Early warning method for myelosuppression risk caused by treatment and related equipment

Abstract

The invention provides a treatment-caused myelosuppression risk early warning method and related equipment, and is applied to the technical field of data processing. The method comprises the following steps: processing multi-modal data information of a target user to generate a target physiological state prediction factor; processing the serum marker feature information of the target user to generate myelosuppression influence factors; processing the living habit information of the target user to generate a myelosuppression risk adjustment factor; processing the myelosuppression influence factor and the myelosuppression risk adjustment factor to generate dynamic risk parameter information of the target user; and processing the target physiological status prediction factor and the dynamic risk parameter information of the target user based on a target large-dose methotrexate bone marrow suppression risk prediction model to generate a bone marrow suppression risk value and a bone marrow transplantation risk level.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method for early warning of risk of bone marrow suppression caused by treatment and related equipment. Background Art

[0002] In the field of tumor treatment, high-dose methotrexate (HDMTX) is a drug commonly used in first-line chemotherapy for diseases such as acute lymphoblastic leukemia, non-Hodgkin's lymphoma, and osteosarcoma. However, the bone marrow suppression caused by it cannot be ignored. According to literature reports, the incidence of bone marrow suppression caused by HDMTX can be as high as 32%.

[0003] Early identification and prediction of individuals at high risk of adverse events after using such drugs is crucial to ensure the safety of users and subsequent conditions. However, the current prediction models for adverse events related to this drug have significant defects. Most of these models are based on data from a single source, and the number of samples is extremely limited, which makes the model prone to overfitting and greatly weakens its applicability in different scenarios. For example, common research samples are only dozens to hundreds of cases. Although a few larger-scale studies have a certain sample size, the data source is limited to the same region and cannot fully cover individual characteristics in different environments. In addition, the existing prediction models mainly focus on the prediction of a specific adverse condition (similar to delayed clearance), and there is little research on the problem of bone marrow suppression, which has a higher incidence, and it is difficult to meet the urgent need for bone marrow suppression risk assessment in practical applications.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of this application is to provide a method and related equipment for early warning of the risk of bone marrow suppression caused by treatment, which at least overcomes the problems existing in the prior art to a certain extent, by obtaining multiple types of information of the target user, such as multimodality, serum markers, lifestyle habits, medication information, models and samples. Then, in data processing, multimodal data is converted to generate target physiological state prediction factors, serum information is processed to obtain bone marrow suppression influencing factors, and lifestyle information is used to obtain risk adjustment factors and combine to generate dynamic risk parameters. When constructing the model, the sampling ratio is determined from the training samples, and the training and verification are performed to obtain the target model. Finally, the target model is used to fuse the relevant factors, and the bone marrow suppression risk value and level are calculated, and effective early warning is achieved by comprehensive consideration of the parameters of each factor.

[0006] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present invention.

[0007] According to one aspect of the present application, a method for early warning of myelosuppression risk caused by treatment is provided, comprising: obtaining multimodal data information of a target user, serum marker characteristic information of the target user, life habit information of the target user, medication information of the target user, a preset high-dose methotrexate myelosuppression risk prediction model and a training sample set, wherein the multimodal data information of the target user includes the target user's age, weight, blood creatinine, BMI, height, red blood cell count, lymphocyte count, potassium, urine white blood cells, high-density lipoprotein, magnesium and uric acid; processing the multimodal data information of the target user to generate a target physiological state prediction factor; processing the serum marker characteristic information of the target user to generate a target physiological state prediction factor; The target user's characteristic information is processed to generate a bone marrow suppression influencing factor; the target user's living habit information is processed to generate a bone marrow suppression risk adjustment factor; the bone marrow suppression influencing factor and the bone marrow suppression risk adjustment factor are processed to generate dynamic risk parameter information of the target user; based on the training sample set, the preset high-dose methotrexate bone marrow suppression risk prediction model is processed to generate a target high-dose methotrexate bone marrow suppression risk prediction model; based on the target high-dose methotrexate bone marrow suppression risk prediction model, the target physiological state prediction factor and the target user's dynamic risk parameter information are processed to generate a bone marrow suppression risk value and a bone marrow transplantation risk level.

[0008] Another aspect of the present application is a device for early warning of the risk of myelosuppression caused by treatment, characterized in that it includes: an acquisition module for acquiring multimodal data information of a target user, serum marker characteristic information of the target user, life habit information of the target user, medication information of the target user, a preset high-dose methotrexate myelosuppression risk prediction model and a training sample set, wherein the multimodal data information of the target user includes the target user's age, weight, blood creatinine, BMI, height, red blood cell count, lymphocyte count, potassium, urine white blood cells, high-density lipoprotein, magnesium and uric acid; a processing module for processing the multimodal data information of the target user to generate a target physiological state prediction factor; and a processing module for processing the multimodal data information of the target user to generate a target physiological state prediction factor. The target user's serum marker characteristic information is processed to generate a bone marrow suppression influencing factor; the target user's living habit information is processed to generate a bone marrow suppression risk adjustment factor; the bone marrow suppression influencing factor and the bone marrow suppression risk adjustment factor are processed to generate dynamic risk parameter information of the target user; based on the training sample set, the preset high-dose methotrexate bone marrow suppression risk prediction model is processed to generate a target high-dose methotrexate bone marrow suppression risk prediction model; based on the target high-dose methotrexate bone marrow suppression risk prediction model, the target physiological state prediction factor and the target user's dynamic risk parameter information are processed to generate a bone marrow suppression risk value and a bone marrow transplantation risk level.

[0009] According to another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a second processor, the above-mentioned method for early warning of the risk of bone marrow suppression caused by treatment is implemented.

[0010] The present application provides a method for early warning of the risk of bone marrow suppression caused by treatment and related equipment, and the server obtains multiple types of information of the target user, such as multimodality, serum markers, lifestyle habits, medication information, models and samples. Then in the data processing, the multimodal data is converted to generate the target physiological state prediction factor, the serum information is processed to obtain the bone marrow suppression influencing factor, and the lifestyle information is used to obtain the risk adjustment factor and combine to generate dynamic risk parameters. When the model is constructed, the sampling ratio is determined from the training sample, and the training and verification are performed to obtain the target model. Finally, the target model is used to fuse the relevant factors, and the bone marrow suppression risk value and level are calculated, and effective early warning is achieved by comprehensive consideration of the parameters of each factor.

