Auxiliary generation method and system for personalized medication blood concentration prediction algorithm

Abstract

The present application discloses an auxiliary generation method and system for an individualized medication blood concentration prediction algorithm. The method first extracts the model parameters of the existing medication blood concentration prediction model and uses machine learning technology to feature encode the model parameters of each medication blood concentration prediction model to learn the relationship between the various parameters in the model. Then, by performing multi-dimensional energy potential analysis on the parameter information of each medication blood concentration prediction model, the kernel features of the model parameters are dynamically aggregated to learn the core distribution pattern of the model parameters, and then based on this, the model parameters are restored to generate a new medication blood concentration prediction model. Through this intelligent model generation method, the complexity of model construction can be significantly reduced, which helps to improve the accuracy of individualized medication blood concentration prediction and provide clinicians with more scientific and accurate medication guidance.

Description

Technical Field

[0001] The present application relates to the field of intelligent prediction, and more specifically, to a method and system for assisting in generating an algorithm for predicting individualized medication blood concentration. Background Art

[0002] In clinical treatment, drug blood concentration is an important factor in determining drug efficacy and safety. However, changes in the patient's physiological and pathological characteristics may cause the drug's pharmacokinetic characteristics to differ from those of healthy volunteers, resulting in some patients experiencing poor efficacy due to low blood drug concentrations, and some patients experiencing adverse reactions due to high blood drug concentrations. Therefore, the standard dosing regimen recommended in the instructions may not necessarily be suitable for clinical patients. In clinical practice, further monitoring of blood drug concentrations is needed to guide clinicians in developing individualized drug dosing regimens based on patient characteristics.

[0003] A model predicting blood drug concentration after medication use uses mathematical and statistical methods to predict changes in drug concentration in the patient's body based on the drug's pharmacokinetic properties. Specifically, population pharmacokinetics, through the establishment of a personalized mathematical model for medication use, calculates the appropriate dosage distribution based on the patient's physiological parameters. Doctors can use the characteristic values of this distribution (such as the expected value) to achieve differentiated and precise medication treatment for each patient.

[0004] However, the population pharmacokinetic model currently used in practice also has some problems, such as:

[0005] 1. In the model, the variance of the core parameters is relatively large, which leads to divergent model calculation results. Corresponding to actual patients, this means that there may be relatively large deviations.

[0006] 2. The parameters of these models are basically the results obtained by calculation through some actual medical case data in early years. There are problems such as different regional distribution of population, deviation of measurement equipment, and small number of cases.

[0007] 3. In therapeutic practice, there is often a large difference between the predicted blood drug concentration and the monitored value, which leads to doubts about the applicability of the model.

[0008] Therefore, based on the population pharmacokinetic model, we expect an optimized auxiliary generation method for the prediction algorithm of individualized drug blood concentration, which can redesign the blood drug concentration prediction model to improve the accuracy and reliability of the prediction. Summary of the Invention

[0009] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides an auxiliary generation method and system for an individualized medication blood concentration prediction algorithm, which first extracts the model parameters of the established blood drug concentration prediction model, and uses machine learning technology to feature encode the model parameters of each medication blood drug concentration prediction model to learn the relationship between the various parameters in the model. Then, by performing multi-dimensional energy potential analysis on the parameter information of each medication blood drug concentration prediction model, the kernel features of the model parameters are dynamically aggregated to learn the core distribution pattern of the model parameters, and then based on this, the model parameters are restored to generate a new medication blood drug concentration prediction model. Through this intelligent model generation method, the complexity of model construction can be significantly reduced, which helps to improve the accuracy of individualized medication blood drug concentration prediction and provide clinicians with more scientific and accurate medication guidance.

[0010] According to one aspect of the present application, a method for assisting in generating an algorithm for predicting individualized medication blood concentration is provided, comprising:

[0011] Step S1: extracting model parameters of the first to Nth drug blood concentration prediction models to obtain a set of prediction model parameters;

[0012] Step S2: semantically encoding the model parameters of each prediction model in the set of prediction model parameters to obtain a set of semantic encoding vectors of prediction model parameter information;

[0013] Step S3: performing kernel feature extraction on the set of semantic encoding vectors of the prediction model parameter information to obtain a distilled representation vector of the prediction model parameter information;

[0014] Step S4: performing model parameter reduction based on the distillation representation vector of the prediction model parameter information to obtain the N+1th medication blood concentration prediction model;

[0015] Step S5: using the training data to determine the prediction accuracy of the N+1th medication blood concentration prediction model;

[0016] Step S6: If the prediction accuracy of the N+1th medication blood concentration prediction model is the highest, the N+1th medication blood concentration prediction model is determined as the current optimal model.

[0017] According to another aspect of the present application, a system for assisting in generating an algorithm for predicting individualized medication blood concentration is provided, comprising:

[0018] A model parameter extraction module is used to extract model parameters of the first to Nth drug blood concentration prediction models to obtain a set of prediction model parameters;

[0019] A model parameter information semantic encoding module, configured to semantically encode the model parameters of each prediction model in the set of prediction model parameters to obtain a set of prediction model parameter information semantic encoding vectors;

[0020] A model parameter information distillation module is used to perform kernel feature extraction on the set of semantic encoding vectors of the prediction model parameter information to obtain a distilled representation vector of the prediction model parameter information;

[0021] A model parameter restoration module, configured to perform model parameter restoration based on the distillation representation vector of the prediction model parameter information to obtain an N+1th medication blood concentration prediction model;

[0022] A concentration prediction module, configured to determine the prediction accuracy of the N+1th medication blood concentration prediction model using training data;

[0023] The current optimal model generation module is used to determine the N+1th medication blood concentration prediction model as the current optimal model if the prediction accuracy of the N+1th medication blood concentration prediction model is the highest.

