Intestinal tumor detection system based on intestinal environmental data

Abstract

The present invention relates to the technical field of intestinal tumor detection, and in particular, to an intestinal tumor detection system based on intestinal environmental data. It includes a processing and analysis unit, a judgment and evaluation unit, a tumor detection unit, and a personalized program unit. The judgment and evaluation unit integrates the analyzed intestinal microbial combination data and the analyzed metabolite data, and uses the integrated intestinal data and the normal intestinal environmental data in the reference library for judgment, and then evaluates the probability of intestinal tumors based on the judged intestinal environmental abnormalities and the processed patient clinical data. The intestinal analysis module receives the command of the evaluated low probability of intestinal tumors, and analyzes the biomarkers based on the intestinal inflammatory markers and tumor markers in the processed related intestinal environmental data. By analyzing the inflammatory markers and tumor markers in the intestinal environment, signs of early intestinal tumors can be found, and early disease treatment is of great significance, effectively reducing the spread of intestinal tumor diseases.

Description

Technical Field

[0001] The present invention relates to the technical field of intestinal tumor detection, and in particular to an intestinal tumor detection system based on intestinal environmental data. Background Art

[0002] In this medical reality scenario, intestinal tumors occur in benign and malignant tumors of the small intestine and large intestine. The clinical manifestations vary depending on the tumor.

[0003] The nature and location of the occurrence vary. Generally speaking, benign tumors may be asymptomatic or have very mild symptoms. Some malignant tumors also have no obvious symptoms in the early stages, which affects diagnosis, treatment and prognosis. When the patient's related intestinal environmental data is obtained for the detection of intestinal tumor abnormalities, due to the low probability of the detected tumor, it is impossible to accurately judge the signs of early intestinal tumors based on abnormal conditions in a short period of time, and it is even more impossible to detect whether the intestinal tumor is a malignant tumor or a benign tumor. Therefore, as time goes by, the intestinal tumor disease will slowly develop and spread, and whether the development and spread of intestinal tumor disease is related to diabetes factors. In order to avoid accurately detecting the presence of intestinal tumors in patients with low probability and short time, we provide an intestinal tumor detection system based on intestinal environmental data. Summary of the invention

[0004] The purpose of the present invention is to provide an intestinal tumor detection system based on intestinal environmental data to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above-mentioned purpose, the present invention provides an intestinal tumor detection system based on intestinal environmental data, comprising a processing and analysis unit, a judgment and evaluation unit, a tumor detection unit, and a personalized solution unit;

[0006] The processing and analysis unit is used to obtain data related to the intestinal environment and clinical data of patients, as well as other historical data, and process the acquired data, and then analyze the intestinal microbial composition and metabolites based on the processed intestinal environment data;

[0007] The judgment and evaluation unit is used to receive the intestinal microbial combination data, the metabolite data and the processed patient clinical data analyzed in the processing and analysis unit, and integrate the analyzed intestinal microbial combination data and the analyzed metabolite data, and make a judgment based on the integrated intestinal data and the normal intestinal environment data in the reference library to determine whether there is an abnormality in the integrated intestinal data, and if there is an abnormality, then evaluate the probability of intestinal tumors based on the judged intestinal environment abnormality and the processed patient clinical data;

[0008] The tumor detection unit is used to receive the intestinal environment abnormality determined by the determination and evaluation unit and the intestinal tumor probability data evaluated to detect intestinal tumors;

[0009] The processing and analysis unit receives the intestinal tumor data detected by the tumor detection unit and other historical data processed by the processing and analysis unit and performs correlation analysis on diabetes factors;

[0010] The personalized program unit is used to receive the factor data of the correlation analysis in the processing and analysis unit and the processed patient clinical data, the intestinal environmental abnormalities judged in the judgment and evaluation unit, and the intestinal tumor data detected in the tumor detection unit to formulate a personalized program.

