Medical data processing method and system

Abstract

The invention relates to a medical data processing method and system. The method comprises the following steps: acquiring medical data of a patient; inputting the medical data into the filling model to obtain a corresponding predicted filling value; wherein the filling model is obtained by training a deep learning model based on sample medical data, the sample medical data comprises a plurality of different types of sample data, and the training process comprises the following steps: extracting context information of each piece of sample data from the plurality of different types of sample data, a dependency graph structure is constructed based on the context information of each piece of sample data, the dependency graph structure comprises a plurality of nodes and edges connecting the adjacent nodes, each node represents one piece of sample data and the context information of the sample data, and each edge represents the dependency relationship between the sample data of the adjacent nodes; the weight of the edge represents the similarity of the context information of the sample data of the adjacent nodes; outputting a predicted fill value based on dependency graph structure learning; and filling the medical data based on the predicted filling value corresponding to the missing value in the medical data to obtain new medical data.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of data processing technology, and in particular, to a medical data processing method and system. Background Art

[0002] At present, the widespread application of high-dimensional and multimodal data of patients in the medical field provides rich information for clinical diagnosis and treatment. Artificial intelligence-based machine learning technology can use the patient's medical data information to provide, for example, a reference for diagnostic results, which requires training machine learning models based on training data. The quality of training data will affect the performance of the model, such as reducing the accuracy of the diagnostic results given by the model.

[0003] In the related technology, medical data used for model training usually undergoes preprocessing such as missing value filling before model training. Since missing values ​​are common in medical data used for training, traditional missing value filling methods are often based on the overall distribution of a single data and perform simple processing such as interpolation. This leads to inaccurate filling results of medical data, reduces the performance of the trained model, and thus reduces medical staff's trust in and ability to apply the model in clinical practice. Summary of the invention

[0004] In order to solve the above technical problems or at least partially solve the above technical problems, the embodiments of the present disclosure provide a medical data processing method and system.

[0005] In a first aspect, an embodiment of the present disclosure provides a medical data processing method, comprising:

[0006] Access to patients’ medical data;

[0007] The medical data is input into a filling model to obtain a predicted filling value corresponding to the missing value in the medical data; wherein the filling model is obtained by training a deep learning model based on sample medical data, and the sample medical data includes multiple different types of sample data, and the training process of the deep learning model includes: extracting context information of each sample data from the multiple different types of sample data, and constructing a dependency graph structure based on the context information of each sample data, wherein the dependency graph structure includes multiple nodes and edges connecting each adjacent node; wherein each node represents a sample data and its context information, each edge represents a dependency relationship between sample data of adjacent nodes, and the weight of the edge represents the similarity of the context information of sample data of adjacent nodes; learning and outputting predicted filling values ​​based on the dependency graph structure until the convergence condition is met and the training is terminated;

[0008] Based on the predicted filling values ​​corresponding to the missing values ​​in the medical data, the medical data are filled to obtain new medical data.

[0009] In one embodiment, the training process of the deep learning model further includes:

[0010] A probability graph model is used to obtain the conditional probability distribution corresponding to each sample data in the dependency graph structure; the dependency graph structure is optimized and updated based on the conditional probability distribution corresponding to each sample data, and a predicted fill value is output based on the learning of the updated dependency graph structure.

[0011] In one embodiment, the deep learning model includes a graph neural network, and outputs a predicted fill value based on learning the dependency graph structure by the graph neural network.

[0012] In one embodiment, the method further comprises:

[0013] Acquire new sample medical data, and extract context information corresponding to the new sample medical data;

[0014] Update the dependency graph structure based on the difference in similarity between the context information corresponding to the new sample medical data and the context information of each sample data;

[0015] The predicted fill value is re-learned based on the updated dependency graph structure.

[0016] In one embodiment, the deep learning model adopts a self-supervised learning mechanism and is provided with a first loss function and a second loss function. The first loss function defines that the goal of missing value filling is to minimize the loss value of the first loss function so that the loss value of the first loss function is less than a set threshold; the second loss function is a contrast loss function, which defines the difference in feature similarity of sample data before and after filling.