[0024] Compared with the prior art, the present application provides an auxiliary generation method and system for an individualized medication blood concentration prediction algorithm. The method first extracts the model parameters of the existing medication blood concentration prediction model, and uses machine learning technology to feature encode the model parameters of each medication blood concentration prediction model to learn the relationship between the various parameters in the model. Then, by performing multi-dimensional energy potential analysis on the parameter information of each medication blood concentration prediction model, the kernel features of the model parameters are dynamically aggregated to learn the core distribution pattern of the model parameters, and then based on this, the model parameters are restored to generate a new medication blood concentration prediction model. Through this intelligent model generation method, the complexity of model construction can be significantly reduced, which helps to improve the accuracy of individualized medication blood concentration prediction and provide clinicians with more scientific and accurate medication guidance. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The above and other purposes, features, and advantages of the present application will become more apparent through a more detailed description of the embodiments of the present application in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0026] Figure 1 Flowchart of a method for assisting in generating an algorithm for predicting individualized medication blood concentration according to an embodiment of the present application;

[0027] Figure 2Schematic diagram of data flow for an auxiliary generation method of an algorithm for predicting individualized medication blood concentration according to an embodiment of the present application;

[0028] Figure 3 This is a flowchart of sub-step S3 of the method for assisting in generating an algorithm for predicting individualized medication blood concentration according to an embodiment of the present application;

[0029] Figure 4 4 is a block diagram of an auxiliary generation system for an individualized medication blood concentration prediction algorithm according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described herein.

[0031] As used in this application and the claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" are not intended to refer to the singular but may include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0032] Although the present application makes various references to certain modules in the system according to embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are illustrative only, and different aspects of the system and method can use different modules.

[0033] Flowcharts are used in this application to illustrate the operations performed by the systems according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the various steps may be processed in reverse order or simultaneously, as needed. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0034] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described herein.

[0035] The population pharmacokinetic model currently in use also has some problems, such as:

[0036] 1. In the model, the variance of the core parameters is relatively large, which leads to divergent model calculation results. Corresponding to actual patients, this means that there may be relatively large deviations.

[0037] 2. The parameters of these models are basically the results obtained by calculation through some actual medical case data in early years. There are problems such as different regional distribution of population, deviation of measurement equipment, and small number of cases.

[0038] 3. In therapeutic practice, there is often a large difference between the predicted blood drug concentration and the monitored value, which leads to doubts about the applicability of the model.

[0039] Therefore, based on the population pharmacokinetic model, we expect an optimized auxiliary generation method for the prediction algorithm of individualized drug blood concentration, which can redesign the blood drug concentration prediction model to improve the accuracy and reliability of the prediction.

[0040] Based on this, in the technical solution of this application, a method for assisting in generating an algorithm for predicting individualized medication blood concentration is proposed. Figure 1 Flowchart of a method for assisting in generating an algorithm for predicting individualized medication blood concentration according to an embodiment of the present application. Figure 2 Schematic diagram of data flow of the auxiliary generation method of the personalized medication blood concentration prediction algorithm according to the embodiment of the present application. Figure 1 and Figure 2 As shown, the auxiliary generation method of the personalized medication blood concentration prediction algorithm according to the embodiment of the present application includes the following steps: S1, extracting the model parameters of the first to Nth medication blood concentration prediction models to obtain a set of prediction model parameters; S2, semantically encoding the model parameters of each prediction model in the set of prediction model parameters to obtain a set of prediction model parameter information semantic encoding vectors; S3, performing kernel feature extraction on the set of prediction model parameter information semantic encoding vectors to obtain a prediction model parameter information distillation representation vector; S4, performing model parameter restoration based on the prediction model parameter information distillation representation vector to obtain the N+1th medication blood concentration prediction model; S5, using training data to determine the prediction accuracy of the N+1th medication blood concentration prediction model; S6, if the prediction accuracy of the N+1th medication blood concentration prediction model is the highest, determining the N+1th medication blood concentration prediction model as the current optimal model.

[0041] In particular, the S1 extracts the model parameters of the first to Nth medication blood concentration prediction models to obtain a set of prediction model parameters. It should be understood that the existing medication blood concentration prediction models have accumulated a large amount of clinical data and practical experience and have certain reference value. Therefore, in the technical solution of the present application, by extracting the model parameters of multiple medication blood concentration prediction models, model parameter analysis can be performed from multiple perspectives, making full use of the prior knowledge and experience of existing models, thereby helping to improve the comprehensiveness and accuracy of the construction of new medication blood concentration prediction models.

[0042] In one example, first, multiple existing drug blood concentration prediction models are selected to ensure that these models cover different types of drugs and patient groups so that more comprehensive parameter information can be extracted. For example, nonlinear mixed-effect models, Bayesian models, and decision tree models can be selected. Next, for each selected model, its core parameters are extracted, such as absorption rate constant (Ka), distribution volume (Vd), clearance (Cl), and half-life (t1 / 2). The parameter extraction method can be manual extraction or automated extraction through programming, and the specific method depends on the storage format and data structure of the model. To ensure that the extracted parameters are accurate, the correctness of the parameters can be verified by consulting the original literature or model documentation. In addition, data cleaning techniques can be used to remove outliers or missing values to ensure the quality of the extracted parameters.