[0011] As a further improvement of the technical solution, the processing and analysis unit includes an acquisition processing module and an intestinal analysis module;

[0012] The acquisition and processing module is used to acquire data related to the intestinal environment and clinical data of patients, as well as other historical data, and process the acquired data;

[0013] Other historical data include data related to diabetes;

[0014] The intestinal analysis module is used to receive the relevant intestinal environmental data processed in the acquisition processing module, and use intestinal sequencing technology to analyze the intestinal microbial composition based on the processed relevant intestinal environmental data, and analyze the microbial composition in the individual's intestine, which includes bacteria, viruses and fungi;

[0015] Then, mass spectrometry technology is used to analyze the metabolites based on the processed relevant intestinal environmental data, and to analyze the intestinal microbial metabolites, which include short-chain fatty acids, bile acids and amino acids.

[0016] As a further improvement of the technical solution, the judgment and evaluation unit includes an abnormality judgment module and a probability evaluation module;

[0017] The abnormality judgment module is used to receive and integrate the intestinal microbial composition and metabolite data analyzed in the intestinal analysis module, and make judgments using the integrated intestinal environment data and the normal intestinal environment data in the reference library;

[0018] When it is determined that the integrated intestinal environment data is different from the normal intestinal environment data in the reference library, it means that there is an abnormality in the integrated intestinal data, and the determined intestinal environment abnormality is transmitted to the probability evaluation module;

[0019] The reference library includes intestinal environment data of normal people, patients with intestinal diseases, intestinal tumors or other related health information.

[0020] As a further improvement of the present technical solution, the probability assessment module is used to receive the intestinal environmental abnormality determined by the abnormality determination module and the patient clinical data processed by the acquisition processing module, and use the probability assessment algorithm to assess the probability of intestinal tumors based on the determined intestinal environmental abnormality and the processed patient clinical data;

[0021] Probability evaluation algorithm formula:

[0022] ;

[0023] in, represents the estimated probability of intestinal tumor, Refers to the constant, and also represents the maximum probability in evaluating the probability of intestinal tumors. is the base of natural logarithms, Refers to the different abnormal data values ​​in the judged intestinal environment abnormality. Refers to the regression coefficient corresponding to different abnormal data.

[0024] As a further improvement of the present technical solution, the probability assessment module has the following situations when using the probability assessment algorithm to assess the probability of intestinal tumors:

[0025] Case 1: When evaluating the probability of intestinal tumors Less than When , it indicates that the patient has a low probability of intestinal tumor, and the command of the low probability of intestinal tumor is transmitted to the intestinal analysis module;

[0026] The intestinal analysis module receives the command of low probability of intestinal tumors evaluated in the probability evaluation module, uses immunological technology to analyze biomarkers based on intestinal inflammatory markers and tumor marker data in the processed relevant intestinal environmental data, and transmits the analyzed biomarker data to the tumor detection unit;

[0027] Case 2: When evaluating the probability of intestinal tumors Greater than , it indicates that the patient has a high probability of intestinal tumor, and the command of the assessed high probability of intestinal tumor is transmitted to the tumor detection unit.

[0028] As a further improvement of the present technical solution, the tumor detection unit is used to receive the intestinal environmental abnormalities judged in the abnormal judgment module, and receive the high probability data of intestinal tumors evaluated in the probability evaluation module or the biomarker data analyzed in the intestinal analysis module to detect intestinal tumors, detect whether the tumor in the intestine is a benign tumor or a malignant tumor, and use random forest technology to detect intestinal tumors.

[0029] As a further improvement of the present technical solution, the intestinal analysis module receives the intestinal tumor data detected in the tumor detection unit and obtains other historical data processed in the processing module and performs association analysis on diabetes factors, and uses association analysis technology to perform association analysis to analyze the association between diabetes factors and intestinal tumors.

