By comparing the established intestinal flora distribution model with the standard model of healthy flora, the imbalance of the intestinal flora of the subject is detected, and the excessive proliferation of harmful bacteria or the lack of beneficial bacteria are identified; and based on the detection results of the imbalance, a personalized regulation plan is generated for the subject.

7. A health status detection method based on intestinal bacterial liquid analysis according to claim 6, characterized in that: The method of detecting the imbalance of the intestinal flora of the subject includes: Extracting the relative abundance of each flora species according to the intestinal flora distribution model, and comparing it with the corresponding flora proportion in a pre-established health standard model; The KL divergence algorithm is used to quantify the difference between the bacterial flora distribution of the subject and the healthy standard distribution; The imbalance of the bacterial flora is analyzed based on the results of the imbalance detection. When the KL divergence exceeds the set threshold, it is identified as excessive proliferation of harmful bacteria or lack of beneficial bacteria, and potential health risks are marked.

8. The method for detecting health status based on intestinal bacterial fluid analysis according to claim 1, characterized in that: The step of evaluating the health status according to the information analysis result includes: Constructing a health assessment model based on the information analysis results; Using the health assessment model to assess the health status of the subject; Wherein, constructing the health assessment model includes: Constructing a relative abundance matrix of the intestinal flora and extracting a feature matrix; Constructing a first training matrix based on the classification columns and the feature matrix and performing data set training; Selecting a number of optimal feature columns and sample classification columns in the first training matrix to construct a second training matrix; The second training matrix is ​​trained with a data set and a risk assessment model is constructed based on the training result.

9. The method for detecting health status based on intestinal bacterial fluid analysis according to claim 1, characterized in that: Establishing the intestinal tract-health association model includes: Screening out intestinal microbial characteristics related to health status based on the information analysis results and the health assessment results; Based on the intestinal microbial characteristics, a machine learning model is used to establish the intestinal-health association model; The intestinal tract-health association model is used to establish the association between the intestinal flora and health status, and to identify the relationship between key microorganisms and health parameters; Establishing the disease risk prediction model comprises: Integrating the recognition result of the intestinal tract-health association model with the acquired information of various intestinal tract-related diseases to obtain integrated information; Based on the integrated information, the disease risk prediction model is established using random forest; The random forest is used to analyze the relationship between intestinal characteristics and different intestinal-related diseases, and to predict the risk level of the intestinal-related diseases in combination with the identification results of the intestinal-health association model.

10. A health status detection system based on intestinal bacterial liquid analysis, using a health status detection method based on intestinal bacterial liquid analysis as claimed in any one of claims 1 to 9, characterized in that: include: Sample collection and processing module: used to collect stool samples and obtain intestinal bacterial fluid samples after sample processing; Biological information extraction module: used to extract information from the intestinal bacterial liquid sample to obtain microbial information; Bioinformatics analysis module: used to perform bioinformatics analysis on the microbial information to obtain information analysis results; Health assessment module: used to assess the health status according to the information analysis results and obtain the health assessment results; Association model building module: establish an intestinal-health association model based on the information analysis results and the health assessment results; obtain disease information of multiple intestinal-related diseases and establish an association relationship between them and the intestinal-health association model to form a disease risk prediction model and use it to predict the risk level of the intestinal-related diseases; Wherein, extracting information from the intestinal bacterial liquid sample includes: Obtaining high-throughput sequencing data from the intestinal bacterial fluid sample; Classifying the intestinal flora based on the high-throughput sequencing data and establishing an intestinal flora distribution model according to the classification results; Obtaining a bacterial species abundance table of all bacterial species types according to the intestinal flora distribution model; Screening the main components of the intestinal flora based on the bacterial species abundance table; Mining SNPs of the intestinal flora according to the main components of the intestinal flora; The microbial information includes intestinal flora types, bacterial species abundance table, main components of intestinal flora, SNPs of intestinal flora, and k groups of intestinal type difference characteristics of differential bacteria.

Images