Intelligent coding method and device for infectious disease data, computer equipment and storage medium

Abstract

The embodiment of the invention discloses an intelligent coding method and device for infectious disease data, computer equipment and a storage medium. The method comprises the following steps: acquiring medical text data related to infectious diseases; extracting local features of the medical text data; constructing a clinical medicine knowledge graph, and modeling the coding relation to obtain a modeling result; fusing the local features with the modeling result to obtain a feature fusion result; inputting the feature fusion result into a coding decision model for coding to obtain an ICD coding result; and outputting the ICD coding result. By implementing the method provided by the embodiment of the invention, the feature extraction and coding prediction process of the infectious disease data can be improved, so that the coding accuracy and efficiency are enhanced.

Description

Technical Field

[0001] The present invention relates to a medical information processing method, and more specifically to an infectious disease data intelligent coding method, device, computer equipment and storage medium. Background Art

[0002] In modern hospital management, accurate coding of infectious diseases is crucial for disease monitoring, treatment analysis, and medical insurance settlement. With the popularization of electronic medical record systems, a large amount of unstructured medical data has emerged, including medical records, laboratory results, and clinical diagnosis information. However, manual coding of this information is not only time-consuming but also prone to errors, so the need for automated coding has become increasingly urgent.

[0003] The traditional ICD (International Classification of Diseases) coding method relies on manual judgment and is affected by the doctor's experience and the quality of information entry, which may lead to inaccurate or missing coding. Although the existing automatic coding technology has made some progress, it still faces challenges in feature extraction and context understanding, and the coding relationship modeling is often not accurate enough. Some current technologies, such as multi-scale convolutional neural networks and graph convolutional networks, can process text features and coding relationships, but have limited capabilities in processing long texts and consume a lot of computing resources.

[0004] Therefore, it is necessary to design a new method to improve the feature extraction and coding prediction process of infectious disease data to enhance the accuracy and efficiency of coding. Summary of the invention

[0005] The purpose of the present invention is to overcome the defects of the prior art and provide a method, device, computer equipment and storage medium for intelligent encoding of infectious disease data.

[0006] To achieve the above object, the present invention adopts the following technical solution: an intelligent coding method for infectious disease data, comprising: Obtain medical text data related to infectious diseases; Extracting local features from the medical text data; Construct a clinical medical knowledge graph and model the coding relationship to obtain modeling results; The local features are fused with the modeling results to obtain a feature fusion result; Inputting the feature fusion result into the coding decision model for coding to obtain an ICD coding result; Output the ICD encoding result.

[0007] A further technical solution is: extracting local features from the medical text data includes: Performing text decomposition and embedding on the medical text data to obtain an embedding matrix; Performing a convolution operation on the embedding matrix to obtain a convolution result; Performing maximum pooling layer processing on the convolution result to obtain a pooling result; The pooling results are subjected to feature map splicing and full connection processing to obtain local features.

[0008] A further technical solution is: constructing a clinical medical knowledge graph and modeling the coding relationship to obtain a modeling result, including: Construct a clinical medical knowledge graph and use graph neural network to model the encoding relationship to obtain the modeling results.

[0009] The further technical solution is: the construction of the clinical medical knowledge graph uses a graph neural network to model the encoding relationship to obtain a modeling result, including: Construct clinical medical knowledge graph; Performing multi-layer graph convolution processing on the clinical medical knowledge graph to obtain a node embedding representation; Extracting global features using a pooling operation on the node embedding representation; Calculate the similarity between nodes according to the global feature representation to determine the dependency relationship between the nodes; The node embedding representation and the dependencies between nodes are combined to obtain a modeling result.

[0010] A further technical solution is: performing multi-layer graph convolution processing on the clinical medical knowledge graph to obtain a node embedding representation includes: Aggregating information of neighbor nodes in the clinical medical knowledge graph and calculating a weighted sum of features of each node; The weight matrix and bias term of the graph convolution layer are applied, and the ReLU activation function is used for nonlinear transformation to obtain the node embedding representation.

[0011] A further technical solution is: fusing the local features with the modeling results to obtain feature fusion results, including: Concatenating the local features with the modeling results to obtain a high-dimensional feature vector; Performing dimensionality reduction processing on the high-dimensional feature vector to obtain a dimensionality reduction result; The dimension reduction result is input into the integrated learning model for feature fusion to obtain a feature fusion result.

[0012] A further technical solution is: inputting the feature fusion result into a coding decision model for coding to obtain an ICD coding result, including: The feature fusion result is input into the coding decision model for coding, and the ICD coding result is determined by using fuzzy logic; Among them, the coding decision model is a multi-level neural network model constructed using a reinforcement learning framework.

[0013] The present invention also provides an infectious disease data intelligent encoding device, comprising: A data acquisition unit, used for acquiring medical text data related to infectious diseases; A local feature extraction unit, used for extracting local features from the medical text data; A modeling unit is used to construct a clinical medical knowledge graph and model the coding relationship to obtain a modeling result; A fusion unit, used for fusing the local features with the modeling results to obtain a feature fusion result; An encoding unit, used for inputting the feature fusion result into an encoding decision model for encoding to obtain an ICD encoding result; An output unit is used to output the ICD coding result.

[0014] The present invention further provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor implements the above method when executing the computer program.

[0015] The present invention also provides a storage medium, wherein the storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0016] The beneficial effects of the present invention compared with the prior art are: the present invention obtains medical text data related to infectious diseases and extracts local features, constructs a clinical medical knowledge graph, models the coding relationship, and fuses the local features with the modeling results. The fusion results are input into the coding decision model, and the ICD coding results are generated and output, thereby improving the feature extraction and coding prediction process of infectious disease data to enhance the accuracy and efficiency of coding.