[0030] As a further improvement of the present technical solution, the personalized solution unit is used to receive the factor data of the correlation analysis in the intestinal analysis module, obtain the patient clinical data processed in the processing module, the intestinal environmental abnormalities judged in the abnormality judgment module and the intestinal tumor data detected in the tumor detection unit to formulate a personalized solution, and vector solution technology is adopted.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] 1. In the intestinal tumor detection system of the intestinal environmental data, the intestinal analysis module receives the command of the low probability of intestinal tumor assessment, and performs biomarker analysis based on the intestinal inflammatory markers and tumor markers in the processed relevant intestinal environmental data. By analyzing the inflammatory markers and tumor markers in the intestinal environment, early signs of intestinal tumors can be found. Early diagnosis of intestinal tumors is of great significance for disease treatment and can effectively reduce the development and spread of intestinal tumors.

[0033] 2. In the intestinal tumor detection system of the intestinal environmental data, the intestinal analysis module conducts correlation analysis on diabetes factors based on the intestinal tumor data detected in the tumor detection unit and other historical data processed in the acquisition processing module. It can explore the correlation between diabetes and intestinal tumors, discover possible common risk factors, pathophysiological mechanisms and the mutual influence between the two, and conduct early intestinal tumor risk assessment for patients, and conduct personalized health management and disease prevention. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 is an overall block diagram of the present invention;

[0035] Figure 2 It is a block diagram of the processing and analysis unit of the present invention;

[0036] Figure 3 It is a block diagram of the judgment and evaluation unit of the present invention.

[0037] The meaning of each number in the figure is:

[0038] 1. Processing and analysis unit; 11. Acquisition and processing module; 12. Intestinal analysis module;

[0039] 2. Judgment and evaluation unit; 21. Abnormal judgment module; 22. Probability evaluation module;

[0040] 3. Tumor detection unit; 4. Personalized program unit. DETAILED DESCRIPTION

[0041] The following will be combined with the accompanying drawings in the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Example 1

[0042] Considering that the probability of detecting tumors is low, it is impossible to accurately judge the signs of early intestinal tumors based on abnormal conditions in a short period of time, and it is even more impossible to detect whether the intestinal tumor is a malignant tumor or a benign tumor. Therefore, as time goes by, the intestinal tumor disease will slowly develop and spread, and whether the development and spread of the intestinal tumor disease is related to diabetes factors. In order to avoid accurately detecting the presence of intestinal tumors in patients with low probability and short time, the present invention provides an intestinal tumor detection system based on intestinal environmental data, please refer to Figure 1-Figure 3 , including a processing and analysis unit 1, a judgment and evaluation unit 2, a tumor detection unit 3, and a personalized solution unit 4;

[0043] The processing and analysis unit 1 is used to obtain data related to the intestinal environment and patient clinical data, as well as other historical data, and process the acquired data, and then analyze the intestinal microbial combination and metabolites based on the processed intestinal environment data. The judgment and evaluation unit 2 is used to receive the intestinal microbial combination data, the analyzed metabolite data and the processed patient clinical data analyzed in the processing and analysis unit 1, and integrate the analyzed intestinal microbial combination data and the analyzed metabolite data, and judge whether there is an abnormality in the integrated intestinal data based on the integrated intestinal data and the normal intestinal environment data in the reference library. If there is an abnormality, the probability of intestinal tumor is judged based on the judged intestinal environment abnormality and the processed patient clinical data. Evaluation, the tumor detection unit 3 is used to receive the intestinal environmental abnormalities judged in the judgment and evaluation unit 2 and the evaluated intestinal tumor probability data to detect intestinal tumors, the processing and analysis unit 1 receives the intestinal tumor data detected in the tumor detection unit 3 and other historical data processed in the processing and analysis unit 1 and performs correlation analysis on diabetes factors, and the personalized program unit 4 is used to receive the factor data of the correlation analysis in the processing and analysis unit 1 and the processed patient clinical data, the intestinal environmental abnormalities judged in the judgment and evaluation unit 2 and the intestinal tumor data detected in the tumor detection unit 3 to formulate personalized programs, which can improve the cure rate and survival rate of intestinal tumors. Personalized programs can better meet the needs of patients and make treatment more targeted and effective.