[0017] In one embodiment, the deep learning model adopts a Bayesian deep learning method, and the method further includes:

[0018] The uncertainty estimate of the predicted filling value is calculated through Bayesian reasoning to assist medical personnel in evaluating the credibility of the filling results of medical data.

[0019] In one embodiment, the method further comprises:

[0020] The contribution value of each feature data in the medical data input into the filling model to the output predicted filling value is obtained through the model interpretation tool SHAP, so as to determine the most critical feature data of the filling model in the decision-making process;

[0021] And / or, introducing an attention mechanism into the filling model so that the filling model uses the attention mechanism to automatically focus on obtaining the most important contextual information for the filling task.

[0022] In a second aspect, an embodiment of the present disclosure provides a medical data processing system, including:

[0023] An acquisition module, used to obtain the patient's medical data;

[0024] A prediction module, used for inputting the medical data into a filling model to obtain a predicted filling value corresponding to the missing value in the medical data; wherein the filling model is obtained by training a deep learning model based on sample medical data, and the sample medical data includes a plurality of different types of sample data, and the training process of the deep learning model includes: extracting context information of each sample data from the plurality of different types of sample data, and constructing a dependency graph structure based on the context information of each sample data, wherein the dependency graph structure includes a plurality of nodes and edges connecting adjacent nodes; wherein each node represents a sample data and its context information, each edge represents a dependency relationship between sample data of adjacent nodes, and the weight of the edge represents the similarity of the context information of sample data of adjacent nodes; learning and outputting a predicted filling value based on the dependency graph structure until the convergence condition is met and the training is terminated;

[0025] A filling module is used to fill the medical data to obtain new medical data based on the predicted filling value corresponding to the missing value in the medical data.

[0026] In a third aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the medical data processing method described in any of the above embodiments.

[0027] In a fourth aspect, an embodiment of the present disclosure provides an electronic device, including:

[0028] Processor; and

[0029] Memory for storing computer programs;

[0030] Wherein, the processor is configured to execute the medical data processing method described in any of the above embodiments by executing the computer program.

[0031] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0032] The medical data processing method and system provided by the embodiments of the present disclosure obtain the medical data of the patient, input the medical data into a filling model to obtain the predicted filling value corresponding to the missing value in the medical data; wherein the filling model is obtained by training a deep learning model based on sample medical data, and the sample medical data includes multiple different types of sample data, and the training process of the deep learning model includes: extracting the context information of each sample data from the multiple different types of sample data, and constructing a dependency graph structure based on the context information of each sample data, and the dependency graph structure includes multiple nodes and edges connecting each adjacent node; wherein each node represents a sample data and its context information, each edge represents the dependency relationship between the sample data of adjacent nodes, and the weight of the edge represents the similarity of the context information of the sample data of adjacent nodes; based on the dependency graph structure learning output predicted filling values, until the convergence condition is met to terminate the training; based on the predicted filling values ​​corresponding to the missing values ​​in the medical data, the medical data is filled to obtain new medical data. In this embodiment, a pre-trained filling model is used to accurately predict the filling value, which takes into account the local data characteristics of the type of data corresponding to the missing value in the medical data, such as the difference in context and the difference in the dependency relationship between different types of data, and makes full use of the correlation between different types of data to reduce information loss, thereby improving the performance of the trained model, and thus improving the accuracy of the final filling result of the medical data. During model training, this implementation scheme extracts the context information of the data to construct a dependency graph structure to accurately capture the complex relationship between multi-source data, thereby achieving accurate filling of missing values, which can effectively cope with the challenges of local feature differences and alignment of multimodal data, and use the accuracy and practicality of the results of disease diagnosis or efficacy evaluation based on the model filled with data in clinical applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0035] Figure 1 This is a flow chart of the medical data processing method according to an embodiment of the present disclosure;

