Colorectal cancer prediction system and method

Abstract

The invention relates to the technical field of disease prediction, in particular to a colorectal cancer prediction system and method, and the method comprises the steps: collecting various data related to colorectal cancer, carrying out cleaning, normalization, dimension reduction and missing value filling, extracting key features related to the colorectal cancer, constructing a colorectal cancer prediction model based on the extracted key features, and predicting the colorectal cancer. The model is trained and optimized, an output result of the prediction model is analyzed and explained, a colorectal cancer prediction report is generated, and the report content comprises a prediction conclusion, key feature contribution degree analysis and personalized risk assessment. According to the method, a comprehensive and accurate prediction model is constructed by integrating various data sources including clinical data, genome data, metabolite data, microbiota data and image data, and efficient prediction of the colorectal cancer is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of disease prediction, and in particular to a colorectal cancer prediction system and method. Background Art

[0002] Colorectal cancer is a common and fatal digestive tract malignancy worldwide. Early detection and diagnosis are crucial to improving patient survival. Existing detection methods mainly include endoscopy, imaging examination and biomarker detection.

[0003] However, the inventors have discovered that this technical solution still has at least the following defects:

[0004] First: Although traditional endoscopy and imaging examinations have certain diagnostic value, their invasive procedures and high costs make widespread screening difficult to achieve.

[0005] Second: In addition, although biomarker detection methods are non-invasive, they often lead to misdiagnosis and missed diagnosis due to insufficient sensitivity and specificity, and cannot effectively meet the needs of early screening. The existing single data source analysis method is difficult to fully reflect the complex pathological mechanism of colorectal cancer, resulting in limited prediction accuracy and reliability. Summary of the invention

[0006] Based on the above objectives, the present invention provides a colorectal cancer prediction system and method.

[0007] A colorectal cancer prediction system includes a data acquisition module, a data preprocessing module, a feature extraction module, and a prediction model module. The modules cooperate with each other, specifically including:

[0008] Data collection module: collects various data related to colorectal cancer, including clinical data, genomic data, metabolite data, microbiome data and imaging data of patients;

[0009] Data preprocessing module: cleans, normalizes, reduces dimension and fills missing values ​​for the data collected by the data acquisition module;

[0010] Feature extraction module: extract key features related to colorectal cancer from the preprocessed data;

[0011] Prediction model module: construct a colorectal cancer prediction model based on the extracted key features, and train and optimize the model;

[0012] Result analysis module: Analyze and interpret the output results of the prediction model to generate a colorectal cancer prediction report. The report content includes prediction conclusions, key feature contribution analysis, and personalized risk assessment.

[0013] Optionally, the data acquisition module includes:

[0014] Clinical data collection: Automatically extract the patient's clinical data through the electronic health record system, conduct a questionnaire survey on the patient, collect additional detailed information such as the patient's living habits and eating habits, and enter them into the system;

[0015] Genomic data collection: Extract blood samples from patients, extract DNA using a laboratory DNA extraction kit, and perform whole-genome sequencing on the extracted DNA using high-throughput sequencing technology to obtain genomic information such as gene mutations, single nucleotide polymorphisms, and copy number variations;

[0016] Metabolite data collection: Blood, urine and feces samples are collected from patients, and metabolites in the samples are detected using liquid chromatography-mass spectrometry to analyze their concentration levels and metabolic pathway characteristics;

[0017] Microbiome data collection: Collect stool samples from patients, preserve and process them, and sequence the microorganisms in the samples using 16SrRNA gene sequencing or metagenomic sequencing technology to obtain the types, abundance, and functional characteristics of the microorganisms;

[0018] Image data acquisition: Perform colorectal examination on patients to obtain images of the inside of the colorectum, and perform imaging examination of the patient's colorectum through computer tomography and magnetic resonance imaging to obtain imaging data.

