Hepatocellular carcinoma treatment effect analysis system and method based on metabolism comprehensive analysis

Abstract

The invention relates to the technical field of physiological monitoring, in particular to a hepatocellular carcinoma treatment effect analysis system and method based on metabolism comprehensive analysis, and the method comprises the steps: obtaining the evolution condition of hepatocellular carcinoma, the composition condition of drugs and the composition condition of metabolites; drug absorption and transformation analysis is carried out based on the composition condition of the drug and the marking condition of the composition condition of the metabolite, future drug transformation component prediction is carried out based on the drug absorption and transformation analysis result and the evolution condition of the corresponding hepatocellular carcinoma, and drug treatment effect early warning is carried out based on the future drug transformation component prediction. The first-pass effect is corrected through mass spectrum imaging and enzyme activity, the inhibition effect of the tumor microenvironment on drug transformation is quantified, prediction is dynamically adjusted through the future tumor anomaly score ratio, and the accuracy of the time of drug replacement is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of physiological monitoring, and in particular to a system and method for analyzing the therapeutic effect of hepatocellular carcinoma based on comprehensive metabolic analysis. Background Art

[0002] Hepatocellular carcinoma (HCC), a common and highly lethal malignant tumor worldwide, poses a serious threat to human health. Despite recent advances in the treatment of HCC, including the use of multiple therapeutic approaches, including surgical resection, chemotherapy, radiotherapy, targeted therapy, and immunotherapy, overall treatment outcomes remain unsatisfactory, and improvements in patient survival and quality of life face numerous challenges. Traditional treatment approaches often fail to adequately account for tumor heterogeneity and dynamic changes. HCC exhibits complex biological characteristics, with tumors from different patients exhibiting significant differences in gene expression, metabolic profiles, and microenvironment. This heterogeneity can lead to drastically different responses to the same treatment regimen in different patients, resulting in some patients failing to benefit from existing treatments and even experiencing disease progression and recurrence. Furthermore, tumor cells can evolve and develop drug resistance during treatment, a major cause of treatment failure in HCC. For example, with prolonged treatment with the targeted drug sorafenib, some patients develop sorafenib resistance due to CYP3A4 inactivation, which can hinder the drug's effectiveness and lead to continued tumor growth and metastasis.

[0003] Drug metabolism is crucial for drug efficacy and safety. In the treatment of hepatocellular carcinoma (HCC), drugs undergo a complex metabolic process after entering the body, including absorption, distribution, metabolism, and excretion. However, current research on the mechanisms and patterns of drug metabolism in HCC patients remains limited. Traditional pharmacokinetic studies are primarily based on population pharmacokinetic models, which often overlook the impact of individual differences and the tumor microenvironment on drug metabolism. The tumor microenvironment is a complex ecosystem encompassing tumor cells, immune cells, stromal cells, and various cytokines and metabolites. Some metabolites, such as lactate, can inhibit drug conversion and affect drug efficacy. However, current pharmacokinetic studies rarely consider these tumor microenvironmental factors, resulting in inaccurate predictions of drug metabolism and efficacy in patients. Furthermore, existing drug metabolism research methods are mostly static and cannot monitor the dynamic changes in drug metabolism in real time. Drug metabolism in the body is a dynamic, time-dependent process, and drug metabolites and concentrations can vary significantly at different time points. However, traditional research methods can only perform sampling and analysis at limited time points, and cannot fully and timely reflect the dynamic process of drug metabolism, making it difficult to meet the needs of clinical precision treatment.

[0004] In order to solve these problems, this application designs a system and method for analyzing the therapeutic effect of hepatocellular carcinoma based on comprehensive metabolic analysis. Summary of the Invention

[0005] The purpose of the present invention is to provide a system and method for analyzing the therapeutic effects of hepatocellular carcinoma based on comprehensive metabolic analysis. This solution integrates the evolutionary data, drug components and metabolite dynamics of hepatocellular carcinoma, combines deep learning to construct a multimodal time series prediction model, realizes the dynamic correlation analysis of drug metabolic pathways and tumor abnormality scores, quantifies the inhibitory effect of the tumor microenvironment on drug conversion through mass spectrometry imaging and enzyme activity correction, and uses the future tumor abnormality score ratio to dynamically adjust the prediction, thereby improving the accuracy of the timing of drug replacement.