[0036] Figure 2 This is a flow chart of a medical data processing method according to another embodiment of the present disclosure;

[0037] Figure 3 is a schematic diagram of a medical data processing system according to another embodiment of the present disclosure;

[0038] Figure 4 Schematic diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0039] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0040] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0041] It should be understood that, in the following, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0042] In the related art, multimodal data of patients, such as images of patients (such as CT images, X-ray images), physiological characteristic parameters, etc., have significant differences in feature space, data format and time scale, making effective multimodal data integration and alignment more complicated. Therefore, it is often impossible to fully utilize the correlation between different modal data, resulting in information loss and reduced accuracy of data filling results. In addition, existing filling methods are usually based on a single type of overall data distribution, which cannot effectively deal with local feature differences and the alignment challenges of multimodal data, and ignore the complex dependencies between different types of data features, resulting in reduced accuracy of data filling results.

[0043] Figure 1 This is a flow chart of a medical data processing method according to an embodiment of the present disclosure. The method may be executed by a computing device such as a computer or a mobile terminal, and may specifically include the following steps:

[0044] Step S101: Acquire the patient's medical data.

[0045] For example, the patient's medical data can be high-dimensional data and multimodal data, such as multimodal (type) data such as imaging, genome, and electronic health records such as patient physiological characteristics data. Each type can include multiple specific data such as physiological characteristics data at different times, and the specific data corresponding to each type may have some missing values.

[0046] Step S102: Input the medical data into the filling model to obtain the predicted filling value corresponding to the missing value in the medical data. The filling model is obtained by training a deep learning model based on sample medical data, and the sample medical data includes multiple different types of sample data. The training process of the deep learning model includes: extracting the context information of each sample data from the multiple different types of sample data, and constructing a dependency graph structure based on the context information of each sample data, wherein the dependency graph structure includes multiple nodes and edges connecting each adjacent node; wherein each node represents a sample data and its context information, each edge represents the dependency relationship between the sample data of adjacent nodes, and the weight of the edge represents the similarity of the context information of the sample data of adjacent nodes; and outputting the predicted filling value based on the dependency graph structure learning until the convergence condition is met and the training is terminated.

[0047] For example, the sample medical data may include multiple different types of sample data such as patient physiological characteristic change data and disease text such as descriptive information in case records, etc., as the basis for building dependency modeling, without limiting the specific data type. Assume that the clinical data set is set to X, where Representing the sample data i (i is a natural number) of the mth mode (or type), its context information can be defined as It can be composed of multiple dimensional features, namely: Among them, c k Represents the kth context feature, for example, it may include context features at the missing value in multiple sample data of the type to which the sample data i belongs, and may also include context features associated with the missing value in other types of sample data.

[0048] Then a dependency graph structure G = (V, E) is constructed. In this graph structure, node V represents sample data and its contextual information The edge E represents the dependency between different sample data, and the weight of the edge Determined by the similarity measure of context information. As an example, the weight of the edge can be determined by, but not limited to, the following formula:

[0049]

[0050] in, is the Gaussian similarity function based on the context information of sample data i and j, and Σ represents the covariance matrix of the context information.

[0051] In this embodiment, during model training, the context information in the medical data is analyzed to construct a dependency graph structure to accurately capture the interdependence between different sample data. By calculating the similarity of the context information of the sample data, an effective and accurate dependency graph structure is formed, providing high-quality pre-processed data for model training, thereby improving the performance of the trained model and improving the accuracy of the final medical data filling results. In this embodiment, for each type of data in the medical data, the filling model can achieve accurate prediction of missing values, which is conducive to subsequent accurate filling. The convergence condition can be that the loss value of the loss function of the deep learning model is less than a preset value.

[0052] Step S103: filling the medical data based on the predicted filling value corresponding to the missing value in the medical data to obtain new medical data.

