Rehabilitation theory-based paradigm map generation method and system

Abstract

The invention relates to the technical field of electric digital data processing, in particular to a rehabilitation theory-based paradigm map generation method and system, and the method comprises the steps: obtaining an electronic health record and rehabilitation medical literature of a target object, and forming a reserve data set; performing data processing on the reserve data set to obtain a processed data set; performing information extraction on the processing data set to obtain an extracted data set; fusing the extracted data set to obtain a data set to be used; and performing visual presentation on the to-be-used data set to generate a graph. Through a chain data set processing mode, a generation method capable of better realizing an example graph is obtained, based on the method, related medical personnel can more comprehensively and quickly obtain the knowledge graph of a target needing to be known, and a powerful guarantee is provided for subsequent work of the medical personnel; meanwhile, according to the method, through multiple processing of the data, the accuracy of the data is achieved, and the effect of follow-up rehabilitation work is guaranteed.

Description

Technical Field

[0001] The present application relates to the technical field of electrical digital data processing, and in particular to a method for generating a paradigmatic atlas based on rehabilitation theory, and also to a generation system. Background Art

[0002] Rehabilitation medicine is an emerging discipline, a new concept that emerged in the mid-20th century. Rehabilitation medicine, along with preventive medicine, health care medicine, and clinical medicine, is known as one of the "four major medical disciplines." It aims to eliminate and alleviate functional impairments, compensate for and restore functional deficiencies, and improve and enhance all aspects of human function. This encompasses the prevention, diagnosis, assessment, treatment, training, and management of functional impairments. Due to its broad scope, comprehensive and logical training is often lacking when it comes to new employee training or related knowledge points. This is because existing technologies lack a reasonable method for generating logic trees or knowledge graphs in this area.

[0003] The existing publication number is CN116561338A, and its name is A method for generating an industrial knowledge graph. It discloses constructing preset standard data into a first knowledge graph based on an association pattern model; determining the knowledge source in the industrial production process, performing co-reference resolution and entity disambiguation on the data contained in the knowledge source to obtain a second knowledge graph; and generating a target knowledge graph based on the first knowledge graph and the second knowledge graph.

[0004] This technology can efficiently integrate preset standard data and knowledge sources in the industrial production process to achieve the integration and cohesion of industrial data. However, when used in the direction of rehabilitation medicine, it cannot be directly converted and cannot adapt to the generation requirements of rehabilitation medical information maps. Summary of the Invention

[0005] Through research, the inventors found that the generation of knowledge graphs in the rehabilitation field faces many challenges, mainly due to its data characteristics, domain complexity and the particularity of application requirements. Among them, multi-source data integration is difficult, and knowledge representation and reasoning have strong limitations. Therefore, the generation of knowledge graphs generally requires a lot of manpower, and this process will cause a large waste of resources.

[0006] The purpose of this application is to provide a method and system for generating paradigmatic atlases based on rehabilitation theory. By storing data sets, processing data sets, extracting data sets, and then to standby data sets, and finally visually presenting atlases, the present application solves the technical problem that the existing technology cannot provide a reasonable and accurate method for generating paradigmatic atlases in the field of rehabilitation. The present application also solves the technical problem that the existing technology cannot provide a corresponding generation system.

[0007] According to one aspect of the present application, a paradigmatic atlas generation method based on rehabilitation theory is provided, which is executed by a processor and at least includes: obtaining the electronic health records and rehabilitation medicine literature of the target object to form a reserve data set; performing data processing on the reserve data set to obtain a processed data set; performing information extraction on the processed data set to obtain an extracted data set; performing fusion on the extracted data set to obtain a stand-by data set; and performing visual presentation on the stand-by data set to generate an atlas.

[0008] In some embodiments, the process of obtaining the target subject's electronic health records and rehabilitation medicine literature to form a reserve data set is as follows:

[0009] At least obtain the target subject's rehabilitation process from the electronic health record, as well as at least obtain evidence-based knowledge from rehabilitation medicine literature, standardized processes from clinical guidelines, and outcomes reported by the target subject;

[0010] The rehabilitation process of the target subjects, evidence-based knowledge from rehabilitation medicine literature, standardized procedures from clinical guidelines, and outcomes reported by the target subjects were collected to generate a preliminary data set;

[0011] Perform data cleaning on the preliminary data set, where data cleaning at least includes missing value processing, duplicate data processing, noisy data processing, and inconsistent data processing;

[0012] Based on the cleaned data set, data inspection is performed to obtain a reserve data set.

