Diabetes standardized digital intelligence patient diagnosis and treatment training platform based on mapping knowledge domain

Abstract

The invention belongs to the technical field of diabetes diagnosis and treatment training, and provides a diabetes standardized digital intelligence patient diagnosis and treatment training platform based on a knowledge graph, and the platform comprises a knowledge graph construction module which is used for collecting diabetes related data in multiple channels; the digital intelligent patient model generation module is used for creating a dynamic digital intelligent patient model based on the knowledge graph; the diagnosis and treatment training function module provides a vivid clinical diagnosis and treatment interface; an evaluation feedback module; the comprehensive and accurate knowledge graph is constructed, and the dynamic digital intelligent patient model is created, so that the platform not only effectively integrates diabetes related data acquired in multiple channels, but also provides vivid clinical diagnosis and treatment training and rich case learning resources for medical staff; and meanwhile, through automatic and comprehensive evaluation feedback, the platform is helpful for the medical personnel to timely discover own defects and seek a promotion way, so that the efficiency and the quality of diabetes diagnosis and treatment training are improved, and powerful support is provided for occupational development of the medical personnel.

Description

Technical Field

[0001] The present invention belongs to the technical field of diabetes diagnosis and treatment training, and specifically relates to a standardized digital intelligent patient diagnosis and treatment training platform for diabetes based on a knowledge graph. Background Art

[0002] In the current medical education and training system, diabetes diagnosis and treatment training faces many difficulties. Traditional teaching methods mainly rely on theoretical lectures and limited clinical internships, lacking a full presentation of the diversity and complexity of real patients' conditions. Existing simulation training tools are mostly simple static models, unable to dynamically simulate the development of diabetes conditions and the emergence of complex complications. At the same time, knowledge resources are scattered, lacking an effective integration and in-depth mining mechanism, making it difficult for medical staff to quickly obtain comprehensive and accurate diabetes knowledge. Although medical information technology has developed rapidly and the application of knowledge graph technology in the medical field has gradually emerged, a mature and perfect application system has not yet been formed in diabetes diagnosis and treatment training.

[0003] Therefore, those skilled in the art have proposed a standardized digital intelligent patient diagnosis and treatment training platform for diabetes based on a knowledge graph to solve the problems raised in the background art. Summary of the Invention

[0004] To solve the above technical problems, the present invention provides a standardized digital intelligent patient diagnosis and treatment training platform for diabetes based on a knowledge graph to solve problems such as the lack of a mature and perfect application system in diabetes diagnosis and treatment training in the prior art.

[0005] A standardized digital intelligent patient diagnosis and treatment training platform for diabetes based on a knowledge graph includes:

[0006] A knowledge graph construction module for collecting diabetes-related data from multiple channels and constructing a comprehensive, accurate, and deeply associated knowledge graph based on the collected data;

[0007] A digital intelligent patient model generation module for creating a dynamic digital intelligent patient model based on the knowledge graph, which can simulate the disease condition change process of diabetes patients and dynamically adjust the disease evolution trajectory according to treatment intervention measures;

[0008] A diagnosis and treatment training function module for providing a realistic clinical diagnosis and treatment interface, enabling medical staff to perform full-process diagnosis and treatment operations on simulated patients, and having a rich and representative diabetes clinical case library built-in, as well as designing an intelligent question-and-answer system to consolidate the knowledge of medical staff;

[0009] An evaluation and feedback module for automatically and comprehensively evaluating the operation performance of medical staff on the platform through a preset evaluation index system, and providing a quantitative score and a detailed written report.

[0010] Preferably, the knowledge graph construction module further includes in-depth mining and analysis of the pathophysiological mechanisms, symptom manifestations, diagnostic criteria, treatment methods, drug information, diet and exercise guidance, and prevention and treatment of complications of diabetes.

[0011] Preferably, the construction of a comprehensive, accurate and deeply associated knowledge graph is achieved by introducing entity recognition and relationship extraction algorithms based on deep learning.