[0011] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A flow chart showing a method for early warning of risk of bone marrow suppression caused by treatment provided by an embodiment of the present application;

[0013] Figure 2 A schematic structural diagram of a device for early warning of risk of bone marrow suppression caused by treatment provided in one embodiment of the present application is shown. DETAILED DESCRIPTION

[0014] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0015] Combine the following Figure 1 The following describes a method for early warning of myelosuppression risk caused by treatment according to an exemplary embodiment of the present application. In one embodiment, the present application also proposes a method for early warning of myelosuppression risk caused by treatment and related equipment. Figure 1 The flowchart of a method for early warning of the risk of myelosuppression caused by treatment according to an embodiment of the present application is schematically shown. Figure 1 As shown, the method is applied to a server, comprising:

[0016] S101, obtaining multimodal data information of a target user, serum marker characteristic information of a target user, life habit information of a target user, medication information of a target user, a preset high-dose methotrexate bone marrow suppression risk prediction model, and a training sample set.

[0017] In one embodiment, it is assumed that the target user is a 55-year-old male. Age is an important physiological characteristic. In the risk assessment of bone marrow suppression, different age groups have different tolerance to drugs. With the increase of age, various functions of the body gradually decline, and the hematopoietic function of the bone marrow is also affected to a certain extent. The tolerance to high-dose methotrexate decreases, thereby increasing the risk of bone marrow suppression. The user weighs 70 kg. The relative relationship between body weight and drug dosage is of great significance in assessing the risk of bone marrow suppression. The drug dosage is calculated to a certain extent based on body weight. If the weight is too light or too heavy, it will affect the metabolic process and concentration distribution of the drug in the body, thereby affecting the probability of bone marrow suppression. For example, patients who are underweight face a higher risk of bone marrow suppression due to relatively high drug doses.

[0018] The user's blood creatinine value is 100μmol / L. Blood creatinine is one of the important indicators reflecting renal function. Whether renal function is normal or not is directly related to the excretion of drugs. If blood creatinine rises, it indicates that there is a certain degree of damage to renal function, which leads to a slow excretion of methotrexate in the body, and the concentration of the drug in the body is maintained at a higher level for a longer time, thereby increasing the toxic effect on the bone marrow and increasing the risk of bone marrow suppression. After calculation, the user's BMI is 25. BMI comprehensively reflects the relationship between height and weight, and can be used to assess the nutritional status and body fat content of patients. Higher BMI is associated with some chronic diseases such as cardiovascular disease and diabetes, which indirectly affect the function of the bone marrow and its response to drugs. For example, obesity (higher BMI) causes the body to be in a state of chronic inflammation, affects the bone marrow microenvironment, and increases the risk of bone marrow suppression. The user's height is 175 cm. When combined with indicators such as weight, height helps to more accurately assess the overall condition and physiological function of the body. Height is used as an auxiliary variable in the calculation to more comprehensively reflect the differences in individual physiological characteristics.

[0019] The red blood cell count was 4.5 × 10 12 / L. Red blood cells are mainly responsible for transporting oxygen in the body, and changes in their number reflect the state of hematopoietic function. If the red blood cell count is lower than the normal range, it indicates that the bone marrow hematopoietic function is suppressed or there are other blood system diseases, which also increases the risk of bone marrow suppression after high-dose methotrexate treatment. The lymphocyte count is 1.5×10 9 / L, lymphocytes play an important role in the immune system, and changes in their number reflect the functional state of the immune system and the body's response to disease or drugs. In the case of bone marrow suppression, lymphocyte counts will change, and certain factors that affect lymphocyte function are also associated with the mechanism of bone marrow suppression. The blood potassium concentration is 4.0mmol / L. Potassium ions are one of the important electrolytes for maintaining the physiological function of cells, and their balance in the body is essential for neuromuscular excitability, cardiac function, etc. Abnormal blood potassium levels affect the metabolic process of cells, including the metabolism of bone marrow cells, which in turn has an indirect effect on the risk of bone marrow suppression. The urine white blood cell test result is 5 / uL. The presence of urine white blood cells indicates infection or inflammation of the urinary system, which reflects the overall immune status of the body or the presence of potential diseases. The inflammatory state of the body affects the microenvironment and hematopoietic function of the bone marrow through the regulation of the immune system, thereby changing the risk of bone marrow suppression to a certain extent. The high-density lipoprotein level is 1.2mmol / L.

[0020] High-density lipoprotein is mainly involved in the reverse transport of cholesterol in the body, which is of great significance to cardiovascular health. By affecting the overall metabolism and blood circulation of the body, changes in high-density lipoprotein levels indirectly affect the risk of bone marrow suppression. The blood magnesium concentration is 0.8mmol / L. Magnesium ions play an important role in many enzymatic reactions and cell physiological processes, including participating in the synthesis of DNA and RNA, maintaining the stability of cell membranes, etc. The proliferation and differentiation of bone marrow cells also depend on the normal progress of these enzymatic reactions and cell physiological processes. Therefore, abnormal blood magnesium concentration affects the hematopoietic function of the bone marrow, which is related to the risk of bone marrow suppression. The uric acid value is 400μmol / L. Uric acid is the end product of purine metabolism in the body, and hyperuricemia is related to gout, kidney disease, etc. These diseases affect the body's metabolic function and internal environment stability, thereby potentially affecting the hematopoietic function of the bone marrow and increasing the risk of bone marrow suppression.

[0021] The target user's alanine aminotransferase (ALT) is 40U / L, lactate dehydrogenase (LDH) is 200U / L, and aspartate aminotransferase (AST) is 35U / L. These serum markers usually reflect the functional status of the liver and other tissues. ALT and AST are mainly present in hepatocytes, and their increase indicates hepatocyte damage, such as drug-induced liver injury or other liver diseases. During treatment with high-dose methotrexate, abnormal liver function affects the metabolism and detoxification process of the drug, resulting in abnormally increased drug concentrations in the body, thereby increasing the risk of bone marrow suppression. LDH is present in many tissues, and its increase is related to damage or metabolic abnormalities of tissue cells. In the case of bone marrow suppression, damage to bone marrow cells or abnormal hematopoietic function leads to increased LDH release, so LDH levels can be used as a potential reference indicator for bone marrow suppression.

