Nutrition nursing intervention method and device for tumor radiotherapy and chemotherapy patients and medium

Abstract

The invention discloses a nutrition nursing intervention method and device for tumor chemoradiotherapy patients and a medium, and relates to the technical field of medical nursing, and the method comprises the steps: obtaining patient chemoradiotherapy regimen parameters, collecting tumor metabolism data, muscle metabolism data and serum circulating tumor marker concentration, and obtaining a monitoring data set; the monitoring data set comprises toxicity risk factors and radiation dose distribution; the monitoring data set is input into a tumor nutrition competition model to calculate a sweep coefficient, when the sweep coefficient exceeds a pathological threshold value, a deceptive nutrition starting instruction is generated, a composite risk value is calculated based on the toxicity risk factor and radiation dose distribution, and when the composite risk value exceeds a critical threshold value, a double-blocking protocol is triggered, and a decision instruction is generated; blending and applying a liposome injection, an oral controlled release preparation and a functional patch according to the decision instruction to form an integrated intervention composition; according to the method, the optimization of local intervention parameters is realized, and the local mucous membrane repair efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of medical and nursing technology, and in particular to a method, equipment and medium for nutritional nursing intervention for cancer patients undergoing radiotherapy and chemotherapy. Background Technology

[0002] With the continuous advancement of tumor diagnosis and treatment technologies, radiotherapy and chemotherapy, as core methods for the clinical treatment of malignant tumors, play an irreplaceable role in inhibiting tumor proliferation and controlling disease progression. However, while killing tumor cells, radiotherapy and chemotherapy also significantly disrupt the metabolic homeostasis of normal tissues, especially easily causing complications such as malnutrition, muscle atrophy, mucosal damage, and systemic toxicity, seriously affecting treatment adherence and prognosis. In recent years, individualized nutritional support strategies have gradually become an important component of comprehensive cancer treatment.

[0003] The main limitations of existing technologies are twofold: First, most nutritional assessment models fail to deeply integrate multidimensional data such as radiotherapy and chemotherapy regimen parameters, tumor metabolic activity, and circulating biomarkers, lacking quantitative analysis of the "tumor nutrient depletion effect" and its coupling mechanism with treatment toxicity, resulting in delayed intervention timing and insufficient targeting; Second, existing intervention methods are mostly independent modules (such as oral nutritional supplementation, intravenous infusion, etc.), lacking a multi-pathway synergistic regulation mechanism based on dynamic feedback, especially when dealing with local mucosal damage and systemic metabolic imbalance caused by uneven radiation dose distribution, it is difficult to achieve the combined effect of "deceptive nutritional supply" and "dual toxicity blocking" with precise spatiotemporal matching. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a nutritional care intervention method for cancer radiotherapy and chemotherapy patients to solve the problems of delayed timing of nutritional intervention and lack of dynamic synergistic regulation of multiple intervention methods in the prior art.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides a method for nutritional care intervention for cancer patients undergoing radiotherapy and chemotherapy, comprising: acquiring parameters of the patient's radiotherapy and chemotherapy regimen, collecting tumor metabolic data, muscle metabolic data, and serum circulating tumor marker concentrations, and acquiring a monitoring dataset; the monitoring dataset includes toxicity risk factors and radiation dose distribution; inputting the monitoring dataset into a tumor nutrition competition model to calculate a predation coefficient, generating a deceptive nutrition initiation command when the predation coefficient exceeds a pathological threshold, and calculating a composite risk value based on toxicity risk factors and radiation dose distribution, triggering a dual-blocking protocol and generating a decision command when the composite risk value exceeds a critical threshold; preparing and administering liposome injection, oral controlled-release preparation, and functional patch according to the decision command to form an integrated intervention composition; after the integrated intervention composition has been applied, detecting the rate of change in tumor metabolism and the mucosal healing rate, generating an optimized value for the predation coefficient, and dynamically updating the drug loading of the functional patch to generate a safety optimization parameter set; inputting the safety optimization parameter set into the tumor nutrition competition model to reset the baseline, and generating control parameters for the functional patch in the next cycle based on mucosal healing data; generating a nutritional care plan when the patient's pain feedback exceeds a warning threshold.

[0007] As a preferred embodiment of the nutritional care intervention method for cancer patients undergoing radiotherapy and chemotherapy according to the present invention, the specific steps for obtaining the monitoring dataset are as follows: Extract the types, doses, and radiotherapy target coordinates of radiotherapy and chemotherapy drugs from the electronic health record database, and simultaneously collect tumor metabolic data and muscle metabolic data to generate a basic treatment metabolic set. Serum circulating tumor marker concentrations were detected, and combined with the basic treatment metabolic set, neurotoxicity risk scores and mucosal irradiation risk scores were calculated to generate a molecular-toxicity joint dataset. By integrating basic therapeutic metabolic datasets and molecular-toxicity joint datasets, and through structured data encoding, monitoring datasets are obtained.