[0019] Optionally, the data preprocessing module includes:

[0020] Data cleaning: Preliminary screening of the collected raw data, removal of noise data and duplicate data, and use of outlier detection algorithms to identify and remove abnormal data points;

[0021] Data normalization: Select a normalization method based on the data type, including Min-Max normalization and Z-score normalization, convert data of different dimensions to the same dimension, and review the normalized data;

[0022] Data dimensionality reduction: Use principal component analysis to reduce the dimensionality of high-dimensional data, extract the main components, reduce the data dimension, and verify the dimensionality reduction results;

[0023] Missing value filling: Analyze the missing values ​​in the data, determine the missing pattern, select the filling method based on the missing pattern, and verify the filled data.

[0024] Optionally, the feature extraction module includes:

[0025] Gene mutation feature extraction: perform mutation detection on preprocessed genomic data, identify gene mutation sites, identify key mutation genes associated with colorectal cancer, calculate mutation frequency, mutation type and mutation location, and perform feature screening and extraction;

[0026] Metabolite level feature extraction: Quantitative analysis of preprocessed metabolite data, determination of the concentration level of each metabolite, pathway enrichment analysis of metabolite data using metabolic pathway analysis tools, identification of metabolic pathways related to colorectal cancer, extraction of metabolite concentrations and metabolic pathway activities, and feature screening and extraction;

[0027] Extraction of microbiome structural features: perform taxonomic analysis on the preprocessed microbiome data to determine the types and abundance of microorganisms, use microbiome analysis tools to perform diversity analysis on the microbiome data, evaluate the structural features of the microbiome, extract microbial species abundance, diversity index and functional characteristics, and perform feature screening and extraction;

[0028] Image feature extraction: Perform image segmentation on the preprocessed image data to separate the colorectal area, use image processing algorithms to extract features from the image data, identify the morphological features and lesion areas of the colorectum, extract image features such as texture features, shape features, and density features, and perform feature screening and extraction.

[0029] Optionally, the image feature extraction includes:

[0030] Image segmentation: Perform image segmentation on the preprocessed image data and use segmentation algorithms to separate the colorectal area from the background;

[0031] Morphological processing: Perform morphological processing on the segmented colorectal area and use Canny edge detection to identify the edge contour of the colorectal area.

[0032] Feature extraction: Use image processing algorithms to extract features from image data.

[0033] Optionally, the prediction model module includes:

[0034] Data preparation: Divide the key feature data set obtained from the feature extraction module into a training set and a test set. The training set is used for model training, and the test set is used for model verification.

[0035] Model construction: Build an initial colorectal cancer prediction model and set the initial parameters and structure of the model;

[0036] Model training: Use the training set data to train the initial model, adopt the supervised learning method, and optimize the model parameters by minimizing the loss function;

[0037] Model optimization: Tune the model.

[0038] Optionally, the model optimization includes:

[0039] Cross-validation tuning: The model's hyperparameters are tuned through cross-validation technology. The training set data is divided into K equally divided subsets, of which K-1 subsets are used to train the model and the remaining 1 subset is used to verify the model. This cycle is repeated K times, and each time a different subset is selected as the verification set. The remaining subsets are used as the training set. The performance index of each verification is calculated and the average value is taken as the evaluation standard of the model performance. The model's hyperparameters are adjusted to find the parameter combination that optimizes the average performance index.

[0040] Grid search or random search optimization: Use grid search or random search methods to further optimize the model's hyperparameters, use cross-validation technology to calculate the performance indicators of each combination, and select the hyperparameter combination with the best performance indicators as the final model hyperparameters.

[0041] Optionally, the result analysis module includes:

[0042] Prediction result generation: extract the prediction probability value and related prediction information, and generate the prediction conclusion of colorectal cancer based on the prediction probability value;

[0043] Key feature contribution analysis: Calculate the contribution of each feature to the prediction results, generate feature contribution analysis charts, combine feature contribution analysis results, explain the decision-making process of the prediction model, and provide transparent and explainable analysis reports;

[0044] Personalized risk assessment: Based on the patient's individual characteristic data, the personalized risk level of colorectal cancer is assessed, a personalized risk assessment report is generated, and personalized prevention and intervention recommendations are provided;

[0045] Report generation: Comprehensive prediction conclusions, key feature contribution analysis and personalized risk assessment results are used to generate a colorectal cancer prediction report. The report content includes prediction conclusions, key feature contribution analysis charts, personalized risk assessment and health management recommendations.