[0044] The following is a refinement of the above units, please refer to Figure 2-Figure 3 ;

[0045] The processing and analysis unit 1 includes an acquisition processing module 11 and an intestinal analysis module 12;

[0046] The acquisition and processing module 11 is used to acquire data related to the intestinal environment and clinical data of patients, as well as other historical data, including diabetes-related data, and process the acquired data to reduce deviations in the data and improve data accuracy.

[0047] The intestinal analysis module 12 is used to receive the relevant intestinal environmental data processed in the acquisition processing module 11, and use the intestinal sequencing technology to analyze the intestinal microbial composition based on the processed relevant intestinal environmental data, and analyze the microbial composition in the individual's intestine. The microbial composition includes bacteria, viruses and fungi, which can help scientists understand the types and quantities of microorganisms in the individual's intestine, and then explore the relationship between intestinal microorganisms and health. The intestinal microbial composition is affected by many factors, including eating habits, lifestyle, and medication history;

[0048] Steps to implement intestinal sequencing technology:

[0049] Step 1: First, it is necessary to collect intestinal samples from individuals according to the relevant intestinal environmental data to be processed, usually through fecal samples, and the corresponding operating specifications need to be followed when collecting samples;

[0050] Step 2: Extracting microbial DNA or RNA from intestinal samples. A common method is to use a commercial DNA or RNA extraction kit to obtain nucleic acid from microorganisms in the sample.

[0051] Step 3: The extracted microbial DNA or RNA will be further sequenced for bacterial analysis and comprehensive microbiome analysis, and the DNA or RNA sequence information of each microorganism can be obtained;

[0052] Step 4. Finally, a large amount of sequence data will be obtained after sequencing. These sequence data can be preprocessed and quality controlled to remove low-quality reads, human DNA or RNA contamination, and interpret the characteristics of the microbial composition, such as the relative abundance, richness and community structure of different microorganisms, to understand the microbial composition of individuals.

[0053] Then, mass spectrometry is used to analyze metabolites based on the processed intestinal environmental data, and to analyze intestinal microbial metabolites, including short-chain fatty acids, bile acids, and amino acids. By analyzing intestinal microbial metabolites, we can have a more comprehensive understanding of the functions and metabolic activities of microorganisms, further reveal the relationship between microorganisms and intestinal tumors, understand the mechanism of action of microorganisms in intestinal health and disease, and provide important information for personalized health management and disease prevention. It should be pointed out that metabolite analysis usually needs to be studied and verified in combination with other research methods and clinical data to more accurately evaluate the association between intestinal microorganisms and intestinal tumors.

[0054] Mass spectrometry technology implementation steps:

[0055] Step ①: First, collect intestinal samples based on the relevant intestinal environmental data. With appropriate preparation, fecal samples can usually be selected as the source of metabolites. Other sample types can also be considered. Sample preparation may include extraction, deproteinization, and dissolution steps to obtain metabolites.

[0056] Step ②, sending the prepared sample to a mass spectrometer for analysis. The mass spectrometer will generate a large amount of raw data, including mass spectrometry and chromatographic data, and a large amount of raw data needs to be interpreted to obtain information about metabolites;

[0057] Step ③: Identify metabolites based on the interpreted data to identify and quantify the metabolites, and then perform bioinformatics analysis on the identified metabolites to understand their information on metabolic pathways, physiological functions, and disease relevance.