[0043] The extracted parameters are then standardized to ensure that parameters from different models are compared and analyzed on the same scale. Standardization methods can include normalization and standardization. Normalization scales parameter values to between 0 and 1, while standardization converts parameter values to a standard normal distribution with a mean of 0 and a standard deviation of 1. Using the normalization method, all parameter values are scaled to between 0 and 1. By calculating the minimum and maximum values of each parameter and normalizing the parameters using the normalization formula, dimensional differences between parameters from different models can be eliminated, improving the consistency and accuracy of subsequent processing.

[0044] Finally, all extracted and normalized parameters are organized into a set. Each model's parameters can be represented as a vector, and the parameter vectors of all models form a matrix. For example, if there are N models, each with M parameters, the final parameter set can be represented as an N×M matrix. This parameter set matrix facilitates subsequent feature encoding, kernel feature extraction, and model parameter restoration.

[0045] These steps ensure the high quality and broad representativeness of the extracted parameter set, providing a solid foundation for generating new models for predicting blood drug concentrations. Successful implementation of this step is a key component of the entire algorithm-assisted generation of personalized drug blood concentration prediction methods, helping to improve the accuracy and reliability of predictions and provide clinicians with more scientific and precise medication guidance.

[0046] In particular, the S2 semantically encodes the model parameters of each prediction model in the set of prediction model parameters to obtain a set of semantic encoding vectors of prediction model parameter information. In a specific example of the present application, first, each prediction model parameter in the set of prediction model parameters is vectorized to obtain a set of prediction model parameter vectors; that is, in order to learn the potential correlation pattern between each model parameter in the medication blood concentration prediction model, the present application further vectorizes each prediction model parameter in the set of prediction model parameters. By arranging the model parameters of each medication blood concentration prediction model into a vector form to form a set of prediction model parameter vectors, it is helpful to unify the data format and structure, thereby facilitating the use of deep learning algorithms to identify and learn the parameter characteristics of each medication blood concentration prediction model. Next, a model parameter information encoder based on a multi-layer perceptron model is used to encode each prediction model parameter vector in the set of prediction model parameter vectors to obtain a set of semantic encoding vectors of prediction model parameter information. It should be understood that deep learning algorithms have significant advantages in processing high-dimensional data and identifying complex data association patterns, and the multi-layer perceptron model, as a basic structure of deep learning, can extract features and abstractly represent data through multi-layer nonlinear transformations. Therefore, in the technical solution of the present application, a multi-layer perceptron model is used to construct a model parameter information encoder, and information is encoded for each prediction model parameter vector in the set of prediction model parameter vectors. Through layer-by-layer processing of multiple layers of neurons, the potential association pattern between the parameters in the prediction model parameter vector is captured, and the deep semantic information therein is extracted, thereby generating a set of prediction model parameter information semantic encoding vectors.

[0047] Specifically, each prediction model parameter in the set of prediction model parameters is vectorized to obtain a set of prediction model parameter vectors. By arranging the model parameters of each medication blood concentration prediction model into vector form to form a set of prediction model parameter vectors, it helps to unify the data format and structure, thereby facilitating the use of deep learning algorithms to identify and learn the parameter characteristics of each medication blood concentration prediction model.

[0048] Next, to semantically encode these parameter vectors, a suitable deep learning model is selected. Commonly used models include multi-layer perceptrons (MLPs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs). In this technical solution, a model parameter information encoder based on the multi-layer perceptron model is selected because the multi-layer perceptron model can extract features and abstractly represent data through multiple layers of nonlinear transformations. The multi-layer perceptron (MLP) is a feedforward neural network consisting of multiple input layers, hidden layers, and output layers. Each hidden layer contains multiple neurons, which are nonlinearly transformed using activation functions (such as ReLU and Sigmoid). The MLP model can capture complex patterns and features in the input data through layer-by-layer processing of multiple layers of neurons.

[0049] To train a multilayer perceptron model, the following steps are required:

[0050] Use a normalized and vectorized set of parameters as input data.

[0051] Define the architecture of a multilayer perceptron model, consisting of an input layer, multiple hidden layers, and an output layer. Each hidden layer can have a different number of neurons and activation function. Suppose we define a simple multilayer perceptron model with two hidden layers, each with 10 neurons, using the ReLU activation function, and an output layer with 4 neurons (the same number of input parameters).

[0052] In particular, the S3 performs kernel feature extraction on the set of semantic encoding vectors of the prediction model parameter information to obtain a distilled representation vector of the prediction model parameter information. Taking into account that different medication blood concentration prediction models usually have different prediction accuracy and scope of application, in order to fully integrate the advantages of each model, the core distribution pattern of the model parameters is extracted from the set of semantic encoding vectors of the prediction model parameter information. This application proposes a kernel feature extraction method based on multi-dimensional potential analysis, which dynamically aggregates parameter information by performing multi-dimensional potential analysis on the semantic encoding vectors of each prediction model parameter information, so as to learn the core distribution pattern of the model parameters. In a specific example of the present application, such as Figure 3 As shown, the S3 includes: S31, performing multi-dimensional feature energy potential analysis on the set of semantic encoding vectors of the prediction model parameter information to obtain a set of superposition state energy potential factors of the prediction model parameter information; S32, based on the set of superposition state energy potential factors of the prediction model parameter information, performing kernel feature aggregation on the set of semantic encoding vectors of the prediction model parameter information to obtain the distillation representation vector of the prediction model parameter information.

