Tumor radiotherapy patient symptom management and prognosis evaluation method and system

Abstract

The invention discloses a symptom management and prognosis evaluation method and system for a tumor radiotherapy patient, and relates to the technical field of tumor radiotherapy patient management.The method comprises the steps that basic information of the tumor radiotherapy patient is obtained, prognosis evaluation is conducted according to the basic information, a first result is generated, and the risk category is judged according to the first result; obtaining symptom information of a tumor radiotherapy patient, evaluating the symptom severity according to the symptom information, and generating a second result; and performing symptom management according to the second result and the risk category, generating prognosis data, and updating the first result through the prognosis data. According to the invention, by fusing the dual contrast learning network and the dual-path decision tree integrated model, the dynamic association analysis and adaptive feature enhancement of the multi-dimensional medical data of the tumor radiotherapy patient are realized, so that a precise prognosis evaluation and a personalized symptom management scheme are provided for clinical practice.

Description

Technical Field

[0001] The present invention relates to the technical field of tumor radiotherapy patient management, and in particular to a method and system for symptom management and prognosis assessment of tumor radiotherapy patients. Background Art

[0002] With the continuous development of tumor radiotherapy technology, the widespread application of new treatment methods such as precision radiotherapy and intensity-modulated radiotherapy has greatly improved the therapeutic effect of radiotherapy. However, as a local treatment method, radiotherapy will inevitably damage normal tissues while killing tumor cells, causing a variety of radiotherapy-related adverse reactions. At present, the symptom management of radiotherapy patients in clinical practice mainly relies on the doctor's experience and judgment, and the treatment plan is adjusted by observing the patient's symptoms. This traditional symptom management method has obvious limitations: first, symptom assessment lacks standardized and quantitative indicators, making it difficult to accurately judge the severity of symptoms; second, it is difficult to effectively predict the patient's prognosis risk based solely on experience, and it is impossible to achieve timely and accurate adjustments to the treatment plan; third, the existing prognosis evaluation model often separates the patient's basic characteristics, symptom manifestations, and treatment response information, and fails to fully explore the correlation between multi-dimensional medical data, resulting in limited reliability and accuracy of the prediction results.

[0003] In addition, artificial intelligence technology has been deeply applied in the medical field in recent years, and prognosis assessment methods based on machine learning have gradually become a research hotspot. Existing technologies usually use shallow neural networks or traditional tree models for prognosis prediction. These methods have the following problems when dealing with heterogeneous medical data: First, feature engineering relies too much on manual experience, and it is difficult to adaptively discover and enhance feature combinations that are valuable for prognosis prediction; second, the model structure is relatively simple and cannot effectively capture the complex temporal dependencies and feature interaction patterns in medical data; third, the prediction results lack interpretability and it is difficult to provide a reliable quantitative basis for clinical decision-making; fourth, the model update mechanism is not flexible enough, and it is impossible to dynamically adjust the prediction strategy according to the changes in symptoms during the patient's treatment process. Therefore, how to design a technical solution that can comprehensively utilize the patient's basic characteristics, symptom information and treatment response to achieve accurate prognosis evaluation and intelligent symptom management has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the present invention provides a method and system for symptom management and prognosis assessment of tumor radiotherapy patients, which can solve the problems mentioned in the background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for symptom management and prognosis assessment of patients undergoing tumor radiotherapy, comprising: obtaining basic information of patients undergoing tumor radiotherapy, performing prognosis assessment based on the basic information, generating a first result, and judging the risk category based on the first result; obtaining symptom information of patients undergoing tumor radiotherapy, assessing the severity of symptoms based on the symptom information, and generating a second result; performing symptom management based on the second result and the risk category, and generating prognosis data at the same time, and updating the first result through the prognosis data. Among them, performing prognosis assessment based on the basic information to generate the first result. The method comprises the following steps: constructing a patient feature matrix, standardizing and encoding the numerical features and categorical features in the basic information, respectively, to generate a standardized feature matrix; constructing a double contrast learning network to enhance the features of the standardized feature matrix, and generating an enhanced feature matrix; based on the enhanced feature matrix, performing prognosis assessment modeling through an integrated tree model and outputting the first result.

[0007] As a preferred embodiment of the method for symptom management and prognosis assessment of patients undergoing tumor radiotherapy described in the present invention, the basic information includes demographic characteristics, disease-related information, treatment-related information, medical history, and laboratory test results of patients undergoing tumor radiotherapy; the dual contrast learning network includes a global contrast learning module and a local contrast learning module.

[0008] As a preferred scheme of the method for symptom management and prognosis assessment of tumor radiotherapy patients described in the present invention, wherein: constructing a patient feature matrix, standardizing and encoding the numerical features and categorical features in the basic information respectively, and generating a standardized feature matrix, includes the following steps: constructing an original feature matrix, and dividing the features in the original feature matrix into numerical features and categorical features; applying time attenuation-based standardization to the numerical features, and applying weighted target encoding conversion to the categorical features; recombining the standardized numerical feature values ​​and the encoded categorical feature values ​​according to the corresponding positions of the original features to generate a standardized feature matrix.

[0009] Constructing a double contrast learning network to enhance the features of the standardized feature matrix and generate an enhanced feature matrix, including the following steps: calculating the Pearson correlation coefficient between every two features in the standardized feature matrix to generate a feature correlation coefficient matrix; traversing all the correlation coefficients in the feature correlation coefficient matrix, and dividing the features into first-category features and second-category features according to the absolute values ​​of the correlation coefficients; wherein the condition for satisfying the first-category features is that in the feature correlation coefficient matrix, there is at least one feature whose absolute value of the correlation coefficient is greater than a first preset threshold; the condition for satisfying the second-category features is that in the feature correlation coefficient matrix, the absolute values ​​of all the correlation coefficients are less than or equal to the first preset threshold; inputting the first-category features into the global contrast learning module to generate a global feature representation matrix; inputting the second-category features into the local contrast learning module to generate a local feature representation matrix; taking the ratio of the number of first-category features to the total number of features as the global feature weight; taking the ratio of the number of second-category features to the total number of features as the local feature weight; generating an enhanced feature matrix through feature concatenation operation according to the global feature representation matrix and the local feature representation matrix, the global feature weight, and the local feature weight.