[0058] The judgment and evaluation unit 2 includes an abnormality judgment module 21 and a probability evaluation module 22;

[0059] The abnormality judgment module 21 is used to receive and integrate the intestinal microbial composition and metabolite data analyzed by the intestinal analysis module 12, and make judgments using the integrated intestinal environment data and the normal intestinal environment data in the reference library;

[0060] When it is determined that the integrated intestinal environment data is different from the normal intestinal environment data in the reference library, it indicates that there is an abnormality in the integrated intestinal data, and the determined intestinal environment abnormality is transmitted to the probability evaluation module 22;

[0061] The reference library includes intestinal environment data of normal people, patients with intestinal diseases, intestinal tumors or other related health information.

[0062] The probability evaluation module 22 is used to receive the intestinal environmental abnormality determined by the abnormality determination module 21 and the patient clinical data processed by the acquisition processing module 11, and use the probability evaluation algorithm to evaluate the probability of intestinal tumors according to the determined intestinal environmental abnormality and the processed patient clinical data;

[0063] Probability evaluation algorithm formula:

[0064] ;

[0065] in, represents the estimated probability of intestinal tumor, Refers to the constant, and also represents the maximum probability in evaluating the probability of intestinal tumors. is the base of natural logarithms, Refers to the different abnormal data values ​​in the judged intestinal environment abnormality. Refers to the regression coefficient corresponding to different abnormal data. This formula is used to evaluate the probability of intestinal tumors. Early screening of intestinal tumors is crucial for the prevention and treatment of this cancer. Using intestinal environmental abnormalities and clinical data evaluation can effectively evaluate the probability of intestinal tumors, and provide early warnings and corresponding interventions and treatments to reduce the risk of intestinal tumor spread.

[0066] The following situations occur when the probability assessment module 22 uses the probability assessment algorithm to assess the probability of intestinal tumors:

[0067] Case 1: When evaluating the probability of intestinal tumors Less than When , it indicates that the patient has a low probability of intestinal tumor, and the command of the low probability of intestinal tumor is transmitted to the intestinal analysis module 12;

[0068] The intestinal analysis module 12 receives the command of low probability of intestinal tumors evaluated by the probability evaluation module 22, uses immunological technology to analyze biomarkers based on the intestinal inflammatory markers and tumor markers in the processed relevant intestinal environmental data, and transmits the analyzed biomarker data to the tumor detection unit 3;

[0069] Case 2: When evaluating the probability of intestinal tumors Greater than When , it indicates that the patient has a high probability of intestinal tumor, and the command of the high probability of intestinal tumor is transmitted to the tumor detection unit 3;

[0070] Principle of Immunological Technology:

[0071] ①. Collect biological samples that need to be analyzed based on the intestinal inflammatory marker data and tumor marker data in the processed intestinal environmental data, including serum, plasma, and tissues, and then centrifuge the analyzed biological samples to remove cells or solid particles;

[0072] ② Select specific antibodies or probes according to the markers to be analyzed. These antibodies / probes can be monoclonal antibodies, polyclonal antibodies or other specific binding molecules. Label the selected antibodies with appropriate markers, including enzymes, fluorescent dyes, and radioactive isotopes.

[0073] ③. Combine the sample with the labeled antibody or probe to form an immune complex, and then detect and quantify the signal based on the selected marker;

[0074] ④. Perform data analysis and interpretation based on the obtained signals, and then convert the signals into quantitative concentrations of corresponding markers according to the standard curve or internal control samples. Interpret the analysis results based on existing research or clinical guidelines, and correlate them with the patient's clinical data to derive potential intestinal tumor abnormalities in the patient.

[0075] When evaluating the probability of intestinal tumors Greater than When , it indicates that the patient has a high probability of intestinal tumor, and the command of the assessed high probability of intestinal tumor is transmitted to the tumor detection unit 3.