[0012] Preferably, the TransE model is introduced, which is used to embed the entities and relationships in the knowledge graph into a low-dimensional vector space.

[0013] Preferably, the digital intelligent patient model generation module can simulate the blood glucose fluctuation law, the occurrence and development process of complications, etc. of diabetic patients according to the set initial condition parameters and combined with the actual clinical probability distribution.

[0014] Preferably, the diagnosis and treatment training function module further includes a case learning and analysis function, which allows medical staff to deeply learn the diagnosis and treatment ideas and methods of different cases, and strengthens the learning effect through an interactive operation session.

[0015] Preferably, the diagnosis and treatment training function module introduces a reinforcement learning algorithm to optimize the diagnosis and treatment decision-making process.

[0016] Preferably, the evaluation and feedback module can also provide targeted improvement suggestions and learning resource recommendations according to the evaluation results, that is, this module evaluates the operation performance of medical staff and recommends personalized learning resources by introducing a clustering algorithm (K-means).

[0017] A processor configured to execute the diabetes standardized digital intelligent patient diagnosis and treatment training platform based on the knowledge graph as described above.

[0018] A computer-readable storage medium having stored thereon a computer program, which when executed by a processor implements the diabetes standardized digital intelligent patient diagnosis and treatment training platform based on the knowledge graph as described above.

[0019] Compared with the prior art, the present invention has the following beneficial effects:

[0020] 1. By constructing a comprehensive, accurate and deeply associated knowledge graph, the present invention effectively integrates diabetes-related data collected from multiple channels, providing systematic and comprehensive diabetes knowledge resources for medical staff; this solves the problem of scattered knowledge resources and lack of effective integration in traditional teaching methods, and helps medical staff quickly obtain accurate information.

[0021] 2. The present invention utilizes a digital intelligent patient model generation module to create a dynamic digital intelligent patient model that can simulate the disease progression process of diabetic patients. This model can dynamically adjust the disease evolution trajectory according to treatment intervention measures, thus realistically reproducing the development of diabetes and the emergence of complex complications. This makes up for the deficiency that most existing simulation training tools are static models and improves the ability of medical staff to cope with the diversity and complexity of the conditions of real patients.

[0022] 3. Through the diagnosis and treatment training function module, the present invention provides a realistic clinical diagnosis and treatment interface and a rich clinical case library, enabling medical staff to perform full-process diagnosis and treatment operations and consolidate the knowledge they have learned. At the same time, this module also designs an intelligent question-and-answer system and a case learning and analysis function, further strengthening the learning effect of medical staff. This not only improves the diagnosis and treatment skills of medical staff but also enhances their clinical decision-making ability.

[0023] 4. Through the evaluation and feedback module, the present invention realizes the automatic and comprehensive evaluation of the operation performance of medical staff on the platform, and provides a quantitative score and a detailed written report. This module can also provide targeted improvement suggestions and learning resource recommendations according to the evaluation results, helping medical staff to promptly discover their own deficiencies and seek ways to improve. This improves the efficiency and quality of diabetes diagnosis and treatment training and provides strong support for the professional development of medical staff. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a framework diagram of a standardized digital intelligent patient diagnosis and treatment training platform for diabetes based on a knowledge graph according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0025] The following further describes in detail the embodiments of the present invention in conjunction with the drawings and examples. The following examples are used to illustrate the present invention but cannot be used to limit the scope of the present invention.

[0026] Example: The present invention provides a standardized digital intelligent patient diagnosis and treatment training platform for diabetes based on a knowledge graph, as Figure 1 shown. The platform includes a knowledge graph construction module, a digital intelligent patient model generation module, a diagnosis and treatment training function module, and an evaluation and feedback module. The knowledge graph construction module, the digital intelligent patient model generation module, the diagnosis and treatment training function module, and the evaluation and feedback module are electrically connected in sequence:

[0027] The knowledge graph construction module is used to collect diabetes-related data from multiple channels and construct a comprehensive, accurate, and deeply associated knowledge graph based on the collected data;

[0028] The digital intelligent patient model generation module creates a dynamic digital intelligent patient model based on the knowledge graph. This model can simulate the disease progression process of diabetic patients and dynamically adjust the disease evolution trajectory according to treatment intervention measures;

[0029] The diagnosis and treatment training function module provides a realistic clinical diagnosis and treatment interface, enabling medical staff to perform full-process diagnosis and treatment operations on simulated patients. It also has a rich and representative clinical case library for diabetes built-in, and an intelligent Q&A system is designed to consolidate the knowledge of medical staff.