[0022] In the daily diet of target users, the intake of vegetables and fruits is relatively small, with an average weekly intake of about 1,000 grams of vegetables and about 500 grams of fruits; while the intake of meat and fat is high, with an average weekly intake of about 1,500 grams of meat and about 200 grams of fat. This unbalanced diet structure leads to problems such as nutritional deficiencies (such as vitamins, minerals, etc.) and obesity. Vitamin and mineral deficiencies affect the normal metabolism and hematopoietic function of bone marrow cells, while the chronic inflammatory state associated with obesity interferes with the bone marrow microenvironment and increases the risk of bone marrow suppression. Users usually mainly perform some light exercises, such as walking three times a week for about 30 minutes each time, and rarely perform high-intensity aerobic exercise or strength training. Moderate exercise helps promote blood circulation and metabolism, enhance the body's immunity and tolerance to drugs. Lack of sufficient exercise reduces the body's functions, affects the blood supply to the bone marrow and the delivery of nutrients, thereby increasing the risk of bone marrow suppression. Users have a drinking habit, with an average weekly drinking volume of about 200 ml, mainly drinking white wine. Alcohol and its metabolites are toxic to organs such as the liver and bone marrow. Long-term drinking causes liver damage, affects drug metabolism, and directly damages bone marrow cells, increasing the probability of bone marrow suppression. The user smokes about 10 cigarettes a day. Smoking is a clear bad habit. Harmful substances in tobacco (such as nicotine, tar, etc.) can reach the bone marrow through the blood circulation, causing damage to bone marrow cells, inhibiting the hematopoietic function of the bone marrow, and significantly increasing the risk of bone marrow suppression.

[0023] In addition to high-dose methotrexate treatment, the target user also took an antihypertensive drug (such as nifedipine) and an antibiotic (such as amoxicillin) at the same time. The combined use of drugs will cause drug interactions with methotrexate, affecting the metabolism, distribution or efficacy of the drug. For example, some drugs inhibit the excretion of methotrexate, causing its concentration in the body to increase, increasing the risk of bone marrow suppression; or some drugs affect the normal function of the bone marrow, which is superimposed on the bone marrow suppression effect of methotrexate, aggravating damage to the bone marrow.

[0024] The preset high-dose methotrexate bone marrow suppression risk prediction model is constructed using the LightGBM algorithm. The model as a whole can be regarded as an integrated model containing multiple decision trees, which processes and learns the input data in a layered and progressive manner. During the training process, each decision tree is learned and optimized based on the residual of the previous tree, continuously improving the model's predictive ability. This hierarchical structure enables the model to capture the complex nonlinear relationships in the data and analyze and model factors related to bone marrow suppression risk from different angles and levels.

[0025] The model includes an input layer, a hidden layer, and an output layer. The specific structure is as follows: The input layer is used to receive the pre-processed multimodal data information, serum marker feature information, lifestyle information, and medication information of the target user as input features. These features are pre-processed by standardization and normalization to make them consistent in numerical range and distribution so that the model can learn and process better. For example, for numerical features such as age and weight, normalization is performed to make them fall within the interval [0,1]; for categorical features such as gender and smoking, one-hot encoding is used to convert them into binary vector form. The hidden layer consists of multiple decision trees, and the structural parameters such as the depth and number of nodes of these decision trees are automatically adjusted and optimized according to the data characteristics and model performance during the training process. Each decision tree splits and grows based on the input features, and divides the data into different subsets by selecting the optimal features and split points to minimize the loss function. When constructing the decision tree, optimization techniques such as the histogram-based algorithm are used to reduce data storage and calculation and improve training efficiency. The output layer is used to output the risk value of bone marrow suppression and the risk level of bone marrow transplantation. The risk value is a continuous value obtained through calculation and mapping within the model. Its range is set in [0,1] or other reasonable intervals according to specific training and adjustment, indicating the magnitude of bone marrow suppression. The risk level is divided into different levels according to the pre-set threshold, such as low risk, medium risk and high risk, so that clinicians can more intuitively understand and apply the prediction results of the model.

[0026] The learning rate of the model is set to 0.05. The learning rate controls the update step size of the model parameters in each iteration. A smaller learning rate helps the model converge more stably, but requires more training time; a larger learning rate causes the model to skip the optimal solution during training, but the training speed is faster. Through multiple experiments and tuning, 0.05 is determined to be a more appropriate learning rate in this model, which can complete the training process relatively quickly while ensuring the convergence of the model. The number of iterations is determined to be 500 after training and verification. The number of iterations determines the number of rounds of learning of the model for the data. As the number of iterations increases, the performance of the model on the training set usually gradually improves, but overfitting occurs. By monitoring the performance indicators of the model on the validation set (such as AUC, accuracy, etc.), it is found that when the number of iterations reaches 500, the performance of the model on the validation set reaches a relatively stable state. Continuing to increase the number of iterations does not significantly improve the performance of the model, and leads to an increased risk of overfitting. Therefore, the number of iterations is determined to be 500.

[0027] The final model contains 200 decision trees. The number of decision trees is closely related to the complexity and generalization ability of the model. More decision trees can improve the expressiveness of the model, but also increase the computational burden and overfitting risk of the model. During the training process, by gradually increasing the number of decision trees and observing the performance of the model on the validation set, it is found that when the number of decision trees reaches 200, the model achieves a good balance between prediction accuracy and generalization ability. The average tree depth is 6. The depth of the tree limits the growth complexity of the decision tree. Shallow trees cannot fully capture the complex relationships in the data, while too deep trees are prone to overfitting. Through experiments and evaluations of different tree depths, it is found that when the average tree depth is 6, the performance of the model on the training set and validation set is relatively ideal, which can not only better learn the characteristic patterns in the data, but also maintain a certain generalization ability. The number of leaf nodes in each tree is between 30 and 50. The number of leaf nodes is related to the complexity of the tree and the fitting ability of the model. The appropriate number of leaf nodes can ensure that the model can effectively classify and predict the data without overfitting. During the model training process, the number of leaf nodes was dynamically adjusted and optimized according to the distribution and characteristics of the data, so that the number of leaf nodes of each tree was kept between 30 and 50 to obtain better model performance.

