Tumor prognosis prediction method based on tumor database text recognition

Abstract

The invention relates to the technical field of medical care, in particular to a tumor prognosis prediction method based on tumor database text recognition, which comprises the following steps: S1, data collection and preprocessing: collecting medical data related to tumors from a plurality of tumor databases; s2, text information extraction: performing information extraction on clinical text data; s3, predicting a tumor metastasis path: predicting the metastasis path by utilizing the graph neural network model, predicting a potential metastasis path of the tumor, and analyzing the influence of different metastasis paths on the prognosis of the patient; s4, prognosis evaluation and risk prediction: predicting the tumor prognosis risk in combination with the medical data of the patient, and comprehensively evaluating the five-year survival rate and the recurrence risk of the patient. According to the method, the medical institution can be assisted in optimizing resource allocation, a scientific personalized diagnosis and treatment scheme is formulated, and the life quality and the treatment effect of the patient are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of medical care technology, and in particular to a tumor prognosis prediction method based on tumor database text recognition. Background Art

[0002] With the rapid accumulation of medical data and the continuous development of artificial intelligence technology, tumor prognosis prediction based on big data has become one of the hot spots in precision medicine research. The prognosis evaluation of tumor patients is of great significance for the formulation of treatment plans and the long-term management of patients. By analyzing the patient's clinical text records, imaging data and genomic data, combined with data modeling technology, it is possible to not only predict the patient's five-year survival rate, but also evaluate the risk of recurrence. However, due to the diverse sources and heterogeneity of medical data, how to efficiently integrate multimodal data and build an accurate prediction model has become a key problem in current medical artificial intelligence research.

[0003] Existing technologies face the following major problems in the field of tumor prognosis prediction: First, there are differences in format and feature expression between multimodal data (such as clinical text, imaging, and genomic data), and traditional data preprocessing methods are limited in eliminating noise information and retaining important features; second, the prediction of tumor metastasis pathways relies on complex heterogeneous relationship modeling, and traditional methods have difficulty in effectively capturing the semantic associations between tumor types, treatment options, and metastasis locations, resulting in insufficient prediction accuracy; in addition, existing prognostic assessment methods often fail to fully consider the combined impact of individualized characteristics and metastasis pathways, making it difficult to provide targeted risk grading recommendations, limiting their application value in clinical practice.

[0004] The purpose of the present invention is to provide a tumor prognosis prediction method based on tumor database text recognition, which not only improves the accuracy and interpretability of tumor metastasis path prediction, but also can provide patients with quantitative five-year survival rate and recurrence risk prediction results, further realize accurate grading and personalized management, and provide a scientific basis for the formulation of tumor treatment plans. Summary of the invention

[0005] The present invention provides a tumor prognosis prediction method based on tumor database text recognition.

[0006] A tumor prognosis prediction method based on tumor database text recognition comprises the following steps: S1, data collection and preprocessing: collect tumor-related medical data from multiple tumor databases, including clinical text data, imaging data and genomic data, and perform denoising and word segmentation on text data, standardization on imaging data, and missing value filling and normalization on genomic data; S2, text information extraction: use natural language processing technology to extract information from clinical text data, including tumor type, treatment plan, and metastasis location; S3, Tumor metastasis path prediction: Based on the extracted tumor type, treatment plan, and metastasis location, the graph neural network (GNN) model is used to predict the potential metastasis path of the tumor and analyze the impact of different metastasis paths on patient prognosis, including: S31, graph construction: based on the extracted tumor types, treatment plans, and metastasis locations, a graph structure consisting of nodes and edges is constructed; S32, metastasis pathway prediction: Based on the constructed graph structure, the graph neural network (GNN) model is used to extract the potential rules of tumor metastasis pathways and predict the metastasis pathways; S33, metastatic pathway assessment: based on the prediction results of metastatic pathways, analyze the impact of different metastatic pathways on patient prognosis; S4, Prognosis assessment and risk prediction: Based on the results of tumor metastasis path prediction, combined with the patient's medical data, the tumor prognosis risk is predicted, and the patient's five-year survival rate and recurrence risk are comprehensively evaluated.

[0007] Optionally, the data collection and preprocessing in S1 includes: S11, data collection: collect tumor-related medical data from multiple tumor databases, including clinical text data, imaging data, and genomic data; S12, clinical text data preprocessing: denoising and word segmentation of clinical text data; S13, image data preprocessing: image data were standardized using the Z-score standardization method; S14, genomic data preprocessing: missing value filling and normalization of genomic data.