[0008] As a preferred embodiment of the nutritional care intervention method for cancer patients undergoing radiotherapy and chemotherapy according to the present invention, the specific steps for generating the deceptive nutrition activation instruction are as follows: The tumor metabolic data, muscle metabolic data, and radiation dose distribution in the monitoring dataset are input into the tumor nutrient competition model and mapped to a metabolism-dose coupled manifold using differential geometry methods to generate manifold parameters. Based on manifold parameters, the predation coefficient is calculated by integrating topological invariants. When the predation coefficient exceeds the pathological threshold, a metabolic abnormality signal is generated. In response to abnormal metabolic signals, a deceptive nutrient activation command is generated through field theory transformation.

[0009] As a preferred embodiment of the nutritional care intervention method for cancer patients undergoing radiotherapy and chemotherapy according to the present invention, the specific steps for generating decision instructions are as follows: By mapping toxicity risk factors to quantum external field strength and radiation dose distribution to spin coupling strength, a set of quantum parameters is generated. Based on the quantum parameter set, the composite risk value is calculated through neuromorphic quantum computing. When the composite risk value exceeds the critical threshold, a dual blocking activation signal is generated. Decision instructions are generated based on deceptive nutrient activation instructions and dual-blocking activation signals.

[0010] As a preferred embodiment of the nutritional care intervention method for cancer patients undergoing radiotherapy and chemotherapy according to the present invention, the specific steps for forming the integrated intervention composition are as follows: Based on the surface modification parameters in the decision-making instructions, drug-loaded liposomes were prepared and modified with a biomimetic coating of apolipoprotein E to generate liposome injection solution. Based on decision-making instructions, core-shell structured spatiotemporal controlled-release capsules were prepared to generate oral controlled-release formulations; Based on the decision-making instructions, a functional patch containing a topological insulator matrix is ​​applied to a designated body part to generate a positioning patch; Liposome injection, oral controlled-release formulation, and positioning patch are integrated into a single intervention composition using bioprinting technology.

[0011] As a preferred embodiment of the nutritional care intervention method for cancer patients undergoing radiotherapy and chemotherapy according to the present invention, the specific steps for generating the optimized value of the predation coefficient are as follows: After the integrated intervention composition was administered, the rate of tumor metabolic changes and mucosal healing rate were detected, and the patient pain feedback index was collected to generate a efficacy dataset. Based on the therapeutic efficacy dataset, the optimal value of the plunder coefficient is generated by iteratively converging to a steady-state solution through nonlinear dynamic coupling equations.

[0012] As a preferred embodiment of the nutritional care intervention method for cancer patients undergoing radiotherapy and chemotherapy according to the present invention, the specific steps for generating the safety optimization parameter set are as follows: Based on the optimized value of the predation coefficient and the mucosal healing rate, the drug loading and release frequency of the functional patch are updated through the microwave resonant response equation to generate the control parameters of the functional patch. The control parameters of functional patches are constrained by toxicity thresholds and validated for efficacy prediction, generating a set of safety optimization parameters.

[0013] As a preferred embodiment of the nutritional care intervention method for cancer patients undergoing radiotherapy and chemotherapy according to the present invention, the specific steps for generating the nutritional care plan are as follows: The safe and optimized parameter set is input into the tumor nutrition competition model, and the future metabolic-healing synergistic effect is obtained through the mucosa-metabolic prospective operator, and a reset tumor nutrition competition model is generated. Based on the reset tumor nutrient competition model, the control parameters for the next cycle of functional patches are generated through the spatiotemporal distribution function; In the next cycle, based on the current effects of the functional patch, the patient's pain feedback data stream will be collected in real time, and the patient's pain index will be calculated. At the same time, a nutritional care plan will be generated using a cross-departmental decision-making mechanism.

[0014] In a second aspect, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the nutritional care intervention method for cancer radiotherapy and chemotherapy patients as described in the first aspect of the present invention.

[0015] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein, when the computer program is executed by a processor, it implements any step of the nutritional care intervention method for cancer radiotherapy and chemotherapy patients as described in the first aspect of the present invention.

[0016] The beneficial effects of this invention are as follows: by calculating the plunder coefficient through topological invariant integration, the geometric and dynamic quantitative modeling of the tumor nutrient plunder effect is realized, breaking through the limitations of traditional static nutrient assessment; by dynamically updating the drug loading of the functional patch through the microwave resonance response equation, the adaptive optimization of local intervention parameters is realized, thereby improving the efficiency of local mucosal repair. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart of nutritional care intervention methods for cancer patients undergoing radiotherapy and chemotherapy.

[0019] Figure 2 A flowchart for generating the monitoring dataset.