[0053] Specifically, the S31 performs a multi-dimensional feature potential analysis on the set of semantic encoding vectors of the prediction model parameter information to obtain a set of superposition state potential factors of the prediction model parameter information. In an embodiment of the present application, first, the positional mean vector of the set of the prediction model parameter information feature vectors is calculated to obtain the initial aggregate representation vector of the prediction model parameter information; that is, the positional mean calculation is performed on the set of the prediction model parameter information feature vectors to construct a typical example reflecting the overall characteristics of the prediction model parameters, capture the overall distribution pattern of the prediction model parameters, and thus obtain the initial aggregate representation vector of the prediction model parameter information. Next, the static potential factor of each prediction model parameter information feature vector in the set of the prediction model parameter information feature vectors is calculated to obtain a set of static potential factors of the prediction model parameter information; for each prediction model parameter information feature vector, its static potential factor is calculated to reveal the information density it carries, and the inherent properties and information importance of each prediction model parameter information feature vector when it is independent of other vectors are evaluated. Then, the dynamic energy potential factor of each prediction model parameter information feature vector in the set of the prediction model parameter information feature vectors is calculated relative to the prediction model parameter information initial aggregate representation vector to obtain a set of prediction model parameter information dynamic energy potential factors; considering that each prediction model parameter information feature vector has a certain influence on the overall model parameter distribution, the dynamic energy potential factor of each prediction model parameter information feature vector relative to the prediction model parameter information initial aggregate representation vector is further calculated to capture the relative relationship between the data, measure its interaction and influence with the overall distribution pattern of the prediction model parameters, and thus more deeply understand how the parameter information of each prediction model affects its overall distribution. Subsequently, based on the set of the prediction model parameter information static energy potential factors and the set of the prediction model parameter information dynamic energy potential factors, the superposition state energy potential factors of each prediction model parameter information feature vector in the set of the prediction model parameter information feature vectors are determined to obtain the set of the prediction model parameter information superposition state energy potential factors. Here, in order to comprehensively consider the static and dynamic properties of each prediction model parameter information feature vector, the static energy potential factor and dynamic energy potential factor of each prediction model parameter information feature vector are further integrated to form a superposition energy potential factor. This comprehensive indicator is used to reflect the composite influence of each prediction model parameter information feature vector in the entire set, and to more comprehensively evaluate its contribution to the core distribution pattern of the model parameters.

[0054] Among them, the specific process of calculating the static energy potential factor of each prediction model parameter information feature vector in the set of prediction model parameter information feature vectors to obtain the set of prediction model parameter information static energy potential factors includes: calculating the fourth-order central moment of the prediction model parameter information feature vector divided by the fourth power of its characteristic variance to obtain the prediction model parameter information static energy potential factor.

[0055] More specifically, the specific process of calculating the dynamic energy potential factor of each prediction model parameter information feature vector in the set of the prediction model parameter information feature vector relative to the prediction model parameter information initial aggregation representation vector to obtain the set of prediction model parameter information dynamic energy potential factors includes: calculating the position-weighted sum of the prediction model parameter information feature vector and the prediction model parameter information initial aggregation representation vector to obtain the prediction model parameter information dynamic energy potential representation vector; calculating the square of the L2 norm of the point-added vector between the prediction model parameter information dynamic energy potential representation vector and the bias vector to obtain the prediction model parameter information dynamic energy potential factor.

[0056] More specifically, based on the set of static energy potential factors of the prediction model parameter information and the set of dynamic energy potential factors of the prediction model parameter information, the specific process of determining the superposition state energy potential factors of each prediction model parameter information feature vector in the set of prediction model parameter information feature vectors to obtain the set of superposition state energy potential factors of the prediction model parameter information includes: using the squares of the static energy potential factor and the dynamic energy potential factor of the prediction model parameter information feature vector as exponents, respectively, calculating the exponential function value with base e to obtain the exponential static energy potential factor and the exponential dynamic energy potential factor, and adding the exponential static energy potential factor and the exponential dynamic energy potential factor to obtain the superposition state energy potential factor of the prediction model parameter information.

[0057] In summary, in the above embodiment, a multi-dimensional feature potential analysis is performed on the set of semantic encoding vectors of the prediction model parameter information to obtain a set of superposition state energy potential factors of the prediction model parameter information, including: performing a multi-dimensional feature potential analysis on the set of semantic encoding vectors of the prediction model parameter information using the following multi-dimensional feature potential analysis formula to obtain a set of superposition state energy potential factors of the prediction model parameter information; wherein the specific formula is:

[0058] ;

[0059] ;

[0060] ;

[0061] ;

[0062] ;

[0063] in, represents a set of feature vectors of parameter information of the prediction model, 、 、 and Respectively represent the first, second, and third in the set of the prediction model parameter information feature vectors and prediction model parameter information feature vector, is the number of characteristic vectors of parameter information of the prediction model, is the initial aggregation representation vector of the prediction model parameter information, Indicates the The first feature vector of the prediction model parameter information eigenvalues, and Respectively represent the The characteristic mean and characteristic variance of the characteristic vector of the prediction model parameter information, represents the length of the prediction model parameter information feature vector, 、 and Respectively represent the The static energy potential factor, dynamic energy potential factor and superposition energy potential factor of the prediction model parameter information feature vector, represents the bias vector, and Represents different weight parameters, represents dot product, It means calculating the square of the L2 norm of the vector.