[0017] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0019] Figure 1A schematic diagram of an application scenario of the method for intelligent encoding of infectious disease data provided by an embodiment of the present invention; Figure 2 A schematic diagram of a flow chart of an intelligent coding method for infectious disease data provided by an embodiment of the present invention; Figure 3 A schematic diagram of a sub-process of the method for intelligent encoding of infectious disease data provided by an embodiment of the present invention; Figure 4 A schematic diagram of a sub-process of the method for intelligent encoding of infectious disease data provided by an embodiment of the present invention; Figure 5 A schematic diagram of a sub-process of the method for intelligent encoding of infectious disease data provided by an embodiment of the present invention; Figure 6 A schematic diagram of a sub-process of the method for intelligent encoding of infectious disease data provided by an embodiment of the present invention; Figure 7 A schematic block diagram of an intelligent encoding device for infectious disease data provided by an embodiment of the present invention; Figure 8 A schematic block diagram of a local feature extraction unit of an infectious disease data intelligent encoding device provided by an embodiment of the present invention; Fig. 9 A schematic block diagram of a modeling unit of an infectious disease data intelligent encoding device provided by an embodiment of the present invention; Fig.10 A schematic block diagram of a multi-layer graph convolution subunit of the infectious disease data intelligent encoding device provided by an embodiment of the present invention; Fig.11 A schematic block diagram of a fusion unit of an infectious disease data intelligent encoding device provided by an embodiment of the present invention; Fig.12 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0022] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0023] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0024] See also Figure 1 and Figure 2 , Figure 1 A schematic diagram of an application scenario of the infectious disease data intelligent encoding method provided in an embodiment of the present invention. Figure 2 A schematic flow chart of the method for intelligent coding of infectious disease data provided by an embodiment of the present invention. The method for intelligent coding of infectious disease data is applied to a server. The server interacts with the terminal to obtain medical text data from the electronic medical record system; uses a deep convolutional neural network (CNN) to extract text features to capture important information in the disease description; constructs a clinical medical knowledge graph, and applies a graph neural network (GNN) to process the complex relationship between disease codes to achieve a deeper semantic understanding; uses an integrated learning method to fuse the features extracted by CNN and GNN to improve the performance of the model; optimizes model training through reinforcement learning and meta-learning to improve its adaptability and effectiveness; uses a fuzzy logic system and a dynamic threshold adjustment strategy to make coding decisions to ensure that the final generated ICD code is accurate. This method aims to improve the accuracy of disease coding, while being able to effectively process a large amount of complex medical data, thereby improving the efficiency of medical services.

[0025] Figure 2 FIG. 1 is a flow chart of the method for intelligently encoding infectious disease data provided by an embodiment of the present invention. Figure 2 As shown, the method includes the following steps S110 to S160.

[0026] S110. Obtain medical text data related to infectious diseases.

[0027] In this embodiment, the medical text data includes relevant records of infectious diseases, such as medical history descriptions, laboratory test results, and doctors' diagnoses.

[0028] Specifically, medical text data is received from the hospital's electronic medical record system, mainly including medical record descriptions, laboratory test results, and doctors' diagnosis information; patients' symptoms, medical history, and physical signs are extracted from medical records to identify information related to infectious diseases. These descriptions help understand the patient's specific conditions; laboratory test results (such as blood tests and urine analysis) are obtained, which help confirm the presence and severity of infectious diseases; and diagnostic conclusions about infectious diseases are extracted from doctors' diagnostic reports, including preliminary diagnosis, etiology analysis, and treatment recommendations.

[0029] Ensure that medical text data is stored in structured or unstructured formats and preprocessed, including noise removal, word segmentation, and entity recognition, to ensure data quality.

[0030] Data standardization: De-noise and format standardize the received data to unify the data format for subsequent processing.

[0031] Word segmentation and named entity recognition: Perform word segmentation on medical texts and use named entity recognition (NER) technology to extract entities related to infectious diseases, such as disease names, symptoms, and detection indicators.

[0032] Labeling and model training: Label the text data of each record with the corresponding ICD code to provide label data for subsequent model training and help improve the accuracy of disease coding.

[0033] Through these steps, key information can be extracted from medical texts more effectively to provide support for subsequent analysis and decision-making.

[0034] S120: extracting local features from the medical text data.

[0035] In this example, local features refer to small snippets or phrases in the text, such as specific symptoms, disease names, experimental results, etc. By sliding the convolution kernel over the text, CNN is able to capture these local features and identify important keywords and patterns. For example, in the sentence "The patient had a high fever and cough", local features may include "high fever" and "cough".

[0036] Contextual information representation refers to understanding local features by taking into account their position and relationship in the entire text. Through multi-layer convolution and pooling operations, CNN can integrate the connections between different local features to form a more comprehensive understanding of the text. For example, the previous "high fever" and "cough" combined with other descriptions of the patient (such as medical history, treatment response) can help the model better understand the entire case.

[0037] Combining these two, CNN can effectively extract key information from medical texts and provide rich representations to support subsequent analysis or decision-making.

[0038] In one embodiment, see Figure 3 , the above-mentioned step S120 may include steps S121~S124.

[0039] S121. Perform text decomposition and embedding on the medical text data to obtain an embedding matrix.

[0040] In this embodiment, the embedding matrix refers to a matrix obtained after text decomposition and embedding of medical text data.

[0041] Specifically, the medical text is segmented into words or character sequences. Existing word segmentation tools (such as Jieba word segmentation, SpaCy, etc.) or custom word segmenters can be used for processing; for example, the sentence "patients need regular checkups" can be decomposed into "patients", "needs", "regularly", and "checkups".

[0042] Convert the segmented text into an embedding matrix. Use word embedding techniques such as Word2Vec, GloVe, or pre-trained models (such as BERT); the embedding matrix maps each word into a vector of fixed dimensions, usually tens to hundreds of dimensions, which retains the semantic information of the word.

[0043] Word embedding technology can capture the semantic relationship between words. Words with similar meanings are close to each other in the vector space, making the model more accurate in understanding the context. It can convert high-dimensional sparse representations into low-dimensional dense representations, reduce computational complexity, and improve training efficiency. By using pre-trained models, existing knowledge can be directly used to accelerate the model's learning process and improve performance.

[0044] S122: Perform a convolution operation on the embedding matrix to obtain a convolution result.

[0045] In this embodiment, the convolution result refers to the result obtained after the embedded matrix is ​​convolved.

[0046] Specifically, a convolution operation is performed by sliding a convolution kernel (filter) on the embedding matrix. Each convolution kernel is responsible for extracting a specific type of local feature; for example, using a 3-gram convolution kernel, it can detect consecutive combinations of three words. The weighted sum of the local area is calculated to obtain the feature map.