[0020] Figure 3 This is a flowchart for calculating the plunder coefficient.

[0021] Figure 4 A flowchart for generating an integrated intervention composition. Detailed Implementation

[0022] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0023] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0024] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0025] Reference Figures 1-4 As one embodiment of the present invention, this embodiment provides a nutritional care intervention method for cancer radiotherapy and chemotherapy patients, including the following steps: S1: Obtain the patient's radiotherapy and chemotherapy regimen parameters, and collect tumor metabolic data, muscle metabolic data, and serum circulating tumor marker concentrations, and obtain a monitoring dataset; the monitoring dataset includes toxicity risk factors and radiation dose distribution.

[0026] The types, doses, and target coordinates of radiotherapy and chemotherapy drugs are extracted from the electronic health record database, and tumor metabolic data and muscle metabolic data are collected simultaneously to generate a basic treatment metabolic set.

[0027] The specific process includes extracting the types, dose intensities, and target coordinates of radiotherapy and chemotherapy drugs from the electronic health record database. Simultaneously, standardized uptake values ​​of the tumor region and lactate concentration in muscle tissue are collected through positron emission tomography and magnetic resonance spectroscopy. The types, dose intensities, target coordinates, standardized uptake values ​​of the tumor region, and lactate concentration in muscle tissue are integrated into a structured dataset to generate a basic treatment metabolism set, which is used for subsequent calculation of tumor nutrition competition models and optimization of intervention strategies.

[0028] Serum circulating tumor marker concentrations were measured, and combined with the baseline treatment metabolic set, neurotoxicity risk scores and mucosal irradiation risk scores were calculated to generate a molecular-toxicity joint dataset, expressed as: ; ; in, Indicates neurotoxicity risk score, This indicates the cumulative dose of oxaliplatin. Indicates the patient's age. This represents the weighting coefficient of the molecule correction term. This indicates the reference concentration of circulating tumor DNA in serum. This indicates the concentration of circulating tumor DNA in the serum. Indicates the risk score of mucosal exposure to radiation. Represents the space-time coupling coefficient. Indicates the number of voxels in the mucosal region. Voxel numbers representing mucosal regions Represents the S-type dose response function. Indicates the first Spatial coordinates of individual elements Represents spatial coordinates The radiation dose value at that location, Represents spatial coordinates Anatomical weighting factors at the location, This represents the natural exponential function. This indicates the time interval after the end of radiotherapy. This represents the time constant for mucosal repair. This represents the weighting coefficient of the radiomics term. Represents spatial coordinates Radiomics risk score.

[0029] The specific process includes detecting serum circulating tumor marker concentrations using electrochemiluminescence immunoassay; performing multi-parameter regression analysis on serum circulating tumor marker concentrations with the types, dose intensities, radiotherapy target coordinates, standardized tumor uptake values, and muscle tissue lactate concentrations within the baseline treatment metabolic focus; calculating a neurotoxicity risk score using logistic regression; and simultaneously calculating a mucosal irradiation risk score based on radiotherapy target coordinates and dose intensities using a linear quadratic equation. The neurotoxicity risk score and mucosal irradiation risk score are then integrated with the serum circulating tumor marker concentrations into structured data, generating a molecular-toxicity joint dataset. This molecular-toxicity joint dataset contains multidimensional correlation features between treatment parameters, metabolic indicators, and toxicity scores, used for subsequent calculation of composite risk values ​​and intervention decisions.

[0030] Integrate basic therapeutic metabolic datasets and molecular-toxicity joint datasets, encode structured data, and acquire monitoring datasets.

[0031] The specific process involves aligning the types, dose intensities, radiotherapy target coordinates, standardized tumor uptake values, and muscle tissue lactate concentrations of the basic treatment metabolic dataset with the serum circulating tumor marker concentrations, neurotoxicity risk scores, and mucosal radiation risk scores from the molecular-toxicity joint dataset. A structured data coding method is used to uniformly map the fields of both datasets to a standardized format. Key features are then merged using data fusion techniques to generate a monitoring dataset. This monitoring dataset integrates complete information on treatment parameters, metabolic indicators, toxicity scores, and molecular markers for subsequent dynamic calculation of the predation coefficient and composite risk value.

[0032] The monitoring dataset includes toxicity risk factors and radiation dose distribution.

[0033] It should be noted that toxicity risk factors and radiation dose distribution are key indicators derived from the integration of multi-source clinical data. Toxicity risk factors include a neurotoxicity risk score and a mucosal radiation risk score. The neurotoxicity risk score is derived from the type of radiotherapy / chemotherapy drug, cumulative dose, patient age, and serum circulating tumor DNA concentration. The mucosal radiation risk score is derived from dose distribution data in the radiotherapy plan and analysis of patient anatomical images. Radiation dose distribution is directly derived from the radiotherapy plan. A three-dimensional dose matrix is ​​exported in DICOM-RT format and spatially registered with patient images to ensure accurate mapping of dose values ​​to anatomical structures. After structured processing and quality control, this data is used to generate a monitoring dataset, providing a quantitative basis for subsequent intervention strategies.