[0008] Optionally, the text information extraction in S2 includes: S21, word segmentation and text cleaning: clinical text data is segmented using a probability-based maximum entropy model to remove stop words and irrelevant characters; S22, named entity recognition: using a bidirectional long short-term memory network (Bi-LSTM) combined with a conditional random field (CRF) model to identify entity information of tumor type, treatment regimen, and metastasis location in clinical texts; Relation extraction: Based on the extracted named entities, a relation extraction model with attention mechanism is used to identify the associations between tumor type, treatment regimen, and metastasis location.

[0009] Optionally, the map construction in S31 includes: S311, Node definition and representation: According to the extracted tumor type, treatment plan and metastasis location, each independent clinical text data is used as a node in the graph, recorded as a node set ,in Represents the corresponding clinical text data, and the feature vector of each node is expressed as ; S312, Edge definition and weight calculation: Construct edge sets based on the relationships between nodes , indicating a node and The relationship between them is extracted and the weight of the edge is calculated through the relationship extraction model; S313, Construction of graph structure: Using node sets and edge set Building the graph structure ,In the graph structure, nodes represent tumor types, treatment schemes or ,metastasis locations, and edges represent the association between nodes (e.g., the relationship between treatment schemes and tumor types, the association between tumor types and ,metastasis locations, etc.); S314, Calculation of normalized adjacency matrix: Organize edge weights into an adjacency matrix , and normalize the adjacency matrix.

[0010] Optionally, the transfer path prediction in S32 includes: S321, input representation: the graph structure to be constructed The node feature matrix and normalized adjacency matrix as input to the graph neural network (GNN) model; S322, graph convolution layer calculation: extract node features and update node representation through the graph convolution network (GCN) model; S323, Aggregation and Prediction: After multiple layers of graph convolution, extract the final node feature representation ,in is the number of layers in the network. The fully connected layer is used to process the node features and predict the potential metastasis path of the tumor. The prediction result is output as the probability of each metastasis path through the classifier. S324, metastasis path extraction and sorting: extract the metastasis path based on the predicted probability distribution, sort it by probability, and output the potential rules and paths of tumor metastasis.

[0011] Optionally, the transfer path evaluation in S33 includes: S331, feature extraction of transfer path: Based on the transfer path prediction results, the final node feature matrix output from the graph neural network (GNN) model Extract the node features related to the transfer path, aggregate all node features on the path, and generate a path representation vector ; S332, prognostic score calculation: representation vector for each transfer pathway The prognostic score was calculated using a fully connected layer; S333, analysis of the overall impact of the pathway on prognosis: All predicted metastatic pathways and their prognostic scores were combined to calculate the overall prognostic impact value , indicating the overall prognosis of the patient.

[0012] Optionally, the prognosis assessment and risk prediction in S4 include: S41, Comprehensive feature fusion: Calculated overall prognostic impact value , which is fused with the patient’s medical data to generate a comprehensive feature representation of the patient; S42, prediction of prognostic risk indicators: Based on the fused comprehensive characteristics of the patient, the patient's prognostic risk indicators, including five-year survival rate and recurrence risk, are predicted through a multi-layer neural network; S43, Comprehensive assessment and grading recommendations: Combined with the patient's five-year survival rate, recurrence risk and overall prognostic impact value , comprehensively calculate the patient's personalized prognostic assessment value, which is used to comprehensively reflect the patient's prognostic risk level and give corresponding prognostic recommendations.

[0013] Optionally, the comprehensive feature fusion in S41 includes: S411, Feature Fusion: The overall prognostic impact value obtained by predicting the tumor metastasis pathway And the patient's medical data are spliced ​​to generate a comprehensive feature representation of the patient ; S412, Feature Normalization and Dimensionality Reduction: Comprehensive Feature Representation after Concatenation Perform normalization and dimensionality reduction.

[0014] Optionally, the prediction of the prognostic risk indicator in S42 includes: S421, Neural network structure: Through a multi-layer fully connected neural network, the comprehensive feature representation after dimensionality reduction is extracted layer by layer and nonlinearly transformed to output the patient's five-year survival rate and recurrence risk, including: S4211, calculation of hidden layer: Calculate the Layer hidden feature representation ; S4212, calculation of the output layer: the last layer outputs the patient's five-year survival rate and recurrence risk ; S422, Loss function optimization: Use the binary cross entropy loss function to optimize the prediction results of the multi-layer fully connected neural network, and optimize the five-year survival rate and recurrence risk respectively.