[0010] Based on the enhanced feature matrix, prognosis assessment modeling is performed through an integrated tree model and a first result is output, comprising the following steps: for each enhanced feature in the enhanced feature matrix, a dual-path decision tree integrated model is constructed according to the corresponding value of each enhanced feature in the global feature representation matrix and the local feature representation matrix, as well as the global feature weight and the local feature weight: the product of the global feature weight and the corresponding enhanced feature value in the global feature representation matrix is ​​calculated, and the product of the local feature weight and the corresponding enhanced feature value in the local feature representation matrix is ​​calculated; the total variance, the intra-group variance and the inter-group variance of each enhanced feature in the enhanced feature matrix are calculated; the ratio of the intra-group variance to the total variance is compared with a second preset threshold The enhanced feature values ​​are compared to determine whether each enhanced feature value is in a feature stability interval; each enhanced feature in the enhanced feature matrix is ​​classified and judged: if the product of the global feature weight and the corresponding enhanced feature value in the global feature representation matrix is ​​greater than the product of the local feature weight and the corresponding enhanced feature value in the local feature representation matrix, and the enhanced feature value is in the feature stability interval, a depth-first decision tree is used for prediction; if the product of the local feature weight and the corresponding enhanced feature value in the local feature representation matrix is ​​greater than the product of the global feature weight and the corresponding enhanced feature value in the global feature representation matrix, or the enhanced feature value exceeds the feature stability interval, a breadth-first decision tree is used for prediction.

[0011] Calculate the weight coefficient of the depth-first decision tree and the weight coefficient of the breadth-first decision tree, multiply the prediction result of the depth-first decision tree by the weight coefficient of the depth-first decision tree, and add the product of the prediction result of the breadth-first decision tree and the weight coefficient of the breadth-first decision tree to obtain the survival probability prediction value, local recurrence risk prediction value, distant metastasis risk prediction value, and complication risk prediction value, respectively, to form the first result.

[0012] As a preferred embodiment of the method for symptom management and prognosis assessment of tumor radiotherapy patients described in the present invention, wherein: for each predicted value in the first result, the credibility calculation rule is as follows: calculate the confidence interval stability score of each predicted value; calculate the similarity score between the predicted distribution and the true distribution of each predicted value; according to the comparison result of the confidence interval stability score with the third preset threshold, and the comparison result of the similarity score with the fourth preset threshold and the fifth preset threshold, divide the credibility into four levels: when the confidence interval stability score is higher than the third preset threshold, and the similarity score is higher than the fifth preset threshold, the credibility is level 3; when the confidence interval stability score is higher than the third preset threshold, and the similarity score is higher than the fourth preset threshold but not higher than the fifth preset threshold, the credibility is level 2; when the confidence interval stability score is higher than the third preset threshold, the credibility is level 1; in other cases, the credibility is level 0.

[0013] As a preferred embodiment of the method for symptom management and prognosis assessment of patients undergoing radiotherapy for tumors described in the present invention, the risk category is determined according to the first result, including the following steps: calculating a comprehensive score of a predicted survival probability; calculating a comprehensive score of risk events based on a predicted local recurrence risk, a predicted distant metastasis risk and a predicted complication risk; weightedly combining the comprehensive score of the predicted survival probability with the comprehensive score of risk events, and calculating a final risk classification score in combination with the credibility, and dividing patients undergoing radiotherapy for tumors into three categories: low risk, medium risk and high risk: when the final risk classification score is greater than or equal to the sixth preset threshold and the credibility is greater than or equal to level 2, it is determined to be low risk; when the final risk classification score is greater than or equal to the seventh preset threshold and less than the sixth preset threshold, or the credibility is level 1, it is determined to be medium risk; when the final risk classification score is less than the seventh preset threshold, or the credibility is 0, it is determined to be high risk.

[0014] As a preferred embodiment of the method for symptom management and prognosis assessment of tumor radiotherapy patients described in the present invention, the symptom information includes symptom name, symptom onset time, symptom duration, symptom location and symptom manifestation; based on the symptom information, the symptom severity is assessed against the radiotherapy acute reaction grading standard to generate a second result including the symptom severity level.

[0015] As a preferred embodiment of the method for symptom management and prognosis assessment of tumor radiotherapy patients described in the present invention, wherein: symptom management is performed according to the second result and the risk category, and prognosis data is generated at the same time, and the first result is updated by the prognosis data, including the following steps: according to the symptom severity level and the risk category in the second result, the corresponding radiotherapy adjustment plan and nursing intervention measures are extracted from the supporting symptom management database; each treatment record collected by the radiotherapy treatment room and the symptom severity level are obtained to generate prognosis data containing symptom change trends; the treatment record includes actual irradiation dose, cumulative irradiation dose, symptom duration, and complication record; the prognosis data is standardized, and if there is data missing in the prognosis data, the missing value is filled; the standardized prognosis data is input into the double contrast learning network, if the similarity between the obtained new global feature representation matrix and the new local feature representation matrix is ​​lower than the similarity of the corresponding matrix in the enhanced feature matrix, the feature weight is recalculated and feature contrast learning is performed, the optimized enhanced feature matrix is ​​input into the dual-path decision tree integrated model, and the survival probability prediction value, local recurrence risk prediction value, distant metastasis risk prediction value and complication risk prediction value in the first result are updated.

[0016] To further solve the above-mentioned technical problems, the present invention provides the following technical solutions: a symptom management and prognosis assessment system for tumor radiotherapy patients, comprising: a prognosis assessment module, used to obtain basic information of tumor radiotherapy patients, perform prognosis assessment based on the basic information, generate a first result, and judge the risk category based on the first result; a symptom assessment module, used to obtain symptom information of tumor radiotherapy patients, evaluate the severity of symptoms based on the symptom information, and generate a second result; a dynamic management module, used to perform symptom management based on the second result and the risk category, and generate prognosis data at the same time, and update the first result through the prognosis data.

[0017] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and wherein when the processor executes the computer program, the steps of the above-mentioned method for symptom management and prognosis assessment of patients undergoing tumor radiotherapy are implemented.

[0018] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the above-mentioned method for symptom management and prognosis assessment of tumor radiotherapy patients are implemented.