[0006] The present invention is achieved in that: In a first aspect, the present invention provides a method for analyzing the therapeutic effect of hepatocellular carcinoma based on comprehensive metabolic analysis, comprising the following steps: S1. Obtain the evolution of hepatocellular carcinoma, the composition of drugs, and the composition of metabolites; S2. Conduct drug absorption and conversion analysis based on the labeling of the drug's composition and metabolite composition; S3. Predict future drug conversion components based on drug absorption and conversion analysis results and the corresponding hepatocellular carcinoma evolution; S4. Early warning of drug treatment effects based on predictions of future drug conversion components.

[0007] As an implementation method of the present invention, the evolution of hepatocellular carcinoma in step S1 includes images before and after the application of the drug. The tumor evolution trajectory is tracked through continuous imaging examinations to obtain the changes in the tumor and the metabolic characteristics of the tumor microenvironment, including lactate and glutamine levels. The composition of the drug includes the composition, concentration, half-life and tissue of the drug used, and the composition of the metabolite includes the drug concentration in the metabolite and the concentration of the component formed after the drug conversion in the corresponding metabolite.

[0008] As an implementation of the present invention, the drug absorption conversion analysis in step S2 includes the following specific steps: S21. Obtain the composition of the drug and the composition of the metabolites, obtain the composition of the consumed drug, obtain the composition of the consumed drug by subtracting the corresponding components remaining in the metabolites from the composition of each component of the consumed drug, obtain the distribution of various consumed drug components in various locations in the liver, and obtain the composition of the consumed drug and the conversion path of the generated metabolites based on the constructed metabolic pathway based on enzyme reactions. The specific steps are: obtain the historical enzyme concentration, the enzyme's living environment, the composition of the consumed drug, the composition of the metabolites, and the metabolic conversion path of the drug, and construct an enzyme concentration, enzyme living environment, the composition of the consumed drug, and the metabolites as input. The component composition in the deep learning neural network model is output as the metabolic transformation pathway of the drug. Based on the constructed deep learning neural network model, the transformation pathway of the drug into metabolites is analyzed. The transformation pathway includes the transformation of the drug in various tissues in the liver. By accurately measuring the content of the drug prototype and metabolites, combined with the drug residues in the excreta and serum, the actual consumption of the drug is quantitatively calculated. This method can correct the influence of the first-pass effect of the liver, ensure the accuracy of the metabolic kinetic data, and provide a reliable foundation for subsequent modeling. Using technologies such as mass spectrometry imaging, the concentration gradient distribution of the drug in different functional areas of the liver is visualized, revealing its differential penetration in tumor tissue and normal tissue. This helps to understand the targeting efficiency of the drug and provides a basis for optimizing the dosing regimen. In combination with microenvironmental parameters such as metabolic enzyme activity, pH, and temperature, the LSTM neural network is used to dynamically predict the drug metabolic pathway, thereby improving the accuracy of the prediction. S22. Simultaneously obtain the tumor evolution status of each liver tissue and determine tumor abnormality based on the size, mutation load, and image changes of the tumor in each tissue; The specific steps are as follows: obtaining the size of tumor evolution, mutation load, and image changes of each tissue, where the image change is the average difference between the pixel value of a pixel point and the pixel value of normal tissue, dividing each by the corresponding set standard value to obtain a standardized value, and performing weighted summation to obtain the corresponding tumor abnormality judgment result; wherein the weighted weight is obtained through historical data experiments, that is, obtaining the abnormal damage caused by the tumor to the corresponding tissue, making the corresponding tissue unable to absorb and convert drugs, and integrating mutation, imaging and other data to quantify the degree of tissue functional damage, reflecting the decline in drug metabolism capacity, such as tumor damage to liver cytochrome enzymes (such as CYP3A4) leading to metabolic disorders; S23. Perform drug conversion and absorption analysis of the corresponding conversion pathway based on drug consumption and tumor abnormality determination of the corresponding tissue; The specific steps are: obtaining the tumor abnormality judgment results of each tissue along the conversion pathway of drugs into metabolites, and the corresponding drug consumption; The tumor abnormality judgment results on the conversion path are obtained by weighted summation based on the tumor abnormality judgment results of each tissue. The weighted weight here is allocated according to the proportion of the drug conversion amount of each tissue to the total drug conversion amount; The drug consumption coefficient is obtained by dividing the drug consumption by the corresponding drug consumption standard value. The corresponding drug conversion analysis result is obtained by dividing the drug consumption coefficient by the tumor abnormality judgment result. The inhibitory effect of the tumor on the metabolic pathway is directly evaluated by the ratio of the drug consumption coefficient to the tumor score. The higher the proportion of abnormal tissue, the lower the drug conversion rate. Weighted summation and standardization are common methods for multivariate data analysis.