[0030] The evaluation and feedback module automatically and comprehensively evaluates the operation performance of medical staff on the platform through a preset evaluation index system, and provides a quantitative score and a detailed written report.

[0031] As can be seen from the above, by constructing a comprehensive and accurate knowledge graph and creating a dynamic digital intelligent patient model, this platform not only effectively integrates diabetes-related data collected from multiple channels, but also provides medical staff with a realistic clinical diagnosis and treatment training and rich case learning resources. At the same time, through automatic and comprehensive evaluation and feedback, this platform helps medical staff to timely discover their own deficiencies and seek ways to improve, thus improving the efficiency and quality of diabetes diagnosis and treatment training and providing strong support for the professional development of medical staff.

[0032] Furthermore, the knowledge graph construction module also includes in-depth mining and analysis of the pathophysiological mechanism, symptom manifestations, diagnostic criteria, treatment methods, drug information, diet and exercise guidance, and prevention and treatment of complications of diabetes.

[0033] As can be seen from the above, this module collects relevant data through multiple channels, and conducts in-depth integration and analysis, providing medical staff with systematic and detailed diabetes knowledge resources, helping them quickly obtain accurate information, better understand and cope with the complexity of diabetes, and thus improving the diagnosis and treatment level and the quality of patient care.

[0034] Furthermore, the construction of the comprehensive, accurate and deeply associated knowledge graph introduces an entity recognition and relationship extraction algorithm based on deep learning, and the algorithm formula includes:

[0035] P(y|x) = softmax(W y ·h x + b y );

[0036] where h x is the hidden state representation of the input x, W y and b y are model parameters, and y is the predicted entity or relationship category.

[0037] As can be seen from the above, in the process of constructing a comprehensive, accurate, and deeply associated knowledge graph, by introducing entity recognition and relationship extraction algorithms based on deep learning, the present invention realizes the efficient and accurate processing of diabetes-related data. This algorithm can automatically identify and extract key entities and relationships in the data, and then construct a more comprehensive, accurate, and deeply associated knowledge graph. It not only improves the construction efficiency of the knowledge graph, but also ensures the accuracy and relevance of the information in the graph, providing more reliable and useful knowledge resources for medical staff, and helping them achieve better learning effects in diabetes diagnosis and treatment training.

[0038] Furthermore, the TransE model is introduced. This model is used to embed entities and relationships in the knowledge graph into a low-dimensional vector space. The formula of the TransE model is as follows:

[0039] L=Σ (h,r,t)∈S [γ + d(h + r, t) - d(h′, r′, t′)] + ;

[0040] where S is the set of positive samples, (h′, r′, t′) is the negative sample, d represents the distance function, γ is the margin value, and [x] + represents max(0, x).

[0041] As can be seen from the above, when constructing a diabetes standardized digital patient diagnosis and treatment training platform based on a knowledge graph, introducing the TransE model to embed entities and relationships in the knowledge graph into a low-dimensional vector space has the beneficial effect of significantly enhancing the representation ability and computational efficiency of the knowledge graph. Through this model, the platform can more effectively process and analyze graph data, and achieve fast and accurate reasoning between entities and relationships. It not only improves the overall performance of the platform, but also provides a more efficient and convenient diabetes diagnosis and treatment training experience for medical staff, helping them better apply the knowledge they have learned in actual work, and improving the diagnosis and treatment level and patient care quality.