[0019] Beneficial effects of the present invention: The present invention realizes dynamic correlation analysis and adaptive feature enhancement of multi-dimensional medical data of patients undergoing tumor radiotherapy by constructing an innovative architecture of a dual contrast learning network and a dual-path decision tree integrated model. The present invention can not only accurately quantify the patient's prognostic risk, but also realize personalized treatment plan adjustment based on symptom severity grading, and has the following significant advantages: First, the feature expression ability of heterogeneous medical data is improved by using time-attenuation-based standardized processing and weighted target coding conversion; second, through the synergistic effect of global and local contrast learning, the semantic correlation between features is enhanced, and the generalization performance of the model is improved; third, based on the integrated strategy of the dual-path decision tree and the multi-level credibility evaluation mechanism, the accuracy and reliability of the prediction results are significantly improved; finally, the dynamic prognosis data update mechanism enables the model to adaptively adjust the feature weights, realizes the continuous optimization of symptom management, and provides more scientific and accurate decision support for clinical practice. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0021] Figure 1 This is an overall flow chart of a method for symptom management and prognosis assessment of tumor radiotherapy patients proposed by the present invention; Figure 2 A computer device diagram of a method for symptom management and prognosis assessment of tumor radiotherapy patients proposed by the present invention. DETAILED DESCRIPTION

[0022] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0023] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0024] Example 1, reference Figure 1, which is an embodiment of the present invention, provides a method for symptom management and prognosis assessment of tumor radiotherapy patients.

[0025] In the relevant technologies, clinical symptom management of radiotherapy patients mainly relies on doctors' experience and judgment. This traditional method has limitations such as lack of standardization of symptom assessment, inaccurate prediction of prognosis risk, and insufficient mining of multi-dimensional medical data correlation. Although artificial intelligence technology has been widely used in the medical field in recent years, the existing machine learning methods still face problems such as feature engineering relying on manual experience, simple model structure, poor interpretability of prediction results, and inflexible update mechanism when processing heterogeneous medical data. Therefore, developing a technical solution that can comprehensively utilize multi-dimensional patient information to achieve accurate prognosis assessment and intelligent symptom management has become a clinical problem that needs to be solved urgently.

[0026] The present application provides an effective solution to the above-mentioned problems. Next, multiple embodiments will be combined to explain in detail how to implement the symptom management and prognosis assessment method for tumor radiotherapy patients.

[0027] Figure 1 The overall flow chart of a method for symptom management and prognosis assessment of patients undergoing radiotherapy for tumors is shown, including: S1: obtaining basic information of a patient undergoing tumor radiotherapy, performing a prognosis assessment based on the basic information, generating a first result, and determining a risk category based on the first result; S2: Acquire symptom information of patients undergoing tumor radiotherapy, evaluate the severity of the symptoms according to the symptom information, and generate a second result; S3: Perform symptom management according to the second result and the risk category, generate prognostic data, and update the first result through the prognostic data.

[0028] Next, this embodiment will elaborate on S1 to S3 one by one: S1: Obtain basic information of patients undergoing tumor radiotherapy, conduct prognosis assessment based on the basic information, generate a first result, and determine the risk category based on the first result.

[0029] S1.1 Obtain basic information of patients undergoing tumor radiotherapy.

[0030] Specifically, in one embodiment, the basic information of tumor radiotherapy patients can be: demographic characteristics of patients (such as age, gender, height, weight, etc.), disease-related information (such as tumor type, stage, pathological classification, tumor size and location, etc.), treatment-related information (such as radiotherapy plan, cumulative dose, fractionated dose, target range, etc.), past medical history (such as underlying diseases, surgical history, medication history, etc.), lifestyle (such as smoking and drinking history, eating habits, exercise habits, etc.) and laboratory test results (such as blood routine, biochemical indicators, tumor markers, etc.). This basic information can be collected through a variety of channels and methods: first, using the hospital's existing information system, such as the hospital information system (HIS) can provide patients' medical records, prescription information, etc., and the electronic medical record system (EMR) contains detailed records of the diagnosis and treatment process; second, through a specially designed information collection form, which should have standardized data item settings, support structured information entry, and be able to connect with the hospital's existing system; in addition, it can also be convenient for medical staff to supplement and update information at any time through the information collection interface of the mobile terminal APP or web page. All collected information needs to undergo standardized processing and quality control to ensure the accuracy and completeness of the data. These processed basic data will provide comprehensive and reliable data support for subsequent prognosis assessment and risk classification.

[0031] S1.2: Perform prognostic assessment based on basic information and generate the first result.

[0032] S1.2.1: Construct a patient feature matrix, standardize and encode the numerical features and categorical features in the patient's basic information, and generate a standardized feature matrix A.

[0033] Specifically, the basic information of the patient is first constructed into an original feature matrix X containing a demographic feature vector, a disease-related feature vector, a treatment-related feature vector, a medical history feature vector, a lifestyle feature vector, and a laboratory test feature vector: ; Where m is the number of patients to be evaluated; n is the number of features; x ij is the jth eigenvalue of the i-th patient to be evaluated.

[0034] The features in the original feature matrix X are divided into numerical features and categorical features.

[0035] It should be noted that numerical features include: age, height, and weight in the demographic feature vector, tumor size and tumor location coordinates in the disease-related feature vector, radiotherapy cumulative dose, fractionated dose, and target range values ​​in the treatment-related feature vector, and blood routine test values, biochemical index values, and tumor marker test values ​​in the laboratory test feature vector. Categorical features include: gender in the demographic feature vector, tumor type, stage, and pathological classification in the disease-related feature vector, basic disease type, surgical history type, and medication history type in the past medical history feature vector, and smoking and drinking type, eating habit type, and exercise habit type in the lifestyle feature vector.

[0036] Then, the numerical features in the original feature matrix X are normalized using the Z-score based on time decay: ; in, is the standardized value of the jth feature; is the original value of the jth feature of the patient to be evaluated; is the mean value of the jth characteristic of the patient to be evaluated; is the standard deviation of the jth feature of historical patients; is the current time point; The data collection time points for historical patients; is the time attenuation coefficient, and its value range is [0.1, 0.5].

[0037] The weighted target encoding conversion is used for the categorical features in the original feature matrix X: ; in, is the coded value of category c, is the target variable value of the rth historical patient in category c, is the historical number of patients in category c, is the time weight coefficient of the rth historical patient, calculated by the following formula: ; in, is the time weight attenuation coefficient, and its value range is [0.2, 0.6]; is the data collection time point for the rth historical patient.

[0038] Finally, the standardized numerical eigenvalues ​​and the categorical eigenvalues ​​after encoding conversion are recombined according to the corresponding positions of the original features to generate a standardized feature matrix A: ; in, is the jth standardized feature value of the i-th patient to be evaluated. If the jth feature is a numerical feature, then ; If the jth feature is a categorical feature, then .