[0028] The training sample set collects a large amount of relevant information about patients receiving high-dose methotrexate treatment, including the above-mentioned multimodal data information, serum marker characteristic information, lifestyle information, medication information, and whether the patient has bone marrow suppression. These samples come from patients in different regions, different age groups, and different types of diseases. Through learning and training these samples, the model can identify the potential relationship between different factors and the risk of bone marrow suppression, so that when facing new target users, it can accurately predict the risk value and risk level of bone marrow suppression based on the information they input. For example, the training sample set contains data on 1,000 patients with hematological malignancies who received high-dose methotrexate treatment, of which 300 had bone marrow suppression. Through the analysis of these data and model training, the parameters and structure of the model are continuously optimized to improve the prediction performance of the model. During the model training process, the SHAP (SHapley Additive ex Planations) method is used to calculate the contribution of each feature to the model prediction results, thereby evaluating the importance of the feature. The larger the SHAP value, the more critical the role of the feature in the model prediction. By analyzing the SHAP values, we can understand the relative importance of different factors (such as age, serum markers, lifestyle habits, etc.) in predicting the risk of bone marrow suppression, providing a basis for further model interpretation and clinical application.

[0029] S102: Process the multimodal data information of the target user to generate a target physiological state prediction factor.

[0030] In one embodiment, the multimodal data information of the target user is processed to generate physiological state classification information and physiological characteristic influencing factors of the target user. At the age of 55, it is in the transition stage from middle age to old age. The physical function is reduced compared with that of young and middle-aged people. The drug metabolism and tolerance are affected to a certain extent, and it belongs to the medium-risk physiological age category. The BMI calculated according to weight and height is in the normal range, indicating that the body's nutritional status is relatively balanced, and the tolerance basis for drug treatment is good, which can be classified as a nutritionally balanced type. The red blood cell count is within the normal range, indicating that the hematopoietic function is basically normal at present, and it belongs to the normal hematopoietic function category. The lymphocyte count is normal, reflecting that the immune system function is in a stable state, and it is classified as a normal immune function category. The weight of the age factor is set to 0.2, taking into account its potential impact on the overall function of the body and drug metabolism. The BMI weight is set to 0.1, because it is in the normal range and has a relatively small impact on the overall risk. The weights of the red blood cell count and lymphocyte count are each set to 0.15. Although they are within the normal range, they are still indicators reflecting important physiological functions of the body and have a certain indicative effect on the risk of bone marrow suppression. The weights of indicators such as blood potassium, urine white blood cells, high-density lipoprotein, blood magnesium and uric acid were set at 0.05. Among them, urine white blood cells were slightly higher than the lower limit of the normal range, indicating mild inflammation, and proper attention should be paid to its potential impact on the bone marrow microenvironment; other indicators were basically normal and had relatively little impact on the overall risk.

[0031] The physiological status classification information and the physiological characteristics influencing factors of the target user are processed to generate risk abnormality characteristic information. The medium-risk physiological age category, combined with a weight of 0.2, increases the overall risk base value by 20 points (assuming a full score of 100 points, this is a relative quantification). The nutritionally balanced BMI has a small impact on the risk due to its weight of 0.1, and the risk score is not increased for the time being. The red blood cell count of the normal hematopoietic function category and the lymphocyte count of the normal immune function category, according to their respective weights of 0.15, basically do not increase the additional risk score. Indicators such as blood potassium, blood magnesium and high-density lipoprotein are normal and do not increase the risk. However, the urine white blood cell is slightly high, and because of its weight of 0.05, the risk is increased by 3 points. Uric acid 400μmol / L is at a normal high value, considering its weight of 0.05, the risk is increased by 2 points. Combining the above items, the generated risk abnormality characteristic information is that the user has a certain bone marrow suppression risk tendency in terms of basic physiological state, with a total score of 25 points, and the main risk contribution comes from age and urine white blood cells, uric acid and other indicators.

[0032] The risk abnormality characteristic information is processed to generate the target physiological state prediction factor. The above risk abnormality characteristic information is further analyzed and standardized. Using the linear conversion formula, the converted target physiological state prediction factor is set to be P, P = 0.3 + 0.003 × 25 = 0.375 (here 0.3 is the basic offset and 0.003 is the adjustment coefficient). This target physiological state prediction factor P will serve as one of the important inputs for the subsequent comprehensive assessment of bone marrow suppression risk, and will participate in the calculation of the final bone marrow suppression risk value and risk level together with other factors (such as serum marker influencing factors, lifestyle risk adjustment factors, etc.). The higher the value, the higher the risk of bone marrow suppression based on the physiological state.

[0033] S103, processing the serum marker characteristic information of the target user to generate a bone marrow suppression influencing factor.

[0034] In one embodiment, the target user's serum marker characteristic information is processed to generate target serum marker characteristic information, wherein the target serum marker characteristic information includes alanine aminotransferase, lactate dehydrogenase and aspartate aminotransferase. Assume that the alanine aminotransferase (ALT) of this 55-year-old male is 45U / L, lactate dehydrogenase (LDH) is 220U / L, and aspartate aminotransferase (AST) is 40U / L. Compared with the normal reference range, ALT and AST are slightly higher than the upper limit of normal (generally ALT normal range is 0-40U / L, AST normal range is 0-37U / L), indicating that there is mild damage or inflammatory response in liver cells. LDH is also higher than the normal range (generally LDH normal range is 109-245U / L), reflecting that the tissue cells have a certain degree of damage or metabolic abnormalities, and these three items are determined as target serum marker characteristic information.

[0035] The characteristic information of target serum markers is mapped to generate a continuous low-dimensional vector space. Using dimensionality reduction algorithms such as principal component analysis (PCA), the characteristic information of target serum markers (values ​​of ALT, LDH, and AST) is mapped to a three-dimensional continuous low-dimensional vector space. In this space, each dimension represents a comprehensive feature, and its coordinate value reflects the relative size and change trend of these characteristic information.

[0036] The semantic analysis and processing of the characteristic information of the target serum markers is performed to generate the semantic information of each characteristic information. For ALT elevation, the semantic information is "mild liver cell damage, affecting the drug metabolism process, and increasing the risk of bone marrow suppression"; for LDH elevation, the semantic information is "tissue cell damage or metabolic abnormality, which is associated with the state of bone marrow cells and has a potential impact on bone marrow suppression"; for AST elevation, the semantic information is "abnormal liver cell function, interfering with the biochemical balance in the body, and affecting the bone marrow microenvironment". The semantic information of each characteristic information and the continuous low-dimensional vector space are processed to generate the bone marrow suppression influencing factor. The semantic information of each characteristic information and its positional relationship in the continuous low-dimensional vector space are comprehensively considered, and the calculation is performed through a pre-trained machine learning model or a specific mathematical algorithm. Assume that the model calculates a bone marrow suppression influencing factor of 0.45 based on this information (the value range is between 0-1, 0 means almost no effect, and 1 means a great effect). This factor will be used as one of the important parameters for the subsequent calculation of bone marrow suppression risk, and will work together with other factors to more accurately assess the risk of bone marrow suppression in the 55-year-old male.