[0046] A colorectal cancer prediction method, implemented by the above-mentioned colorectal cancer prediction system, comprises the following steps:

[0047] S1, data collection: collecting various data related to colorectal cancer, including clinical data, genomic data, metabolite data, microbiome data and imaging data of patients;

[0048] S2, data preprocessing: cleaning, normalizing, dimension reduction and missing value filling of the data collected by the data acquisition module;

[0049] S3, feature extraction: extract key features related to colorectal cancer from the preprocessed data;

[0050] S4, prediction model: constructing a colorectal cancer prediction model based on the extracted key features, and training and optimizing the model;

[0051] S5, result analysis: Analyze and interpret the output results of the prediction model to generate a colorectal cancer prediction report. The report content includes prediction conclusions, key feature contribution analysis, and personalized risk assessment.

[0052] Beneficial effects of the present invention:

[0053] The present invention integrates multiple data sources, including clinical data, genomic data, metabolite data, microbiome data and imaging data, to build a comprehensive and accurate prediction model, achieving efficient prediction of colorectal cancer. Compared with the prior art, the present invention significantly improves the sensitivity and specificity of prediction and reduces the risk of misdiagnosis and missed diagnosis.

[0054] The present invention generates a comprehensive report containing prediction conclusions, key feature contribution analysis and personalized risk assessment by analyzing and interpreting the output results of the prediction model in detail. Through transparent feature contribution analysis and personalized health management suggestions, the present invention not only improves the interpretability of the model and user trust, but also provides patients with scientific prevention and intervention suggestions, which helps to improve the patient's health management level. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0056] Figure 1 A schematic diagram of a colorectal cancer prediction system and method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0058] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0059] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0060] like Figure 1 As shown, a colorectal cancer prediction system and method includes a data acquisition module, a data preprocessing module, a feature extraction module, and a prediction model module. The modules cooperate with each other, specifically including:

[0061] Data collection module: collects a variety of data related to colorectal cancer, including patients' clinical data, genomic data, metabolite data, microbiome data, and imaging data;

[0062] Data preprocessing module: cleans, normalizes, reduces dimension and fills missing values ​​for the data collected by the data acquisition module;

[0063] Feature extraction module: extract key features related to colorectal cancer from the preprocessed data;

[0064] Prediction model module: build a colorectal cancer prediction model based on the extracted key features, and train and optimize the model;

[0065] Result analysis module: Analyze and interpret the output results of the prediction model to generate a colorectal cancer prediction report. The report content includes prediction conclusions, key feature contribution analysis, and personalized risk assessment.

[0066] The data acquisition module includes:

[0067] Clinical data collection: Automatically extract the patient's clinical data through the electronic health record system, conduct a questionnaire survey on the patient, collect additional detailed information such as the patient's living habits and eating habits, and enter them into the system;

[0068] Genomic data collection: Extract blood samples from patients, extract DNA using a laboratory DNA extraction kit, and perform whole-genome sequencing on the extracted DNA using high-throughput sequencing technology to obtain genomic information such as gene mutations, single nucleotide polymorphisms, and copy number variations;

[0069] Metabolite data collection: Blood, urine and feces samples are collected from patients, and metabolites in the samples are detected using liquid chromatography-mass spectrometry to analyze their concentration levels and metabolic pathway characteristics;

[0070] Microbiome data collection: Collect stool samples from patients, preserve and process them, and sequence the microorganisms in the samples using 16SrRNA gene sequencing or metagenomic sequencing technology to obtain the types, abundance, and functional characteristics of the microorganisms;

[0071] Image data acquisition: Perform colorectal examination on patients to obtain images of the inside of the colorectum, and perform imaging examination of the patient's colorectum through computer tomography and magnetic resonance imaging to obtain imaging data.