[0034] Key features include a basic therapeutic metabolic dataset (chemoradiotherapy drug type / dose intensity / radiotherapy target coordinates / tumor metabolic data / muscle metabolic data) and a molecular-toxicity joint dataset (serum circulating tumor marker concentration / neurotoxicity risk score / mucosal irradiation risk score), which are fused and generated through structured data encoding technology to quantify tumor nutrient depletion and toxicity risk.

[0035] S2: Input the monitoring dataset into the tumor nutrition competition model to calculate the predation coefficient. When the predation coefficient exceeds the pathological threshold, generate a deceptive nutrition initiation command. Calculate the composite risk value based on toxicity risk factors and radiation dose distribution. When the composite risk value exceeds the critical threshold, trigger the dual blocking protocol and generate a decision command.

[0036] The tumor metabolic data, muscle metabolic data, and radiation dose distribution from the monitoring dataset are input into the tumor nutrient competition model and mapped to a metabolism-dose coupled manifold using differential geometry methods to generate manifold parameters.

[0037] The specific process involves inputting the standardized uptake sequence of tumor metabolic data, the rate of change in lactate concentration from muscle metabolic data, and the gradient vector of radiation dose distribution from the monitoring dataset into a tumor nutrient competition model. The spatiotemporal characteristics of these three types of data are uniformly mapped to an eight-dimensional pseudo-Riemannian space using a Riemannian manifold embedding method. Differential homeomorphism is then used to maintain the topological correlation between the data, yielding the curvature tensor and connection coefficients on the manifold, thus generating metabolism-dose coupled manifold parameters. These parameters fully characterize the dynamic interaction between tumor predation and normal tissue defense, providing a geometric basis for calculating the predation coefficient.

[0038] Furthermore, the pre-training process of the tumor nutrient competition model involves constructing a training set by collecting tumor metabolic indicators, muscle metabolic indicators, and radiotherapy parameters from historical clinical treatment data. A deep neural network architecture is used to initialize the model weights, and the backpropagation algorithm is employed to optimize the feature extraction capability of the metabolism-dose coupling manifold. Parameter tuning is completed by minimizing the root mean square error between the prediction error of the plunder coefficient and the actual clinical observations. Finally, a pre-trained tumor nutrient competition model with metabolic state assessment and nutrient competition prediction functions is generated. This pre-training process ensures that the tumor nutrient competition model can accurately identify abnormal changes in metabolic pathways within the tumor microenvironment, providing a reliable computational foundation for real-time intervention decisions.

[0039] Based on manifold parameters, the predation coefficient is calculated through topological invariant integration. When the predation coefficient exceeds the pathological threshold, a metabolic abnormality signal is generated, expressed as: ; in, Indicates the plunder coefficient. Represents manifold parameters, Represents the determinant of the metric tensor. Represents Ricci scalar curvature. Represents four-dimensional spacetime coordinates.

[0040] The specific process involves calculating the topological invariants of closed loops on the manifold using the Chern-Wey integral method based on the metric and curvature tensors in the manifold parameters. The integral results are then coupled with the mucosal healing rate via a hyperbolic tangent function to generate a predation coefficient. When the predation coefficient exceeds a pathological threshold, a metabolic abnormality signal generation process is triggered. This metabolic abnormality signal contains information on the intensity of predation and the direction of metabolic imbalance, which guides subsequent adjustments to intervention strategies.

[0041] The pathological threshold is preset by analyzing the correlation between the predation coefficient and the incidence of grade III or higher toxicity in historical clinical data.

[0042] In response to abnormal metabolic signals, a deceptive nutrient activation command is generated through field theory transformation.

[0043] The specific process includes constructing a canonical field communication form triggered by abnormal metabolic signals, using the predation coefficient and mucosal healing rate in the abnormal metabolic signals as canonical potential inputs, obtaining a phase factor through Wilson line integrals, and performing a canonical transformation on the phase factor and the basic nutritional formula to generate a deceptive nutrient initiation instruction. This deceptive nutrient initiation instruction includes modified amino acid ratios and liposome surface receptor camouflage strategies to interfere with tumor nutrient predation behavior.

[0044] The basic nutritional formula is generated by integrating the nutritional baseline values ​​of healthy people with the differences in resting metabolic needs of cancer patients. Specifically, it includes the standard amino acid ratio, essential fatty acid threshold, and trace element ratio, which are used as the benchmark for subsequent deceptive nutritional interventions.

[0045] The toxicity risk factor is mapped to the quantum external field strength, and the radiation dose distribution is mapped to the spin coupling strength, thus generating a set of quantum parameters.