[0009] As an implementation of the present invention, the prediction of future drug conversion components in step S3 specifically includes the following steps: S31. Obtain the conversion analysis results of the corresponding drug and the tumor abnormality judgment results along the corresponding conversion pathway; integrate the drug conversion analysis results (e.g., metabolite concentration, enzyme activity) with the tumor abnormality score (e.g., imaging features, mutation load) to construct a multimodal time-series dataset. This is based on the fact that pharmacokinetic studies have shown that the tumor microenvironment (e.g., hypoxia) can significantly affect drug conversion efficiency. S32. Predicting future tumor abnormality determination results on the conversion path based on historical corresponding drug conversion analysis results and tumor abnormality determination results on the conversion path, wherein the prediction of future tumor abnormality determination results on the conversion path is performed using a deep learning neural network; S33. Obtain the ratio of the predicted tumor abnormality judgment result on the future conversion path to the current tumor abnormality judgment result, obtain the future drug conversion analysis prediction result by dividing the corresponding drug conversion analysis result by the corresponding ratio, and use the ratio of the future to current tumor abnormality scores as a correction factor for drug conversion efficiency; basis: changes in tumor load are negatively correlated with drug metabolic clearance rate; benefit: adjust the prediction result through dynamic ratio to avoid misjudgment caused by static threshold.

[0010] As an implementation of the present invention, step S4 performs a warning of drug treatment effect based on the prediction of future drug conversion components, including the following specific steps: Obtain the predicted results of future drug conversion analysis and compare them with the set drug conversion analysis threshold. If the corresponding predicted results of future drug conversion analysis are greater than or equal to the set drug conversion analysis threshold, it means that the drug effect is appropriate and there is no need to issue a warning for drug replacement. If the corresponding predicted results of future drug conversion analysis are less than the set drug conversion analysis threshold, it means that the drug effect is not appropriate and a warning for drug replacement is required. Compare the predicted results with the drug conversion threshold to trigger the warning. The threshold is usually obtained based on historical pharmacodynamics or clinical drug resistance threshold. Predicting a decrease in metabolic efficiency can trigger drug replacement in advance.

[0011] In a second aspect, the present invention provides a hepatocellular carcinoma treatment effect analysis system based on comprehensive metabolic analysis, comprising: Data acquisition module, which obtains the evolution of hepatocellular carcinoma, the composition of drugs, and the composition of metabolites; Drug absorption and conversion analysis module, which performs drug absorption and conversion analysis based on the labeling of drug components and metabolite components; The future drug conversion component prediction module predicts future drug conversion components based on the drug absorption and conversion analysis results and the corresponding hepatocellular carcinoma evolution; The treatment effect early warning module provides early warning of drug treatment effects based on the prediction of future drug conversion components.

[0012] In a third aspect, the present invention provides an electronic device comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes a hepatocellular carcinoma treatment effect analysis method based on comprehensive metabolic analysis by calling the computer program stored in the memory.