[0015] Optionally, the comprehensive evaluation and grading suggestion in S43 includes: S431, Calculation of personalized prognostic assessment value: based on the patient's five-year survival rate prediction value , recurrence risk prediction value and overall prognostic impact value , comprehensively calculate the patient's personalized prognostic assessment value ; S432, Risk level classification: based on personalized prognostic assessment values , classify the patient's risk level and determine the corresponding prognostic recommendations, including: High risk: When When , it indicates high risk and poor prognosis for the patient, and focused intervention is recommended, including intensive treatment plans, intensive monitoring, and auxiliary examinations; Medium risk: When , it indicates medium risk and the patient has a moderate prognosis. Conventional treatment is recommended, while regular review and monitoring are strengthened; Low risk: When When , it indicates low risk and the patient’s prognosis is normal. It is recommended to follow the treatment plan and pay attention to follow-up.

[0016] Beneficial effects of the present invention: The present invention significantly improves the consistency, comparability and robustness of the data by integrating clinical text data, imaging data and genomic data and combining a variety of preprocessing algorithms and data processing technologies. In the preprocessing stage, it not only removes the noise information in the data, but also retains the semantic and feature information of the medical data, thus solving the problem of difficulty in simultaneously processing multimodal medical data and greatly improving the prediction accuracy and generalization ability of the model.

[0017] The present invention uses a graph neural network model to perform in-depth modeling and metastasis path prediction on the relationship between tumor type, treatment plan and metastasis location, effectively capturing the complex heterogeneous medical relationship structure. Through a multi-step process of constructing a graph, extracting graph features, path prediction and sorting, it can accurately predict the tumor metastasis path and analyze its impact on patient prognosis. At the same time, the normalized adjacency matrix and multi-layer graph convolution operations of the graph structure are used to improve not only the numerical stability of the model, but also the interpretability of the path prediction, which makes up for the deficiency of traditional models in modeling complex medical data relationships and provides an important reference for the formulation of personalized tumor treatment plans.

[0018] The present invention, through a prognostic evaluation and risk prediction framework, comprehensively integrates the overall prognostic impact value of the tumor metastasis pathway and the patient's individualized multimodal data, combines a multi-layer neural network to predict the five-year survival rate and recurrence risk, and provides patients with accurate risk assessment and grading recommendations through quantitative personalized prognostic evaluation values ​​and clear risk grading standards, thereby solving the problem of insufficient consideration of individualized characteristics in prognostic evaluation, greatly improving the accuracy and clinical applicability of prognostic evaluation, and ultimately, assisting medical institutions in optimizing resource allocation, formulating scientific personalized diagnosis and treatment plans, and significantly improving patients' quality of life and treatment effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] 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.

[0020] Figure 1 A schematic diagram of a prediction method flow chart of an embodiment of the present invention; Figure 2 This is a schematic diagram of tumor metastasis path prediction according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] 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.

[0022] like Figure 1-Figure 2 As shown, a tumor prognosis prediction method based on tumor database text recognition includes the following steps: S1, data collection and preprocessing: collect tumor-related medical data from multiple tumor databases, including clinical text data, imaging data and genomic data, and perform denoising and word segmentation on text data, standardization on imaging data, and missing value filling and normalization on genomic data; S2, text information extraction: use natural language processing technology to extract information from clinical text data, including tumor type, treatment plan, and metastasis location; S3, Tumor metastasis path prediction: Based on the extracted tumor type, treatment plan, and metastasis location, the graph neural network (GNN) model is used to predict the potential metastasis path of the tumor and analyze the impact of different metastasis paths on patient prognosis, including: S31, graph construction: based on the extracted tumor types, treatment plans, and metastasis locations, a graph structure consisting of nodes and edges is constructed; S32, metastasis pathway prediction: Based on the constructed graph structure, the graph neural network (GNN) model is used to extract the potential rules of tumor metastasis pathways and predict the metastasis pathways; S33, metastatic pathway assessment: based on the prediction results of metastatic pathways, analyze the impact of different metastatic pathways on patient prognosis; S4, prognosis assessment and risk prediction: Based on the results of tumor metastasis path prediction, combined with the patient's medical data, the tumor prognosis risk is predicted, and the patient's five-year survival rate and recurrence risk are comprehensively evaluated; Through the above content, data from different sources can be effectively integrated to provide accurate tumor metastasis pathway analysis and personalized prognosis prediction, which not only improves the accuracy of tumor metastasis prediction, but also can predict the patient's survival rate and recurrence risk based on their specific situation, providing more scientific and data-driven support for the formulation of tumor treatment plans.