[0013] In some embodiments, the process of performing data processing on the reserve dataset to obtain the processed dataset is:

[0014] Perform structured, semi-structured, and unstructured classification on the reserve data set, where structured data at least includes literature databases, semi-structured data at least includes rehabilitation reports in XML format, and unstructured data at least includes rehabilitation medical records and research papers;

[0015] Based on the classification results, a first processed data set, a second processed data set, and a third processed data set are formed.

[0016] In some embodiments, the process of performing information extraction on the processed data set to obtain the extracted data set is:

[0017] Performing entity recognition on the first processed data set, the second processed data set, and the third processed data set to obtain an extracted entity information set;

[0018] Perform relation extraction based on the extracted entity information set to obtain a rehabilitation association dataset;

[0019] Based on the rehabilitation association dataset, characterization attribute determination is performed to obtain the extracted dataset.

[0020] In some embodiments, the process of performing fusion on the extracted data set to obtain the data set to be used is:

[0021] Standardize the extracted dataset based on clinical medical terminology standards;

[0022] Conflict elimination is performed on the standardized extracted dataset to obtain a stand-by dataset.

[0023] In some embodiments, the process of visualizing the dataset to be used and generating a graph is as follows:

[0024] Based on the graph database, the relationship between nodes and edges of the used dataset is displayed;

[0025] Perform semantic modeling based on the resource description framework to obtain a graph.

[0026] According to another aspect of the present application, a system for generating a paradigmatic atlas based on rehabilitation theory is provided, the system comprising a processor, including at least:

[0027] A rehabilitation data acquisition module, which is used to acquire the target subject's electronic health records and rehabilitation medicine literature to form a reserve data set;

[0028] a rehabilitation information processing module, wherein the rehabilitation information extraction module is used to perform data processing on the reserve data set to obtain a processed data set;

[0029] a rehabilitation information extraction module, wherein the rehabilitation information fusion module is used to perform information extraction on the processed data set to obtain an extracted data set;

[0030] The rehabilitation information fusion module, the rehabilitation knowledge storage module is used to perform fusion on the extracted data set to obtain a standby data set;

[0031] The rehabilitation information display module performs visual presentation on the dataset to be used and generates a graph.

[0032] In some embodiments, the processor is respectively data-connected to the rehabilitation data acquisition module, the rehabilitation information processing module, the rehabilitation information extraction module, the rehabilitation information fusion module, and the rehabilitation information display module.

[0033] Compared with the existing technology, the present application has the following beneficial effects: the present application obtains a method for generating a paradigmatic graph through a chain data set processing method. Based on this method, relevant medical staff can obtain the knowledge graph they need to understand the target more comprehensively and quickly, providing strong guarantees for their subsequent work; at the same time, the method of the present application realizes the accuracy of the data itself through multiple processing of the data, thereby ensuring the effectiveness of subsequent rehabilitation work. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0035] Figure 1 It is a flow chart of the generation method of this application;

[0036] Figure 2 This is a schematic diagram of the composition of the generation system of this application. DETAILED DESCRIPTION

[0037] The following is a combination of the appended examples of the present application Figure 1-2 The technical solutions in the embodiments of the present application are described clearly and completely. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments.

[0038] Example 1

[0039] Figure 1 This is a flowchart of the exemplary atlas generation method based on rehabilitation theory provided in this embodiment. The method is executed by a processor, which can be a central processing unit (CPU), 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. The general-purpose processor can be a microprocessor or any conventional processor.

[0040] Based on the above, the method of this embodiment is specifically as follows:

[0041] Acquire the target subject's electronic health records and rehabilitation medicine literature to form a reserve dataset. Because rehabilitation data is scattered across clinical records, research papers, rehabilitation device sensors, and patient follow-up records, with widely varying formats and inconsistent terminology, this leads to extremely high data cleaning and integration costs. Therefore, acquiring a reserve dataset can form a systematic dataset for subsequent use.

[0042] In some possible implementations, at least the rehabilitation process of the target subject in the electronic health record is obtained, as well as at least the evidence-based knowledge in the rehabilitation medicine literature, the standardized process of clinical guidelines, and the outcomes reported by the target subject. The outcomes reported by the target subject are information directly from the patient's report on their own health status, functional status, and treatment experience; the electronic health record is an electronic version of the paper medical record, which contains comprehensive information such as medical history, diagnosis, and medication to support doctors in making decisions. The rehabilitation process of the target subject, as well as the evidence-based knowledge in the rehabilitation medicine literature, the standardized process of clinical guidelines, and the outcomes reported by the target subject are collected to generate a preliminary data set; data cleaning is performed on the preliminary data set, wherein data cleaning at least includes missing value processing, duplicate data processing, noise data processing, and inconsistent data processing, for example, cleaning garbled, ambiguous, and irrelevant symbols or text information in the data; based on the cleaned data set, data inspection is performed to re-evaluate the data quality to ensure that relevant issues have been resolved, thereby obtaining a reserve data set.