[0039] It should be noted that in the actual application of prognosis assessment of tumor radiotherapy patients, firstly, the existing technology usually uses simple standardization or normalization methods to process numerical features, ignoring the timeliness characteristics of medical data, resulting in the same influence weight of new and old data on the model, and unable to reflect the dynamic change characteristics of the patient's status; secondly, for categorical features, traditional one-hot encoding (One-Hot Encoding) or label encoding (Label Encoding) methods cannot effectively utilize the inherent correlation information between categories, especially when dealing with categorical features with medical professional knowledge connotations such as disease classification and pathological grading, which often leads to information loss; thirdly, existing feature processing methods often separate different types of features (such as demographic characteristics, disease-related characteristics, treatment-related characteristics, etc.), and fail to fully consider the interactive relationship between features. In response to these problems, the present invention introduces a time-weighted Z-score standardization method, which not only maintains the numerical distribution characteristics of the features, but also gives higher weights to recent data through an exponential decay function, which more accurately reflects the patient's current status; at the same time, the weighted target coding conversion method provided by the present invention encodes the category features by using the prognosis information of historical patients, which not only retains the medical semantic information of the category, but also introduces time weights to balance the impact of new and old cases. This improvement brings about three significant effects: first, it improves the sensitivity of the model to changes in patient status, and the prediction accuracy is improved compared to traditional methods; second, through the time weighting mechanism, the prediction results are more in line with the empirical cognition in clinical practice that "recent cases have higher reference value", which improves the reliability of the model in practical applications; third, the weighted target coding method enables the prognostic information carried by the category features to be fully utilized.

[0040] S1.2.2: Construct a double contrastive learning network to enhance the features of the standardized feature matrix A and generate an enhanced feature matrix B.

[0041] The dual contrastive learning network includes a global contrastive learning module and a local contrastive learning module.

[0042] Among them, the loss function of the global contrastive learning module is: ; in, is the characteristic representation of the i-th patient to be evaluated; is the feature representation corresponding to the positive matching historical patient of the i-th patient to be evaluated; is the feature representation of the vth negative matching historical patient; is the cosine similarity function; is the global temperature parameter, ranging from [0.1, 1.0]; N is the number of negative matching historical patients.

[0043] Among them, the loss function of the local contrast learning module is: ; in, Representation of local features of the patient to be evaluated; is the local feature representation of the wth nearest historical patient; is the local feature representation of the zth non-neighbor historical patient; K is the number of neighbor historical patients; M is the number of non-neighbor historical patients; is the local temperature parameter, and its value range is [0.1, 1.0]; the value range of the preset threshold T1 is [0.3, 0.7].

[0044] Specifically, the Pearson correlation coefficient between every two features in the standardized feature matrix A is calculated to generate a feature correlation coefficient matrix.

[0045] Traverse all correlation coefficients in the feature correlation coefficient matrix, and divide the features into first-category features and second-category features according to the absolute value of the correlation coefficient. The condition for satisfying the first-category features is that in the feature correlation coefficient matrix, there is at least one feature whose absolute value of the correlation coefficient is greater than the first preset threshold; the condition for satisfying the second-category features is that in the feature correlation coefficient matrix, the absolute values ​​of all correlation coefficients are less than or equal to the first preset threshold.

[0046] The first type of features are input into the global contrast learning module to generate a global feature representation matrix; the second type of features are input into the local contrast learning module to generate a local feature representation matrix.

[0047] The ratio of the number of first-category features to the total number of features is taken as the global feature weight; the ratio of the number of second-category features to the total number of features is taken as the local feature weight.

[0048] According to the global feature representation matrix and the local feature representation matrix, the global feature weights and the local feature weights, an enhanced feature matrix B is generated through feature concatenation operation.

[0049] It should be noted that, firstly, traditional feature engineering methods often rely on artificial experience to design feature combinations, which is difficult to adapt to the rapidly updated medical knowledge in the field of tumor treatment; secondly, although existing automatic feature learning methods such as autoencoders or variational autoencoders can learn implicit representations of features, they often ignore the hierarchical and local correlations of medical data, resulting in the lack of interpretability of the learned feature representations; thirdly, the existing technology is susceptible to noise interference when dealing with high-dimensional and sparse medical features, and it is difficult to extract truly valuable feature associations. In response to these problems, the present invention proposes a dual contrast learning network architecture, which realizes adaptive enhancement of features through contrast learning modules at both global and local levels. Among them, the global contrast learning module learns the overall correlation pattern between features by comparing positive and negative sample pairs; the local contrast learning module focuses on the feature differences between neighboring patients and captures the local feature structure. The dual contrast learning mechanism can automatically discover and enhance feature combinations that are valuable for prognosis prediction, avoiding the limitations of artificial feature engineering in traditional methods and improving feature representation capabilities; secondly, the scope of action of the two modules is dynamically adjusted through the correlation coefficient threshold, thereby achieving the adaptability of feature enhancement and enabling the model to better handle different types of medical features; thirdly, the feature enhancement method based on contrastive learning provides a clear explanation of feature importance. By analyzing the comparison results of positive and negative sample pairs, doctors can intuitively understand which feature combinations have a key impact on the prediction results, significantly improving the clinical interpretability and credibility of the model.

[0050] S1.2.3: Based on the enhanced feature matrix B, the prognostic evaluation model is performed through the enhanced feature adaptive ensemble tree model and the first result is output.

[0051] Specifically, for each enhanced feature in the enhanced feature matrix, a dual-path decision tree integration model is constructed according to the corresponding values ​​of each enhanced feature in the global feature representation matrix and the local feature representation matrix, as well as the global feature weight and the local feature weight: First, the product of the global feature weight and the corresponding enhanced eigenvalue in the global feature representation matrix, as well as the product of the local feature weight and the corresponding enhanced eigenvalue in the local feature representation matrix are calculated.

[0052] Secondly, the total variance, intra-group variance and inter-group variance of each enhanced feature in the enhanced feature matrix are calculated; the ratio of the intra-group variance to the total variance is compared with a second preset threshold to determine whether each enhanced feature value is in a feature stability interval.

[0053] Then, each enhanced feature in the enhanced feature matrix is ​​classified and judged: if the product of the global feature weight and the corresponding enhanced feature value in the global feature representation matrix is ​​greater than the product of the local feature weight and the corresponding enhanced feature value in the local feature representation matrix, and the enhanced feature value is within the feature stability interval, the depth-first decision tree is used for prediction; if the product of the local feature weight and the corresponding enhanced feature value in the local feature representation matrix is ​​greater than the product of the global feature weight and the corresponding enhanced feature value in the global feature representation matrix, or the enhanced feature value exceeds the feature stability interval, the breadth-first decision tree is used for prediction.