[0013] Compared with the prior art, the present invention has the following advantages and beneficial effects: This approach integrates the evolutionary data of hepatocellular carcinoma, drug components, and metabolite dynamics, and combines deep learning to construct a multimodal time-series prediction model to achieve dynamic correlation analysis between drug metabolic pathways and tumor abnormality scores. Through mass spectrometry imaging and enzyme activity correction of the first-pass effect, the inhibitory effect of the tumor microenvironment on drug conversion is quantified. Dynamic adjustment predictions are made using future tumor abnormality score ratios, thereby improving the accuracy of the timing of drug replacement. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments made with reference to the following drawings: Figure 1 Schematic diagram of the overall process of the method for analyzing the therapeutic effect of hepatocellular carcinoma based on comprehensive metabolic analysis of the present invention; Figure 2 Schematic diagram of the analysis flow of step S3 of the method for analyzing the therapeutic effect of hepatocellular carcinoma based on comprehensive metabolic analysis of the present invention; Figure 3 This is an analysis flow chart of drug conversion and absorption analysis of the conversion pathway of the method for analyzing the therapeutic effect of hepatocellular carcinoma based on comprehensive metabolic analysis of the present invention; Figure 4 This is a structural diagram of the hepatocellular carcinoma treatment effect analysis system based on comprehensive metabolic analysis of the present invention. DETAILED DESCRIPTION