[0053] This embodiment provides a context-driven missing value filling solution. During model training, the context information of each sample data is extracted and a dependency graph structure is constructed to ensure the integrity and accuracy of the data, significantly improve the performance and robustness of the filling algorithm model, and adaptively and accurately fill in missing values ​​in medical data.

[0054] In this embodiment, a pre-trained filling model is used to accurately predict the filling value, which takes into account the local data characteristics of the type of data corresponding to the missing value in the medical data, such as the difference in context and the difference in the dependency relationship between different types of data, and makes full use of the correlation between different types of data to reduce information loss, thereby improving the performance of the trained model, and thus improving the accuracy of the final filling result of the medical data. During model training, this implementation scheme extracts the context information of the data to construct a dependency graph structure to accurately capture the complex relationship between multi-source data, thereby achieving accurate filling of missing values. It can effectively cope with the challenges of local feature differences and alignment of multimodal data, and utilize the accuracy and practicality of the results of disease diagnosis or efficacy evaluation based on the filled data in clinical applications.

[0055] In one embodiment, in combination Figure 2 As shown, the training process of the deep learning model also includes steps S201 to S202: Step S201, using a probability graph model to obtain the conditional probability distribution corresponding to each sample data in the dependency graph structure; Step S202, optimizing and updating the dependency graph structure based on the conditional probability distribution corresponding to each sample data, and learning and outputting a predicted fill value based on the updated dependency graph structure.

[0056] For example, the probabilistic graphical model is a theory that uses graphs to represent the probability dependency of variables. It combines the knowledge of probability theory and graph theory and uses graphs to represent the joint probability distribution of variables related to the model. In this embodiment, based on the dependency graph structure, the probabilistic graphical model is used to capture the dependency relationship between sample data. There is a conditional dependency between the observed value and its context information and the sample data of the adjacent nodes. The conditional probability distribution of the observed value can be expressed as:

[0057]

[0058] Among them, neigh(i) represents the set of neighbor nodes of node i. is the sample data And its neighbor sample data The distance function between:

[0059]

[0060] Among them, Λ is a positive definite matrix used to weight the distance and estimate the data similarity weighted by context information. The conditional probability distribution of , thereby capturing contextual dependencies.

[0061] In this embodiment, the probability graph model is applied to accurately obtain the conditional probability distribution corresponding to the sample data, and the dependency graph structure is optimized and updated accordingly. That is, the previously established dependency graph structure may not be accurate enough, such as the edge weights are not precise enough. The dependency graph structure such as the edge weights can be further optimized through the conditional probability distribution, so that the dependency graph structure can more accurately capture the complex relationship between multi-source data, thereby making the trained model perform better and achieving accurate filling of missing values. Similarly, the filling results are optimized to ensure the rationality and effectiveness of the filling strategy.

[0062] Based on any one of the above embodiments, in one embodiment, the deep learning model may include a graph neural network (Graph Neural Network), which learns and outputs a predicted fill value based on the dependency graph structure using a graph neural network GNN.

[0063] Exemplarily, in this embodiment, a graph structured data such as a dependency graph structure is constructed. Therefore, in order to further improve the performance of the trained model, an adaptive graph neural network is used for training, which can better extract and mine the data features of the learning dependency graph structure, so that more accurate filling of missing values ​​can be achieved based on the final trained filling model.

[0064] Based on any one of the above embodiments, in one embodiment, the method may further include the following steps: acquiring new sample medical data, extracting context information corresponding to the new sample medical data; updating the dependency graph structure based on the difference in similarity between the context information corresponding to the new sample medical data and the context information of each sample data; and relearning and outputting predicted fill values ​​based on the updated dependency graph structure.

[0065] Exemplarily, the context information corresponding to the new sample medical data may also be the context information of each sample data therein. The difference in similarity between the context information corresponding to the new sample medical data and the context information of each sample data in the sample medical data may be the difference in similarity of the context information of each pair of corresponding sample data. When, for example, the differences corresponding to half of the sample data are greater than the set differences, the dependency graph structure may be updated. Of course, this is not limited to this.