[0076] The tumor detection unit 3 is used to receive the intestinal environment abnormality determined by the abnormality determination module 21, and receive the intestinal tumor high probability data evaluated by the probability evaluation module 22 or the biomarker data analyzed by the intestinal analysis module 12 to detect intestinal tumors, detect whether the tumor in the intestine is a benign tumor or a malignant tumor, and use the random forest technology to detect intestinal tumors;

[0077] Random forest technology implementation steps:

[0078] Step 1: First, prepare a data set containing the judged intestinal environmental abnormalities, the evaluated intestinal tumor high probability data, or the analyzed biomarker data, and ensure that the data set contains sufficient samples and features;

[0079] Step 2: Divide the entire data set into a training set and a test set. Usually, a common ratio of 70% of the data is used as the training set and 30% of the data is used as the test set. Build a prediction model on the training set.

[0080] Implementation principle of prediction model:

[0081] First, determine the hyperparameters of the random forest algorithm, including the number of decision trees, the maximum depth of each tree, the minimum number of node samples, and the size of the feature subset. These parameters will affect the performance and generalization ability of the random forest model.

[0082] Second, apply the random forest algorithm on the training set, train multiple decision trees and form a prediction model. Each decision tree is built based on randomly sampled data and features.

[0083] Step 3: Use the training set to train the prediction model, and then use the test set to evaluate the prediction model to evaluate the performance and prediction accuracy of the model. Use the trained prediction model to input new intestinal environmental abnormalities and intestinal tumor high probability data or analyzed biomarker data for prediction;

[0084] Step 4: When prediction is required, each tree will classify the input data, and the final prediction result will be determined by the voting results of all trees. For classification problems, the majority voting method is used to determine the final classification result, and the benign or malignant nature of the intestinal tumor is determined based on the final classification result.

[0085] The intestinal analysis module 12 receives the intestinal tumor data detected by the tumor detection unit 3 and other historical data processed by the acquisition processing module 11 and performs a correlation analysis of the diabetes factor, and adopts a correlation analysis technology to perform a correlation analysis to analyze the correlation between the diabetes factor and the intestinal tumor. The result of the correlation analysis can determine which individuals with diabetes should receive more frequent or earlier intestinal tumor screening and early diagnosis, so as to detect and treat the tumor early;

[0086] Steps to implement association analysis technology:

[0087] Step ①: First, the detected intestinal tumor data and other processed historical data are integrated into a data set, and the data set is classified into variables, which need to be converted into binary representation for association rule mining;

[0088] Step ②: extract frequent item sets and association rules from the data set. Frequent item sets refer to the collection of items that frequently appear in the data set, while association rules are rules that contain a premise (i.e., prerequisite) and a conclusion.

[0089] Step 3: According to the set support and confidence thresholds, select association rules with sufficient support and high confidence. Support measures the frequency of item sets in the data set, while confidence measures the reliability of the rules.

[0090] Step ④: Explain the selected association rule analysis. Through the premise and conclusion of the association rule, the association between diabetes can be identified, and their connection with intestinal tumors can be further analyzed;

[0091] Implementation principle of association rule analysis:

[0092] Suppose we find the following association rules:

[0093] Rule: {diabetes}=>{intestinal tumor} (support: 20%, confidence: 60%). Through this rule, we can explain the relationship between diabetes and intestinal tumors:

[0094] According to the rules, 20% of the samples had both diabetes and intestinal tumors, and 60% of all samples with diabetes also had intestinal tumors, which may indicate that there is a certain degree of association between diabetes and intestinal tumors, and individuals with diabetes may be more likely to develop intestinal tumors.

[0095] The personalized program unit 4 is used to receive the factor data of the association analysis in the intestinal analysis module 12, the patient clinical data processed in the acquisition processing module 11, the intestinal environmental abnormalities judged in the abnormality judgment module 21 and the intestinal tumor data detected in the tumor detection unit 3 to formulate a personalized program, and adopts the vector program technology;

[0096] Vector solution technology implementation steps:

[0097] Step 1: Integrate the diabetes factor data from the association analysis, the processed patient clinical data, the judged intestinal environmental abnormalities, and the detected intestinal benign and malignant tumor data, select and extract the features related to the target (personalized solution), and construct a feature set based on the results of the association analysis and domain knowledge;

[0098] Step 2: Divide the feature set into a training set and a test set to ensure the randomness and sufficiency of the data. Use the prepared training set data to establish a treatment model suitable for personalized programs by adjusting the parameters and kernel functions in the feature set.

