Intelligent medical follow-up visit system based on large language model

Abstract

An intelligent medical follow-up visit system based on a large language model comprises a user interface layer, a voice recognition module, a natural language processing module, a medical knowledge base, a data management module, an intelligent recommendation module, a doctor assistance module, a data analysis module and a safety and privacy protection module. Personalized medical suggestions and health management schemes are provided for the user, the quality and efficiency of medical services are improved, the user is helped to better manage own health, doctors are helped to make diagnosis and treatment suggestions, and the working efficiency and accuracy of the doctors are improved; the system ensures that personal health data of a user is fully protected through the security and privacy protection module, and the personal health data conforms to related privacy laws and regulations, in short, the intelligent medical follow-up visit system based on the large language model is remarkably improved in the aspects of understanding patient requirements, personalized suggestions, data analysis, knowledge bases and the like, and the system has a wide application prospect. The efficiency and quality of medical follow-up visit can be better improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical information management, and particularly to an intelligent medical follow-up system based on a large language model. Background Art

[0002] A medical follow-up system is an information system used to track and manage a patient's health status, treatment plan, and medical services. The design of such systems aims to improve medical efficiency, patient care, and doctor-patient communication. The following are some common functions and features of medical follow-up systems: Patient file management: A medical follow-up system usually includes functions for managing information such as a patient's personal information, medical records, past disease history, and medication records. This helps doctors better understand the patient's overall health status.

[0003] Follow-up reminder and scheduling: The system can generate follow-up reminders to ensure that patients follow up according to the treatment plan. This can also include scheduling appointments for the next follow-up.

[0004] Electronic medical records and real-time updates: Incorporating a patient's medical records into the system enables doctors to view the patient's latest information at any time and place. This also helps with collaborative work among multiple medical professionals.

[0005] Symptom tracking and monitoring: Through patient reports or sensor data, the system can help doctors track a patient's symptoms and physiological parameters, providing a more comprehensive health assessment.

[0006] Telemedicine services: Some medical follow-up systems support telemedicine services, including online doctor consultations, remote monitoring, etc., enabling patients to more conveniently obtain medical advice.

[0007] Patient education: Providing patient education materials to help patients understand their condition, treatment plan, and lifestyle management.

[0008] Data analysis and reporting: The system can analyze patient data and generate reports to help doctors make more accurate diagnoses and treatment decisions.

[0009] Security and privacy protection: Strict security measures, including data encryption and access control, to ensure the confidentiality of patient data.

[0010] Integratability: Capable of integrating with other medical information systems, laboratory information systems, etc. to achieve information sharing and circulation.

[0011] Feedback mechanism: Supporting two-way communication between patients and doctors, including patient feedback and doctor suggestions.

[0012] Existing medical follow-up systems have certain defects and difficulties to be solved.

[0013] 1. Interoperability issues: Medical follow-up systems may face integration problems with other medical information systems because the standards and technologies used by different systems may vary, resulting in ineffective data sharing.

[0014] Difficulty: Developing consistent standards to ensure seamless integration between different systems involves coordination of technology, policies, and standards.

[0015] 2. Data privacy and security issues: Medical information involves sensitive patient health data, so the system must protect patient privacy and ensure data security.

[0016] Difficulty: Designing a strong authentication and access control system, encrypting sensitive data, and complying with strict privacy regulations such as HIPAA (Health Insurance Portability and Accountability Act).

[0017] 3. Data quality issues: The data input into the system may be inaccurate, incomplete, or inconsistent, which may affect doctors' accurate assessment of patients' health conditions.

[0018] Difficulty: Introducing data validation and cleaning mechanisms, providing training to ensure medical staff enter data correctly, and using automated means to improve data accuracy.

[0019] 4. User experience issues: Some systems may have problems in user interface design, usability, and user experience, affecting the usage experience of doctors and patients.

[0020] Difficulty: Conducting user experience research, understanding user needs, optimizing the system interface, and providing training to improve users' usage ability.

[0021] 5. Dependence on technical devices: Some medical follow-up systems may require patients and doctors to use specific technical devices, which may limit access for some people.

[0022] Difficulty: Designing a flexible system that supports multiple devices and platforms to adapt to different users and environments.

[0023] 6. Patient engagement issues: Although medical follow-up systems can improve patient engagement, some patients may be reluctant or have difficulty using these systems due to technical literacy or other reasons.

[0024] Difficulty: Providing training and support to ensure patients can use the system effectively and considering the needs of different patient groups.

[0025] 7. Cost issues: Implementing and maintaining a medical follow-up system may require a significant investment, which may burden some medical institutions and patients.

[0026] Difficulty: Finding cost-effective solutions while wisely managing the maintenance and upgrade costs of the system. Summary of the Invention

[0027] The object of the present invention is to solve the problems existing in the background technology and provide an intelligent medical follow-up system based on large language models.