[0015] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0016] Example 1

[0017] like Figures 1 to 3 As shown, this embodiment provides a method for analyzing the therapeutic effect of hepatocellular carcinoma based on comprehensive metabolic analysis, which specifically includes the following steps: S1. Obtain the evolution of hepatocellular carcinoma, the composition of drugs, and the composition of metabolites; Exemplarily, the evolution of hepatocellular carcinoma in step S1 includes images before and after drug administration, and the tumor evolution trajectory is tracked through continuous imaging examinations to obtain changes in the tumor and metabolic characteristics of the tumor microenvironment, including lactate and glutamine levels. The composition of the drug includes the composition, concentration, half-life, and tissue of action of the drug, such as the location of sorafenib in the liver and the corresponding concentration in the liver. The composition of the metabolite includes the drug concentration in the metabolite and the concentration of the component formed after drug conversion in the corresponding metabolite, such as the component generated by the active ingredient in the drug reacting with cancer cells at the tumor location. This can be obtained by isotope labeling. The drug can be labeled with carbon-14 to track its metabolic pathway in hepatocellular carcinoma tissue. The specific method is to select patients diagnosed with hepatocellular carcinoma from the hospital and screen suitable research subjects according to inclusion and exclusion criteria. Inclusion criteria may include a clear diagnosis of hepatocellular carcinoma and no previous specific treatment; exclusion criteria may include other serious diseases and inability to cooperate with examinations. Patients are divided into different groups according to treatment plans or research purposes, such as drug treatment group and control group; Prepare imaging equipment such as CT and MRI, and perform debugging and calibration to ensure image quality and accuracy; prepare reagents for detecting metabolic characteristics of the tumor microenvironment, such as kits for detecting lactate and glutamine levels; prepare carbon-14 labeled drugs, ensuring labeling stability and accuracy; prepare instruments for analyzing drug composition, concentration, and metabolite components, such as high-performance liquid chromatography (HPLC) and mass spectrometry (MS); Before drug administration, all patients undergo CT or MRI examinations to obtain initial imaging information of the tumor, including tumor size, location, and morphology. During drug treatment, patients undergo imaging examinations at predetermined time intervals (such as weekly, biweekly, or monthly) to track the evolution of the tumor and record changes in tumor size, morphology, and boundaries. During each imaging examination, tumor tissue or blood samples are collected from patients to detect the metabolic characteristics of the tumor microenvironment. The levels of metabolites such as lactate and glutamine in the samples are detected using appropriate kits or detection methods. The composition and concentration of the drugs used are recorded, and blood or tissue samples are collected from patients regularly during treatment. The concentration of the drug in the body is detected using methods such as HPLC or MS. By collecting samples multiple times, the change in the concentration of the drug in the body over time is measured, and the half-life of the drug is calculated. The tissue location of the drug's action and the concentration in the corresponding tissue are determined by combining the imaging examination and drug concentration test results. For example, the location of action and concentration of sorafenib in the liver. Patients in the drug treatment group were given a carbon-14 labeled drug at a predetermined dose and route of administration. At various time points after drug administration, tumor tissue or blood samples were collected from the patients. HPLC-MS and other methods were used to analyze the drug concentration in metabolites and the concentration of components formed after drug conversion, tracking the drug's metabolic pathway in hepatocellular carcinoma tissue. S2. Conduct drug absorption and conversion analysis based on the labeling of the drug's composition and metabolite composition; The specific steps are: S21, obtain the composition of the drug and the composition of the metabolites, obtain the composition of the consumed drug, obtain the composition of the consumed drug by subtracting the corresponding components remaining in the metabolites from the composition of each component of the consumed drug, obtain the distribution of various consumed drug components in various locations in the liver, and obtain the composition of the consumed drug and the conversion path of the generated metabolites based on the constructed metabolic pathway based on enzyme reactions. The specific steps are: obtain the historical enzyme concentration, the living environment of the enzyme (including temperature, humidity and pH, etc.), the composition of the consumed drug, the composition of the metabolites and the metabolic conversion path of the drug, and construct an enzyme concentration, enzyme living environment, consumed drug and other metabolic pathways. The deep learning neural network model that outputs the drug's metabolic transformation pathway is based on the composition of the components of the substance and the composition of the components of the metabolites. The transformation pathway of the drug into metabolites is analyzed based on the constructed deep learning neural network model. The transformation pathway includes the transformation of the drug in various tissues in the liver. By accurately measuring the content of the drug prototype and metabolites, combined with the drug residues in the excreta and serum, the actual consumption of the drug is quantitatively calculated. This method can correct the influence of the first-pass effect of the liver, ensure the accuracy of the metabolic kinetic data, and provide a reliable foundation for subsequent modeling. Using technologies such as mass spectrometry imaging, the concentration gradient distribution of the drug in different functional areas of the liver is visualized, revealing its differential penetration in tumor tissue and normal tissue. This helps to understand the targeting efficiency of the drug and provides a basis for optimizing the dosing regimen (such as local delivery). In combination with microenvironmental parameters such as metabolic enzyme activity, pH, and temperature, the LSTM neural network is used to dynamically predict the drug metabolic pathway, improving the accuracy of the prediction. The specific content of the neural network is as follows: First, the data collection stage: comprehensive collection of enzyme-related data, including enzyme concentration and the enzyme's living environment, such as temperature, humidity, and pH. These factors have a significant impact on enzyme activity and drug metabolism. At the same time, detailed records are recorded of the components of consumed drugs and the specific components of metabolites. In addition, in-depth research and recording of drug metabolic transformation pathways are carried out to provide a rich and accurate data foundation for subsequent model training. Then the data is divided, and the collected historical data is divided into 85% and 15% ratios, of which 85% of the data is used as weight and bias training sets for model training; the other 15% of the data is used as weight