[0099] Step 3: Use the test set data to evaluate the trained treatment model, examine the performance and generalization ability of the treatment model, and then tune the treatment model based on the evaluation results, including adjusting hyperparameters and kernel function selection;

[0100] Step 4. Finally, use the trained and tuned treatment model to predict the patient's diabetes factors, clinical data, intestinal environmental abnormalities, and benign and malignant intestinal tumor data. Then, based on the prediction results of the treatment model, formulate a personalized plan, including tumor treatment, drug therapy, diet and exercise.

[0101] Usage process:

[0102] The intestinal analysis module 12 receives the command of the low probability of intestinal tumor assessment, and performs biomarker analysis based on the intestinal inflammatory markers and tumor marker data in the processed related intestinal environmental data, and transmits the analyzed biomarker data to the tumor detection unit 3. The tumor detection unit 3 detects intestinal tumors based on the intestinal environmental abnormality judged in the abnormality judgment module 21 and the high probability data of intestinal tumor assessed in the probability assessment module 22 or the biomarker data analyzed in the intestinal analysis module 12, and transmits the detected intestinal tumor data to the intestinal analysis module 12. The intestinal analysis module 12 performs association analysis of diabetes factors based on the intestinal tumor data detected in the tumor detection unit 3 and other historical data processed in the acquisition processing module 11, and analyzes the association between diabetes factors and intestinal tumors.

[0103] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. An intestinal tumor detection system based on intestinal environmental data, characterized by: It includes a processing and analysis unit (1), a judgment and evaluation unit (2), a tumor detection unit (3), and a personalized program unit (4); The processing and analysis unit (1) is used to obtain data related to the intestinal environment and clinical data of patients, as well as other historical data, and to process the obtained data, and then to analyze the intestinal microbial composition and metabolites based on the processed intestinal environment data; The judgment and evaluation unit (2) is used to receive the intestinal microbial combination data, the metabolite data and the processed patient clinical data analyzed by the processing analysis unit (1), and integrate the analyzed intestinal microbial combination data and the analyzed metabolite data, and make a judgment based on the integrated intestinal data and the normal intestinal environment data in the reference library to determine whether there is an abnormality in the integrated intestinal data. If there is an abnormality, the probability of intestinal tumor is evaluated based on the judged intestinal environment abnormality and the processed patient clinical data; The tumor detection unit (3) is used to receive the intestinal environmental abnormality determined by the determination and evaluation unit (2) and the intestinal tumor probability data evaluated to perform intestinal tumor detection; The processing and analysis unit (1) receives the intestinal tumor data detected by the tumor detection unit (3) and other historical data processed by the processing and analysis unit (1) and performs correlation analysis on diabetes factors; The personalized program unit (4) is used to receive the factor data of the correlation analysis in the processing analysis unit (1) and the processed patient clinical data, the intestinal environmental abnormalities determined in the judgment and evaluation unit (2) and the intestinal tumor data detected in the tumor detection unit (3) to formulate a personalized program.

2. The intestinal tumor detection system based on intestinal environmental data according to claim 1, characterized in that: The processing and analysis unit (1) comprises an acquisition processing module (11) and an intestinal analysis module (12); The acquisition and processing module (11) is used to acquire data related to the intestinal environment and clinical data of patients, as well as other historical data, and to process the acquired data; Other historical data include data related to diabetes; The intestinal analysis module (12) is used to receive the relevant intestinal environmental data processed in the acquisition processing module (11), and use intestinal sequencing technology to analyze the intestinal microbial composition based on the processed relevant intestinal environmental data, and analyze the microbial composition in the individual's intestine, where the microbial composition includes bacteria, viruses and fungi; Then, mass spectrometry technology is used to analyze the metabolites based on the processed relevant intestinal environmental data, and to analyze the intestinal microbial metabolites, which include short-chain fatty acids, bile acids and amino acids.