[0047] Perform nonlinear transformation on the features after convolution operation, usually using ReLU (Rectified Linear Unit) as the activation function. This operation can introduce nonlinear factors and increase the model's expressiveness.

[0048] Convolution operations can effectively extract important local features in text, such as keywords and phrases, and help capture contextual information. Activation functions such as ReLU enable the model to learn more complex patterns, improve prediction accuracy, and avoid the limitations of linear models.

[0049] S123. Perform maximum pooling layer processing on the convolution result to obtain a pooling result.

[0050] In this embodiment, the pooling result refers to the result obtained by performing maximum pooling layer processing on the convolution result.

[0051] Specifically, after the convolution operation, a max pooling layer is used to select local maxima from the convolution feature map. This process helps reduce the dimensionality of the feature map and retain important information. For example, if the feature map is two-dimensional, the feature map is reduced by selecting the maximum value in each 2x2 area.

[0052] In addition to maximum pooling, average pooling can also be applied to calculate the average value from each local area to extract smoother features.

[0053] Max pooling can significantly reduce feature dimensions, reduce computational effort, help control model complexity, and reduce the risk of overfitting. The pooling operation enhances the model’s robustness to small changes in input, making it more stable when facing texts in different formats.

[0054] S124, performing feature map splicing and full connection processing on the pooling results to obtain local features.

[0055] In this embodiment, multiple convolution kernels are used to generate different feature maps, and these feature maps are spliced ​​to merge the features extracted by different convolution kernels; through splicing, the features extracted by different convolution kernels are combined to form a richer feature representation.

[0056] The pooled feature map is flattened into a one-dimensional vector and then further processed through a fully connected layer to map the features into a high-dimensional space.

[0057] Through splicing, the model can comprehensively consider multiple local features and improve the overall representation ability; the fully connected layer can transform low-dimensional features into high-dimensional representations, so that the model can learn more complex decision boundaries, thereby improving the accuracy of classification or regression tasks.

[0058] Through the above process, the final feature map will be flattened into a one-dimensional vector. This vector, as a high-dimensional feature representation of medical text, can be used for subsequent classification or regression tasks.

[0059] The flattened feature vector provides a unified input format, which is convenient for combination with other machine learning algorithms and supports subsequent analysis and decision-making; the final feature vector effectively condenses the important information in the text, facilitates subsequent processing and in-depth analysis, and improves the efficiency and effectiveness of medical text processing.

[0060] Through these steps, deep convolutional neural networks can effectively extract rich features from medical texts and improve the model's ability to understand and analyze text content. These features not only retain semantic information, but also enhance the model's expressiveness through multi-level processing, providing strong support for medical analysis and decision-making.

[0061] S130. Construct a clinical medical knowledge graph and model the coding relationship to obtain a modeling result.

[0062] In this embodiment, the modeling results refer to the node representation and relationship information obtained by processing the clinical medical knowledge graph through the graph neural network (GNN). These results can be used to achieve a variety of applications, such as: Node embedding representation: A vector representation of each node (such as disease, symptom, drug, etc.) that captures its characteristics and relationships.

[0063] Similarity calculation: The similarity between nodes is used to determine the correlation or similarity between different medical entities, which is very important for disease diagnosis and treatment plan recommendation.

[0064] Dependencies: Revealing the dependencies between different medical concepts helps understand their roles in clinical decision making.

[0065] Knowledge reasoning: Use the relationship between nodes to reason and assist doctors in making more accurate diagnoses and treatment recommendations.

[0066] Decision support: Provide data support for clinical decision-making systems to improve the efficiency and accuracy of medical services.

[0067] These modeling results can help medical staff better understand the complex medical knowledge system and thus improve patient treatment outcomes.

[0068] Specifically, a clinical medical knowledge graph is constructed, and a graph neural network is used to model the encoding relationship to obtain the modeling results.

[0069] Graph neural networks (GNNs) are used to process graph-structured data to capture the complex relationships and dependencies between disease codes.

[0070] In one embodiment, see Figure 4 The above-mentioned step S130 may include steps S131~S135.

[0071] S131. Construct a clinical medicine knowledge graph.

[0072] In this embodiment, in the knowledge graph, the main nodes include: Disease coding node: a code that uniquely identifies each disease; Disease name node: describes the name of a specific disease; Symptom nodes: various symptoms associated with the disease.

[0073] Each node is represented by a feature vector. For example, the embedding vector of a disease code can contain various attribute information of the disease (such as severity, transmission route, etc.).

[0074] Definition of relations and edges: Nodes are connected by edges, which represent the relationship between nodes: Parent-child relationship: Disease coding nodes can be represented by a hierarchical relationship. For example, a large disease category can be the parent node of a sub-category disease.

[0075] Association strength: The edge weights between disease nodes and symptom nodes can be set based on statistical data or clinical research results to reflect the strength of the association between symptoms and diseases.

[0076] There are two ways to initialize the embedding representation of each node: Random initialization: Generate random initial embedding vectors.

[0077] Based on pre-trained models: Use existing medical text data for pre-training to obtain more effective embedding representations and improve model performance.

[0078] S132. Perform multi-layer graph convolution processing on the clinical medical knowledge graph to obtain a node embedding representation.

[0079] In one embodiment, see Figure 5 , the above-mentioned step S132 may include steps S1321~S1322.

[0080] S1321, aggregating information of neighbor nodes in the clinical medical knowledge graph, and calculating the weighted sum of features of each node; S1322. Apply the weight matrix and bias term of the graph convolution layer and use the ReLU activation function for nonlinear transformation to obtain the node embedding representation.

[0081] In this embodiment, the embedding representation of each node is initialized , can be randomly initialized or embedded based on a pre-trained model. For each node Perform graph convolution operation, which includes the following steps: By aggregating the information of neighboring nodes, the weighted sum of the neighboring node features of each node is calculated. The formula is as follows: ;in, is the normalization coefficient, is the weight matrix of the current layer, is the bias term.

[0082] Use the aggregation results to perform nonlinear transformation on the node representation: ;here, Usually it is the ReLU activation function to enhance the expressiveness of the model.

[0083] S133, extracting global features from the node embedding representation using a pooling operation.