[0037] For example, alanine aminotransferase (ALT) is 45U / L, which accounts for 0.1 in the calculation after standardization and weight distribution; lactate dehydrogenase (LDH) is 220U / L, accounting for 0.2; aspartate aminotransferase (AST) is 40U / L, accounting for 0.1.

[0038] The bone marrow suppression influence factor is calculated by a pre-set weighted summation formula: bone marrow suppression influence factor = (0.1×ALT standardized value) + (0.1×LDH standardized value) + (0.1×AST standardized value) = (0.04+0.1+0.03=0.17). The bone marrow suppression influence factor calculated here is 0.17, indicating that based on the comprehensive evaluation of these serum markers, the user has a certain degree of bone marrow suppression risk tendency in this regard, and this factor will be further used together with other factors to evaluate and calculate the final bone marrow suppression risk.

[0039] S104: Process the target user's lifestyle information to generate a bone marrow suppression risk adjustment factor.

[0040] In one embodiment, feature extraction processing is performed on the target user's living habit information to generate dietary intake features, exercise type features, drinking type features and smoking type features, and the dietary intake features, exercise type features, drinking type features and smoking type features are processed to generate dietary risk values, drinking risk values, smoking risk values ​​and dynamic feature weight values, wherein the dynamic feature weight values ​​are generated based on the living habit information of different target users in a preset time period. For this 55-year-old male, the intake of vegetables and fruits in his daily diet is relatively small, with an average weekly intake of about 1000 grams of vegetables and about 500 grams of fruits; while the intake of meat and fat is high, with an average weekly intake of about 1500 grams of meat and about 200 grams of fat. This unbalanced diet structure leads to problems such as nutritional deficiencies (such as vitamins, minerals, etc.) and obesity. Usually, some light exercises are mainly performed, such as walking 3 times a week, each time for about 30 minutes, and high-intensity aerobic exercise or strength training is rarely performed. There is a habit of drinking, with an average weekly drinking volume of about 200 ml, mainly drinking white wine, and smoking about 10 cigarettes a day.

[0041] Due to the unbalanced diet structure, lack of important nutrients and the risk of obesity, the dietary risk value is calculated to be 0.4 according to the pre-set dietary risk assessment model. For example, insufficient intake of vitamin C, vitamin K and dietary fiber affects the normal metabolism and hematopoietic function of bone marrow cells, while excessive intake of fat and meat causes chronic inflammation and increases the risk of bone marrow suppression. Taking into account the high alcohol content of liquor and the frequency and amount of drinking, according to the drinking risk assessment rules, the drinking risk value is 0.3. Alcohol and its metabolites have toxic effects on organs such as the liver and bone marrow. Long-term drinking can cause liver damage, affect drug metabolism, and also directly damage bone marrow cells. Smoking 10 cigarettes a day, based on research on the health hazards of smoking and related assessment models, the smoking risk value is 0.35. Harmful substances in tobacco (such as nicotine, tar, etc.) can reach the bone marrow through the blood circulation, damage bone marrow cells, and inhibit the hematopoietic function of the bone marrow.

[0042] By analyzing and statistically modeling the living habits data of a large number of different users in the past year (preset time period), it was found that for the 55-year-old male group, the relative importance weights of diet, exercise, drinking and smoking in the risk of bone marrow suppression were 0.3, 0.2, 0.25 and 0.25 respectively. These weights will vary according to factors such as different age groups, gender and disease background, and will be continuously updated and optimized as new data accumulates. The diet risk value, exercise risk value, drinking risk value, smoking risk value and dynamic feature weight value are processed to generate a bone marrow suppression risk adjustment factor. The bone marrow suppression risk adjustment factor is calculated by weighted summation. The calculation formula is: bone marrow suppression risk adjustment factor = diet risk value × diet weight + exercise risk value × exercise weight + drinking risk value × drinking weight + smoking risk value × smoking weight. Substituting the above values ​​into the formula, it can be obtained: bone marrow suppression risk adjustment factor = 0.4 × 0.3 + 0.2 × 0.3 + 0.3 × 0.25 + 0.35 × 0.25 = 0.31. This bone marrow suppression risk adjustment factor will be used together with other factors (such as bone marrow suppression influencing factors, target physiological state predictors, etc.) to calculate the subsequent bone marrow suppression risk value and risk level to more comprehensively assess the risk of bone marrow suppression in this male.

[0043] S105: Process the myelosuppression influencing factor and the myelosuppression risk adjustment factor to generate dynamic risk parameter information of the target user.

[0044] In one embodiment, the bone marrow suppression influencing factor and the bone marrow suppression risk adjustment factor are processed to generate a bone marrow hematopoietic stem cell morphological change value. Assume that the bone marrow suppression influencing factor of the 55-year-old male is calculated to be 0.17 (as in the previous example) and the bone marrow suppression risk adjustment factor is 0.31. First, the bone marrow suppression influencing factor and the bone marrow suppression risk adjustment factor are processed to generate a bone marrow hematopoietic stem cell morphological change value. Through a pre-trained mathematical model based on a large amount of clinical data and experimental results, assuming that the model is a linear weighted model, the two factors are weighted and summed and converted by a specific function. Let the bone marrow hematopoietic stem cell morphological change value be M, and the calculation formula is M=0.4×bone marrow suppression influencing factor+0.6×bone marrow suppression risk adjustment factor+0.1 (the coefficients and constants here are based on model training and experience settings), then M=0.4×0.17+0.6×0.31+0.1=0.252. This value represents the degree of morphological change of bone marrow hematopoietic stem cells under the influence of the current comprehensive factors. The larger the value, the more obvious the morphological change and the higher the risk of bone marrow suppression.

[0045] The morphological change values ​​of bone marrow hematopoietic stem cells are processed to generate characteristic parameter information of different detection cycles and dynamic bone marrow hematopoietic stem cell structural information. Assume that the detection cycle is set to once a week for 4 consecutive weeks. In the first week, based on the M value and other relevant physiological data, the characteristic parameter information is calculated through a complex biological model, such as a 10% decrease in cell proliferation rate, an 8% increase in cell apoptosis rate, and a 12% decrease in cell metabolic activity. At the same time, advanced imaging technology and image analysis algorithms are used to obtain dynamic bone marrow hematopoietic stem cell structural information, such as irregular morphology of the cell nucleus, a relatively reduced proportion of cytoplasm, and a certain degree of abnormality in the number and function of mitochondria. In the following weeks, these characteristic parameter information and structural information will continue to update and change with the passage of time and changes in physical condition.