[0023] Data collection and preprocessing in S1 include: S11, data collection: collect tumor-related medical data from multiple tumor databases, including clinical text data, imaging data, and genomic data; S12, clinical text data preprocessing: denoising and word segmentation of clinical text data, including: Denoising: The TF-IDF (term frequency-inverse document frequency) method is used to perform denoising on clinical text data to remove low-frequency irrelevant words, expressed as: ; in, Words In the documentation The importance (weight) of Words In the documentation The frequency in To contain words The number of documents, is the total number of documents; Word segmentation: Use the Word2Vec embedding model to convert clinical text data into word vector representation, retain meaningful words, and remove stop words and irrelevant high-frequency words; S13, image data preprocessing: The image data is standardized using the Z-score standardization method, expressed as: ; in, is the standardized value, is the original value of the image data, is the mean of the image data, is the standard deviation of the image data; S14, genomic data preprocessing: missing value filling and normalization of genomic data, including: Missing value filling: Use KNN interpolation to fill missing values ​​by selecting known values ​​of neighboring samples, expressed as: ; in, To fill in missing values, is the number of neighboring samples selected, is the known value of the neighboring samples; Normalization: Use Min-Max normalization method to normalize genomic data to The interval is expressed as: ; in, is the original genome data, and are the minimum and maximum values ​​of the feature, respectively. is the normalized result; Through the above content, we ensure the consistency and comparability of different data sources, remove noise information, and improve the accuracy and effectiveness of the data. In addition, by combining algorithms such as TF-IDF denoising, Word2Vec word embedding, Z-score normalization, and KNN interpolation, we fully retain the semantic and feature information of the data, greatly improving the robustness and predictive ability of the model.

[0024] Text information extraction in S2 includes: S21, word segmentation and text cleaning: The clinical text data is segmented by a probability-based maximum entropy model to remove stop words and irrelevant characters, expressed as: ; in, Indicates the current word, Indicates context, is the characteristic function, is the feature weight, is the normalization factor, is the total number of characteristic functions; ; S22, named entity recognition: A bidirectional long short-term memory network (Bi-LSTM) was used in combination with a conditional random field (CRF) model to identify entity information of tumor type, treatment plan, and metastasis location in clinical texts. The objective function of entity recognition is expressed as: ; in, For a given input sequence The output sequence is The conditional probability of is the current annotation label, For input sequence, clinical text data, For the time step When, label With the previous label The joint feature score depends on the input sequence , For all possible label sequences, For the input sequence The length of , that is, the total number of time steps, is the sum of the scores of all possible output sequences, used to normalize the probabilities; Relation extraction: Based on the extracted named entities, the relationship extraction model using the attention mechanism is used to identify the associations between tumor type, treatment regimen, and metastasis location, expressed as: ; ; in, is the attention weight, , , are query, key and value vectors respectively, is a context vector, which represents the semantic relationship between tumor type, treatment regimen, and metastasis location. is the number of all feature vectors or words present in the context, Transpose the sign of a vector; Through the above content, accurate extraction and structured representation of key information such as tumor type, treatment plan and metastasis location are achieved, which not only solves the problem that traditional methods are difficult to efficiently process unstructured medical texts, but also improves the accuracy and semantic completeness of extraction.