[0084] In this embodiment, after completing multiple layers of graph convolution, a pooling operation is applied to extract global features.

[0085] Specifically, key features are selected from the neighbors of each node to reduce the dimension and retain important information. This process helps control overfitting and improve the efficiency of the model.

[0086] S134. Calculate the similarity between nodes according to the global feature representation to determine the dependency relationship between the nodes.

[0087] In this embodiment, the final node embedding representation is obtained Finally, the important relationships are identified by calculating the similarity between nodes. The specific methods include: Inner Product: Calculate the inner product between node embedding vectors to get the similarity score.

[0088] Distance metric: Use methods such as Euclidean distance or cosine similarity.

[0089] S135. Combine the node embedding representation and the dependencies between nodes to obtain a modeling result.

[0090] Specifically, the role of node embedded representation is Node embedding is a vector representation generated by calculating the features and neighbor relationships of each node in the knowledge graph through a graph neural network (GNN). These embedding vectors contain the properties of the node itself and its relationship with other nodes. The specific functions are as follows: 1. Provide high-dimensional feature representation of nodes. In the knowledge graph, node embedding represents the conversion of the complex characteristics of each node into a high-dimensional vector. These vectors capture the semantic information of the nodes and contain the relationship between the nodes. The embedding representation of disease coding nodes is of higher dimension and can contain multi-dimensional feature information, such as the common symptoms, course of disease, treatment methods, etc. of a specific disease. This high-dimensional embedding enables the system to perform more accurate matching during the encoding process.

[0091] Second, enrich contextual information and enhance predictive capabilities. This embedding can represent the interdependence and influence between nodes and capture complex semantic relationships. For example, a disease coding node can capture the strength of its association with the symptom through its neighbor relationship with the symptom node. If multiple similar disease coding nodes share similar symptom information, their embedding representations will become similar, helping the system identify the connection between these diseases when encoding.

[0092] 3. Used for feature fusion and combined with the output of other models. In the subsequent feature fusion process, the node embedding representation will be used in combination with the medical text features extracted by CNN. This multimodal feature fusion can provide the system with more comprehensive disease coding decision support.

[0093] Combining medical text features: The features extracted by CNN mainly focus on the local patterns and language information of medical texts. The node embedding representation reflects more the context and structured relationships in the knowledge graph. Therefore, the combination of the two can make full use of the detailed information in the text and the global information in the knowledge graph to achieve a complementary effect.

[0094] The role of inter-node dependencies is as follows: The dependency between nodes is calculated by GNN in the knowledge graph, which is a pattern that reflects the mutual influence or association between nodes (such as disease codes, symptoms, etc.). The role of this dependency in coding decisions is as follows: Identify complex disease and symptom associations: In clinical practice, some diseases have strong dependencies on specific symptoms, and these dependencies are reflected through edge weights and feature propagation in GNN. In the decision-making process of disease coding, the system can use this dependency to improve accuracy.

[0095] For example, if the relationship between a specific symptom node and multiple disease coding nodes is very strong (such as a certain symptom is a common manifestation of multiple diseases), the system can further confirm the rationality of the coding selection through these dependencies.

[0096] In addition, some diseases may have a parent-child relationship. For example, the dependency relationship between a sub-category disease (such as an infection caused by a specific virus) and its superordinate disease (such as a generalized viral infection) can also be represented by this dependency model. These parent-child relationships help find the best match in similar encodings and reduce errors.

[0097] Support for similarity calculation in encoding decisions: Based on the dependencies between nodes, the system can calculate node similarity to identify nodes with higher correlation. This similarity calculation method helps capture the interactions and similarities between different nodes, and is especially effective when screening between similar disease codes.

[0098] Inner product or distance measurement: Through the inner product or distance measurement, the system can calculate the similarity between two nodes (such as disease code nodes or symptom nodes). If the similarity between two code nodes is high, the system can determine that they may have similar meanings in medical semantics.

[0099] Decision support: Nodes with high similarity may share the same symptoms or clinical manifestations. The system can use this dependency to further distinguish or cluster similar disease codes. When making coding decisions, this information can assist the system in making more detailed disease coding selections.

[0100] Optimize the hierarchical structure processing of disease coding: Disease codes often have a hierarchical structure, for example, some disease codes have parent-child relationships or different levels of classification. The dependencies between nodes can help the system better handle this hierarchical structure problem when coding, ensuring that the selection of codes conforms to the standardized classification system.

[0101] Parent-child code selection: In some complex cases, the disease may belong to multiple levels of classification. The system can make reasonable selections among parent-child codes through the dependencies between disease code nodes. For example, a specific infectious disease may be a subclass of the previous level classification (such as "infectious disease"). Through this parent-child relationship, the system can select the appropriate code more accurately.

[0102] Specific application of node embedding representation and dependency in feature fusion: Specific application of feature fusion: The system combines the node embedding representation with the text features extracted by CNN to form a multi-dimensional feature vector. The key to this step is how to effectively fuse features from different sources.

[0103] Ensemble learning: The system uses ensemble learning methods (such as random forest) to improve the robustness of the model based on the fusion of node embedding and text features. Ensemble learning methods can combine different features and reduce the deviation of a single model and enhance the stability of prediction by integrating multiple models.

[0104] Application in coding decisions: In the final coding decision process, the system uses node similarity calculation and dependency to optimize the selection of coding. By handling uncertainty through fuzzy logic, the system can dynamically adjust the threshold to make the coding selection more flexible and accurate.

[0105] Uncertainty handling: Based on the node embedding representation and similarity, the system can determine the prediction probability of different encodings. If the similarity of some encodings is high, the system will be more inclined to select these encodings and dynamically adjust according to the corresponding threshold.

[0106] Auxiliary decision-making based on dependencies: Dependencies between nodes also provide the system with rich auxiliary information. For example, between symptom nodes and disease coding nodes, the system can make more accurate coding decisions through these dependencies, ensuring that the selected coding closely matches the patient's symptoms.

[0107] In this embodiment, the embedded representation of each node is finally output, which is used for subsequent feature fusion and coding decisions. These embedded information is rich in relational features, which significantly enhances the understanding and accuracy of intelligent coding of infectious diseases.