[0046] The characteristic parameter information of different detection cycles and the structural information of dynamic bone marrow hematopoietic stem cells are processed to generate dynamic risk parameter information of the target user. The time series analysis method and the recurrent neural network (RNN) model in the machine learning algorithm are used. The dynamic risk parameter information obtained after model processing is a risk score ranging from 0 to 100. The dynamic risk parameter information of this male is 45 points. This score reflects the dynamic changes in the risk of bone marrow suppression of the user over a period of time, which can provide doctors and researchers with a more comprehensive understanding of the patient's risk status and take corresponding intervention measures in a timely manner.

[0047] S106, processing the preset high-dose methotrexate bone marrow suppression risk prediction model based on the training sample set to generate a target high-dose methotrexate bone marrow suppression risk prediction model.

[0048] In one embodiment, any number of data features in the training sample set is obtained, and a sampling ratio is generated based on the number of each data feature in the training sample set. The training sample set is processed based on the sampling ratio to generate a preset number of sampling features. From the training sample set of 1000 patients, data features (such as age, weight, various blood indicators, medication status, etc.) of 200 patients are randomly selected for analysis. According to statistics, it is found that the age feature has 200 different values, the weight feature has 180 different values, and the serum marker feature (such as alanine aminotransferase, etc.) has 150 different values. Calculate the sampling ratio: for example, for the age feature, the sampling ratio = 200 (the number of age features in the sample extracted) / 1000 (the total number of age features in the training sample set) = 0.2; for the weight feature, the sampling ratio = 180 / 1000 = 0.18; and so on, calculate the sampling ratio of each data feature.

[0049] Based on any data feature and each sampling feature, multiple data groups are generated, wherein each data group contains a preset number of data samples, and at least one data sample includes identification information. According to the calculated sampling ratio, the training sample set is sampled with replacement. For example, for the age feature, according to the sampling ratio of 0.2, 200 (with duplication) are randomly selected from 1000 age data as sampling features; for the weight feature, 180 are selected, etc. Finally, 500 preset number of sampling features are generated (the 500 here is set according to actual needs and model training experience). Then, any extracted data feature (such as the complete information of a patient) is combined with each sampling feature for processing. For example, the age, weight, serum markers and other information of a patient are matched one by one with these 500 sampling features to form a data group. Each data group contains 10 data samples (also set according to the model training requirements), and at least one data sample includes identification information of whether the patient has bone marrow suppression. In this way, multiple data groups are generated for subsequent model training.

[0050] Based on the data samples in the multiple data sets, the preset high-dose methotrexate bone marrow suppression risk prediction model is trained to generate a trained high-dose methotrexate bone marrow suppression risk prediction model. Based on the validation sample set, the trained high-dose methotrexate bone marrow suppression risk prediction model is processed to generate a validation result. If the data sample containing the identification information in the validation result is a risk factor that characterizes the risk of bone marrow suppression, the trained high-dose methotrexate bone marrow suppression risk prediction model is used as the target high-dose methotrexate bone marrow suppression risk prediction model. These data sets are used to train the preset high-dose methotrexate bone marrow suppression risk prediction model. During the training process, the model continuously learns the relationship between each feature in the data set and the bone marrow suppression result, and adjusts the node splitting rules and weights of the decision tree. After the training is completed, the trained model is processed using an independent validation sample set (assuming that it contains 200 patient information). The model predicts the patient data in the validation sample set and compares it with the actual identification information (whether bone marrow suppression occurs). For example, the model predicts that 80 patients have bone marrow suppression, while 75 patients in the actual validation sample set have bone marrow suppression. The verification results are evaluated by calculating indicators such as accuracy and recall.

[0051] In the verification results, patients who were correctly predicted by the model to have bone marrow suppression (i.e., data samples containing identification information and accurate model predictions) are indeed those who characterize risk factors affecting bone marrow suppression (such as these patients having older age, abnormal serum markers, unhealthy living habits, etc.). Therefore, this trained high-dose methotrexate bone marrow suppression risk prediction model is used as the target high-dose methotrexate bone marrow suppression risk prediction model to predict the risk of bone marrow suppression for target users such as 55-year-old men.

[0052] S107, processing the target physiological state prediction factor and the dynamic risk parameter information of the target user based on the target high-dose methotrexate bone marrow suppression risk prediction model to generate a bone marrow suppression risk value and a bone marrow transplantation risk level.

[0053] In one embodiment, the target physiological state prediction factor and the dynamic risk parameter information of the target user are fused based on the target high-dose methotrexate bone marrow suppression risk prediction model to generate a fusion feature sequence. For a 55-year-old male target user, the data are as follows: the physiological state prediction factor PF = 0.375, which is generated by processing multimodal data information, comprehensively considering the influence of factors such as age, BMI, red blood cell count, and lymphocyte count on the physiological state, reflecting that there is a certain bone marrow suppression risk tendency in basic physiology. The bone marrow suppression influence factor MF = 0.35 is jointly determined by the serum marker characteristic information (alanine aminotransferase ALT = 45U / L, lactate dehydrogenase LDH = 220U / L, aspartate aminotransferase AST = 40U / L), indicating that there is a certain risk of bone marrow suppression under the action of these factors.

[0054] The bone marrow suppression risk adjustment factor AF = 0.31, which is calculated based on his lifestyle information (unbalanced diet, mild exercise, drinking about 200 ml of liquor per week, and smoking about 10 cigarettes per day), reflecting the impact of bad lifestyle habits on the risk of bone marrow suppression. The medication information factor DF = 0.2 is determined by the interaction between the simultaneous use of antihypertensive drugs (nifedipine) and antibiotics (amoxicillin) and high-dose methotrexate. Comorbidity factor CF = 0.1, the man has no other obvious comorbidities. Medical history factor HF = 0.05, no history of bone marrow suppression or related blood system diseases. The model parameters are set as:

[0055] Weight coefficients: a1=0.2, a2=0.2, a3=0.15, a4=0.15, a5=0.1, a6=0.2.