and bias test sets for performance evaluation of the trained model; then comes the model training phase. The 85% weight and bias training sets are input into the deep learning neural network model. During the training process, the model continuously adjusts its own parameters and structure to learn the patterns and features in the data. Through multiple iterations and optimizations, the initial deep learning neural network model is obtained; finally, the model is tested and screened, and the initial deep learning neural network model is tested using the 15% weight and bias test sets. During the test process, the focus is on the accuracy of the model's judgment of the drug metabolic transformation pathway. By continuously comparing the performance of different models, the initial deep learning neural network model that can meet the maximum metabolic transformation pathway judgment accuracy is screened out and used as the final deep learning neural network model; S22. Simultaneously obtain the tumor evolution status of each liver tissue and determine tumor abnormality based on the size, mutation load, and image changes of the tumor in each tissue; The specific steps are as follows: obtaining the size of tumor evolution, mutation load, and image changes of each tissue, where the image change is the average difference between the pixel value of a pixel point and the pixel value of normal tissue, dividing each by the corresponding set standard value to obtain a standardized value, and performing weighted summation to obtain the corresponding tumor abnormality judgment result; wherein the weighted weight is obtained through historical data experiments, that is, obtaining the abnormal damage caused by the tumor to the corresponding tissue, making the corresponding tissue unable to absorb and convert drugs, and integrating mutation, imaging and other data to quantify the degree of tissue functional damage, reflecting the decline in drug metabolism capacity, such as tumor damage to liver cytochrome enzymes (such as CYP3A4) leading to metabolic disorders; S23. Perform drug conversion and absorption analysis of the corresponding conversion pathway based on drug consumption and tumor abnormality determination of the corresponding tissue; The specific steps are: obtaining the tumor abnormality judgment results of each tissue along the conversion pathway of drugs into metabolites, and the corresponding drug consumption; The tumor abnormality judgment results on the conversion path are obtained by weighted summation based on the tumor abnormality judgment results of each tissue. The weighted weight here is allocated according to the proportion of the drug conversion amount of each tissue to the total drug conversion amount; The drug consumption coefficient is obtained by dividing the drug consumption by the corresponding drug consumption standard value. The corresponding drug conversion analysis result is obtained by dividing the drug consumption coefficient by the tumor abnormality judgment result. The inhibitory effect of the tumor on the metabolic pathway is directly evaluated by the ratio of the drug consumption coefficient to the tumor score. The higher the proportion of abnormal tissue, the lower the drug conversion rate. Weighted summation and normalization are common methods for multivariate data analysis. S3. Predict future drug conversion components based on drug absorption and conversion analysis results and the corresponding hepatocellular carcinoma evolution; The specific steps are as follows: S31, obtain the conversion analysis results of the corresponding drug and the tumor abnormality judgment results on the corresponding conversion pathway; integrate the drug conversion analysis results (such as metabolite concentration, enzyme activity) with the tumor abnormality score (such as imaging genomics characteristics, mutation load) to construct a multimodal time series data set, based on: Pharmacokinetic studies have shown that the tumor microenvironment (such as hypoxia) can significantly affect drug conversion efficiency; S32. Predicting future tumor abnormality determination results on the conversion path based on historical corresponding drug conversion analysis results and tumor abnormality determination results on the conversion path, wherein the prediction of future tumor abnormality determination results on the conversion path is performed using a deep learning neural network; The specific steps are as follows: obtaining historical conversion analysis results of corresponding drugs and tumor abnormality judgment results on the conversion path, dividing the obtained historical data into an 85% weighted and biased training set and a 15% weighted and biased test set; inputting the 85% weighted and biased training set into the deep learning neural network model for training to obtain an initial deep learning neural network model; using the 15% weighted and biased test set to test the initial deep learning neural network model, and outputting the initial deep learning neural network model output that meets the maximum accuracy rate for tumor abnormality judgment on the future conversion path as the deep learning neural network model; S33. Obtain the ratio of the predicted tumor abnormality judgment result on the future conversion path to the current tumor abnormality judgment result, divide the corresponding drug conversion analysis result by the corresponding ratio to obtain the future drug conversion analysis prediction result, and use the ratio of the future to current tumor abnormality scores as a correction factor for drug conversion efficiency; Basis: Changes in tumor burden are negatively correlated with drug metabolic clearance rate; Benefit: Adjusting the prediction result through dynamic ratio avoids misjudgment caused by static thresholds; S4. Early warning of drug treatment effects based on prediction of future drug conversion components; The specific steps are as follows: obtaining the predicted results of the future drug conversion analysis and comparing them with the set drug conversion analysis threshold; if the corresponding predicted results of the future drug conversion analysis are greater than or equal to the set drug conversion analysis threshold, it means that the drug effect is appropriate and no drug replacement warning is needed; if the corresponding predicted results of the future drug conversion analysis are less than the set drug conversion analysis threshold, it means that the drug effect is not appropriate and a drug replacement warning is needed; comparing the predicted results with the drug conversion threshold, triggering the warning, the threshold is usually obtained based on historical pharmacodynamics or clinical drug resistance threshold, and predicting a decrease in metabolic efficiency can trigger drug replacement in advance; The setting parameters (such as weights and thresholds) of this embodiment are determined by obtaining the evolution of hepatocellular carcinoma, the composition of drugs, and the composition of metabolites of various patients, obtaining the corresponding dressing change time, and simultaneously obtaining information of liver cancer patients whose survival time is greater than or equal to the average value and importing it into each step of this application to determine whether a dressing change is needed. At the same time, the result of whether the patient actually changes the dressing is obtained, and the actual result and the judgment result are imported into MATLAB fitting software to continuously fit the data to obtain the value of the setting parameters that meets the maximum judgment accuracy.