[0072] The data preprocessing module includes:

[0073] Data cleaning: Preliminary screening of the collected raw data, removal of noise data and duplicate data, and use of outlier detection algorithms to identify and remove abnormal data points;

[0074] Data normalization: Select a normalization method based on the data type, including Min-Max normalization and Z-score normalization, convert data of different dimensions to the same dimension, and review the normalized data;

[0075] Data dimensionality reduction: Use principal component analysis to reduce the dimensionality of high-dimensional data, extract the main components, reduce the data dimension, and verify the dimensionality reduction results;

[0076] Missing value filling: Analyze the missing values ​​in the data, determine the missing pattern, select the filling method based on the missing pattern, and verify the filled data.

[0077] The feature extraction module includes:

[0078] Gene mutation feature extraction: perform mutation detection on preprocessed genomic data, identify gene mutation sites, identify key mutation genes associated with colorectal cancer, calculate mutation frequency, mutation type and mutation location, and perform feature screening and extraction;

[0079] Metabolite level feature extraction: Quantitative analysis of preprocessed metabolite data, determination of the concentration level of each metabolite, pathway enrichment analysis of metabolite data using metabolic pathway analysis tools, identification of metabolic pathways related to colorectal cancer, extraction of metabolite concentrations and metabolic pathway activities, and feature screening and extraction;

[0080] Extraction of microbiome structural features: perform taxonomic analysis on the preprocessed microbiome data to determine the types and abundance of microorganisms, use microbiome analysis tools to perform diversity analysis on the microbiome data, evaluate the structural features of the microbiome, extract microbial species abundance, diversity index and functional characteristics, and perform feature screening and extraction;

[0081] Image feature extraction: Perform image segmentation on the preprocessed image data to separate the colorectal area, use image processing algorithms to extract features from the image data, identify the morphological features and lesion areas of the colorectum, extract image features such as texture features, shape features, and density features, and perform feature screening and extraction.

[0082] Image feature extraction includes:

[0083] Image segmentation: Perform image segmentation on the preprocessed image data and use segmentation algorithms to separate the colorectal area from the background;

[0084] Morphological processing: Perform morphological processing on the segmented colorectal area and use Canny edge detection to identify the edge contour of the colorectal area.

[0085] Feature extraction: Use image processing algorithms to extract features from image data.

[0086] The prediction model module includes:

[0087] Data preparation: Divide the key feature data set obtained from the feature extraction module into a training set and a test set. The training set is used for model training, and the test set is used for model verification.

[0088] Model construction: Build an initial colorectal cancer prediction model and set the initial parameters and structure of the model;

[0089] Model training: Use the training set data to train the initial model, adopt the supervised learning method, and optimize the model parameters by minimizing the loss function;

[0090] Model optimization: Tune the model.

[0091] Model optimization includes:

[0092] Cross-validation tuning: The model's hyperparameters are tuned through cross-validation technology. The training set data is divided into K equally divided subsets, of which K-1 subsets are used to train the model and the remaining 1 subset is used to verify the model. This cycle is repeated K times, and each time a different subset is selected as the verification set. The remaining subsets are used as the training set. The performance index of each verification is calculated and the average value is taken as the evaluation standard of the model performance. The model's hyperparameters are adjusted to find the parameter combination that optimizes the average performance index.

[0093] Grid search or random search optimization: Use grid search or random search methods to further optimize the model's hyperparameters, use cross-validation technology to calculate the performance indicators of each combination, and select the hyperparameter combination with the best performance indicators as the final model hyperparameters.

[0094] The result analysis module includes:

[0095] Prediction result generation: extract the prediction probability value and related prediction information, and generate the prediction conclusion of colorectal cancer based on the prediction probability value;

[0096] Key feature contribution analysis: Calculate the contribution of each feature to the prediction results, generate feature contribution analysis charts, combine feature contribution analysis results, explain the decision-making process of the prediction model, and provide transparent and explainable analysis reports;

[0097] Personalized risk assessment: Based on the patient's individual characteristic data, the personalized risk level of colorectal cancer is assessed, a personalized risk assessment report is generated, and personalized prevention and intervention recommendations are provided;

[0098] Report generation: Comprehensive prediction conclusions, key feature contribution analysis and personalized risk assessment results are used to generate a colorectal cancer prediction report. The report content includes prediction conclusions, key feature contribution analysis charts, personalized risk assessment and health management recommendations.