[0064] Specifically, the S32, based on the set of superposition state energy potential factors of the prediction model parameter information, performs kernel feature aggregation on the set of semantic encoding vectors of the prediction model parameter information to obtain the distillation representation vector of the prediction model parameter information. In an embodiment of the present application, first, the set of superposition state energy potential factors of the prediction model parameter information is input into the energy potential factor gated weighting network to obtain a set of prediction model parameter information feature energy potential weight coefficients; that is, based on the gated mask mechanism, each generated superposition state energy potential factor is normalized and weighted, so as to perform weighted aggregation on the set of prediction model parameter information feature vectors, thereby explicitly marking the prediction model parameter information that has a greater impact on the core distribution pattern of the model parameters, filtering out the feature representation that contributes less to the overall pattern, and obtaining the prediction model parameter information distillation representation vector, thereby achieving accurate extraction of the core distribution pattern of the model parameters, and providing a solid data foundation for subsequent model parameter restoration and new model generation. Finally, based on the set of prediction model parameter information feature energy potential weight coefficients, the position-weighted sum of the set of prediction model parameter information feature vectors is calculated to obtain the prediction model parameter information distillation representation vector. That is, based on the set of potential weight coefficients of the prediction model parameter information feature, the position-weighted sum of the set of prediction model parameter information feature vectors is calculated to obtain the prediction model parameter information distillation representation vector.

[0065] Among them, the specific process of inputting the set of energy potential factors of the superposition state of the prediction model parameter information into the energy potential factor gated weighting network to obtain the set of characteristic energy potential weight coefficients of the prediction model parameter information includes: inputting the set of energy potential factors of the superposition state of the prediction model parameter information into the sigmoid function for normalization processing, and then performing mask inactivation processing on the normalized set of energy potential factors of the superposition state of the prediction model parameter information based on the mask threshold to obtain the set of characteristic energy potential weight coefficients of the prediction model parameter information.

[0066] In summary, in the above embodiment, based on the set of state energy potential factors of the prediction model parameter information superimposed, kernel feature aggregation is performed on the set of semantic encoding vectors of the prediction model parameter information to obtain the distilled representation vector of the prediction model parameter information, including: based on the set of state energy potential factors of the prediction model parameter information superimposed, kernel feature aggregation is performed on the set of semantic encoding vectors of the prediction model parameter information using the following kernel feature aggregation formula to obtain the distilled representation vector of the prediction model parameter information, wherein the kernel feature aggregation formula is:

[0067] ;

[0068] ;

[0069] ;

[0070] ;

[0071] in, Indicates the A normalized prediction model parameter information superposition state energy potential factor, is the mask function, represents the mask threshold, For the The information characteristic energy potential weight coefficient of the prediction model parameter, A distilled representation vector representing the prediction model parameter information.

[0072] In particular, S4 performs model parameter reduction based on the distilled representation vector of the prediction model parameter information to obtain the blood concentration prediction model for the N+1 medication. In a specific example of the present application, the distilled representation vector of the prediction model parameter information is input into a decoder-based model parameter reducer to obtain the blood concentration prediction model for the N+1 medication. In the technical solution of the present application, to achieve model parameter reduction and new model generation, the present application utilizes a decoder to construct a model parameter reducer. The decoder performs decoding and regression on the distilled representation vector of the prediction model parameter information to reduce it to specific model parameters, thereby generating the blood concentration prediction model for the N+1 medication. In a specific example of the present application, the decoder utilizes a recurrent neural network (RNN) structure. Through layer-by-layer expansion of the RNN, the decoder gradually reduces the distilled representation vector of the prediction model parameter information to a complete model parameter sequence. The RNN utilizes its cyclic memory capability to maintain the dependencies between the generated model parameters, thereby ensuring the logical consistency and clinical applicability of the newly generated blood concentration prediction model parameters.

[0073] Here, the decoder model's role is to restore specific model parameters from the prediction model parameter information distilled representation vector. Common decoder models include recurrent neural networks (RNNs) and multilayer perceptrons (MLPs). In the technical solution of this application, a decoder based on an MLP model was chosen because it can extract and restore data features through multiple layers of nonlinear transformations.

[0074] Preferably, in the technical solution of the present application, in the process of performing kernel feature extraction on the set of the prediction model parameter information semantic coding vectors to obtain the prediction model parameter information distillation representation vector, because each prediction model parameter information semantic coding vector in the set of the prediction model parameter information semantic coding vectors respectively represents the semantic coding features of the model parameters of each prediction model, but because the model parameters of each prediction model themselves have convergence inconsistency and strong unexplainability, it will cause the prediction model parameter information distillation representation vector obtained based on kernel feature extraction to have decoding space uncertainty, that is, it will affect the accuracy of the model parameters of the N+1th medication blood concentration prediction model obtained by inputting it into the model parameter reducer based on the decoder.

[0075] Based on this, in a preferred embodiment, in the process of inputting the prediction model parameter information distilled representation vector into the decoder-based model parameter reducer to obtain the N+1 medication blood concentration prediction model, the prediction model parameter information distilled representation vector is subjected to feature expression optimization, and the process includes:

[0076] Arranging the prediction model parameter information distillation representation vector based on the eigenvalue size to obtain a prediction model parameter information distillation sequence response encoding vector;

[0077] Calculating a transposed vector of the prediction model parameter information distillation representation vector to obtain a prediction model parameter information distillation representation transposed vector;

[0078] Multiplying the prediction model parameter information distillation order response encoding vector by the prediction model parameter information distillation representation transpose vector to obtain a prediction model parameter information distillation order topology encoding matrix;

[0079] Calculating a hyperbolic sine function value of the sum of squares of all eigenvalues of the prediction model parameter information distillation representation vector to obtain a topological scaling factor;

[0080] ;

[0081] in, The first representation vector of the parameter information distillation of the prediction model eigenvalues, Indicates the length of the distillation representation vector of the prediction model parameter information, represents the hyperbolic sine function, represents the topological scaling factor;

[0082] Multiplying the topological scaling factor by the prediction model parameter information distillation order topological coding matrix to obtain a prediction model parameter information distillation order topological coding scale adaptation matrix;

[0083] The prediction model parameter information distillation representation vector is multiplied by the prediction model parameter information distillation order topology coding scale adaptation matrix to obtain an optimized prediction model parameter information distillation representation vector.