[0046] The specific process involves normalizing the neurotoxicity risk score and mucosal irradiation risk score from the toxicity risk factors and using them as quantum external field intensity components. It also involves normalizing the gradient vector magnitude in the radiation dose distribution and using it as the spin coupling strength component. A Hamiltonian representation of the quantum external field and spin coupling is constructed using the Pauli matrix, generating a quantum parameter set containing external field intensity, coupling strength, and quantum tunneling coefficient. This quantum parameter set fully encodes the quantum characteristics of the toxicity-dose interaction, providing a quantum mechanical basis for subsequent calculations of the composite risk value.

[0047] Based on the quantum parameter set, a composite risk value is calculated using neuromorphic quantum computing. When the composite risk value exceeds a critical threshold, a dual-blocking activation signal is generated, expressed as follows: ; in, Indicates the composite risk value. Let K represent the activation function, K represent the total number of quantum neurons, and k represent the index of the quantum neuron. To take the real part of a complex number, Indicates the first The conjugate transpose of a quantum neuron state Represents a weighted quantum observation operator.

[0048] The specific process includes calculating the ground-state wavefunction using a variable quantum eigenvalue solver based on the quantum external field strength, spin coupling strength, and quantum tunneling coefficient from the quantum parameter set. The real part of the Pauli operator's expectation value is extracted, and a weighted average is performed using a Chern phase modulation factor to generate a composite risk value. When the composite risk value exceeds a critical threshold, a dual-blocking activation signal generation process is triggered. The nerve blocking dose and mucosal blocking dose are calculated using a non-equilibrium diffusion equation, and a dual-blocking activation signal is output. This dual-blocking activation signal contains blocking parameters and execution timing, guiding the formulation of subsequent intervention compositions.

[0049] The critical threshold is preset by analyzing the correlation between composite risk values ​​and severe treatment toxicity events in historical clinical data.

[0050] Decision instructions are generated based on deceptive nutrient activation instructions and dual-blocking activation signals.

[0051] The specific process involves co-optimizing the amino acid ratio adjustment parameters and liposome camouflage parameters in the deceptive nutritional initiation command with the neural blocking dose and mucosal blocking dose in the dual-blocking activation signal. A multi-objective decision-making algorithm is then used to generate a joint command encompassing the nutritional intervention protocol and the dual-blocking strategy, outputting a decision command. This decision command integrates the dual intervention logic of nutritional deception and toxicity blocking to guide the precise formulation and administration of the physical intervention composition.

[0052] S3: Prepare and administer liposome injections, oral controlled-release formulations, and functional patches according to decision-making instructions to form an integrated intervention composition.

[0053] Based on the surface modification parameters in the decision-making instructions, drug-loaded liposomes were prepared and modified with a biomimetic coating of apolipoprotein E to generate liposome injection solution.

[0054] The specific process includes: according to the surface modification parameters in the decision-making instructions, mixing phosphatidylcholine and cholesterol in a certain proportion to form a lipid bilayer membrane; preparing drug-loaded liposomes via thin-film hydration; and using a microfluidic chip to mix the apolipoprotein E solution with the liposome suspension in laminar flow mode, allowing the apolipoprotein E to embed into the liposome surface through hydrophobic interactions, forming a biomimetic coating-modified liposome injection solution. The liposome injection solution contains a preset drug loading capacity and targeted modification characteristics, and is used for intravenous infusion intervention.

[0055] Based on decision-making instructions, core-shell structured spatiotemporal controlled-release capsules are prepared to generate oral controlled-release formulations.

[0056] The specific process involves, based on the spatiotemporal release parameters in the decision-making instructions, forming a core-shell structure precursor by coaxial microfluidic printing of sodium alginate and chitosan solution. The core is then solidified in a calcium ion crosslinking bath, and a near-infrared laser is used to trigger the gradient crosslinking of the shell's photosensitive hydrogel, thus achieving the preparation of a 4D-printed spatiotemporally controlled-release capsule. The oral controlled-release formulation possesses dual controlled-release characteristics of a pH-responsive core and a temperature-sensitive shell, ensuring that the drug is released in the target intestinal segment according to a preset time sequence.

[0057] The preset release timing is based on the dynamic coupling relationship between mucosal healing rate and predation coefficient in the decision command, and the optimal release curve is obtained through Legendre polynomial time basis function and metabolism-dose synergy.

[0058] Based on the decision-making instructions, a functional patch containing a topological insulator matrix is ​​applied to a designated body part to generate a positioning patch.