[0108] Through the graph structure, different types of medical information can be effectively integrated to capture complex relationships and dependencies; through multi-level aggregation and nonlinear transformation, the graph convolutional network can learn rich node representations and improve the performance of the model; the improved node similarity calculation provides strong support for disease diagnosis and treatment plans, helping clinicians make more accurate decisions; the combination of knowledge graph and graph convolutional network has good scalability and can adapt to the increasing amount of new data and new knowledge.

[0109] S140: Fusing the local features with the modeling results to obtain feature fusion results.

[0110] In this embodiment, the feature fusion result is a comprehensive feature expression obtained by combining the local features with the modeling results. The goal of this process is to combine local features and global relationship information to improve the accuracy of subsequent encoding decisions.

[0111] In one embodiment, see Figure 6 , the above-mentioned step S140 may include steps S141~S143.

[0112] S141. Concatenate the local features with the modeling results to obtain a high-dimensional feature vector.

[0113] In this embodiment, the high-dimensional feature vector refers to a vector obtained by concatenating the local feature with the modeling result.

[0114] The feature vectors from CNN and GNN are combined into a higher-dimensional feature vector through a concatenation operation. This concatenation operation can effectively fuse different information from image and graph structure data. This integration method ensures that the model can make full use of rich contextual information, making the feature representation more comprehensive.

[0115] S142: Perform dimensionality reduction processing on the high-dimensional feature vector to obtain a dimensionality reduction result.

[0116] In this embodiment, the dimension reduction result refers to the result obtained after the dimension reduction of the high-dimensional feature vector.

[0117] In order to reduce computational complexity and prevent overfitting, the concatenated high-dimensional feature vectors are then subjected to dimensionality reduction. Common dimensionality reduction techniques include principal component analysis (PCA) and linear discriminant analysis (LDA), which can reduce feature dimensions while retaining important feature information. This step not only improves computational efficiency, but also helps the model focus on the most discriminative features and avoids interference from redundant information.

[0118] S143, inputting the dimension reduction result into an integrated learning model for feature fusion to obtain a feature fusion result.

[0119] In this embodiment, the fused feature vector is then input into an ensemble learning model, such as a random forest or gradient boosted tree. These ensemble learning methods significantly improve overall accuracy and stability by combining the prediction results of multiple base learners. In this process, each base learner is trained using the same feature set, and ultimately generates a comprehensive prediction result by weighted voting or averaging.

[0120] The final fusion features will be used as the input of the coding decision model. This feature set provides comprehensive information support and significantly enhances the accuracy and performance of intelligent coding of infectious diseases.

[0121] Combining the features of CNN and GNN, the model can obtain information from multiple data types and improve the diversity of information; through dimensionality reduction, redundant features are removed, the complexity of the model is reduced, and the model has stronger generalization ability on new data; taking advantage of the integrated learning model, the accuracy and reliability of the prediction are improved through the combination of multiple base learners; this feature fusion method can be used for a variety of intelligent decision-making systems, especially in the fields of medicine, finance, etc. It has important application value.

[0122] By combining the above steps and benefits, this feature fusion solution can effectively improve the performance of the model and meet the needs of actual applications.

[0123] Ensemble learning methods (such as random forests) improve the accuracy and stability of predictions by fusing multiple models rather than a single multi-layer perceptron.

[0124] S150, inputting the feature fusion result into a coding decision model for coding to obtain an ICD coding result.

[0125] In this embodiment, the ICD coding result refers to the result of coding diseases and health conditions in the International Classification of Diseases (ICD) system. ICD coding is used to standardize medical records, statistics and research, helping doctors, researchers and public health agencies to accurately record and analyze disease data.

[0126] In specific implementation, ICD coding results are usually obtained by analyzing the patient's clinical data, symptoms, diagnosis and other information, and mapping them to the corresponding codes in the ICD system. This process can use machine learning models to improve the accuracy and efficiency of coding.

[0127] Specifically, the feature fusion result is input into the coding decision model for coding, and the ICD coding result is determined by using fuzzy logic; Among them, the coding decision model is a multi-level neural network model constructed using a reinforcement learning framework.

[0128] A reinforcement learning framework is applied to the coding decision model to optimize the coding decision process. The model parameters are dynamically adjusted through a reward mechanism to improve the adaptability to different cases. At the same time, a meta-learning strategy is introduced so that the model can quickly adapt to the task of new disease coding.

[0129] The fused features are input into the coding decision model. The uncertainty of the predicted results is handled by the fuzzy logic system, and the final coding selection is optimized through the dynamic threshold adjustment strategy. The predicted probability value of each ICD code is compared with the adjusted threshold, and the ICD code that meets the requirements is selected as the final disease code output to complete the coding allocation.

[0130] Specifically, the model used to build the encoding decision usually adopts a multi-layer neural network structure, which can effectively process complex input data and enable the model to capture and express various feature relationships in the data.

[0131] Input: The input of the model is the fused feature vectors, which integrate various disease-related information, such as the patient's medical history, test results, etc.

[0132] Output: The output of the model is the corresponding disease code. The predicted probability of each code reflects the degree of match between the code and the current input features.

[0133] By introducing reinforcement learning algorithms (such as Q-learning or deep Q networks), the model can select the optimal action (a) based on the current state (s) in each prediction and update the Q value based on the reward (r). The specific update formula is: ; where α is the learning rate, γ is the discount factor, For the next state.

[0134] This dynamic updating mechanism enables the model to gradually improve its decision-making strategy, thereby improving the accuracy of the encoding.

[0135] In addition, the introduction of a meta-learning strategy enables the model to quickly adapt to new disease coding tasks. By training on multiple related tasks, the model can learn shared knowledge, thereby speeding up the response to new situations.

[0136] When encountering new tasks, the model can quickly adjust using previously learned knowledge without having to train from scratch. Even when data is scarce, the model is able to effectively learn and infer through existing experience.

[0137] During the model training process, it is crucial to perform performance evaluation regularly. Through techniques such as cross-validation and holdout, the generalization ability of the model can be ensured and overfitting can be avoided.

[0138] Cross-validation: Divide the dataset into multiple subsets and evaluate the performance of the model by alternating between using different subsets for training and testing.

[0139] Hyperparameter adjustment: According to the evaluation results, timely adjust the model's hyperparameters (such as learning rate, number of hidden layers, etc.) to optimize the overall performance of the model.