[0084] That is, by mapping discrete tensors into a topological space defined by the scalar product of vectors, meaningful measurement of the statistical correlation of attribute clusters within a stable domain can be achieved. On this basis, a representation space with a non-coupling framework is constructed through dynamic coordinate mapping with the representation tensor, and the multi-layer topology of the representation tensor is morphologically integrated within the representation space based on vector queries. This can avoid reducing the information fidelity of the representation tensor due to loose morphology, thereby increasing the reliability of the judgment output obtained by the decision module of the discriminant attribute tensor, thereby improving the accuracy and robustness of the model parameters of the N+1th medication blood concentration prediction model obtained by the decoder-based model parameter reducer.

[0085] In particular, S5 uses training data to determine the prediction accuracy of the N+1 medication blood concentration prediction model. In one example, the training data includes known inputs (such as dosage, time, etc.) and outputs (such as the actual measured blood concentration). This data can be used to evaluate the performance of the model under known conditions. The training data helps adjust the parameters of the model to better fit the known data. In other words, the performance of the N+1 medication blood concentration prediction model is verified using a training data set with known inputs and outputs to test the prediction accuracy of the N+1 medication blood concentration prediction model and ensure that the model performs as expected in actual applications.

[0086] In the method for assisting the generation of personalized medication blood concentration prediction algorithms, using training data to determine the prediction accuracy of the N+1 medication blood concentration prediction model is a key step. This process involves multiple sub-steps, including data preparation, model training, model evaluation, and results analysis. The following are the detailed implementation steps:

[0087] First, prepare datasets for training and evaluation. These datasets typically include patient medication records, blood drug concentration measurements, and other relevant features (such as age, weight, and liver and kidney function). The dataset should be divided into training and test sets to allow for independent evaluation after the model is trained. Consider a dataset containing medication records for multiple patients. Each record includes the following information: patient ID, medication dose, administration time, blood drug concentration measurement, age, weight, and liver and kidney function.

[0088] The training dataset is used to train the N+1 medication blood concentration prediction model. During training, the model learns the mapping relationship between input features (such as medication dosage, administration time, age, weight, liver and kidney function, etc.) and blood drug concentration measurements.

[0089] After training is complete, the test dataset is used to evaluate the model's prediction accuracy. Evaluation metrics typically include mean squared error (MSE), mean absolute error (MAE), and coefficient of determination (R²).

[0090] Based on the evaluation results, analyze the prediction accuracy of the model. Common evaluation indicators and their significance are as follows:

[0091] Mean Squared Error (MSE): Measures the average of the squared errors between the predicted values and the true values. A smaller MSE value indicates a smaller prediction error for the model.

[0092] Mean Absolute Error (MAE): Measures the average absolute error between the predicted value and the true value. The smaller the MAE value, the smaller the prediction error of the model.

[0093] Coefficient of determination (R²): This measures the proportion of variability explained by the model. R² values closer to 1 indicate a better fit for the model.

[0094] These results demonstrate that the model performs well on the test dataset, with low prediction errors and good ability to account for data variability. Through the above steps, we can use the training data to determine the prediction accuracy of the N+1 medication plasma concentration prediction model, thereby ensuring the reliability and effectiveness of the model in practical applications.

[0095] In particular, in S6, if the N+1th medication blood concentration prediction model has the highest prediction accuracy, the N+1th medication blood concentration prediction model is determined as the current optimal model. That is, by comparing the prediction results of the N+1th medication blood concentration prediction model with those of the existing prediction model under the same conditions, the performance improvement of the new model is evaluated. If the N+1th medication blood concentration prediction model has the highest prediction accuracy, the N+1th medication blood concentration prediction model is determined as the current optimal model.

[0096] In summary, according to the embodiment of the present application, the auxiliary generation method of the personalized medication blood concentration prediction algorithm is explained. It first extracts the model parameters of the existing medication blood concentration prediction model, and uses machine learning technology to feature encode the model parameters of each medication blood concentration prediction model to learn the relationship between the various parameters in the model. Then, by performing multi-dimensional energy potential analysis on the parameter information of each medication blood concentration prediction model, the kernel features of the model parameters are dynamically aggregated to learn the core distribution pattern of the model parameters, and then based on this, the model parameters are restored to generate a new medication blood concentration prediction model. Through this intelligent model generation method, the complexity of model construction can be significantly reduced, which helps to improve the accuracy of personalized medication blood concentration prediction and provide clinicians with more scientific and accurate medication guidance.

[0097] Furthermore, a system for assisting in generating an algorithm for predicting individualized medication blood concentration is also provided.

[0098] Figure 4 FIG. 1 is a block diagram of an auxiliary generation system for an individualized medication blood concentration prediction algorithm according to an embodiment of the present application. Figure 4 As shown, according to an embodiment of the present application, an auxiliary generation system 300 of an individualized medication blood concentration prediction algorithm includes: a model parameter extraction module 310, which is used to extract model parameters of the first to Nth medication blood concentration prediction models to obtain a set of prediction model parameters; a model parameter information semantic encoding module 320, which is used to semantically encode the model parameters of each prediction model in the set of prediction model parameters to obtain a set of prediction model parameter information semantic encoding vectors; a model parameter information distillation module 330, which is used to perform kernel feature extraction on the set of prediction model parameter information semantic encoding vectors to obtain a prediction model parameter information distillation representation vector; a model parameter restoration module 340, which is used to perform model parameter restoration based on the prediction model parameter information distillation representation vector to obtain the N+1th medication blood concentration prediction model; a concentration prediction module 350, which is used to determine the prediction accuracy of the N+1th medication blood concentration prediction model using training data; and a current optimal model generation module 360, which is used to determine the N+1th medication blood concentration prediction model as the current optimal model if the prediction accuracy of the N+1th medication blood concentration prediction model is the highest.