[0059] The specific process involves preparing a topological insulator matrix by combining bismuth selenide nanosheets with polyethylene glycol hydrogel based on the target area coordinates and blocking dose parameters in the decision-making instructions. Then, using electrospinning technology, the matrix is ​​loaded with a nerve-blocking agent and mucosal repair peptides. Under MRI guidance, the functional patch is precisely applied to the radiotherapy-damaged target area, generating a localization patch. This localization patch possesses microwave resonance response characteristics and conformal fitting capabilities to anatomical structures, enabling on-demand drug release and bioelectrical signal modulation.

[0060] Liposome injection, oral controlled-release formulation, and positioning patch are integrated into a single intervention composition using bioprinting technology.

[0061] The specific process involves simultaneously depositing drug-loaded liposome suspensions from liposome injection solutions, core-shell capsule powders from oral controlled-release formulations, and topological insulator nanofiber membranes from topical patches using a multi-nozzle bioprinter. A three-dimensional heterogeneous structure is then constructed using in-situ cross-linking with calcium alginate, generating an integrated intervention composition. This integrated intervention composition incorporates a synergistic intervention mechanism of intravenous infusion, oral delivery, and topical application, achieving multimodal combined therapy.

[0062] S4: After the integrated intervention composition is applied, the rate of change in tumor metabolism and the rate of mucosal healing are detected, the optimal value of the predation coefficient is generated, and the drug loading of the functional patch is dynamically updated to generate a set of safety optimization parameters.

[0063] After the integrated intervention composition was administered, the rate of tumor metabolic changes and mucosal healing rate were detected, and the patient pain feedback index was collected to generate a efficacy dataset.

[0064] The specific process includes, after the administration of the integrated intervention composition, dynamically monitoring the rate of change of standardized uptake values ​​in the tumor region using positron emission tomography (PET), measuring the reduction rate of mucosal ulcer area using optical coherence tomography (OCT), and simultaneously acquiring the output of the EEG cap. Band power density is used as a pain feedback index. The tumor metabolic change rate, mucosal healing rate, and pain feedback index are aligned by timestamps and stored in a structured manner to generate a treatment efficacy dataset. This dataset contains time-series correlation records between treatment response indicators and symptom relief levels, which are used for subsequent iterative optimization of the predation coefficient and risk value.

[0065] Based on the therapeutic efficacy dataset, the optimal value of the plunder coefficient is generated by iteratively converging to a steady-state solution through nonlinear dynamic coupling equations.

[0066] The specific process includes constructing a nonlinear dynamic equation containing a metabolism-healing-pain coupling term based on the tumor metabolic change rate, mucosal healing rate, and pain feedback index in the efficacy dataset. A phase space trajectory is generated using the implicit Runge-Kutta method. Convergence to a steady-state solution is determined when all real parts of the Jacobian matrix eigenvalues ​​are less than zero, and the optimized predation coefficient is output. The optimized predation coefficient reflects the dynamic equilibrium between the intervention composition and the patient's physiological response and is used to update the decision instructions for the next cycle.

[0067] Based on the optimized value of the predation coefficient and the mucosal healing rate, the drug loading and release frequency of the functional patch are updated through the microwave resonant response equation to generate the control parameters of the functional patch.

[0068] The specific process includes linearly mapping the dielectric constant of bismuth selenide nanosheets to the optimized value of the plunder coefficient and the mucosal healing rate, converting it into a microwave resonant frequency offset. Simultaneously, the drug loading gradient is adjusted according to the logarithm of the mucosal healing rate. The drug diffusion rate under thermodynamic equilibrium is obtained through the Maxwell-Boltzmann distribution, generating control parameters for the functional patch. These control parameters include frequency modulation carrier waves and sustained-release kinetic curves, enabling on-demand triggering of drug release and regulation of bioelectrical signals.

[0069] The control parameters of functional patches are constrained by toxicity thresholds and validated for efficacy prediction, generating a set of safety optimization parameters.

[0070] The specific process involves comparing the drug loading in the functional patch's control parameters with the FDA-approved maximum tolerated dose of neuroblockers, forcibly cutting off any values ​​exceeding the limit, and simultaneously using a support vector machine classifier to predict the synergistic effect between the mucosal repair rate and the optimized predation coefficient. This process screens parameter combinations that meet the expected levels of toxicity, safety, and efficacy, generating a safety-optimized parameter set. This safety-optimized parameter set includes double-validated drug loading, release frequency, and target coordinates, used for the precise preparation of the next cycle's intervention composition.

[0071] S5: Input the safety optimization parameter set into the tumor nutrition competition model to reset the baseline, and generate the control parameters for the next cycle of functional patches based on mucosal healing data. When the patient's pain feedback exceeds the warning threshold, a nutritional care plan is generated.

[0072] The safe and optimized parameter set is input into the tumor nutrition competition model, and the future metabolic-healing synergistic effect is obtained through the mucosa-metabolic prospective operator, and a reset tumor nutrition competition model is generated.