[0066] In this embodiment, the dependency graph structure can be dynamically updated. After the graph neural network is introduced, the dependency graph structure can be dynamically adjusted according to time changes and sample data updates. By measuring the similarity of the context features of new data samples, the dependency graph structure is updated in a timely manner, such as updating the node representation (i.e., the sample data and context information corresponding to the node have changed) and the weight of the edge, to ensure the adaptability of the model to changes in medical data and the accuracy of prediction.

[0067] Specifically, in order to cope with the situation where relevant medical data including patient conditions change over time, a graph neural network is introduced to achieve dynamic update of the graph structure. Suppose the graph structure at time t is G t =(V t ,E t ), as time goes by, the updated graph structure is G t+1 =(V t+1 ,E t+1 ), the updating basis is the similarity measure between the context features of the new sample data and the context features of the existing sample data. By capturing the changes in the similarity measure, such as when the difference in similarity is greater than the preset similarity, the graph neural network can dynamically update the node representation and edge weights.

[0068] This enables the implementation scheme to be dynamically updated. The introduction of graph neural networks enables the model to update the graph structure in real time and adapt to the ever-changing medical data. For example, after the patient's condition changes, the previous model's prediction of the missing values ​​of the patient's new medical data is no longer accurate. The model can be updated based on the new medical data as sample data. This feature ensures that the model can continue to adapt to changes in the patient's condition and improves the subsequent diagnostic accuracy and analysis flexibility based on the new filled medical data.

[0069] Based on any one of the above embodiments, in one embodiment, the deep learning model can adopt a self-supervised learning mechanism, and can be provided with a first loss function and a second loss function, wherein the first loss function defines that the goal of missing value filling is to minimize the loss value of the first loss function, so that the loss value of the first loss function is less than a set threshold; the second loss function is a contrast loss function, which defines the difference in feature similarity of sample data before and after filling.

[0070] Exemplarily, the goal of defining missing value filling is to minimize the following first loss function:

[0071]

[0072] in, represents the true data of the i-th sample data under the m-th mode, Based on contextual information The fill value of the model prediction output, MSE stands for mean square error, is a latent variable The approximate posterior distribution of is the prior distribution of the latent variable, KL stands for Kullback-Leibler divergence, which is used to measure the difference between the approximate posterior distribution and the prior distribution, and λ is a hyperparameter that weighs the MSE and KL divergence.

[0073] In order to improve the reliability of the filling strategy, this embodiment introduces a self-supervised learning mechanism to learn the filling strategy through the characteristics of the sample data itself. The second loss function of the model, namely the contrast loss function, can be set at the same time. The self-supervised learning method based on the contrast loss maximizes the feature similarity between similar samples and minimizes the feature similarity between non-similar samples by comparing the sample data before and after filling, thereby improving the accuracy of the filling result. Exemplarily, the contrast loss function can be defined by the following formula:

[0074]

[0075] Among them, 1(·) is the indicator function, sim(H i ,H j ) represents the feature similarity of sample data i and j. The feature representation of sample data i of the mth mode is The characteristics of the overall sample data are expressed as H, where: During model training, the training can be terminated when the loss value of the first loss function is less than a set threshold and the loss value of the second loss function is less than a set value.

[0076] In this embodiment, the filling target is defined as minimizing the first loss function, so as to achieve efficient and accurate filling of missing values ​​based on the constraint-trained model. At the same time, a self-supervised learning mechanism is introduced, and the filling strategy can be optimized by comparing the loss function constraint-trained model, thereby improving the accuracy and reliability of the filling results.

[0077] In one embodiment, the feature representation of sample data of different modalities can be kept consistent in a shared space through joint embedding or contrastive learning of H, thereby ensuring the effective fusion of sample data of different modalities and improving their feature consistency, thereby further improving the accuracy of the filling results.