[0054] Next, the depth-first decision tree weight coefficient and the breadth-first decision tree weight coefficient are calculated: the depth-first decision tree weight coefficient is the sum of the global feature weights of all enhanced features in the enhanced feature matrix B divided by the sum of the global feature weights and local feature weights of all enhanced features; the breadth-first decision tree weight coefficient is 1 minus the depth-first decision tree weight coefficient.

[0055] Finally, the prediction result of the depth-first decision tree is multiplied by the weight coefficient of the depth-first decision tree, and the product of the prediction result of the breadth-first decision tree and the weight coefficient of the breadth-first decision tree is added to obtain the first result.

[0056] Furthermore, the first result includes the predicted values ​​of 6-month, 12-month and 24-month survival probability, the predicted values ​​of local recurrence risk, the predicted values ​​of distant metastasis risk, and the predicted values ​​of the occurrence risk of complications (which may be the three most common complications, such as infectious complications, cardiovascular complications and respiratory complications). It should be noted that for each predicted value in the first result, its credibility is determined according to the following rules: First, the confidence interval stability score for each predicted value is calculated by subtracting the difference between the upper and lower limits of the confidence interval for each predicted value from each predicted value, and then dividing by each predicted value; Secondly, the similarity score between the predicted distribution and the true distribution of each predicted value is calculated, specifically, the negative exponent of the KL divergence between the predicted distribution and the true distribution is calculated; Finally, according to the comparison result of the confidence interval stability score with the third preset threshold, and the comparison result of the similarity score with the fourth preset threshold and the fifth preset threshold (wherein the fifth preset threshold is greater than the fourth preset threshold), the credibility is divided into four levels: When the confidence interval stability score is higher than the third preset threshold and the similarity score is higher than the fifth preset threshold, the credibility is level 3; When the confidence interval stability score is higher than the third preset threshold, and the similarity score is higher than the fourth preset threshold but not higher than the fifth preset threshold, the credibility is level 2; When the confidence interval stability score is higher than the third preset threshold, the credibility is level 1; In other cases, the credibility is level 0.

[0057] Preferably, in tumor prognosis assessment, the present invention realizes the dynamic weighing and adaptive feature selection of global-local features through a dual-path decision tree integrated model. Specifically, by determining the feature stability by the ratio of the intra-group variance to the total variance, and combining the comparison of the global-local feature weights, the present invention realizes an intelligent switching mechanism that gives priority to global representation (depth first) in the stable interval and emphasizes local representation (breadth first) in the unstable interval. This mechanism can not only effectively cope with the heterogeneity of individualized characteristics of tumor patients, but also adaptively adjust the prediction strategy. In addition, the present invention introduces a multi-level credibility evaluation mechanism based on confidence interval stability and distribution similarity, and provides a more fine-grained reliability guarantee for the prediction results through the similarity threshold constraints of the two dimensions of the validation set and the training set. The present invention significantly improves the robustness and interpretability of the prognosis evaluation model in heterogeneous data scenarios, and provides a more reliable quantitative reference for clinical decision-making.

[0058] S1.3: Determine the risk category based on the first result.

[0059] First, the comprehensive score of the predicted survival probability was calculated. Specifically, the 24-month predicted survival probability was used as the benchmark score. When the decline rate of the 12-month and 6-month predicted survival probability exceeded the decline rate threshold, the benchmark score was multiplied by the weighted penalty coefficient.

[0060] The comprehensive score of the predicted value of survival probability is expressed as: ; in, is the composite score of the predicted value of survival probability; is the predicted value of 24-month survival probability (i.e., the benchmark score); P is the penalty coefficient.

[0061] The penalty coefficient P is calculated by the following formula: ; in, is the rate of decrease in the probability of survival at 12 months; is the rate of decrease in the probability of survival at 6 months; is the descent rate threshold, used to determine whether the descent rate exceeds the standard; It is the penalty adjustment coefficient, with a value range of (0,1), which is used to adjust the penalty intensity for exceeding the drop rate.

[0062] The descent rate is calculated using the following formula: ; ; in, It is the predicted value of 12-month survival probability; The predicted value of 6-month survival probability.

[0063] Secondly, based on the risk prediction values ​​of local recurrence, distant metastasis and complications (infectious complications, cardiovascular complications, respiratory complications), the comprehensive score of risk events was calculated. Specifically, all risk prediction values ​​were weighted and summed up, and the weights were determined according to the impact of each risk event on survival.

[0064] Calculation of comprehensive risk event scores: ; ; Among them, RS is the comprehensive score of risk events; is the weight coefficient corresponding to each risk prediction value (k=1,2,3,4,5); Refers to the risk prediction value of local recurrence, the risk prediction value of distant metastasis and the risk prediction value of complications (infectious complications, cardiovascular complications, respiratory complications). :Prediction value of local recurrence risk, :Prediction value of distant metastasis risk, :Prediction value of infectious complication risk, :Prediction value of cardiovascular complication risk, : Risk prediction value of respiratory complications.

[0065] Finally, the survival probability prediction value is combined into a score The final risk classification score is calculated by weighted combination with the comprehensive score of risk events RS, combined with the credibility level of each prediction value, and tumor radiotherapy patients are divided into three categories: low risk, medium risk and high risk.

[0066] Specifically, the final risk classification score calculation is: ; Among them, FS is the final risk classification score; is the survival probability weight, with a value range of (0.5, 1), which is used to balance the impact of survival probability and risk events.

[0067] When the final risk classification score FS is greater than or equal to the sixth preset threshold T2, and the credibility is greater than or equal to level 2, it is judged as low risk; when the final risk classification score FS is greater than or equal to the seventh preset threshold T3 and less than the sixth preset threshold T2, or the credibility is level 1, it is judged as medium risk; when the final risk classification score FS is less than the seventh preset threshold T3, or the credibility = 0, it is judged as high risk.

[0068] S2: Obtain symptom information of patients undergoing tumor radiotherapy, evaluate the severity of the symptoms based on the symptom information, and generate a second result.

[0069] Specifically, the symptom information includes the symptom name, symptom onset time, symptom duration, symptom location and symptom manifestation.