[0042] Furthermore, the digital patient model generation module can simulate the blood glucose fluctuation law, the occurrence and development process of complications, etc. of diabetes patients according to the set initial condition parameters and in combination with the actual clinical probability distribution.

[0043] As can be seen from the above, through this module, medical staff can perform full-process diagnosis and treatment operations on simulated patients in a virtual environment, facing highly realistic diabetes condition changes, thus effectively exercising their clinical decision-making ability and skills in dealing with complex conditions. This realistic training experience not only enhances the learning effect of medical staff, but also provides valuable practical experience for them in actual work, helping to improve the diagnosis and treatment level of diabetes and patient care quality.

[0044] Furthermore, the diagnosis and treatment training function module also includes a case study and analysis function, which allows medical staff to deeply study the diagnosis and treatment ideas and methods of different cases and strengthen the learning effect through an interactive operation session.

[0045] As can be seen from the above, through this function, medical staff can access a rich variety of diabetes clinical cases, draw valuable diagnosis and treatment experience and wisdom from them, and at the same time, combined with the interactive operation session, closely integrate theoretical knowledge with actual operation, so as to more comprehensively master the diagnosis and treatment skills of diabetes. This comprehensive learning method not only improves the professional quality of medical staff, but also provides strong support for them in actual work, helping to improve the diagnosis and treatment effect of diabetes and patient satisfaction.

[0046] Furthermore, the diagnosis and treatment training function module introduces a reinforcement learning algorithm to optimize the diagnosis and treatment decision-making process. The reinforcement learning algorithm includes:

[0047] Q(s,a)←Q(s,a)+α[r+γmax a′ Q(s′,a′)-Q(s,a)];

[0048] Among them, Q(s,a) is the expected return of taking action a in state s, α is the learning rate, and γ is the discount factor.

[0049] As can be seen from the above, through the reinforcement learning algorithm, the system can give instant feedback based on the performance of medical staff in simulated diagnosis and treatment, guiding them to continuously adjust and optimize the diagnosis and treatment strategy in order to obtain the maximum expected return. It not only strengthens the medical staff's understanding and application of diabetes diagnosis and treatment knowledge, but also exercises their flexible response and decision-making abilities in the face of different conditions. This intelligent training method not only improves the professional level of medical staff, but also provides more scientific and effective diagnosis and treatment support for them in actual work.

[0050] Furthermore, the evaluation and feedback module can also provide targeted improvement suggestions and learning resource recommendations according to the evaluation results, that is, this module evaluates the operation performance of medical staff and recommends personalized learning resources by introducing a clustering algorithm (K-means). The formula of the clustering algorithm includes:

[0051]

[0052] Among them, C i is the i-th cluster, and μ i is the mean of the cluster C i .

[0053] As can be seen from the above, this module can scientifically and comprehensively evaluate medical staff based on their operation performance on the platform using clustering algorithms, and provide targeted improvement suggestions and recommended learning resources accordingly. This personalized feedback method not only helps medical staff clearly recognize their strengths and weaknesses, but also provides them with targeted learning paths and resources, thereby more efficiently improving their diagnosis and treatment skills. It not only optimizes the effect of diabetes diagnosis and treatment training, but also provides strong support for the professional development of medical staff.

[0054] Furthermore, the diabetes standardized digital intelligent patient diagnosis and treatment training platform based on the knowledge graph in the embodiment is compared with the current existing simulation training tools (comparative examples) in terms of effects, and the following table is obtained:

[0055]

[0056]

[0057] As can be seen from the above table, the diabetes standardized digital intelligent patient diagnosis and treatment training platform based on the knowledge graph in the embodiment is superior to the current existing simulation training tools in terms of knowledge integration and presentation, model fidelity, diagnosis and treatment training functions, evaluation and feedback mechanisms, learning effects, and intelligence level, providing a more efficient and convenient diabetes diagnosis and treatment training experience for medical staff.

[0058] An embodiment of the present application provides an electronic device, which is applicable to the above-mentioned diabetes standardized digital intelligent patient diagnosis and treatment training platform based on the knowledge graph, and includes:

[0059] A memory for protecting computer programs and data;

[0060] A processor for running system programs.