[0099] A colorectal cancer prediction method, implemented by the above-mentioned colorectal cancer prediction system, comprises the following steps:

[0100] S1, data collection: collect various data related to colorectal cancer, including patients' clinical data, genomic data, metabolite data, microbiome data, and imaging data;

[0101] S2, data preprocessing: cleaning, normalizing, dimension reduction and missing value filling of the data collected by the data acquisition module;

[0102] S3, feature extraction: extract key features related to colorectal cancer from the preprocessed data;

[0103] S4, prediction model: construct a colorectal cancer prediction model based on the extracted key features, train and optimize the model;

[0104] S5, result analysis: Analyze and interpret the output results of the prediction model to generate a colorectal cancer prediction report. The report content includes prediction conclusions, key feature contribution analysis, and personalized risk assessment.

[0105] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0106] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A colorectal cancer prediction system, characterized in that: It includes data acquisition module, data preprocessing module, feature extraction module and prediction model module. Each module cooperates with each other, including: Data collection module: collects various data related to colorectal cancer, including clinical data, genomic data, metabolite data, microbiome data and imaging data of patients; Data preprocessing module: cleans, normalizes, reduces dimension and fills missing values ​​for the data collected by the data acquisition module; Feature extraction module: extract key features related to colorectal cancer from the preprocessed data; Prediction model module: construct a colorectal cancer prediction model based on the extracted key features, and train and optimize the model; Result analysis module: Analyze and interpret the output results of the prediction model to generate a colorectal cancer prediction report. The report content includes prediction conclusions, key feature contribution analysis, and personalized risk assessment.

2. A colorectal cancer prediction system according to claim 1, characterized in that: The data acquisition module comprises: Clinical data collection: Automatically extract the patient's clinical data through the electronic health record system, conduct a questionnaire survey on the patient, collect additional detailed information such as the patient's living habits and eating habits, and enter them into the system; Genomic data collection: Extract blood samples from patients, extract DNA using a laboratory DNA extraction kit, and perform whole-genome sequencing on the extracted DNA using high-throughput sequencing technology to obtain genomic information such as gene mutations, single nucleotide polymorphisms, and copy number variations; Metabolite data collection: Blood, urine and feces samples are collected from patients, and metabolites in the samples are detected using liquid chromatography-mass spectrometry to analyze their concentration levels and metabolic pathway characteristics; Microbiome data collection: Collect stool samples from patients, preserve and process them, and sequence the microorganisms in the samples using 16SrRNA gene sequencing or metagenomic sequencing technology to obtain the types, abundance, and functional characteristics of the microorganisms; Image data acquisition: Perform colorectal examination on patients to obtain images of the inside of the colorectum, and perform imaging examination of the patient's colorectum through computer tomography and magnetic resonance imaging to obtain imaging data.

3. A colorectal cancer prediction system according to claim 1, characterized in that: The data preprocessing module comprises: Data cleaning: Preliminary screening of the collected raw data, removal of noise data and duplicate data, and use of outlier detection algorithms to identify and remove abnormal data points; Data normalization: Select a normalization method based on the data type, including Min-Max normalization and Z-score normalization, convert data of different dimensions to the same dimension, and review the normalized data; Data dimensionality reduction: Use principal component analysis to reduce the dimensionality of high-dimensional data, extract the main components, reduce the data dimension, and verify the dimensionality reduction results; Missing value filling: Analyze the missing values ​​in the data, determine the missing pattern, select the filling method based on the missing pattern, and verify the filled data.