[0078] Based on any one of the above embodiments, in one embodiment, the deep learning model adopts a Bayesian deep learning method, which also includes: calculating an uncertainty estimate of the predicted filling value through Bayesian reasoning to assist medical personnel in evaluating the credibility of the filling results of medical data.

[0079] In this embodiment, the uncertainty of the filling result is estimated by introducing the Bayesian deep learning method, which can further improve the reliability of the filling result. Bayesian reasoning can provide uncertainty quantification for each filling value, thereby helping medical personnel such as decision makers to evaluate the credibility of the filling result. For example, the uncertainty of the filling result can be defined as:

[0080] Among them, Var[·] represents the latent variable The variance of reflects the confidence interval of the filling result.

[0081] To further analyze the uncertainty, the total uncertainty can be decomposed into model uncertainty and data uncertainty. The inference error caused by insufficient training data or insufficient model complexity can be approximated by sampling the model parameters θ multiple times:

[0082]

[0083] The variance of the observed data is directly approximated by the model to account for the inherent noise or unmeasured variability in the sample data itself:

[0084]

[0085] The accuracy of uncertainty estimates for populated results provided by Bayesian deep learning analysis enables medical professionals to increase their trust in the model outputs and facilitates wider application of this implementation in clinical practice.

[0086] Based on any one of the above embodiments, in one embodiment, the method further includes: obtaining, through the model interpretation tool SHAP, a contribution value of each feature data in the medical data input into the filling model to the output predicted filling value, such as a SHAP value, thereby determining the most critical feature data of the filling model in the decision-making process, such as the feature data with the largest SHAP value.

[0087] In this embodiment, the introduction of SHAP values ​​enhances the interpretability of the model, which helps medical decision makers evaluate the credibility of the filling results and the impact of key feature data. It ensures that the filling results have good interpretability and practicality, thereby enhancing the trust of medical professionals in the data analysis results. Good interpretability can make it easier for medical professionals to understand the process and results of data filling and integration, thereby enhancing their trust in the model and their ability to apply it in clinical practice.

[0088] Based on any of the above embodiments, in one embodiment, an attention mechanism may be introduced into the filling model so that the filling model uses the attention mechanism to automatically focus on acquiring the most important contextual information for the filling task.

[0089] By introducing the attention mechanism, the model automatically focuses on the most important contextual information for the filling task. For example, by visualizing the attention weight, we can intuitively understand how the model uses the contextual information of different sample data for filling, determine the most critical feature data such as the feature data with the largest attention weight, and improve the credibility and interpretability of the filling results, which helps medical decision makers evaluate the credibility of the filling results and the impact of key feature data. Ensure that the filling results have good interpretability and practicality, thereby enhancing the trust of medical professionals in the data analysis results, thereby solving the shortcomings of traditional methods in high-dimensional medical data processing and improving the quality and efficiency of clinical decision-making. Good interpretability can make it easier for medical professionals to understand the process and results of data filling and integration, thereby enhancing trust in the model and application capabilities in clinical practice.

[0090] The solution in this embodiment is applicable to complex high-dimensional data environments, and can reduce or even avoid the problem of data incompleteness caused by missing data, as well as the problem of reduced performance of machine learning models caused by inaccurate filling, and can improve the accuracy of medical data filling results.

[0091] It should be noted that, although the steps of the method in the present disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution, etc. In addition, it is also easy to understand that these steps may be, for example, executed synchronously or asynchronously in multiple modules / processes / threads.