[0140] Through the above methods, the application of reinforcement learning framework in disease coding brings multiple benefits: Improve coding accuracy: The dynamically optimized decision-making process can effectively reduce coding errors and improve the quality and reliability of medical documents.

[0141] Enhanced model adaptability: The meta-learning strategy enables the model to quickly adapt to new encoding tasks, reducing the reliance on large amounts of labeled data.

[0142] Better generalization: Regular performance evaluation and hyperparameter tuning ensure that the model maintains good performance in different situations, facilitating implementation in real clinical settings.

[0143] Support clinical decision-making: Accurate disease coding not only helps with patient management, but also provides reliable data support for clinical decision-making and improves medical efficiency.

[0144] In short, combining the reinforcement learning framework with the meta-learning strategy can significantly optimize the disease coding process and bring more efficient and accurate solutions to the medical industry.

[0145] In this example, during the disease coding process, the model outputs a series of predicted probability values ​​that represent the degree of match between each possible International Classification of Diseases (ICD) code and the input features. In this way, the system is able to provide a clear coding choice for each input, enhancing its interpretability and accuracy.

[0146] The model first generates unnormalized scores based on the input features and then normalizes them using the softmax function. The softmax function converts these scores into probability values, and its formula is as follows: ,in, is the unnormalized score of the corresponding code, and N is the number of all possible codes. In this way, the output probability value can be easily understood and interpreted, allowing medical personnel to more intuitively evaluate the possibility of each code.

[0147] To deal with the uncertainty in the prediction results, the system uses a fuzzy logic system. Based on dynamic threshold setting, the system compares the predicted probability value with the pre-set threshold to determine the final coding selection.

[0148] Dynamic threshold setting: The threshold is not fixed, but is constantly adjusted based on historical data and real-time feedback. In this way, the system can better adapt to the characteristics and needs of different cases, ensuring that appropriate decisions can still be made when uncertainty is high.

[0149] The specific optimization process includes the following steps: By analyzing historical case data, we can identify which combinations of features are associated with successful coding outcomes. This process helps us understand which factors have the greatest impact on coding outcomes.

[0150] Feedback on encoding results is collected in real time and used to continuously update and adjust dynamic thresholds. This feedback mechanism ensures that the system can learn and improve its decision-making process.

[0151] Based on the analysis results and feedback information, the threshold used to determine the encoding selection is dynamically adjusted to improve the accuracy of the decision.

[0152] Based on the adjusted dynamic threshold, the system selects the ICD code that meets the requirements from the predicted probability values ​​as the final disease code output.

[0153] This approach brings multiple benefits to the disease coding process: Improved accuracy: By normalizing probability values ​​and introducing fuzzy logic, the system can make more accurate coding choices when faced with complex and uncertain situations.

[0154] Enhanced explainability: Probability-based outputs enable healthcare professionals to understand the rationale behind each coding choice, thereby increasing trust.

[0155] Strong adaptability: The setting of dynamic thresholds allows the system to be flexibly adjusted according to the characteristics of different cases, enhancing the adaptability of the system.

[0156] Continuous optimization: Through feedback mechanisms and historical data analysis, the system is able to continuously optimize its decision-making process and improve overall performance.

[0157] Support clinical decision-making: The disease codes finally generated will be used for subsequent clinical decision support and data analysis to ensure that the patient's condition is accurately reflected and provide a good data foundation for medical treatment.

[0158] In short, by combining probability output, fuzzy logic system and dynamic threshold adjustment, the disease coding process becomes more intelligent and efficient, effectively improving the quality and reliability of coding.

[0159] S160: Output the ICD coding result.

[0160] In this embodiment, the final ICD coding results are managed and stored, including data storage structure and clinical support functions.

[0161] The above-mentioned intelligent coding method for infectious disease data obtains medical text data related to infectious diseases and extracts local features, constructs a clinical medical knowledge graph, models the coding relationship, and fuses the local features with the modeling results. The fusion results are input into the coding decision model, and the ICD coding results are generated and output, thereby improving the feature extraction and coding prediction process of infectious disease data to enhance the accuracy and efficiency of coding.

[0162] Figure 7 FIG. 3 is a schematic block diagram of an infectious disease data intelligent encoding device 300 provided in an embodiment of the present invention. Figure 7As shown, corresponding to the above infectious disease data intelligent encoding method, the present invention also provides an infectious disease data intelligent encoding device 300. The infectious disease data intelligent encoding device 300 includes a unit for executing the above infectious disease data intelligent encoding method, and the device can be configured in a server. Figure 7 The infectious disease data intelligent encoding device 300 includes a data acquisition unit 301, a local feature extraction unit 302, a modeling unit 303, a fusion unit 304, an encoding unit 305 and an output unit 306.

[0163] The data acquisition unit 301 is used to acquire medical text data related to infectious diseases; the local feature extraction unit 302 is used to extract local features from the medical text data; the modeling unit 303 is used to construct a clinical medical knowledge graph and model the coding relationship to obtain a modeling result; the fusion unit 304 is used to fuse the local features with the modeling result to obtain a feature fusion result; the encoding unit 305 is used to input the feature fusion result into the coding decision model for encoding to obtain an ICD coding result; the output unit 306 is used to output the ICD coding result.

[0164] In one embodiment, if Figure 8 As shown, the local feature extraction unit 302 includes an embedding subunit 3021, a convolution subunit 3022, a maximum pooling subunit 3023 and a splicing fully connected subunit 3024.

[0165] The embedding subunit 3021 is used to perform text decomposition and embedding on the medical text data to obtain an embedding matrix; the convolution subunit 3022 is used to perform a convolution operation on the embedding matrix to obtain a convolution result; the maximum pooling subunit 3023 is used to perform a maximum pooling layer processing on the convolution result to obtain a pooling result; the splicing fully connected subunit 3024 is used to perform feature map splicing and full connection processing on the pooling result to obtain local features.

[0166] In one embodiment, the modeling unit 303 is used to construct a clinical medical knowledge graph and use a graph neural network to model the encoding relationship to obtain a modeling result.

[0167] In one embodiment, if Fig. 9 As shown, the modeling unit 303 includes a graph construction subunit 3031, a multi-layer graph convolution subunit 3032, a pooling operation subunit 3033, a similarity calculation subunit 3034 and a combination subunit 3035.