[0043] Perform data processing on the reserve dataset to obtain a processed dataset. The processed data further optimizes the original data and forms the systematic data required for graph generation, including the data format.

[0044] In some possible implementations, the reserve dataset is classified into structured, semi-structured, and unstructured categories, where structured data includes at least a literature database, semi-structured data includes at least rehabilitation reports in XML format, and unstructured data includes at least rehabilitation medical records and research papers. Based on the classification results, a first processed dataset, a second processed dataset, and a third processed dataset are generated. The first processed dataset includes at least a literature database, the second processed dataset includes at least rehabilitation reports in XML / JSON format, and the third processed dataset includes rehabilitation medical records, research papers, and the like.

[0045] Information extraction is performed on the processed data set to obtain an extracted data set. In order to ensure the accuracy of the generated atlas, information extraction is performed, and at the same time, a natural language processing model is used in the extraction to improve the extraction accuracy. Among them, in the field of rehabilitation, the application of natural language processing models is intended to solve the problems of professional knowledge extraction, analysis and utilization in text data. Since the rehabilitation field involves a large number of medical terms, clinical records and patient feedback, the NLP model needs to have the ability to process complex semantics and domain specificity. In this embodiment, the optional models are BioBERT model, ClinicalBERT model, GPT-4 fine-tuning model, etc. This embodiment is preferably a ClinicalBERT model, which is a pre-trained language model optimized on clinical text based on the BERT (Bidirectional Encoder Representations from Transformers) model. It learns general representations through clinical text pre-training, and then fine-tunes for specific tasks. Finally, it uses deep bidirectional encoding capabilities to process clinical texts to achieve efficient medical information extraction, analysis and generation.

[0046] In some possible implementations, entity recognition is performed on the first processed data set, the second processed data set, and the third processed data set to obtain an extracted entity information set; relationship extraction is performed based on the extracted entity information set to obtain a rehabilitation association data set; and characterization attribute determination is performed based on the rehabilitation association data set to obtain an extracted data set.

[0047] The extracted dataset is fused to obtain the dataset to be used.

[0048] In some possible implementations, the extracted dataset is standardized based on clinical medical terminology standards to eliminate ambiguity of the same entity across different data sources and ensure the uniqueness of entities in the graph. For example, this involves alignment of rehabilitation terminology, disease names, rehabilitation techniques, rehabilitation equipment, rehabilitation institutions, and cross-language entities. Conflict elimination is performed on the standardized extracted dataset to obtain a ready-to-use dataset. This includes addressing contradictions or redundancies within the standardized extracted dataset, such as inconsistent definitions of "rehabilitation cycle" across different sources, to improve the accuracy of the knowledge graph.

[0049] Perform visual presentation of the dataset to be used and generate a graph. Displaying data information as a visual pattern can facilitate subsequent use and also facilitate subsequent annotation and improvement by medical staff.

[0050] In some possible implementations, the graph generation rules are based on the six principles of central graph, lines, keywords, images, colors, and structure, as identified by Tony Buzan, the brain of the world. Specifically, the graph database is used to represent the relationships between nodes and edges in the dataset being used; semantic modeling is performed based on the resource description framework to obtain the graph. Specifically, a graph database, such as Neo4j or OrientDB, is used to represent the relationships between nodes and edges, building a graph framework. This is then built using a knowledge graph framework, such as Google's Knowledge Vault. The visualization tool Gephi is then used to present the graph in an intuitive graphical format for subsequent analysis and interaction.

[0051] Example 2

[0052] Based on the same inventive concept as the paradigm-based atlas generation method based on rehabilitation theory in the aforementioned embodiment, Figure 2 As shown, this embodiment also provides a paradigm-based atlas generation system based on rehabilitation theory. Exemplarily, the generation method can be divided into one or more modules, one or more of which are stored in a memory and executed by a processor to complete the present application. One or more modules can be a series of computer program instruction segments that can perform specific functions, and the instruction segments are used to describe the execution process of the computer program.

[0053] For example, a computer program can be divided into a rehabilitation data acquisition module, a rehabilitation information processing module, a rehabilitation information extraction module, a rehabilitation information fusion module and a rehabilitation information display module. The specific functions of each module are as follows: the rehabilitation data acquisition module is used to obtain the target object's electronic health records and rehabilitation medicine literature to form a reserve data set; the rehabilitation information extraction module is used to perform data processing on the reserve data set to obtain a processed data set; the rehabilitation information fusion module is used to perform information extraction on the processed data set to obtain an extracted data set; the rehabilitation knowledge storage module is used to perform fusion on the extracted data set to obtain a stand-by data set; the rehabilitation information display module performs visual presentation on the stand-by data set to generate a graph.