[0061] An embodiment of the present application provides a computer storage medium, which is applicable to the above-mentioned diabetes standardized digital intelligent patient diagnosis and treatment training platform based on the knowledge graph, and performs hierarchical confidentiality management on the above-mentioned system and data according to the requirements of confidentiality management.

[0062] Those skilled in the art should understand that the embodiments of the present application can be provided as a system or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0063] This application is described with reference to the flowcharts and / or block diagrams of devices (systems) and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0064] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0065] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0066] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0067] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0068] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0069] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, commodity or device including the elements.

[0070] The embodiments of the present invention are provided for the purpose of illustration and description. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present invention. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A standardized digital patient diagnosis and treatment training platform for diabetes based on knowledge graph, characterized by: The platform includes: The knowledge graph construction module is used to collect diabetes-related data from multiple channels and build a comprehensive, accurate and deeply connected knowledge graph based on the collected data; A digital patient model generation module is used to create a dynamic digital patient model based on the knowledge graph, which can simulate the disease progression of diabetic patients and dynamically adjust the disease progression trajectory according to treatment intervention measures; The diagnosis and treatment training function module provides a realistic clinical diagnosis and treatment interface, enabling medical staff to perform full-process diagnosis and treatment operations on simulated patients. It also has a rich and representative diabetes clinical case library and an intelligent question-and-answer system to consolidate the knowledge of medical staff. The evaluation feedback module automatically and comprehensively evaluates the performance of medical staff on the platform through a preset evaluation indicator system, and provides quantitative scores and detailed text reports.

2. A diabetes standardized digital patient diagnosis and treatment training platform based on knowledge graph as claimed in claim 1, characterized in that: The knowledge graph construction module also includes in-depth mining and analysis of the pathophysiological mechanisms of diabetes, symptoms, diagnostic criteria, treatment methods, drug information, diet and exercise guidance, and complication prevention and treatment.

3. A diabetes standardized digital patient diagnosis and treatment training platform based on knowledge graph as claimed in claim 2, characterized in that: The construction of a comprehensive, accurate and deeply connected knowledge graph is achieved by introducing an entity recognition and relationship extraction algorithm based on deep learning.

4. A diabetes standardized digital patient diagnosis and treatment training platform based on knowledge graph as claimed in claim 3, characterized in that: The TransE model is introduced, which is used to embed entities and relations in a graph into a low-dimensional vector space.

5. A diabetes standardized digital patient diagnosis and treatment training platform based on knowledge graph as claimed in claim 1, characterized in that: The digital patient model generation module can simulate the blood sugar fluctuation pattern and the occurrence and development process of complications of diabetic patients based on the set initial disease parameters and combined with the actual clinical probability distribution.

6. A diabetes standardized digital patient diagnosis and treatment training platform based on knowledge graph as claimed in claim 1, characterized in that: The diagnosis and treatment training function module also includes case study and analysis functions, allowing medical staff to deeply learn the diagnosis and treatment ideas and methods of different cases, and enhance the learning effect through interactive operation links.

7. A diabetes standardized digital patient diagnosis and treatment training platform based on knowledge graph as claimed in claim 6, characterized in that: The diagnosis and treatment training function module introduces a reinforcement learning algorithm to optimize the diagnosis and treatment decision-making process.

8. A diabetes standardized digital patient diagnosis and treatment training platform based on knowledge graph as claimed in claim 1, characterized in that: The evaluation feedback module can also provide targeted improvement suggestions and learning resource recommendations based on the evaluation results, that is, the module evaluates the operating performance of medical staff and recommends personalized learning resources by introducing a clustering algorithm.

9. A processor, characterized in that: Configured to execute the standardized digital diabetes patient diagnosis and treatment training platform based on knowledge graph according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the standardized digital intelligence patient diagnosis and treatment training platform for diabetes based on a knowledge graph as described in any one of claims 1 to 8 is implemented.

Images