[0168] The graph construction subunit 3031 is used to construct a clinical medical knowledge graph; the multi-layer graph convolution subunit 3032 is used to perform multi-layer graph convolution processing on the clinical medical knowledge graph to obtain a node embedding representation; the pooling operation subunit 3033 is used to extract global features using a pooling operation on the node embedding representation; the similarity calculation subunit 3034 is used to calculate the similarity between nodes based on the global feature representation to determine the dependency relationship between nodes; the combination subunit 3035 is used to combine the node embedding representation and the dependency relationship between nodes to obtain a modeling result.

[0169] In one embodiment, if Fig.10 As shown, the multi-layer graph convolution subunit 3032 includes a weighted sum module 30321 and a transformation module 30322.

[0170] The weighted sum module 30321 is used to aggregate the information of neighbor nodes in the clinical medical knowledge graph and calculate the weighted sum of the features of each node; the transformation module 30322 is used to apply the weight matrix and bias term of the graph convolution layer and use the ReLU activation function for nonlinear transformation to obtain the node embedding representation.

[0171] In one embodiment, if Fig.11 As shown, the fusion unit 304 includes a splicing subunit 3041, a dimensionality reduction subunit 3042 and a feature fusion subunit 3043.

[0172] The splicing subunit 3041 is used to splice the local features with the modeling results to obtain a high-dimensional feature vector; the dimensionality reduction subunit 3042 is used to perform dimensionality reduction processing on the high-dimensional feature vector to obtain a dimensionality reduction result; the feature fusion subunit 3043 is used to input the dimensionality reduction result into the integrated learning model for feature fusion to obtain a feature fusion result.

[0173] In one embodiment, the encoding unit 305 is used to input the feature fusion result into the encoding decision model for encoding, and use fuzzy logic to determine the ICD encoding result; wherein, the encoding decision model is a multi-level neural network model constructed using a reinforcement learning framework.

[0174] It should be noted that technicians in the relevant field can clearly understand that the specific implementation process of the above-mentioned infectious disease data intelligent encoding device 300 and each unit can refer to the corresponding description in the aforementioned method embodiment, and for the convenience and brevity of description, it will not be repeated here.

[0175] The infectious disease data intelligent encoding device 300 can be implemented in the form of a computer program. The computer program can be used in Fig.12 Runs on the computer device shown.

[0176] See also Fig.12 , Fig.12 5 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device 500 may be a server, wherein the server may be an independent server or a server cluster composed of multiple servers.

[0177] See also Fig.12 The computer device 500 includes a processor 502 , a memory and a network interface 505 connected via a system bus 501 , wherein the memory may include a non-volatile storage medium 503 and an internal memory 504 .

[0178] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions, and when the program instructions are executed, the processor 502 can execute an infectious disease data intelligent encoding method.

[0179] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0180] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute an intelligent encoding method for infectious disease data.

[0181] The network interface 505 is used to communicate with other devices over the network. Fig.12 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device 500 to which the solution of the present application is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0182] The processor 502 is used to run the computer program 5032 stored in the memory to implement the following steps: Acquire medical text data related to infectious diseases; extract local features from the medical text data; construct a clinical medical knowledge graph and model the coding relationship to obtain a modeling result; fuse the local features with the modeling result to obtain a feature fusion result; input the feature fusion result into a coding decision model for encoding to obtain an ICD coding result; and output the ICD coding result.

[0183] In one embodiment, when the processor 502 implements the step of extracting local features from the medical text data, the processor 502 specifically implements the following steps: The medical text data is subjected to text decomposition and embedding to obtain an embedding matrix; a convolution operation is performed on the embedding matrix to obtain a convolution result; a maximum pooling layer is performed on the convolution result to obtain a pooling result; and feature map splicing and full connection processing are performed on the pooling result to obtain local features.

[0184] In one embodiment, the processor 502 implements the following steps when implementing the step of constructing a clinical medical knowledge graph and modeling the coding relationship to obtain a modeling result: Construct a clinical medical knowledge graph and use graph neural network to model the encoding relationship to obtain the modeling results.

[0185] In one embodiment, when the processor 502 implements the step of constructing a clinical medical knowledge graph and using a graph neural network to model the coding relationship to obtain a modeling result, the processor 502 specifically implements the following steps: Construct a clinical medical knowledge graph; perform multi-layer graph convolution processing on the clinical medical knowledge graph to obtain a node embedding representation; use a pooling operation to extract global features from the node embedding representation; calculate the similarity between nodes based on the global feature representation to determine the dependency relationship between nodes; combine the node embedding representation and the dependency relationship between nodes to obtain a modeling result.

[0186] In one embodiment, when the processor 502 implements the step of performing multi-layer graph convolution processing on the clinical medical knowledge graph to obtain a node embedding representation, the processor 502 specifically implements the following steps: The information of neighbor nodes in the clinical medical knowledge graph is aggregated, and the weighted sum of the features of each node is calculated; the weight matrix and bias term of the graph convolution layer are applied, and the ReLU activation function is used for nonlinear transformation to obtain the node embedding representation.

[0187] In one embodiment, when the processor 502 implements the step of fusing the local features with the modeling results to obtain the feature fusion result, the processor 502 specifically implements the following steps: The local features are concatenated with the modeling results to obtain a high-dimensional feature vector; the high-dimensional feature vector is subjected to dimensionality reduction processing to obtain a dimensionality reduction result; the dimensionality reduction result is input into an integrated learning model for feature fusion to obtain a feature fusion result.

[0188] In one embodiment, when the processor 502 implements the step of inputting the feature fusion result into the coding decision model for coding to obtain the ICD coding result, the processor 502 specifically implements the following steps: The feature fusion result is input into the coding decision model for coding, and the ICD coding result is determined by using fuzzy logic; Among them, the coding decision model is a multi-level neural network model constructed using a reinforcement learning framework.

[0189] It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0190] It can be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0191] Therefore, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein when the computer program is executed by a processor, the processor executes the following steps: Acquire medical text data related to infectious diseases; extract local features from the medical text data; construct a clinical medical knowledge graph and model the coding relationship to obtain a modeling result; fuse the local features with the modeling result to obtain a feature fusion result; input the feature fusion result into a coding decision model for encoding to obtain an ICD coding result; and output the ICD coding result.