[0070] Based on the symptom information, the severity of symptoms was assessed against the criteria for grading acute effects of radiation therapy, and a second outcome including the symptom severity grade was generated.

[0071] It should be noted that the grading standards for acute reactions to radiotherapy can be: 1. RTOG / EORTC grading standards for acute reactions to radiotherapy; 2. CTCAE (Common Terminology Criteria for Adverse Events) adverse reaction grading standards; 3. WHO grading standards for adverse reactions to radiotherapy; 4. NCI-CTC (National Cancer Institute Common Toxicity Criteria) toxic reaction grading standards.

[0072] S3: Perform symptom management based on the second result and risk category, generate prognostic data, and update the first result through the prognostic data.

[0073] S3.1: Based on the symptom severity level and risk category in the second result, extract the corresponding radiotherapy adjustment plan and nursing intervention measures from the supporting symptom management database.

[0074] S3.2: Obtain the treatment records and symptom severity levels collected by the radiotherapy treatment room to generate prognostic data including symptom trends.

[0075] Among them, treatment records include actual radiation dose, cumulative radiation dose, symptom duration, and complication records.

[0076] S3.3: Convert the format of the prognostic data, specifically standardize the prognostic data, fill in the missing values ​​if there are missing data in the prognostic data; input the standardized prognostic data into the double contrast learning network, if the similarity between the new global feature representation matrix and the new local feature representation matrix is ​​lower than the similarity of the corresponding matrix in the enhanced feature matrix, recalculate the feature weights and perform feature contrast learning, input the optimized enhanced feature matrix into the dual-path decision tree integration model, and update the survival probability prediction value, local recurrence risk prediction value, distant metastasis risk prediction value and complication risk prediction value in the first result.

[0077] Preferably, in existing radiotherapy, patient symptom management mainly relies on empirical judgment and single symptom severity assessment, which makes it difficult to effectively grasp the correlation between symptom change trends and treatment prognosis, and lacks a flexible treatment plan adjustment mechanism. The present invention realizes the dynamic association between symptom information and prognosis prediction through the synergistic effect of the double contrast learning network and the dual-path decision tree integrated model: first, timely treatment plan adjustments are made based on symptom severity levels and risk categories to ensure treatment safety; secondly, multi-dimensional information such as irradiation dose and symptom changes during treatment is converted into standardized prognosis data; finally, through the feature similarity comparison mechanism, the feature weight is optimized in time when the quality of feature representation is found to be reduced, so that the prognosis prediction results can be dynamically updated with symptom changes, which greatly improves the accuracy of prognosis evaluation and the scientific nature of treatment plan adjustment during radiotherapy, and provides effective technical support for the clinical realization of precise and personalized radiotherapy management.

[0078] In summary, the present invention realizes dynamic correlation analysis and adaptive feature enhancement of multi-dimensional medical data of tumor radiotherapy patients by constructing an innovative architecture of dual contrast learning network and dual-path decision tree integrated model. The present invention can not only accurately quantify the prognosis risk of patients, but also realize personalized treatment plan adjustment based on symptom severity classification, and has the following significant advantages: First, the feature expression ability of heterogeneous medical data is improved by using time-attenuation-based standardization processing and weighted target coding conversion; second, through the synergy of global and local contrast learning, the semantic correlation between features is enhanced, and the generalization performance of the model is improved; third, based on the integrated strategy of dual-path decision trees and multi-level credibility evaluation mechanism, the accuracy and reliability of prediction results are significantly improved; finally, the dynamic prognosis data update mechanism enables the model to adaptively adjust the feature weights, realize the continuous optimization of symptom management, and provide more scientific and accurate decision support for clinical practice.

[0079] Embodiment 2 is an embodiment of the present invention, which provides a symptom management and prognosis assessment system for tumor radiotherapy patients, which is composed of a prognosis assessment module, a symptom assessment module and a dynamic management module.

[0080] The prognosis assessment module is used to obtain basic information of patients undergoing tumor radiotherapy, perform prognosis assessment based on the basic information, generate a first result, and determine the risk category based on the first result; the symptom assessment module is used to obtain symptom information of patients undergoing tumor radiotherapy, evaluate the severity of symptoms based on the symptom information, and generate a second result; the dynamic management module is used to perform symptom management based on the second result and risk category, and generate prognosis data at the same time, and update the prognosis assessment result through the prognosis data.

[0081] Example 3, reference Figure 2, is an embodiment of the present invention, which is different from the previous embodiment in that: if the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0082] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0083] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0084] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0085] Example 4 is an embodiment of the present invention, which provides a method for symptom management and prognosis assessment of tumor radiotherapy patients. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0086] To verify the effectiveness of the present invention, 120 patients with tumor radiotherapy admitted to the radiotherapy department of a tertiary hospital from January 2023 to December 2023 were selected as research subjects. First, the basic information of the patients was collected through the hospital information system, including age, gender, BMI index, KPS score, tumor stage, pathological type, radiotherapy plan dose, etc. The numerical features were processed using a standardized processing method based on time attenuation, and the attenuation coefficient was set to 0.85. At the same time, the categorical features were converted using a weighted target coding method, and the coding weights were determined based on feature importance analysis.

[0087] A dual contrastive learning network was constructed, in which the global contrastive learning module adopted a three-layer fully connected neural network structure, with 256, 128 and 64 hidden layer neurons, and the activation function was ReLU; the local contrastive learning module adopted a two-layer convolutional neural network enhanced by the attention mechanism, with a convolution kernel size of 3×3 and a step size of 1. The first preset threshold was set to 0.6 to distinguish global features from local features. Feature correlation analysis showed that 45% of the features belonged to the first category of features (global features) and 55% belonged to the second category of features (local features). In the dual-path decision tree ensemble model, the maximum depth of the depth-first decision tree was set to 8, and the minimum number of sample splits was 5; the maximum depth of the breadth-first decision tree was 5, and the minimum number of sample splits was 8. The second preset threshold was set to 0.3 to judge feature stability.

[0088] The subjects were randomly divided into an experimental group (60 cases) and a control group (60 cases). The experimental group used the method of the present invention for prognosis assessment and symptom management, and the control group used the traditional assessment method. There was no statistical difference between the two groups in baseline characteristics such as age, gender, and disease stage (p>0.05). All patients completed an 8-week follow-up observation.