[0056] Influence intensity coefficient: b1=0.4, b2=0.5, b3=0.3, b4=0.4, b5=0.2, b6=0.3.

[0057] Offset constants: c1=0.1, c2=0.2, c3=0.1, c4=0.15, c5=0.05, c6=0.1.

[0058] Each factor is input into the multi-layer perceptron (MLP) as a different feature channel. PF =ReLU(W PF ×PF+b PF) and other similar transformations (similar to other factors), and then concatenated in the second layer of MLP to form a fusion feature sequence F = [y PF ,y MF ,y AF ,y DF ,y CF ,y HF ]. Based on the target high-dose methotrexate bone marrow suppression risk prediction model, the fusion feature sequence is processed to generate the target classification header information. The features are further extracted and integrated through the fully connected layer and the activation function layer, such as z = ReLU (W1×F+b1), and then the target classification header information H is obtained through the output layer W2×z+b2, which contains information such as the category and confidence of the bone marrow suppression risk.

[0059] The target classification header information is processed to generate a bone marrow suppression risk value and a bone marrow transplantation risk level. The method includes a calculation formula for obtaining the bone marrow suppression risk value, and the calculation formula is: Risk value =(a1× Among them, PF represents physiological state prediction factor, MF represents bone marrow suppression influencing factor, AF represents bone marrow suppression risk adjustment factor, DF represents medication information factor, CF represents comorbidity factor, HF represents medical history factor, a1, a2, a3, a4, a5, a6 are weight coefficients of each factor in the overall risk assessment, and the sum is 1; b1, b2, b3, b4, b5, b6 are the influence intensity coefficients of each factor, which are used to adjust the influence of each factor on the risk value; c1, c2, c3, c4, c5, c6 are the offset constants of each factor. Substitute the above example data into the formula, specifically, Risk value =(0.2×0.598)+(0.2×0.530)+(0.15×0.629)+(0.15×0.593)+(0.1×0.934)+(0.2×0.891)=0.1196+0.106+0.09435+0.8895+0.934+0.1782=0.6795. According to the pre-set risk level classification rules (0-0.4 is low risk, 0.4-0.7 is medium risk, and 0.7 or above is high risk), the male bone marrow suppression risk level is medium risk. This indicates that when receiving high-dose methotrexate treatment, blood routine and other indicators need to be closely monitored. Doctors can consider adjusting the treatment plan or taking preventive measures based on this result, such as giving hematopoietic drugs, to reduce the occurrence and severity of bone marrow suppression.

[0062] The server obtains all kinds of information covering the target user, such as multimodal data consisting of age, weight, serum marker information containing specific enzyme indicators, lifestyle information covering diet, exercise, tobacco and alcohol, medication details, as well as preset models and training samples. In the data processing process, multimodal data is first converted into physiological state classification and characteristic influencing factors, and then the target physiological state prediction factors are generated. Serum markers are screened, analyzed, mapped and semantically processed to obtain bone marrow suppression influencing factors. Lifestyle information is extracted and calculated to determine the bone marrow suppression risk adjustment factor, and the two are combined to generate dynamic risk parameter information. In terms of model construction, data features are extracted from training samples to determine the sampling ratio, generate sampling features and data groups, and train the preset model and verify it with the validation set. The model that meets the requirements becomes the target model. Finally, the target model is used to fuse related factors, generate sequence and classification header information, and calculate the bone marrow suppression risk value and level according to the formula. The weights, intensity coefficients and offset constants of each factor in the formula work together to comprehensively consider multiple factors and effectively warn of bone marrow suppression risks.

[0063] In one embodiment, if Figure 2 As shown, the present application also provides a device for early warning of risk of bone marrow suppression caused by treatment, comprising:

[0064] An acquisition module 201 is used to acquire multimodal data information of a target user, serum marker characteristic information of the target user, life habit information of the target user, medication information of the target user, a preset high-dose methotrexate bone marrow suppression risk prediction model and a training sample set, wherein the multimodal data information of the target user includes the target user's age, weight, blood creatinine, BMI, height, red blood cell count, lymphocyte count, potassium, urine white blood cells, high-density lipoprotein, magnesium and uric acid;

[0065] Processing module 202 is used to process the multimodal data information of the target user to generate a target physiological state prediction factor; process the serum marker characteristic information of the target user to generate a bone marrow suppression influencing factor; process the living habit information of the target user to generate a bone marrow suppression risk adjustment factor; process the bone marrow suppression influencing factor and the bone marrow suppression risk adjustment factor to generate dynamic risk parameter information of the target user; process the preset high-dose methotrexate bone marrow suppression risk prediction model based on the training sample set to generate a target high-dose methotrexate bone marrow suppression risk prediction model; process the target physiological state prediction factor and the dynamic risk parameter information of the target user based on the target high-dose methotrexate bone marrow suppression risk prediction model to generate a bone marrow suppression risk value and a bone marrow transplantation risk level.

[0066] Each embodiment in the present application is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the method for early warning of the risk of myelosuppression caused by treatment, the electronic device, the electronic device, and the readable storage medium embodiment are basically similar to the above-mentioned method for early warning of the risk of myelosuppression caused by treatment, so the description is relatively simple, and the relevant parts can be referred to the partial description of the above-mentioned method for early warning of the risk of myelosuppression caused by treatment.

Claims

1. A method for early warning of the risk of myelosuppression caused by treatment, characterized in that: include: Acquire multimodal data information of a target user, serum marker characteristic information of the target user, life habit information of the target user, medication information of the target user, a preset high-dose methotrexate bone marrow suppression risk prediction model and a training sample set, wherein the multimodal data information of the target user includes the target user's age, weight, blood creatinine, BMI, height, red blood cell count, lymphocyte count, potassium, urine white blood cells, high-density lipoprotein, magnesium and uric acid; Processing the multimodal data information of the target user to generate a target physiological state prediction factor; Processing the serum marker characteristic information of the target user to generate a bone marrow suppression influencing factor; Processing the target user's lifestyle information to generate a bone marrow suppression risk adjustment factor; Processing the bone marrow suppression influencing factor and the bone marrow suppression risk adjustment factor to generate dynamic risk parameter information of the target user; Processing the preset high-dose methotrexate bone marrow suppression risk prediction model based on the training sample set to generate a target high-dose methotrexate bone marrow suppression risk prediction model; The target physiological state prediction factor and the dynamic risk parameter information of the target user are processed based on the target high-dose methotrexate bone marrow suppression risk prediction model to generate a bone marrow suppression risk value and a bone marrow transplantation risk level.