[0025] The graph construction in S31 includes: S311, Node definition and representation: According to the extracted tumor type, treatment plan and metastasis location, each independent clinical text data is used as a node in the graph, recorded as a node set ,in Represents the corresponding clinical text data, and the feature vector of each node is expressed as , generated by the Word2Vec model; S312, Edge definition and weight calculation: Construct edge sets based on the relationships between nodes , indicating a node and The relationship between them is calculated, and the weight of the edge is calculated through the relationship extraction model, which is expressed as: ; in, Representation Node and The semantic similarity between is the cosine similarity, which measures the strength of the relationship between two nodes; S313, Construction of graph structure: Using node sets and edge set Building the graph structure ,In the graph structure, nodes represent tumor types, treatment schemes or ,metastasis locations, and edges represent the association between nodes (e.g., the relationship between treatment schemes and tumor types, the association between tumor types and ,metastasis locations, etc.); S314, Calculation of normalized adjacency matrix: Organize edge weights into an adjacency matrix , and normalize the adjacency matrix to facilitate subsequent graph neural network calculations, expressed as: ; in, is the node degree matrix, , is the normalized adjacency matrix; Through the above content, the complex relationship between clinical data is accurately expressed, the semantic correlation between each feature is fully retained, and the numerical stability and model adaptability of the graph structure are enhanced through the processing of the normalized adjacency matrix. It not only solves the problem of modeling unstructured clinical data, but also improves the accuracy and interpretability of tumor metastasis path prediction.

[0026] The transfer path prediction in S32 includes: S321, input representation: the graph structure to be constructed The node feature matrix and normalized adjacency matrix as input to the graph neural network (GNN) model; S322, graph convolution layer calculation: extract node features through the graph convolution network (GCN) model and update the node representation, expressed as: ; in, For the The node feature matrix of the layer, For the The trainable weight matrix of the layer, is the ReLU nonlinear activation function, For the The node feature matrix of the layer; S323, Aggregation and Prediction: After multiple layers of graph convolution, extract the final node feature representation ,in is the number of layers in the network. The fully connected layer is used to process the node features and predict the potential metastasis path of the tumor. The prediction result is output through the classifier to output the probability of each metastasis path, which is expressed as: ; in, is the conditional probability distribution, which means that after After processing by the layer graph neural network model, the predicted category (i.e., possible transfer path) is The probability of is the weight matrix of the output layer, is the number of categories (i.e., the number of possible transfer paths); S324, metastasis path extraction and sorting: extract metastasis paths according to the predicted probability distribution, sort them by probability, and output the potential rules and paths of tumor metastasis; Through the above content, the complex relationship between tumor type, treatment plan and metastasis location can be efficiently captured. Combined with the feature extraction of multi-layer graph convolution and the probability output of softmax classifier, it can not only accurately explore the potential rules of tumor metastasis pathways, but also quantify the predicted probability of each pathway, providing scientific support for personalized tumor treatment plans, and effectively solving the problem that traditional methods are difficult to deal with multi-dimensional heterogeneous relationships, greatly improving the accuracy and interpretability of metastasis path prediction.

[0027] The transfer path assessment in S33 includes: S331, feature extraction of transfer path: Based on the transfer path prediction results, the final node feature matrix output from the graph neural network (GNN) model Extract the node features related to the transfer path, aggregate all node features on the path, and generate a path representation vector , expressed as: ; in, For the predicted The set of nodes on the transfer path, For Node The characteristic vector of is a feature aggregation function, such as average or maximum value; S332, prognostic score calculation: representation vector for each transfer pathway The prognostic score is calculated using a fully connected layer, expressed as: ; in, For path The prognostic score ranges from , is the weight vector of the prognostic evaluation model, is the activation function; S333, analysis of the overall impact of the pathway on prognosis: All predicted metastatic pathways and their prognostic scores were combined to calculate the overall prognostic impact value , represents the overall prognosis of the patient, expressed as: ; in, is the total number of predicted transfer paths, For path The weight of Through the above content, the impact of each pathway on the patient's prognosis is accurately quantified, and the patient's overall prognosis is comprehensively evaluated. The node features extracted by the graph neural network (GNN) are combined with feature aggregation and fully connected layer scoring to effectively distinguish the risk levels of different transfer pathways, providing a scientific basis for personalized diagnosis and treatment. It not only improves the accuracy of prognosis assessment, but also enhances clinical interpretability, making medical decisions more intelligent and data-driven.

[0028] Prognostic assessment and risk prediction in S4 include: S41, Comprehensive feature fusion: Calculated overall prognostic impact value , which is fused with the patient’s medical data to generate a comprehensive feature representation of the patient; S42, prediction of prognostic risk indicators: Based on the fused comprehensive characteristics of the patient, the patient's prognostic risk indicators, including five-year survival rate and recurrence risk, are predicted through a multi-layer neural network; S43, Comprehensive assessment and grading recommendations: Combined with the patient's five-year survival rate, recurrence risk and overall prognostic impact value , comprehensively calculate the patient's personalized prognostic assessment value to comprehensively reflect the patient's prognostic risk level and give corresponding prognostic recommendations; Through the above content, the metastasis pathway information and individual characteristics of the patient are fully integrated to generate a high-quality comprehensive feature representation, predict the patient's five-year survival rate and recurrence risk, provide accurate individualized prognostic risk indicators, and combine these indicators to calculate personalized prognostic assessment values, which provides a scientific basis for the patient's comprehensive risk assessment. It can not only accurately reflect the patient's overall prognostic risk level, but also make targeted treatment and management recommendations based on the specific grading results, significantly improving the accuracy, comprehensiveness and clinical practicality of the assessment.