[0089] Table 1 Comparison of model performance evaluation indicators Evaluation Metrics Experimental group results Results of the control group Increase (%) P-value Prediction accuracy (%) 92.5 77.8 18.9 <0.001 Specificity(%) 90.8 75.2 20.7 <0.001 Sensitivity(%) 91.2 76.5 19.2 <0.001 AUC value 0.915 0.782 17.0 <0.001 F1 score 0.898 0.742 21.0 <0.001 Kappa coefficient 0.885 0.728 21.6 <0.001 As shown in Table 1, the present invention shows significant performance improvement in all six core evaluation indicators compared with the prior art. The prediction accuracy was increased from 77.8% to 92.5% (p<0.001), and the specificity and sensitivity reached 90.8% and 91.2%, respectively, which were 20.7% and 19.2% higher than the control group, respectively, fully demonstrating the advantages of the double contrast learning network in feature enhancement. The AUC value reached 0.915, an increase of 17.0% compared with the control group, indicating that the model has excellent classification ability. The significant improvement of the F1 score and the Kappa coefficient (increased by 21.0% and 21.6%, respectively) further verified the accuracy and consistency of the model prediction results. The p values ​​of all evaluation indicators were less than 0.001, which was highly statistically significant, confirming the outstanding advantages of the present invention in predictive performance.

[0090] Table 2 Comparison of symptom management effects Observation indicators Before treatment 2 weeks of treatment 4 weeks of treatment Treatment for 6 weeks 8 weeks of treatment Improvement rate (%) P-value Incidence of radiation dermatitis (%) 0 15.2 28.5 32.1 25.4 21.3 <0.001 The incidence of radiation stomatitis (%) 0 12.8 25.6 28.9 20.1 23.5 <0.001 Incidence of dysphagia (%) 0 10.5 22.3 25.7 18.2 25.8 <0.001 Fatigue score 2.5 3.2 4.1 3.8 2.9 28.4 <0.001 Quality of life score 75.2 72.1 69.8 71.5 76.8 31.2 <0.001 As shown in Table 2, through the analysis of dynamic monitoring data throughout the treatment (8 weeks), it was found that the incidence of the three major radiological complications showed a trend of first increasing and then decreasing, and the peak value was significantly lower than the level reported in the literature. The incidence of radiation dermatitis increased from 15.2% in 2 weeks to 32.1% in 6 weeks and then decreased to 25.4% in 8 weeks, with an overall improvement rate of 21.3%. The incidence trends of radiation stomatitis and dysphagia were similar, with improvement rates of 23.5% and 25.8%, respectively. The highest point of fatigue score appeared in the fourth week of treatment (4.1 points), and then gradually improved, with an overall improvement rate of 28.4%. Although the quality of life score decreased in the middle of the treatment, it rebounded significantly to 76.8 points in the later stage of the treatment, an increase of 31.2% from the lowest point. The improvement of all indicators was statistically significant (p<0.001), indicating that the present invention has significant clinical value in symptom management.

[0091] Table 3 Evaluation of clinical application effect Clinical indicators Experimental Group Control group Difference P-value Treatment plan completion rate (%) 94.5 85.2 9.3 <0.001 Treatment compliance (%) 92.8 78.5 14.3 <0.001 Timely intervention rate of adverse reactions (%) 93.6 76.9 16.7 <0.001 Patient satisfaction rating 92.1 77.8 14.3 <0.001 Hospitalization days (days) 18.5 25.8 -7.3 <0.001 As shown in Table 3, the clinical application effect evaluation data show that the present invention significantly reduces the consumption of medical resources while improving the treatment effect. The treatment plan completion rate (94.5%) and treatment compliance (92.8%) of the experimental group were 9.3 and 14.3 percentage points higher than those of the control group, respectively, and the timely intervention rate of adverse reactions increased by 16.7%. These improvements directly reflect the clinical value of the intelligent management system. In terms of medical resource utilization, the average length of stay in the experimental group was shortened by 7.3 days. The patient satisfaction score increased by 14.3 points to 92.1 points, which comprehensively reflects the advantages of the present invention in improving the quality of medical services and patient experience. The differences in all indicators were statistically significant (p<0.001), which fully confirmed the comprehensive advantages of the present invention in clinical practice.

[0092] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for symptom management and prognosis assessment in patients undergoing radiotherapy for tumors, characterized in that: include: Obtaining basic information of a patient undergoing tumor radiotherapy, performing a prognosis assessment based on the basic information, generating a first result, and determining a risk category based on the first result; Acquiring symptom information of a patient undergoing radiotherapy for a tumor, assessing the severity of the symptoms according to the symptom information, and generating a second result; performing symptom management according to the second result and the risk category, generating prognostic data, and updating the first result by using the prognostic data; The process of performing a prognosis assessment according to the basic information to generate a first result includes the following steps: Constructing a patient feature matrix, standardizing and encoding the numerical features and categorical features in the basic information, respectively, to generate a standardized feature matrix; Constructing a double contrast learning network to perform feature enhancement on the standardized feature matrix to generate an enhanced feature matrix; Based on the enhanced feature matrix, prognostic evaluation modeling is performed through an integrated tree model and a first result is output.

2. The method for symptom management and prognosis assessment of tumor radiotherapy patients according to claim 1, characterized in that: The basic information includes demographic characteristics, disease-related information, treatment-related information, past medical history, and laboratory test results of tumor radiotherapy patients; the dual contrast learning network includes a global contrast learning module and a local contrast learning module.