[0092] like Figure 3 As shown, the embodiment of the present disclosure provides a medical data processing system, including:

[0093] An acquisition module 401 is used to acquire medical data of a patient;

[0094] A prediction module 402 is used to input the medical data into a filling model to obtain a predicted filling value corresponding to the missing value in the medical data; wherein the filling model is obtained by training a deep learning model based on sample medical data, and the sample medical data includes multiple different types of sample data, and the training process of the deep learning model includes: extracting context information of each sample data from the multiple different types of sample data, and constructing a dependency graph structure based on the context information of each sample data, wherein the dependency graph structure includes multiple nodes and edges connecting each adjacent node; wherein each node represents a sample data and its context information, each edge represents a dependency relationship between sample data of adjacent nodes, and the weight of the edge represents the similarity of the context information of sample data of adjacent nodes; learning and outputting a predicted filling value based on the dependency graph structure until the convergence condition is met and the training is terminated;

[0095] The filling module 403 is used to fill the medical data to obtain new medical data based on the predicted filling value corresponding to the missing value in the medical data.

[0096] In one embodiment, the training process of the deep learning model also includes: using a probability graph model to obtain the conditional probability distribution corresponding to each sample data in the dependency graph structure; optimizing and updating the dependency graph structure based on the conditional probability distribution corresponding to each sample data, and learning and outputting a predicted fill value based on the updated dependency graph structure.

[0097] In one embodiment, the deep learning model includes a graph neural network, and outputs a predicted fill value based on learning the dependency graph structure by the graph neural network.

[0098] In one embodiment, the system also includes an update module, which is used to: obtain new sample medical data and extract context information corresponding to the new sample medical data; update the dependency graph structure based on the difference in similarity between the context information corresponding to the new sample medical data and the context information of each sample data; and the deep learning model re-learns to output predicted fill values ​​based on the updated dependency graph structure.

[0099] In one embodiment, the deep learning model adopts a self-supervised learning mechanism and is provided with a first loss function and a second loss function. The first loss function defines that the goal of missing value filling is to minimize the loss value of the first loss function so that the loss value of the first loss function is less than a set threshold; the second loss function is a contrast loss function, which defines the difference in feature similarity of sample data before and after filling.

[0100] In one embodiment, the deep learning model adopts a Bayesian deep learning method, and the system may further include an estimation module for: calculating an uncertainty estimate of the predicted filling value through Bayesian reasoning to assist medical personnel in evaluating the credibility of the filling results of medical data.

[0101] In one embodiment, the system may also include an interpretation module for: obtaining the contribution value of each feature data in the medical data input into the filling model to the output predicted filling value through the model interpretation tool SHAP, so as to determine the most critical feature data of the filling model in the decision-making process.

[0102] In one embodiment, an attention mechanism is introduced into the filling model so that the filling model automatically focuses on acquiring the most important contextual information for the filling task using the attention mechanism.

[0103] Regarding the system in the above embodiment, the specific manner in which each module performs operations and the corresponding technical effects brought about have been described in detail in the embodiment of the method, and will not be elaborated here.

[0104] It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiment of the present disclosure, the features and functions of two or more modules or units described above can be concretized in one module or unit. Conversely, the features and functions of a module or unit described above can be further divided into multiple modules or units for concretization. The components displayed as modules or units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the disclosed solution. Those of ordinary skill in the art can understand and implement it without paying creative work.

[0105] The embodiments of the present disclosure also provide a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the medical data processing method of any of the above embodiments is implemented.

[0106] Exemplarily, the readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0107] The computer readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by an instruction execution system, an apparatus, or a device or used in combination with it. The program code contained on the readable storage medium may be transmitted with any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0108] The present disclosure also provides an electronic device, including a processor and a memory, wherein the memory is used to store a computer program, wherein the processor is configured to execute the medical data processing method in any of the above embodiments by executing the computer program.

[0109] Refer to the following Figure 4The electronic device 600 according to this embodiment of the present invention is described. Figure 4 The electronic device 600 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0110] like Figure 4 As shown, the electronic device 600 is in the form of a general computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0111] The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 performs the steps according to various exemplary embodiments of the present invention described in the above method embodiment section of this specification. For example, the processing unit 610 can perform the following steps: Figure 1 The steps of the method shown in .

[0112] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0113] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0114] Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0115] The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 650. Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0116] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation methods of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to execute the method steps of the above-mentioned embodiments according to the implementation methods of the present disclosure.