[0029] The comprehensive feature fusion in S41 includes: S411, Feature Fusion: The overall prognostic impact value obtained by predicting the tumor metastasis pathway And the patient's medical data are spliced ​​to generate a comprehensive feature representation of the patient , expressed as: ; in, , , The clinical, imaging and genomic characteristics of the patients, It is a feature concatenation operation that integrates all features into a unified representation; S412, Feature Normalization and Dimensionality Reduction: Comprehensive Feature Representation after Concatenation Normalization and dimensionality reduction are performed to improve computational efficiency and model stability, including: Normalization: Use Min-Max normalization to map the feature values ​​to , expressed as: ; in, and The feature matrices are The minimum and maximum values ​​of It is the comprehensive feature representation after normalization; Dimensionality reduction: Use principal component analysis (PCA) to reduce the dimension of the normalized comprehensive feature representation from a high-dimensional space to a low-dimensional space , expressed as: ; in, is the comprehensive feature representation after dimensionality reduction, is the projection matrix of PCA; Through the above content, a comprehensive patient feature representation is generated. After fusion, the data dimension is reduced through normalization and dimensionality reduction operations, which improves the computational efficiency and retains high-quality feature information. It provides a reliable input for subsequent prognostic risk prediction and effectively integrates the global impact of the metastasis pathway on the patient's prognosis with the local information of individual characteristics, significantly improving the comprehensiveness, accuracy and practicality of the prognostic evaluation.

[0030] Prognostic risk indicators predicted in S42 include: S421, Neural network structure: Through a multi-layer fully connected neural network, the comprehensive feature representation after dimensionality reduction is extracted layer by layer and nonlinearly transformed to output the patient's five-year survival rate and recurrence risk, including: S4211, calculation of hidden layer: Calculate the Layer hidden feature representation , expressed as: ; in, For the Layer hidden feature representation, The initial input is the comprehensive feature representation after dimensionality reduction, For the The weight matrix of the layer, For the The bias term of the layer, is the ReLU activation function; S4212, calculation of the output layer: the last layer outputs the patient's five-year survival rate and recurrence risk , expressed as: ; ; in, is the feature representation of the last hidden layer, , are the weight matrices for five-year survival rate and recurrence risk prediction, , are the bias items of the corresponding output layers, is the Sigmoid activation function; S422, loss function optimization: Use the binary cross entropy loss function to optimize the prediction results of the multi-layer fully connected neural network, and optimize the five-year survival rate and recurrence risk respectively, expressed as: ; ; ; in, is the loss function of the five-year survival rate, indicating the predicted five-year survival rate With the actual label The error between is the loss function of recurrence risk, indicating the predicted recurrence risk With the actual label The error between is the total loss function, is the total number of samples; Through the above content, based on the extraction of deep-level features layer by layer by multi-layer neural networks and combined with the modeling ability of activation functions for nonlinear relationships, it is possible to more accurately predict the patient's five-year survival rate and recurrence risk. The binary cross-entropy loss function is used for optimization to ensure the reliability and accuracy of the prediction results. It integrates the combined influence of multimodal data (such as clinical, imaging, and genomic features) and tumor metastasis pathways, provides a scientific basis for personalized risk assessment, and significantly improves the accuracy, comprehensiveness, and clinical practicality of prognosis prediction.