3. The method for symptom management and prognosis assessment of tumor radiotherapy patients according to claim 2, characterized in that: Constructing a patient feature matrix, standardizing and encoding the numerical features and categorical features in the basic information, and generating a standardized feature matrix, including the following steps: Constructing an original feature matrix, and dividing the features in the original feature matrix into numerical features and categorical features; The numerical features are normalized based on time decay, and the categorical features are converted to weighted target encoding; The standardized numerical eigenvalues ​​and the categorical eigenvalues ​​after coding conversion are recombined according to the corresponding positions of the original features to generate a standardized feature matrix; Constructing a double contrast learning network to perform feature enhancement on the standardized feature matrix to generate an enhanced feature matrix includes the following steps: Calculating the Pearson correlation coefficient between every two features in the standardized feature matrix to generate a feature correlation coefficient matrix; Traversing all correlation coefficients in the feature correlation coefficient matrix, and dividing the features into first-category features and second-category features according to the absolute values ​​of the correlation coefficients; wherein the condition for satisfying the first-category features is that in the feature correlation coefficient matrix, there is at least one feature whose absolute value of the correlation coefficient is greater than a first preset threshold; the condition for satisfying the second-category features is that in the feature correlation coefficient matrix, the absolute values ​​of all the correlation coefficients are less than or equal to the first preset threshold; Inputting the first type of features into the global contrast learning module to generate a global feature representation matrix; inputting the second type of features into the local contrast learning module to generate a local feature representation matrix; The ratio of the number of first-category features to the total number of features is used as the global feature weight; the ratio of the number of second-category features to the total number of features is used as the local feature weight; Generate an enhanced feature matrix through feature concatenation operation according to the global feature representation matrix and the local feature representation matrix, the global feature weights, and the local feature weights; Based on the enhanced feature matrix, prognostic evaluation modeling is performed through an integrated tree model and a first result is output, comprising the following steps: For each enhanced feature in the enhanced feature matrix, a dual-path decision tree integration model is constructed according to the corresponding value of each enhanced feature in the global feature representation matrix and the local feature representation matrix, as well as the global feature weight and the local feature weight: Calculating the product of the global feature weight and the corresponding enhanced eigenvalue in the global feature representation matrix, and the product of the local feature weight and the corresponding enhanced eigenvalue in the local feature representation matrix; Calculating the total variance, the intra-group variance and the inter-group variance of each enhanced feature in the enhanced feature matrix; comparing the ratio of the intra-group variance to the total variance with a second preset threshold to determine whether each enhanced feature value is in a feature stability interval; Classify and judge each enhanced feature in the enhanced feature matrix: if the product of the global feature weight and the corresponding enhanced feature value in the global feature representation matrix is ​​greater than the product of the local feature weight and the corresponding enhanced feature value in the local feature representation matrix, and the enhanced feature value is within the feature stability interval, then use the depth-first decision tree for prediction; if the product of the local feature weight and the corresponding enhanced feature value in the local feature representation matrix is ​​greater than the product of the global feature weight and the corresponding enhanced feature value in the global feature representation matrix, or the enhanced feature value exceeds the feature stability interval, then use the breadth-first decision tree for prediction; Calculate the weight coefficient of the depth-first decision tree and the weight coefficient of the breadth-first decision tree, multiply the prediction result of the depth-first decision tree by the weight coefficient of the depth-first decision tree, and add the product of the prediction result of the breadth-first decision tree and the weight coefficient of the breadth-first decision tree to obtain the survival probability prediction value, local recurrence risk prediction value, distant metastasis risk prediction value, and complication risk prediction value, respectively, to form the first result.

4. The method for symptom management and prognosis assessment of tumor radiotherapy patients according to claim 3, characterized in that: For each predicted value in the first result, the credibility calculation rule is as follows: Calculate the confidence interval stability score for each predicted value; Calculate the similarity score between the predicted distribution and the true distribution for each predicted value; According to the comparison result of the confidence interval stability score with the third preset threshold, and the comparison result of the similarity score with the fourth preset threshold and the fifth preset threshold, the credibility is divided into four levels: When the confidence interval stability score is higher than the third preset threshold and the similarity score is higher than the fifth preset threshold, the credibility is level 3; When the confidence interval stability score is higher than the third preset threshold, and the similarity score is higher than the fourth preset threshold but not higher than the fifth preset threshold, the credibility is level 2; When the confidence interval stability score is higher than the third preset threshold, the credibility is level 1; In other cases, the credibility is level 0.

5. The method for symptom management and prognosis assessment of tumor radiotherapy patients according to claim 4, characterized in that: Determining the risk category according to the first result includes the following steps: Calculate the composite score of the predicted value of survival probability; The comprehensive score of risk events was calculated based on the risk prediction values ​​of local recurrence, distant metastasis, and complications. The survival probability prediction value composite score and the risk event composite score are weighted and combined with the credibility to calculate the final risk classification score, and tumor radiotherapy patients are divided into three categories: low risk, medium risk and high risk: When the final risk classification score is greater than or equal to the sixth preset threshold, and the credibility is greater than or equal to level 2, it is judged as low risk; When the final risk classification score is greater than or equal to the seventh preset threshold and less than the sixth preset threshold, or the credibility is level 1, it is judged as medium risk; when the final risk classification score is less than the seventh preset threshold, or the credibility is 0, it is judged as high risk.

6. The method for symptom management and prognosis assessment of tumor radiotherapy patients according to claim 5, characterized in that: The symptom information includes symptom name, symptom onset time, symptom duration, symptom location and symptom manifestation; According to the symptom information, the symptom severity is evaluated according to the radiation therapy acute reaction grading standard to generate a second result including the symptom severity level.

7. The method for symptom management and prognosis assessment of tumor radiotherapy patients according to claim 6, characterized in that: Performing symptom management according to the second result and the risk category, generating prognostic data, and updating the first result by using the prognostic data, comprises the following steps: According to the symptom severity level and the risk category in the second result, extracting corresponding radiotherapy adjustment plans and nursing intervention measures from a supporting symptom management database; Obtaining each treatment record collected by the radiotherapy treatment room and the symptom severity level, and generating prognostic data including the symptom change trend; the treatment record includes the actual irradiation dose, the cumulative irradiation dose, the symptom duration, and the complication record; The prognostic data are standardized, and if there are missing data in the prognostic data, the missing values ​​are filled; the standardized prognostic data are input into the double contrast learning network, and if the similarity between the obtained new global feature representation matrix and the new local feature representation matrix is ​​lower than the similarity of the corresponding matrix in the enhanced feature matrix, the feature weights are recalculated and feature contrast learning is performed, and the optimized enhanced feature matrix is ​​input into the dual-path decision tree integrated model, and the survival probability prediction value, local recurrence risk prediction value, distant metastasis risk prediction value and complication risk prediction value in the first result are updated.

8. A system using the method for symptom management and prognosis assessment of tumor radiotherapy patients as described in any one of claims 1 to 7, characterized in that: include: A prognosis assessment module, used to obtain basic information of patients undergoing tumor radiotherapy, perform prognosis assessment based on the basic information, generate a first result, and determine the risk category based on the first result; A symptom assessment module, used to obtain symptom information of patients undergoing tumor radiotherapy, assess the severity of symptoms based on the symptom information, and generate a second result; A dynamic management module is used to perform symptom management according to the second result and the risk category, generate prognostic data, and update the first result through the prognostic data.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for symptom management and prognosis assessment of tumor radiotherapy patients described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for symptom management and prognosis assessment of tumor radiotherapy patients described in any one of claims 1 to 7 are implemented.

Images