[0099] As described above, the auxiliary generation system 300 of the personalized medication blood concentration prediction algorithm according to the embodiment of the present application can be implemented in various wireless terminals, such as a server having an auxiliary generation algorithm of the personalized medication blood concentration prediction algorithm. In one possible implementation, the auxiliary generation system 300 of the personalized medication blood concentration prediction algorithm according to the embodiment of the present application can be integrated into the wireless terminal as a software module and / or hardware module. For example, the auxiliary generation system 300 of the personalized medication blood concentration prediction algorithm can be a software module in the operating system of the wireless terminal, or it can be an application developed for the wireless terminal; of course, the auxiliary generation system 300 of the personalized medication blood concentration prediction algorithm can also be one of the many hardware modules of the wireless terminal.

[0100] Alternatively, in another example, the auxiliary generation system 300 of the personalized medication blood concentration prediction algorithm and the wireless terminal can also be separate devices, and the auxiliary generation system 300 of the personalized medication blood concentration prediction algorithm can be connected to the wireless terminal through a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.

[0101] While various embodiments of the present disclosure have been described above, the above descriptions are illustrative, non-exhaustive, and not intended to be limiting of the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, their practical applications, or improvements to existing technologies, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for assisting in generating an algorithm for predicting individualized medication blood concentration, characterized in that: include: Step S1: extracting model parameters of the first to Nth blood drug concentration prediction models to obtain a set of prediction model parameters; Step S2: semantically encoding the model parameters of each prediction model in the set of prediction model parameters to obtain a set of semantic encoding vectors of prediction model parameter information; Step S3: performing kernel feature extraction on the set of semantic encoding vectors of the prediction model parameter information to obtain a distilled representation vector of the prediction model parameter information; Step S4: performing model parameter reduction based on the distillation representation vector of the prediction model parameter information to obtain the N+1th medication blood concentration prediction model; Step S5: using the training data to determine the prediction accuracy of the N+1th medication blood concentration prediction model; Step S6: If the prediction accuracy of the N+1th medication blood concentration prediction model is the highest, the N+1th medication blood concentration prediction model is determined as the current optimal model; The step S4 comprises: Inputting the prediction model parameter information distillation representation vector into a decoder-based model parameter reducer to obtain the N+1th medication blood concentration prediction model; In which, in the process of inputting the prediction model parameter information distillation representation vector into the decoder-based model parameter reducer to obtain the N+1th medication blood concentration prediction model, the prediction model parameter information distillation representation vector is subjected to feature expression optimization, and the process includes: arranging the prediction model parameter information distillation representation vector based on the size of the eigenvalue to obtain the prediction model parameter information distillation sequence response coding vector; calculating the transpose vector of the prediction model parameter information distillation representation vector to obtain the prediction model parameter information distillation representation transpose vector; multiplying the prediction model parameter information distillation sequence response coding vector by the prediction model parameter information distillation representation transpose vector to obtain the prediction model parameter information distillation sequence topological coding matrix; calculating the hyperbolic sine function value of the sum of squares of all eigenvalues of the prediction model parameter information distillation representation vector to obtain a topological scaling factor; multiplying the topological scaling factor by the prediction model parameter information distillation sequence topological coding matrix to obtain a prediction model parameter information distillation sequence topological coding scale adaptation matrix; multiplying the prediction model parameter information distillation representation vector by the prediction model parameter information distillation sequence topological coding scale adaptation matrix to obtain an optimized prediction model parameter information distillation representation vector.

2. The method for assisting in generating an algorithm for predicting individualized medication blood concentration according to claim 1, characterized in that: The step S2 includes: Vectorizing each prediction model parameter in the set of prediction model parameters to obtain a set of prediction model parameter vectors; A model parameter information encoder based on a multi-layer perceptron model is used to encode each prediction model parameter vector in the set of prediction model parameter vectors to obtain a set of prediction model parameter information semantic encoding vectors.

3. The method for assisting in generating an algorithm for predicting individualized medication blood concentration according to claim 2, wherein: The step S3 comprises: Performing a multi-dimensional feature energy potential analysis on the set of semantic encoding vectors of the prediction model parameter information to obtain a set of superposition state energy potential factors of the prediction model parameter information; Based on the set of superimposed state energy potential factors of the prediction model parameter information, kernel feature aggregation is performed on the set of semantic encoding vectors of the prediction model parameter information to obtain a distilled representation vector of the prediction model parameter information.

4. The method for assisting in generating an algorithm for predicting individualized medication blood concentration according to claim 3, wherein: Performing a multi-dimensional feature potential analysis on the set of semantic encoding vectors of the prediction model parameter information to obtain a set of superposition state potential factors of the prediction model parameter information, including: Calculating a position-wise mean vector of a set of prediction model parameter information feature vectors to obtain an initial aggregate representation vector of the prediction model parameter information; Calculating the static energy potential factor of each prediction model parameter information feature vector in the set of prediction model parameter information feature vectors to obtain a set of prediction model parameter information static energy potential factors; Calculating the dynamic energy potential factor of each prediction model parameter information feature vector in the set of prediction model parameter information feature vectors relative to the prediction model parameter information initial aggregation representation vector to obtain a set of prediction model parameter information dynamic energy potential factors; Based on the set of static energy potential factors of the prediction model parameter information and the set of dynamic energy potential factors of the prediction model parameter information, the superposition state energy potential factors of each prediction model parameter information feature vector in the set of prediction model parameter information feature vectors are determined to obtain the set of superposition state energy potential factors of the prediction model parameter information.