[0054] The specific example of the paradigmatic atlas generation method based on rehabilitation theory in the aforementioned embodiment 1 is also applicable to the paradigmatic atlas generation system based on rehabilitation theory in this embodiment. Through the aforementioned detailed description of the paradigmatic atlas generation method based on rehabilitation theory, those skilled in the art can clearly understand the paradigmatic atlas generation system based on rehabilitation theory in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0055] The above shows and describes the basic principles and main features of the present application and the advantages of the present application. It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the spirit or basic features of the present application. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present application is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and range of equivalents of the claims are included in the present application. Any figure mark in the claims should not be construed as limiting the claim to which it relates.

[0056] In addition, it should be understood that although this specification is described in terms of implementation methods, not every implementation method contains only one independent technical solution. This narrative method of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other implementation methods that can be understood by those skilled in the art.

Claims

1. A method for generating a paradigmatic atlas based on rehabilitation theory, the method being executed by a processor, characterized in that: At least: Obtain the target subject's electronic health records and rehabilitation medicine literature to form a reserve data set; performing data processing on the reserve data set to obtain a processed data set; Perform information extraction on the processed data set to obtain an extracted data set; Perform fusion on the extracted data set to obtain the data set to be used; Perform visualization on the dataset to be used and generate a graph.

2. The method according to claim 1, characterized in that The process of obtaining the target subject's electronic health records and rehabilitation medicine literature to form a reserve data set is as follows: At least obtain the target subject's rehabilitation process from the electronic health record, as well as at least obtain evidence-based knowledge from rehabilitation medicine literature, standardized processes from clinical guidelines, and outcomes reported by the target subject; The rehabilitation process of the target subjects, evidence-based knowledge from rehabilitation medicine literature, standardized procedures from clinical guidelines, and outcomes reported by the target subjects were collected to generate a preliminary data set; Perform data cleaning on the preliminary data set, where data cleaning at least includes missing value processing, duplicate data processing, noisy data processing, and inconsistent data processing; Based on the cleaned data set, data inspection is performed to obtain a reserve data set.

3. The method according to claim 2, characterized in that The process of performing data processing on the reserve data set to obtain the processed data set is as follows: Perform structured, semi-structured, and unstructured classification on the reserve data set, where structured data at least includes literature databases, semi-structured data at least includes rehabilitation reports in XML format, and unstructured data at least includes rehabilitation medical records and research papers; Based on the classification results, a first processed data set, a second processed data set, and a third processed data set are formed.

4. The method according to claim 3, characterized in that The process of performing information extraction on the processed data set to obtain the extracted data set is as follows: Performing entity recognition on the first processed data set, the second processed data set, and the third processed data set to obtain an extracted entity information set; Perform relation extraction based on the extracted entity information set to obtain a rehabilitation association dataset; Based on the rehabilitation association dataset, characterization attribute determination is performed to obtain the extracted dataset.

5. The method according to claim 4, characterized in that The process of performing fusion on the extracted data set to obtain the data set to be used is as follows: Standardize the extracted dataset based on clinical medical terminology standards; Conflict elimination is performed on the standardized extracted dataset to obtain a stand-by dataset.

6. The method according to claim 5, characterized in that The process of visualizing the dataset to be used and generating a graph is as follows: Based on the graph database, the relationship between nodes and edges of the used dataset is displayed; Perform semantic modeling based on the resource description framework to obtain a graph.

7. A paradigm-based atlas generation system based on rehabilitation theory, the system comprising a processor, characterized in that: At least: A rehabilitation data acquisition module, which is used to acquire the target subject's electronic health records and rehabilitation medicine literature to form a reserve data set; a rehabilitation information processing module, wherein the rehabilitation information extraction module is used to perform data processing on the reserve data set to obtain a processed data set; a rehabilitation information extraction module, wherein the rehabilitation information fusion module is used to perform information extraction on the processed data set to obtain an extracted data set; The rehabilitation information fusion module, the rehabilitation knowledge storage module is used to perform fusion on the extracted data set to obtain a standby data set; The rehabilitation information display module performs visual presentation on the dataset to be used and generates a graph.

8. The system according to claim 7, characterized in that The processor is respectively data-connected to the rehabilitation data acquisition module, the rehabilitation information processing module, the rehabilitation information extraction module, the rehabilitation information fusion module and the rehabilitation information display module.

Images