[0031] The comprehensive assessment and grading recommendations in S43 include: S431, Calculation of personalized prognostic assessment value: based on the patient's five-year survival rate prediction value , recurrence risk prediction value and overall prognostic impact value , comprehensively calculate the patient's personalized prognostic assessment value , expressed as: ; in, It is the patient's personalized prognostic assessment value. The higher the value, the better the prognosis. is the overall prognostic impact value, indicating the overall impact of tumor metastasis pathway on patient prognosis. is the five-year survival rate prediction value, indicating the probability of patient survival. is the recurrence risk prediction value, which indicates the probability of tumor recurrence in patients. , , are the corresponding weight parameters, satisfying ; S432, Risk level classification: based on personalized prognostic assessment values , classify the patient's risk level and determine the corresponding prognostic recommendations, including: High risk: When When , it indicates high risk and poor prognosis for the patient, and focused intervention is recommended, including intensive treatment plans, intensive monitoring, and auxiliary examinations; Medium risk: When , it indicates medium risk and the patient has a moderate prognosis. Conventional treatment is recommended, while regular review and monitoring are strengthened; Low risk: When When , it indicates low risk and the patient’s prognosis is normal. It is recommended to follow the treatment plan and pay attention to follow-up; Through the above content, the patient's overall prognostic risk level can be accurately reflected, providing a scientific quantitative basis to ensure the personalization and clinical applicability of the evaluation results. At the same time, through clear risk classification standards and specific grading recommendations, targeted diagnosis and treatment and management plans can be formulated for patients with different risk levels, which will help optimize the allocation of medical resources and improve patient treatment outcomes and quality of life.

[0032] 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.

[0033] The above is only a preferred embodiment 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 principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A tumor prognosis prediction method based on tumor database text recognition, characterized in that: The following steps are involved: S1, data collection and preprocessing: collect tumor-related medical data from multiple tumor databases, including clinical text data, imaging data and genomic data, and perform denoising and word segmentation on text data, standardization on imaging data, and missing value filling and normalization on genomic data; S2, text information extraction: use natural language processing technology to extract information from clinical text data, including tumor type, treatment plan, and metastasis location; S3, Tumor metastasis path prediction: Based on the extracted tumor type, treatment plan, and metastasis location, the graph neural network model is used to predict the potential metastasis path of the tumor and analyze the impact of different metastasis paths on patient prognosis, including: S31, graph construction: based on the extracted tumor types, treatment plans, and metastasis locations, a graph structure consisting of nodes and edges is constructed; S32, metastasis pathway prediction: Based on the constructed graph structure, the graph neural network model is used to extract the potential rules of tumor metastasis pathways and predict the metastasis pathways; S33, metastatic pathway assessment: based on the prediction results of metastatic pathways, analyze the impact of different metastatic pathways on patient prognosis; S4, Prognosis assessment and risk prediction: Based on the results of tumor metastasis path prediction, combined with the patient's medical data, the tumor prognosis risk is predicted, and the patient's five-year survival rate and recurrence risk are comprehensively evaluated.

2. The method for predicting tumor prognosis based on tumor database text recognition according to claim 1, characterized in that: The data collection and preprocessing in S1 include: S11, data collection: collect tumor-related medical data from multiple tumor databases, including clinical text data, imaging data, and genomic data; S12, clinical text data preprocessing: denoising and word segmentation of clinical text data; S13, image data preprocessing: image data were standardized using the Z-score standardization method; S14, genomic data preprocessing: missing value filling and normalization of genomic data.

3. The method for predicting tumor prognosis based on tumor database text recognition according to claim 1, characterized in that: The text information extraction in S2 includes: S21, word segmentation and text cleaning: clinical text data is segmented using a probability-based maximum entropy model to remove stop words and irrelevant characters; S22, named entity recognition: using a bidirectional long short-term memory network combined with a conditional random field model to identify entity information of tumor type, treatment regimen, and metastasis location in clinical texts; Relation extraction: Based on the extracted named entities, a relation extraction model with attention mechanism is used to identify the associations between tumor type, treatment regimen, and metastasis location.

4. The method for predicting tumor prognosis based on tumor database text recognition according to claim 1, characterized in that: The map construction in S31 includes: S311, Node definition and representation: According to the extracted tumor type, treatment plan and metastasis location, each independent clinical text data is used as a node in the graph, recorded as a node set ,in Represents the corresponding clinical text data, and the feature vector of each node is expressed as ; S312, Edge definition and weight calculation: Construct edge sets based on the relationships between nodes , indicating a node and The relationship between them is extracted and the weight of the edge is calculated through the relationship extraction model; S313, Construction of graph structure: Using node sets and edge set Building the graph structure ,In the graph structure, nodes represent tumor types, treatment ,schemes, or metastasis locations, and edges represent the ,association between nodes; S314, Calculation of normalized adjacency matrix: Organize edge weights into an adjacency matrix , and normalize the adjacency matrix.