4. A colorectal cancer prediction system according to claim 1, characterized in that: The feature extraction module comprises: Gene mutation feature extraction: perform mutation detection on preprocessed genomic data, identify gene mutation sites, identify key mutation genes associated with colorectal cancer, calculate mutation frequency, mutation type and mutation location, and perform feature screening and extraction; Metabolite level feature extraction: Quantitative analysis of preprocessed metabolite data, determination of the concentration level of each metabolite, pathway enrichment analysis of metabolite data using metabolic pathway analysis tools, identification of metabolic pathways related to colorectal cancer, extraction of metabolite concentrations and metabolic pathway activities, and feature screening and extraction; Extraction of microbiome structural features: perform taxonomic analysis on the preprocessed microbiome data to determine the types and abundance of microorganisms, use microbiome analysis tools to perform diversity analysis on the microbiome data, evaluate the structural features of the microbiome, extract microbial species abundance, diversity index and functional characteristics, and perform feature screening and extraction; Image feature extraction: Perform image segmentation on the preprocessed image data to separate the colorectal area, use image processing algorithms to extract features from the image data, identify the morphological features and lesion areas of the colorectum, extract image features such as texture features, shape features, and density features, and perform feature screening and extraction.

5. A colorectal cancer prediction system according to claim 1, characterized in that: The image feature extraction comprises: Image segmentation: Perform image segmentation on the preprocessed image data and use segmentation algorithms to separate the colorectal area from the background; Morphological processing: Perform morphological processing on the segmented colorectal area and use Canny edge detection to identify the edge contour of the colorectal area. Feature extraction: Use image processing algorithms to extract features from image data.

6. A colorectal cancer prediction system according to claim 1, characterized in that: The prediction model module includes: Data preparation: The key feature data set obtained from the feature extraction module is divided into a training set and a test set. The training set is used for model training, and the test set is used for model verification. Model construction: Build an initial colorectal cancer prediction model and set the initial parameters and structure of the model; Model training: Use the training set data to train the initial model, adopt the supervised learning method, and optimize the model parameters by minimizing the loss function; Model optimization: Tune the model.

7. A colorectal cancer prediction system according to claim 1, characterized in that: The model optimization includes: Cross-validation tuning: The model's hyperparameters are tuned through cross-validation technology. The training set data is divided into K equally divided subsets, of which K-1 subsets are used to train the model and the remaining 1 subset is used to verify the model. This cycle is repeated K times, and each time a different subset is selected as the verification set. The remaining subsets are used as the training set. The performance index of each verification is calculated and the average value is taken as the evaluation standard of the model performance. The model's hyperparameters are adjusted to find the parameter combination that optimizes the average performance index. Grid search or random search optimization: Use grid search or random search methods to further optimize the model's hyperparameters, use cross-validation technology to calculate the performance indicators of each combination, and select the hyperparameter combination with the best performance indicators as the final model hyperparameters.

8. A colorectal cancer prediction system according to claim 1, characterized in that: The result analysis module comprises: Prediction result generation: extract the prediction probability value and related prediction information, and generate the prediction conclusion of colorectal cancer based on the prediction probability value; Key feature contribution analysis: Calculate the contribution of each feature to the prediction results, generate feature contribution analysis charts, combine feature contribution analysis results, explain the decision-making process of the prediction model, and provide transparent and explainable analysis reports; Personalized risk assessment: Based on the patient's individual characteristic data, the personalized risk level of colorectal cancer is assessed, a personalized risk assessment report is generated, and personalized prevention and intervention recommendations are provided; Report generation: Comprehensive prediction conclusions, key feature contribution analysis and personalized risk assessment results are used to generate a colorectal cancer prediction report. The report content includes prediction conclusions, key feature contribution analysis charts, personalized risk assessment and health management recommendations.

9. A method for predicting colorectal cancer, implemented by the above-mentioned colorectal cancer prediction system, comprising the following steps: S1, data collection: collecting various data related to colorectal cancer, including clinical data, genomic data, metabolite data, microbiome data and imaging data of patients; S2, data preprocessing: cleaning, normalizing, dimension reduction and missing value filling of the data collected by the data acquisition module; S3, feature extraction: extract key features related to colorectal cancer from the preprocessed data; S4, prediction model: constructing a colorectal cancer prediction model based on the extracted key features, and training and optimizing the model; S5, result analysis: Analyze and interpret the output results of the prediction model to generate a colorectal cancer prediction report. The report content includes prediction conclusions, key feature contribution analysis, and personalized risk assessment.

Images