[0073] The specific process includes inputting drug loading, release frequency, and target coordinates from the safety optimization parameter set into the tumor nutrition competition model; coupling the optimized values ​​of mucosal healing rate and predation coefficient through a Legendre polynomial time basis function to derive a mucosal-metabolic prospective operator; adjusting the metabolic flux weights and radiation response coefficients in the tumor nutrition competition model based on the output of the mucosal-metabolic prospective operator to generate a reset tumor nutrition competition model. The reset tumor nutrition competition model contains updated metabolic-dose dynamic balance parameters for optimizing the treatment strategy in the next cycle.

[0074] Based on the reset tumor nutrient competition model, control parameters for the next cycle of functional patches are generated through a spatiotemporal distribution function.

[0075] The specific process includes: based on the metabolic-dose dynamic balance parameters output by the reset tumor nutrient competition model, mapping the mucosal healing rate and the optimized value of the predation coefficient to a spatiotemporal distribution function using a Fourier-Bessel expansion; obtaining the dielectric constant gradient and drug diffusion rate of the bismuth selenide nanosheets; and generating control parameters for the next cycle of the functional patch. The control parameters for the next cycle of the functional patch include a frequency modulation carrier wave and a sustained-release kinetic curve, enabling on-demand triggering of drug release and regulation of bioelectrical signals.

[0076] In the next cycle, based on the current efficacy of the functional patch, real-time data streams of patient pain feedback will be collected, and the patient pain index will be calculated. Simultaneously, a nutritional care plan will be generated using a cross-disciplinary decision-making mechanism, expressed as: ; in, Indicates the current time point, Indicates the current time point The patient's pain index at the site Indicates the length of the integration time window. Represents the time variable of integration. This indicates the Hanning window function at time point The weight value, Indicates a point in time EEG collected at the site Band power spectral density, This indicates the patient's electroencephalogram (EEG) in a painless, resting state. The baseline value of the band power spectral density, This indicates the electroencephalogram (EEG) value corresponding to the patient's pain response reaching its maximum intensity. Peak value of the power spectral density in the band. EEG data indicating the patient's pain-free state Minimum reference value for band power spectral density.

[0077] The specific process includes, in the next cycle, collecting real-time pain feedback data streams from patients based on the current effectiveness of the functional patch, and transmitting this data via electroencephalography (EEG). The dynamic normalization method for band power density is used to calculate the patient's pain index. This pain index is then compared to the acute critical threshold output by a tumor nutrition competition model. When the patient's pain index exceeds the acute critical threshold, a cross-disciplinary decision-making mechanism is triggered to integrate intervention strategies from neurology and nutrition departments, generating a nutritional care plan that includes amino acid modification ratios and inhibitor dosages. This nutritional care plan is then prepared into the next cycle's intervention composition using bioprinting technology, completing the treatment loop.

[0078] The acute critical threshold is preset by analyzing the correlation between patients' pain index and grade 3 or higher toxic events in historical clinical data.

[0079] This embodiment also provides a computer device applicable to the nutritional care intervention method for cancer radiotherapy and chemotherapy patients, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the nutritional care intervention method for cancer radiotherapy and chemotherapy patients as proposed in the above embodiment.

[0080] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0081] This embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements the nutritional care intervention method for cancer radiotherapy and chemotherapy patients as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0082] In summary, this invention achieves geometric and dynamic quantitative modeling of the tumor nutrient depletion effect by calculating the depletion coefficient through topological invariant integration, breaking through the limitations of traditional static nutrient assessment; and optimizes local intervention parameters by dynamically updating the drug loading of the functional patch through the microwave resonant response equation, thereby improving the efficiency of local mucosal repair.

[0083] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A nutritional nursing intervention method for cancer patients undergoing radiotherapy and chemotherapy, characterized in that: include, The parameters of the patient's radiotherapy and chemotherapy regimen were obtained, and tumor metabolic data, muscle metabolic data, and serum circulating tumor marker concentrations were collected to obtain a monitoring dataset; the monitoring dataset included toxicity risk factors and radiation dose distribution. The monitoring dataset is input into the tumor nutrition competition model to calculate the predation coefficient. When the predation coefficient exceeds the pathological threshold, a deceptive nutrition initiation instruction is generated. Based on the toxicity risk factor and radiation dose distribution, the composite risk value is calculated. When the composite risk value exceeds the critical threshold, the dual blocking protocol is triggered and a decision instruction is generated. Based on decision-making instructions, liposome injections, oral controlled-release formulations, and functional patches are formulated and administered to form an integrated intervention composition; After the integrated intervention composition is applied, the rate of change in tumor metabolism and the rate of mucosal healing are detected, the optimal value of the predation coefficient is generated, and the drug loading of the functional patch is dynamically updated to generate a set of safety optimization parameters. The safety optimization parameter set is input into the tumor nutrition competition model to reset the baseline, and the control parameters for the next cycle of functional patches are generated based on mucosal healing data. When the patient's pain feedback exceeds the warning threshold, a nutritional care plan is generated.