[0018] The benefits of this embodiment are: by integrating the evolutionary data of hepatocellular carcinoma, drug components and metabolite dynamics, and combining deep learning to build a multimodal time series prediction model, dynamic correlation analysis between drug metabolic pathways and tumor abnormality scores can be achieved. Through mass spectrometry imaging and enzyme activity correction of first-pass effects, the inhibitory effect of the tumor microenvironment on drug conversion is quantified, and the future tumor abnormality score ratio is used to dynamically adjust the prediction, thereby improving the accuracy of the timing of drug replacement.

[0019] Example 2

[0020] like Figure 4 As shown, this embodiment provides a hepatocellular carcinoma treatment effect analysis system based on comprehensive metabolic analysis, including the following modules: Data acquisition module, which obtains the evolution of hepatocellular carcinoma, the composition of drugs, and the composition of metabolites; Drug absorption and conversion analysis module, which performs drug absorption and conversion analysis based on the labeling of drug components and metabolite components; The future drug conversion component prediction module predicts future drug conversion components based on the drug absorption and conversion analysis results and the corresponding hepatocellular carcinoma evolution; The treatment effect early warning module provides early warning of drug treatment effects based on the prediction of future drug conversion components.

[0021] The above-mentioned parameters and steps for each unit module to achieve corresponding functions in the hepatocellular carcinoma treatment effect analysis system based on comprehensive metabolic analysis of the present invention can refer to the parameters and steps in the embodiment of the hepatocellular carcinoma treatment effect analysis method based on comprehensive metabolic analysis above, and will not be repeated here.

[0022] Example 3

[0023] An electronic device according to an embodiment of the present invention includes: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes a method for analyzing the therapeutic effect of hepatocellular carcinoma based on comprehensive metabolic analysis by calling the computer program stored in the memory. It should be noted that all computer programs of the method for analyzing the therapeutic effect of hepatocellular carcinoma based on comprehensive metabolic analysis are implemented in C language, wherein the data acquisition module, postoperative brain pathology complexity analysis module, recovery state dynamic analysis module, awakening risk assessment module, awakening intervention plan adjustment module, and control module are all controlled by a remote server.

[0024] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0025] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to the specific embodiments described. Obviously, many modifications and variations are possible based on the content of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for analyzing the therapeutic effect of hepatocellular carcinoma based on comprehensive metabolic analysis, characterized in that: The steps include: S1. Obtain the evolution of hepatocellular carcinoma, the composition of drugs, and the composition of metabolites; S2. Conduct drug absorption and conversion analysis based on the labeling of the drug's composition and metabolite composition; S3. Predict future drug conversion components based on drug absorption and conversion analysis results and the corresponding hepatocellular carcinoma evolution; S4. Early warning of drug treatment effects based on predictions of future drug conversion components.

2. The method for analyzing the therapeutic effect of hepatocellular carcinoma based on comprehensive metabolic analysis according to claim 1, characterized in that: The drug absorption conversion analysis includes the following specific steps: S21. Obtain the composition of the drug and its metabolites, obtain the composition of the consumed drug, obtain the composition of the consumed drug by subtracting the corresponding components remaining in the metabolites from the composition of each component of the consumed drug, obtain the distribution of various consumed drug components at various locations in the liver, and obtain the conversion pathway of the consumed drug composition and generated metabolites based on the constructed enzyme-based metabolic pathway; S22. Simultaneously obtain the tumor evolution status of each liver tissue and determine tumor abnormality based on the size, mutation load, and image changes of the tumor in each tissue; S23. Perform drug conversion and absorption analysis of the corresponding conversion pathway based on drug consumption and tumor abnormality judgment of the corresponding tissue.

3. The method for analyzing the therapeutic effect of hepatocellular carcinoma based on comprehensive metabolic analysis according to claim 2, characterized in that: The prediction of future drug conversion components specifically includes the following steps: S31. Obtain the conversion analysis results of the corresponding drug and the tumor abnormality judgment results on the corresponding conversion pathway; S32. Predicting future tumor abnormality determination results on the conversion path based on historical corresponding drug conversion analysis results and tumor abnormality determination results on the conversion path, wherein the prediction of future tumor abnormality determination results on the conversion path is performed using a deep learning neural network; The specific steps are as follows: obtaining historical conversion analysis results of corresponding drugs and tumor abnormality judgment results on the conversion path, dividing the obtained historical data into an 85% weighted and biased training set and a 15% weighted and biased test set; inputting the 85% weighted and biased training set into the deep learning neural network model for training to obtain an initial deep learning neural network model; using the 15% weighted and biased test set to test the initial deep learning neural network model, and outputting the initial deep learning neural network model output that meets the maximum accuracy rate for tumor abnormality judgment on the future conversion path as the deep learning neural network model; S33. Obtain the ratio of the predicted tumor abnormality judgment result on the future conversion path to the current tumor abnormality judgment result, and obtain the future drug conversion analysis prediction result by dividing the corresponding drug conversion analysis result by the corresponding ratio.