3. The intestinal tumor detection system based on intestinal environmental data according to claim 2, characterized in that: The judgment and evaluation unit (2) comprises an abnormality judgment module (21) and a probability evaluation module (22); The abnormality judgment module (21) is used to receive and integrate the intestinal microbial composition and metabolite data analyzed by the intestinal analysis module (12), and to make judgments using the integrated intestinal environment data and the normal intestinal environment data in the reference library; When it is determined that the integrated intestinal environment data is different from the normal intestinal environment data in the reference library, it indicates that there is an abnormality in the integrated intestinal data, and the determined intestinal environment abnormality is transmitted to the probability evaluation module (22); The reference library includes intestinal environment data of normal people, patients with intestinal diseases, intestinal tumors or other related health information.

4. The intestinal tumor detection system based on intestinal environmental data according to claim 3, characterized in that: The probability assessment module (22) is used to receive the intestinal environmental abnormality determined by the abnormality determination module (21) and the patient clinical data processed by the acquisition processing module (11), and to use a probability assessment algorithm to assess the probability of intestinal tumors based on the determined intestinal environmental abnormality and the processed patient clinical data; Probability evaluation algorithm formula: ； in, represents the estimated probability of intestinal tumor, Refers to the constant, and also represents the maximum probability in evaluating the probability of intestinal tumors. is the base of natural logarithms, Refers to the different abnormal data values ​​in the judged intestinal environment abnormality. Refers to the regression coefficient corresponding to different abnormal data.

5. The intestinal tumor detection system based on intestinal environmental data according to claim 4, characterized in that: The probability assessment module (22) may encounter the following situations when using the probability assessment algorithm to assess the probability of intestinal tumors: Case 1: When evaluating the probability of intestinal tumors Less than When , it indicates that the patient has a low probability of intestinal tumor, and the command of the low probability of intestinal tumor is transmitted to the intestinal analysis module (12); The intestinal analysis module (12) receives the command of low probability of intestinal tumors evaluated by the probability evaluation module (22), uses immunological technology to analyze biomarkers based on intestinal inflammatory markers and tumor marker data in the processed relevant intestinal environmental data, and transmits the analyzed biomarker data to the tumor detection unit (3); Case 2: When evaluating the probability of intestinal tumors Greater than , it indicates that the patient has a high probability of intestinal tumor, and the command of the assessed high probability of intestinal tumor is transmitted to the tumor detection unit (3).

6. The intestinal tumor detection system based on intestinal environmental data according to claim 5, characterized in that: The tumor detection unit (3) is used to receive the intestinal environmental abnormality determined by the abnormality determination module (21), and receive the intestinal tumor high probability data evaluated by the probability evaluation module (22) or the biomarker data analyzed by the intestinal analysis module (12) to detect intestinal tumors, detect whether the tumor in the intestine is a benign tumor or a malignant tumor, and use the random forest technology to detect intestinal tumors.

7. The intestinal tumor detection system based on intestinal environmental data according to claim 6, characterized in that: The intestinal analysis module (12) receives the intestinal tumor data detected by the tumor detection unit (3) and other historical data processed by the acquisition processing module (11) and performs association analysis on diabetes factors, and uses association analysis technology to perform association analysis to analyze the association relationship between diabetes factors and intestinal tumors.

8. The intestinal tumor detection system based on intestinal environmental data according to claim 7, characterized in that: The personalized solution unit (4) is used to receive the factor data of the association analysis in the intestinal analysis module (12), the patient clinical data processed in the acquisition processing module (11), the intestinal environmental abnormalities judged in the abnormality judgment module (21) and the intestinal tumor data detected in the tumor detection unit (3) to formulate a personalized solution, and uses vector solution technology.

Images