[0117] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0118] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A medical data processing method, characterized in that: include: Access to patients’ medical data; The medical data is input into a filling model to obtain a predicted filling value corresponding to the missing value in the medical data; wherein the filling model is obtained by training a deep learning model based on sample medical data, and the sample medical data includes multiple different types of sample data, and the training process of the deep learning model includes: extracting context information of each sample data from the multiple different types of sample data, and constructing a dependency graph structure based on the context information of each sample data, wherein the dependency graph structure includes multiple nodes and edges connecting each adjacent node; wherein each node represents a sample data and its context information, each edge represents a dependency relationship between sample data of adjacent nodes, and the weight of the edge represents the similarity of the context information of sample data of adjacent nodes; learning and outputting predicted filling values ​​based on the dependency graph structure until the convergence condition is met and the training is terminated; Based on the predicted filling values ​​corresponding to the missing values ​​in the medical data, the medical data are filled to obtain new medical data.

2. The method according to claim 1, characterized in that The training process of the deep learning model also includes: A probability graph model is used to obtain the conditional probability distribution corresponding to each sample data in the dependency graph structure; the dependency graph structure is optimized and updated based on the conditional probability distribution corresponding to each sample data, and a predicted fill value is output based on the learning of the updated dependency graph structure.

3. The method according to claim 1, characterized in that The deep learning model includes a graph neural network, which learns and outputs a predicted fill value based on the dependency graph structure.

4. The method according to claim 3, characterized in that The method further includes: Acquire new sample medical data, and extract context information corresponding to the new sample medical data; Update the dependency graph structure based on the difference in similarity between the context information corresponding to the new sample medical data and the context information of each sample data; The output predicted fill value is re-learned based on the updated dependency graph structure.

5. The method according to claim 1, characterized in that The deep learning model adopts a self-supervised learning mechanism and is provided with a first loss function and a second loss function. The first loss function defines that the goal of missing value filling is to minimize the loss value of the first loss function so that the loss value of the first loss function is less than a set threshold; the second loss function is a contrast loss function, which defines the difference in feature similarity of sample data before and after filling.

6. The method according to claim 1, characterized in that The deep learning model adopts a Bayesian deep learning method, and the method also includes: The uncertainty estimate of the predicted filling value is calculated through Bayesian reasoning to assist medical personnel in evaluating the credibility of the filling results of medical data.

7. The method according to any one of claims 1 to 6, characterized in that: The method further includes: The contribution value of each feature data in the medical data input into the filling model to the output predicted filling value is obtained through the model interpretation tool SHAP, so as to determine the most critical feature data of the filling model in the decision-making process; And / or, introducing an attention mechanism into the filling model so that the filling model uses the attention mechanism to automatically focus on obtaining the most important contextual information for the filling task.

8. A medical data processing system, characterized in that: include: An acquisition module, used to obtain the patient's medical data; A prediction module, used for inputting the medical data into a filling model to obtain a predicted filling value corresponding to the missing value in the medical data; wherein the filling model is obtained by training a deep learning model based on sample medical data, and the sample medical data includes a plurality of different types of sample data, and the training process of the deep learning model includes: extracting context information of each sample data from the plurality of different types of sample data, and constructing a dependency graph structure based on the context information of each sample data, wherein the dependency graph structure includes a plurality of nodes and edges connecting adjacent nodes; wherein each node represents a sample data and its context information, each edge represents a dependency relationship between sample data of adjacent nodes, and the weight of the edge represents the similarity of the context information of sample data of adjacent nodes; learning and outputting a predicted filling value based on the dependency graph structure until the convergence condition is met and the training is terminated; A filling module is used to fill the medical data to obtain new medical data based on the predicted filling value corresponding to the missing value in the medical data.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the medical data processing method according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: processor; as well as Memory for storing computer programs; Wherein, the processor is configured to perform the medical data processing method according to any one of claims 1 to 7 by executing the computer program.

Images