5. The method for assisting in generating an algorithm for predicting individualized medication blood concentration according to claim 4, characterized in that: Calculating the static energy potential factor of each prediction model parameter information feature vector in the set of prediction model parameter information feature vectors to obtain a set of prediction model parameter information static energy potential factors includes: The fourth-order central moment of the prediction model parameter information eigenvector is calculated and divided by the fourth power of its eigenvariance to obtain the prediction model parameter information static energy potential factor.

6. The method for assisting in generating an algorithm for predicting individualized medication blood concentration according to claim 5, characterized in that: Calculating the dynamic energy potential factor of each prediction model parameter information feature vector in the set of prediction model parameter information feature vectors relative to the prediction model parameter information initial aggregation representation vector to obtain a set of prediction model parameter information dynamic energy potential factors, including: Calculating a position-weighted sum of the prediction model parameter information feature vector and the prediction model parameter information initial aggregation representation vector to obtain a prediction model parameter information dynamic energy potential representation vector; The square of the L2 norm of the point-added vector between the prediction model parameter information dynamic energy potential representation vector and the bias vector is calculated to obtain the prediction model parameter information dynamic energy potential factor.

7. The method for assisting in generating an algorithm for predicting individualized medication blood concentration according to claim 6, characterized in that: Based on the set of static energy potential factors of the prediction model parameter information and the set of dynamic energy potential factors of the prediction model parameter information, determining the superposition state energy potential factor of each prediction model parameter information feature vector in the set of prediction model parameter information feature vectors to obtain the set of superposition state energy potential factors of the prediction model parameter information, including: The squares of the static energy potential factor and the dynamic energy potential factor of the characteristic vector of the prediction model parameter information are respectively used as exponents, and the exponential function values with base e are calculated to obtain the exponential static energy potential factor and the exponential dynamic energy potential factor, and the exponential static energy potential factor and the exponential dynamic energy potential factor are added and summed to obtain the superposition state energy potential factor of the prediction model parameter information.

8. The method for assisting in generating an algorithm for predicting individualized medication blood concentration according to claim 7, characterized in that: Based on the set of superimposed state energy potential factors of the prediction model parameter information, kernel feature aggregation is performed on the set of semantic encoding vectors of the prediction model parameter information to obtain a distilled representation vector of the prediction model parameter information, including: Inputting the set of the prediction model parameter information superposition state energy potential factors into the energy potential factor gating weighting network to obtain a set of prediction model parameter information characteristic energy potential weight coefficients; Based on the set of the prediction model parameter information feature potential weight coefficients, a position-weighted sum of the set of the prediction model parameter information feature vectors is calculated to obtain the prediction model parameter information distillation representation vector.

9. A system for assisting the generation of an algorithm for predicting individualized medication blood concentration, characterized in that: include: A model parameter extraction module is used to extract the model parameters of the blood drug concentration prediction model from the first to the Nth medication to obtain a set of prediction model parameters; A model parameter information semantic encoding module, configured to semantically encode the model parameters of each prediction model in the set of prediction model parameters to obtain a set of prediction model parameter information semantic encoding vectors; A model parameter information distillation module is used to perform kernel feature extraction on the set of semantic encoding vectors of the prediction model parameter information to obtain a distilled representation vector of the prediction model parameter information; A model parameter restoration module, configured to perform model parameter restoration based on the distillation representation vector of the prediction model parameter information to obtain an N+1th medication blood concentration prediction model; A concentration prediction module, configured to determine the prediction accuracy of the N+1th medication blood concentration prediction model using training data; a current optimal model generating module, configured to determine the N+1th medication blood concentration prediction model as the current optimal model if the N+1th medication blood concentration prediction model has the highest prediction accuracy; The model parameter restoration module includes: Inputting the prediction model parameter information distillation representation vector into a decoder-based model parameter reducer to obtain the N+1th medication blood concentration prediction model; In which, in the process of inputting the prediction model parameter information distillation representation vector into the decoder-based model parameter reducer to obtain the N+1th medication blood concentration prediction model, the prediction model parameter information distillation representation vector is subjected to feature expression optimization, and the process includes: arranging the prediction model parameter information distillation representation vector based on the size of the eigenvalue to obtain the prediction model parameter information distillation sequence response coding vector; calculating the transpose vector of the prediction model parameter information distillation representation vector to obtain the prediction model parameter information distillation representation transpose vector; multiplying the prediction model parameter information distillation sequence response coding vector by the prediction model parameter information distillation representation transpose vector to obtain the prediction model parameter information distillation sequence topological coding matrix; calculating the hyperbolic sine function value of the sum of squares of all eigenvalues of the prediction model parameter information distillation representation vector to obtain a topological scaling factor; multiplying the topological scaling factor by the prediction model parameter information distillation sequence topological coding matrix to obtain a prediction model parameter information distillation sequence topological coding scale adaptation matrix; multiplying the prediction model parameter information distillation representation vector by the prediction model parameter information distillation sequence topological coding scale adaptation matrix to obtain an optimized prediction model parameter information distillation representation vector.

Images