2. The nutritional care intervention method for cancer patients undergoing radiotherapy and chemotherapy as described in claim 1, characterized in that: The specific steps for obtaining the monitoring dataset are as follows: Extract the types, doses, and radiotherapy target coordinates of radiotherapy and chemotherapy drugs from the electronic health record database, and simultaneously collect tumor metabolic data and muscle metabolic data to generate a basic treatment metabolic set. Serum circulating tumor marker concentrations were detected, and combined with the basic treatment metabolic set, neurotoxicity risk scores and mucosal irradiation risk scores were calculated to generate a molecular-toxicity joint dataset. By integrating basic therapeutic metabolic datasets and molecular-toxicity joint datasets, and through structured data encoding, monitoring datasets are obtained.

3. The nutritional care intervention method for cancer patients undergoing radiotherapy and chemotherapy as described in claim 2, characterized in that: The specific steps for generating the deceptive nutrient activation command are as follows: The tumor metabolic data, muscle metabolic data, and radiation dose distribution in the monitoring dataset are input into the tumor nutrient competition model and mapped to a metabolism-dose coupled manifold using differential geometry methods to generate manifold parameters. Based on manifold parameters, the predation coefficient is calculated by integrating topological invariants. When the predation coefficient exceeds the pathological threshold, a metabolic abnormality signal is generated. In response to abnormal metabolic signals, a deceptive nutrient activation command is generated through field theory transformation.

4. The nutritional care intervention method for cancer patients undergoing radiotherapy and chemotherapy as described in claim 3, characterized in that: The specific steps for generating the decision instruction are as follows: By mapping toxicity risk factors to quantum external field strength and radiation dose distribution to spin coupling strength, a set of quantum parameters is generated. Based on the quantum parameter set, the composite risk value is calculated through neuromorphic quantum computing. When the composite risk value exceeds the critical threshold, a dual blocking activation signal is generated. Decision instructions are generated based on deceptive nutrient activation instructions and dual-blocking activation signals.

5. The nutritional care intervention method for cancer patients undergoing radiotherapy and chemotherapy as described in claim 4, characterized in that: The specific steps for forming the integrated intervention composition are as follows: Based on the surface modification parameters in the decision-making instructions, drug-loaded liposomes were prepared and modified with a biomimetic coating of apolipoprotein E to generate liposome injection solution. Based on decision-making instructions, core-shell structured spatiotemporal controlled-release capsules were prepared to generate oral controlled-release formulations; Based on the decision-making instructions, a functional patch containing a topological insulator matrix is ​​applied to a designated body part to generate a positioning patch; Liposome injection, oral controlled-release formulation, and positioning patch are integrated into a single intervention composition using bioprinting technology.

6. The nutritional care intervention method for cancer patients undergoing radiotherapy and chemotherapy as described in claim 5, characterized in that: The specific steps for generating the optimized plunder coefficient value are as follows: After the integrated intervention composition was administered, the rate of tumor metabolic changes and mucosal healing rate were detected, and the patient pain feedback index was collected to generate a efficacy dataset. Based on the therapeutic efficacy dataset, the optimal value of the plunder coefficient is generated by iteratively converging to a steady-state solution through nonlinear dynamic coupling equations.

7. The nutritional care intervention method for cancer patients undergoing radiotherapy and chemotherapy as described in claim 6, characterized in that: The specific steps for generating the security optimization parameter set are as follows: Based on the optimized value of the predation coefficient and the mucosal healing rate, the drug loading and release frequency of the functional patch are updated through the microwave resonant response equation to generate the control parameters of the functional patch. The control parameters of functional patches are constrained by toxicity thresholds and validated for efficacy prediction, generating a set of safety optimization parameters.

8. The nutritional care intervention method for cancer patients undergoing radiotherapy and chemotherapy as described in claim 7, characterized in that: The specific steps for generating the nutritional care plan are as follows. The safe and optimized parameter set is input into the tumor nutrition competition model, and the future metabolic-healing synergistic effect is obtained through the mucosa-metabolic prospective operator, and a reset tumor nutrition competition model is generated. Based on the reset tumor nutrient competition model, the control parameters for the next cycle of functional patches are generated through the spatiotemporal distribution function; In the next cycle, based on the current effects of the functional patch, the patient's pain feedback data stream will be collected in real time, and the patient's pain index will be calculated. At the same time, a nutritional care plan will be generated using a cross-departmental decision-making mechanism.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the nutritional care intervention method for cancer radiotherapy and chemotherapy patients as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the nutritional care intervention method for cancer radiotherapy and chemotherapy patients as described in any one of claims 1 to 8.

Images