[0192] In one embodiment, when the processor executes the computer program to implement the step of extracting local features from the medical text data, the processor specifically implements the following steps: The medical text data is subjected to text decomposition and embedding to obtain an embedding matrix; a convolution operation is performed on the embedding matrix to obtain a convolution result; a maximum pooling layer is performed on the convolution result to obtain a pooling result; and feature map splicing and full connection processing are performed on the pooling result to obtain local features.

[0193] In one embodiment, when the processor executes the computer program to implement the step of constructing a clinical medical knowledge graph and modeling the coding relationship to obtain a modeling result, the processor specifically implements the following steps: Construct a clinical medical knowledge graph and use graph neural network to model the encoding relationship to obtain the modeling results.

[0194] In one embodiment, when the processor executes the computer program to implement the step of constructing a clinical medical knowledge graph and using a graph neural network to model the encoding relationship to obtain a modeling result, the processor specifically implements the following steps: Construct a clinical medical knowledge graph; perform multi-layer graph convolution processing on the clinical medical knowledge graph to obtain a node embedding representation; use a pooling operation to extract global features from the node embedding representation; calculate the similarity between nodes based on the global feature representation to determine the dependency relationship between nodes; combine the node embedding representation and the dependency relationship between nodes to obtain a modeling result.

[0195] In one embodiment, when the processor executes the computer program to implement the step of performing multi-layer graph convolution processing on the clinical medical knowledge graph to obtain a node embedding representation, the processor specifically implements the following steps: The information of neighbor nodes in the clinical medical knowledge graph is aggregated, and the weighted sum of the features of each node is calculated; the weight matrix and bias term of the graph convolution layer are applied, and the ReLU activation function is used for nonlinear transformation to obtain the node embedding representation.

[0196] In one embodiment, when the processor executes the computer program to implement the step of fusing the local features with the modeling results to obtain a feature fusion result, the processor specifically implements the following steps: The local features are concatenated with the modeling results to obtain a high-dimensional feature vector; the high-dimensional feature vector is subjected to dimensionality reduction processing to obtain a dimensionality reduction result; the dimensionality reduction result is input into an integrated learning model for feature fusion to obtain a feature fusion result.

[0197] In one embodiment, when the processor executes the computer program to implement the step of inputting the feature fusion result into the coding decision model for coding to obtain the ICD coding result, the processor specifically implements the following steps: The feature fusion result is input into the coding decision model for coding, and the ICD coding result is determined by using fuzzy logic; Among them, the coding decision model is a multi-level neural network model constructed using a reinforcement learning framework.

[0198] The storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which are computer-readable storage media that can store program codes.

[0199] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0200] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0201] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0202] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0203] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. An intelligent coding method for infectious disease data, characterized in that: include: Obtain medical text data related to infectious diseases; Extracting local features from the medical text data; Construct a clinical medical knowledge graph and model the coding relationship to obtain modeling results; The local features are fused with the modeling results to obtain a feature fusion result; Inputting the feature fusion result into the coding decision model for coding to obtain an ICD coding result; Output the ICD encoding result.

2. The infectious disease data intelligent coding method according to claim 1, characterized in that: The extracting of local features from the medical text data comprises: Performing text decomposition and embedding on the medical text data to obtain an embedding matrix; Performing a convolution operation on the embedding matrix to obtain a convolution result; Performing maximum pooling layer processing on the convolution result to obtain a pooling result; The pooling results are subjected to feature map splicing and full connection processing to obtain local features.

3. The infectious disease data intelligent coding method according to claim 1, characterized in that: The construction of the clinical medical knowledge graph and modeling of the coding relationship to obtain a modeling result includes: Construct a clinical medical knowledge graph and use graph neural network to model the encoding relationship to obtain the modeling results.

4. The infectious disease data intelligent coding method according to claim 3, characterized in that: The construction of the clinical medical knowledge graph uses a graph neural network to model the encoding relationship to obtain a modeling result, including: Construct clinical medical knowledge graph; Performing multi-layer graph convolution processing on the clinical medical knowledge graph to obtain a node embedding representation; Extracting global features using a pooling operation on the node embedding representation; Calculate the similarity between nodes according to the global feature representation to determine the dependency relationship between the nodes; The node embedding representation and the dependencies between nodes are combined to obtain a modeling result.

5. The method for intelligently encoding infectious disease data according to claim 1, characterized in that: The performing multi-layer graph convolution processing on the clinical medical knowledge graph to obtain a node embedding representation includes: Aggregating information of neighbor nodes in the clinical medical knowledge graph and calculating a weighted sum of features of each node; The weight matrix and bias term of the graph convolution layer are applied, and the ReLU activation function is used for nonlinear transformation to obtain the node embedding representation.

6. The infectious disease data intelligent coding method according to claim 1, characterized in that: The fusing of the local features with the modeling results to obtain feature fusion results includes: Concatenating the local features with the modeling results to obtain a high-dimensional feature vector; Performing dimensionality reduction processing on the high-dimensional feature vector to obtain a dimensionality reduction result; The dimension reduction result is input into the integrated learning model for feature fusion to obtain a feature fusion result.

7. The method for intelligently encoding infectious disease data according to claim 1, characterized in that: The step of inputting the feature fusion result into a coding decision model for coding to obtain an ICD coding result includes: The feature fusion result is input into the coding decision model for coding, and the ICD coding result is determined by using fuzzy logic; Among them, the coding decision model is a multi-level neural network model constructed using a reinforcement learning framework.

8. An intelligent encoding device for infectious disease data, characterized in that: include: A data acquisition unit, used for acquiring medical text data related to infectious diseases; A local feature extraction unit, used for extracting local features from the medical text data; A modeling unit is used to construct a clinical medical knowledge graph and model the coding relationship to obtain a modeling result; A fusion unit, used for fusing the local features with the modeling results to obtain a feature fusion result; An encoding unit, used for inputting the feature fusion result into an encoding decision model for encoding to obtain an ICD encoding result; An output unit is used to output the ICD coding result.

9. A computer device, characterized in that: The computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images