4. The method for analyzing the therapeutic effect of hepatocellular carcinoma based on comprehensive metabolic analysis according to claim 3, characterized in that: The method of providing early warning of drug treatment effects based on the prediction of future drug conversion components includes the following specific steps: Obtain the predicted results of future drug conversion analysis and compare them with the set drug conversion analysis threshold. If the corresponding predicted results of future drug conversion analysis are greater than or equal to the set drug conversion analysis threshold, it means that the drug effect is appropriate and no drug replacement warning is needed. If the corresponding predicted results of future drug conversion analysis are less than the set drug conversion analysis threshold, it means that the drug effect is not appropriate and a drug replacement warning is needed. Compare the predicted results with the drug conversion threshold to trigger the warning. Rationale: Thresholds are usually obtained based on historical pharmacodynamics or clinical resistance thresholds, and predicted decreased metabolic efficiency can trigger drug switching in advance.

5. The method for analyzing the therapeutic effect of hepatocellular carcinoma based on comprehensive metabolic analysis according to claim 4, characterized in that: The evolution of hepatocellular carcinoma in step S1 includes images before and after drug administration. Continuous imaging examinations are used to track the trajectory of tumor evolution, obtain changes in the tumor, and simultaneously obtain metabolic characteristics of the tumor microenvironment, including lactate and glutamine levels. The composition of the drug includes the composition, concentration, half-life, and tissue of action of the drug used, and the composition of the metabolite includes the drug concentration in the metabolite and the concentration of the component formed after drug conversion in the corresponding metabolite.

6. The method for analyzing the therapeutic effect of hepatocellular carcinoma based on comprehensive metabolic analysis according to claim 2, characterized in that: The tumor abnormality determination includes the following specific steps: The size of tumor evolution, mutation load, and image changes of the tumor are obtained for each tissue. The image change is the average value of the difference between the pixel value of the pixel point and the pixel value of normal tissue. The normalized value is obtained by dividing it with the corresponding set standard value, and the corresponding tumor abnormality judgment result is obtained after weighted summation.

7. The method for analyzing the therapeutic effect of hepatocellular carcinoma based on comprehensive metabolic analysis according to claim 2, characterized in that: The drug conversion and absorption analysis of the conversion pathway includes the following specific steps: Obtain the tumor abnormality judgment results of each tissue along the conversion pathway of drugs into metabolites, and the corresponding drug consumption; The tumor abnormality judgment results on the conversion path are obtained by weighted summation based on the tumor abnormality judgment results of each tissue. The weighted weight is allocated according to the proportion of the drug conversion amount of each tissue to the total drug conversion amount. The drug consumption coefficient is obtained by dividing the drug consumption by the corresponding drug consumption standard value, and the corresponding drug conversion analysis result is obtained by dividing the drug consumption coefficient by the tumor abnormality judgment result.

8. A hepatocellular carcinoma treatment effect analysis system based on comprehensive metabolic analysis, used to implement the hepatocellular carcinoma treatment effect analysis method based on comprehensive metabolic analysis according to any one of claims 1 to 7, characterized in that: The system comprises: Data acquisition module, which obtains the evolution of hepatocellular carcinoma, the composition of drugs, and the composition of metabolites; Drug absorption and conversion analysis module, which performs drug absorption and conversion analysis based on the labeling of drug components and metabolite components; The future drug conversion component prediction module predicts future drug conversion components based on the drug absorption and conversion analysis results and the corresponding hepatocellular carcinoma evolution; The treatment effect early warning module provides early warning of drug treatment effects based on the prediction of future drug conversion components.

9. An electronic device comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; characterized in that the processor executes the hepatocellular carcinoma treatment effect analysis method based on comprehensive metabolic analysis as described in any one of claims 1 to 7 by calling the computer program stored in the memory.

Images