2. The method according to claim 1, characterized in that Processing the multimodal data information of the target user to generate a target physiological state prediction factor includes: Processing the multimodal data information of the target user to generate physiological state classification information and physiological characteristic influencing factors of the target user; Processing the physiological state classification information and the physiological characteristic influencing factors of the target user to generate risk abnormality characteristic information; The risk abnormality characteristic information is processed to generate a target physiological state prediction factor.

3. The method according to claim 1, characterized in that Processing the target user's serum marker characteristic information to generate a bone marrow suppression influencing factor includes: Processing the serum marker characteristic information of the target user to generate target serum marker characteristic information, wherein the target serum marker characteristic information includes alanine aminotransferase, lactate dehydrogenase and aspartate aminotransferase; Mapping the characteristic information of the target serum marker to generate a continuous low-dimensional vector space; Performing semantic analysis on the characteristic information of the target serum marker to generate semantic information of each characteristic information; The semantic information and continuous low-dimensional vector space of each feature information are processed to generate the bone marrow suppression influencing factor.

4. The method according to claim 3, characterized in that Processing the target user's lifestyle information to generate a bone marrow suppression risk adjustment factor includes: Performing feature extraction processing on the target user's life habit information to generate dietary intake features, exercise type features, drinking type features, and smoking type features; The dietary intake feature, the exercise type feature, the drinking type feature and the smoking type feature are processed to generate a dietary risk value, a drinking risk value, a smoking risk value and a dynamic feature weight value, wherein the dynamic feature weight value is generated based on the life habit information of different target users within a preset time period; The diet risk value, the exercise risk value, the drinking risk value, the smoking risk value and the dynamic feature weight value are processed to generate a bone marrow suppression risk adjustment factor.

5. The method according to claim 4, characterized in that The myelosuppression influencing factor and the myelosuppression risk adjustment factor are processed to generate dynamic risk parameter information of the target user, including: Processing the bone marrow suppression influencing factors and the bone marrow suppression risk adjustment factors to generate bone marrow hematopoietic stem cell morphology change values; Processing the bone marrow hematopoietic stem cell morphology change value to generate characteristic parameter information of different detection cycles and dynamic bone marrow hematopoietic stem cell structure information; The characteristic parameter information of different detection cycles and the structural information of dynamic bone marrow hematopoietic stem cells are processed to generate dynamic risk parameter information of the target user.

6. The method according to claim 1, characterized in that The preset high-dose methotrexate bone marrow suppression risk prediction model is processed based on the training sample set to generate a target high-dose methotrexate bone marrow suppression risk prediction model, including: Get any number of data features in the training sample set; Generate a sampling ratio based on the number of each data feature in the training sample set; Processing the training sample set based on the sampling ratio to generate a preset number of sampling features; Processing based on any data feature and each sampling feature to generate multiple data groups, wherein each data group includes a preset number of data samples, and at least one data sample includes identification information; Training the preset high-dose methotrexate bone marrow suppression risk prediction model based on data samples in multiple data groups to generate a trained high-dose methotrexate bone marrow suppression risk prediction model; Processing the trained high-dose methotrexate bone marrow suppression risk prediction model based on the validation sample set to generate a validation result; If the data sample containing identification information in the verification result is a risk factor that characterizes bone marrow suppression, the trained high-dose methotrexate bone marrow suppression risk prediction model is used as the target high-dose methotrexate bone marrow suppression risk prediction model.

7. The method according to claim 5, characterized in that The target physiological state prediction factor and the dynamic risk parameter information of the target user are processed based on the target high-dose methotrexate bone marrow suppression risk prediction model to generate a bone marrow suppression risk value and a bone marrow transplantation risk level, including: Based on the target high-dose methotrexate bone marrow suppression risk prediction model, the target physiological state prediction factor and the dynamic risk parameter information of the target user are fused to generate a fusion feature sequence; Processing the fusion feature sequence based on the target high-dose methotrexate bone marrow suppression risk prediction model to generate target classification header information; Processing the target classification header information to generate a bone marrow suppression risk value and a bone marrow transplantation risk level; The method includes a calculation formula for obtaining a bone marrow suppression risk value, the calculation formula being: Among them, PF represents physiological status prediction factor, MF represents bone marrow suppression influencing factor, AF represents bone marrow suppression risk adjustment factor, DF represents medication information factor, CF represents comorbidity factor, HF represents medical history factor, a1, a2, a3, a4, a5, a6 are weight coefficients of each factor in the overall risk assessment, and the sum is 1; b1, b2, b3, b4, b5, b6 are the influence intensity coefficients of each factor, which are used to adjust the influence of each factor on the risk value; c1, c2, c3, c4, c5, c6 are the offset constants of each factor.

8. A device for early warning of the risk of myelosuppression caused by treatment, characterized in that: The device comprises: An acquisition module is used to acquire multimodal data information of a target user, serum marker characteristic information of a target user, life habit information of a target user, medication information of a target user, a preset high-dose methotrexate bone marrow suppression risk prediction model, and a training sample set, wherein the multimodal data information of the target user includes the target user's age, weight, blood creatinine, BMI, height, red blood cell count, lymphocyte count, potassium, urine white blood cells, high-density lipoprotein, magnesium, and uric acid; A processing module is used to process the multimodal data information of the target user to generate a target physiological state prediction factor; process the serum marker characteristic information of the target user to generate a bone marrow suppression influencing factor; process the living habit information of the target user to generate a bone marrow suppression risk adjustment factor; process the bone marrow suppression influencing factor and the bone marrow suppression risk adjustment factor to generate dynamic risk parameter information of the target user; process the preset high-dose methotrexate bone marrow suppression risk prediction model based on the training sample set to generate a target high-dose methotrexate bone marrow suppression risk prediction model; process the target physiological state prediction factor and the dynamic risk parameter information of the target user based on the target high-dose methotrexate bone marrow suppression risk prediction model to generate a bone marrow suppression risk value and a bone marrow transplantation risk level.

9. An electronic device, characterized in that: include: a first processor; and a memory for storing executable instructions of the first processor; Wherein, the first processor is configured to execute the method for early warning of risk of myelosuppression caused by treatment as claimed in any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the second processor, the method for early warning of the risk of myelosuppression caused by treatment as claimed in any one of claims 1 to 7 is implemented.

Images