5. The method for predicting tumor prognosis based on tumor database text recognition according to claim 4, characterized in that: The transfer path prediction in S32 includes: S321, input representation: the graph structure to be constructed The node feature matrix and normalized adjacency matrix as input to the graph neural network model; S322, graph convolution layer calculation: extract node features and update node representation through the graph convolution network model; S323, Aggregation and Prediction: After multiple layers of graph convolution, extract the final node feature representation ,in is the number of layers in the network. The fully connected layer is used to process the node features and predict the potential metastasis path of the tumor. The prediction result is output as the probability of each metastasis path through the classifier. S324, metastasis path extraction and sorting: extract the metastasis path based on the predicted probability distribution, sort it by probability, and output the potential rules and paths of tumor metastasis.

6. The method for predicting tumor prognosis based on tumor database text recognition according to claim 5, characterized in that: The transfer path evaluation in S33 includes: S331, feature extraction of transfer path: Based on the transfer path prediction results, the final node feature matrix output from the graph neural network model Extract the node features related to the transfer path, aggregate all node features on the path, and generate a path representation vector ; S332, prognostic score calculation: representation vector for each transfer pathway The prognostic score was calculated using a fully connected layer; S333, analysis of the overall impact of the pathway on prognosis: All predicted metastatic pathways and their prognostic scores were combined to calculate the overall prognostic impact value , indicating the overall prognosis of the patient.

7. The method for predicting tumor prognosis based on tumor database text recognition according to claim 6, characterized in that: The prognostic assessment and risk prediction in S4 include: S41, Comprehensive feature fusion: Calculated overall prognostic impact value , which is fused with the patient’s medical data to generate a comprehensive feature representation of the patient; S42, prediction of prognostic risk indicators: Based on the fused comprehensive characteristics of the patient, the patient's prognostic risk indicators, including five-year survival rate and recurrence risk, are predicted through a multi-layer neural network; S43, Comprehensive assessment and grading recommendations: Combined with the patient's five-year survival rate, recurrence risk and overall prognostic impact value , comprehensively calculate the patient's personalized prognostic assessment value, which is used to comprehensively reflect the patient's prognostic risk level and give corresponding prognostic recommendations.

8. The method for predicting tumor prognosis based on tumor database text recognition according to claim 7, characterized in that: The comprehensive feature fusion in S41 includes: S411, Feature Fusion: The overall prognostic impact value obtained by predicting the tumor metastasis pathway And the patient's medical data are spliced ​​to generate a comprehensive feature representation of the patient ; S412, Feature Normalization and Dimensionality Reduction: Comprehensive Feature Representation after Concatenation Perform normalization and dimensionality reduction.

9. The method for predicting tumor prognosis based on tumor database text recognition according to claim 8, characterized in that: The prediction of the prognostic risk indicator in S42 includes: S421, Neural network structure: Through a multi-layer fully connected neural network, the comprehensive feature representation after dimensionality reduction is extracted layer by layer and nonlinearly transformed to output the patient's five-year survival rate and recurrence risk, including: S4211, calculation of hidden layer: Calculate the Layer hidden feature representation ; S4212, calculation of the output layer: the last layer outputs the patient's five-year survival rate and recurrence risk ; S422, Loss function optimization: Use the binary cross entropy loss function to optimize the prediction results of the multi-layer fully connected neural network, and optimize the five-year survival rate and recurrence risk respectively.

10. The method for predicting tumor prognosis based on tumor database text recognition according to claim 9, characterized in that: The comprehensive assessment and grading recommendations in S43 include: S431, Calculation of personalized prognostic assessment value: based on the patient's five-year survival rate prediction value , recurrence risk prediction value and overall prognostic impact value , comprehensively calculate the patient's personalized prognostic assessment value ; S432, Risk level classification: based on personalized prognostic assessment values , classify the patient's risk level and determine the corresponding prognostic recommendations, including: High risk: When When , it indicates high risk and poor prognosis for the patient, and focused intervention is recommended, including intensive treatment plans, intensive monitoring, and auxiliary examinations; Medium risk: When , it indicates medium risk and the patient has a moderate prognosis. Conventional treatment is recommended, while regular review and monitoring are strengthened; Low risk: When When , it indicates low risk and the patient’s prognosis is normal. It is recommended to follow the treatment plan and pay attention to follow-up.

Images