[0028] An intelligent medical follow-up system based on large language models includes a user interface layer, a speech recognition module, a natural language processing module, a medical knowledge base, a data management module, an intelligent recommendation module, a doctor assistance module, a data analysis module, and a security and privacy protection module.

[0029] The said user interface layer includes a mobile App and a web version. Users can interact with the system through these interfaces, including filling out follow-up questionnaires and obtaining medical advice, etc.

[0030] The said speech recognition module: is used to convert the user's voice input into text form for the system to process and analyze.

[0031] The said natural language processing module is based on large language models and is used to understand and process the text information input by users, including answering the questions raised by users and analyzing the user's condition description, etc.

[0032] The said medical knowledge base includes medical literature, clinical guidelines, doctors' experiences, etc., and is used for the system to provide medical knowledge and advice.

[0033] The said data management module is used to manage the user's personal health data, including medical records, examination reports, medication records, etc.

[0034] The said intelligent recommendation module, based on the user's personal health data and medical knowledge base, provides personalized medical advice and health management solutions for users.

[0035] The said doctor assistance module is used to present the user's questions and condition description to doctors to assist doctors in making diagnoses and treatment suggestions; The said data analysis module is used to analyze the user's health data to discover potential health risks and provide preventive measures.

[0036] The said security and privacy protection module ensures that the user's personal health data is fully protected and complies with relevant privacy regulations and requirements.

[0037] The working principle of the present invention: The present invention discloses an intelligent medical follow-up system based on a large language model, which aims to utilize the powerful natural language processing capabilities of the large language model to improve the efficiency of medical follow-up and the level of personalized services. Based on the user's personal health data and medical knowledge base, the system provides users with personalized medical advice and health management plans, doctor assistance modules, data analysis modules, and security and privacy protection modules. The intelligent medical follow-up system can realize personalized medical services and health management for users, improve the utilization efficiency of medical resources, and provide more convenient and efficient medical services.

[0038] 1. Core Algorithms and Frameworks Natural language processing (NLP) algorithms: NLP algorithms are used to process patients’ natural language input, including text parsing, semantic understanding, entity recognition and other technologies, so that the system can understand patients’ needs and problems.

[0039] Language model: The system needs to build a powerful large language model so that it can perform tasks such as language generation, text completion, and question answering based on patient input. This can use pre-trained large language models such as GPT-3, BERT, etc., or it can be customized according to the characteristics of the medical field.

[0040] Data mining and analysis algorithms: The system needs to be able to analyze the patient's health data in real time, including physical signs, biochemical indicators, etc., so that abnormal conditions can be detected and warnings can be issued in a timely manner. This can be done by using data mining and machine learning algorithms for data analysis and pattern recognition.

[0041] Personalized recommendation algorithm: The system needs to be able to provide personalized health advice and treatment plans based on the patient's health status and history. This can be done with the help of a recommendation system algorithm to recommend appropriate health management plans based on the patient's specific situation and needs.

[0042] Knowledge base and expert system: The system needs to integrate rich medical knowledge and clinical experience to provide reference materials for doctors to help them better serve patients. This can be achieved with the help of technologies such as knowledge graphs and expert systems.

[0043] In short, the core algorithms and frameworks of the intelligent medical follow-up system based on the large language model involve technologies in multiple aspects such as NLP, language model, data mining, personalized recommendation and knowledge base, and require the comprehensive use of multiple algorithms and technical means to realize the functions of the system.

[0044] 2. Data processing and optimization Data preprocessing: The system needs to preprocess the patient's input, including text cleaning, word segmentation, entity recognition, etc., in order to extract effective information and perform semantic understanding. When processing health data, data cleaning, standardization, and denoising are also required to ensure the accuracy and integrity of the data.

[0045] Data integration and annotation: The system needs to integrate medical data from multiple sources, including the patient's medical records, vital signs, biochemical indicators, medical literature, etc., and annotate and associate these data in order to perform data mining and analysis.

[0046] Data mining and model training: The system needs to use machine learning and data mining algorithms to analyze and model medical data to discover potential patterns and regularities. This includes using techniques such as supervised learning and unsupervised learning for model training to improve the system's ability to understand the patient's needs and health status.

[0047] Model optimization and iteration: The system needs to optimize and iterate the language model, recommendation algorithm, etc. to continuously improve the performance and accuracy of the system. This includes adjusting model parameters, improving algorithms, and even updating the model structure to adapt to changing medical needs and new data.

[0048] Privacy and security protection: When processing the patient's health data, the system needs to strictly comply with privacy protection laws and regulations, anonymize the patient data, and take security measures to protect the security and privacy of the data.

[0049] 3. Model fine-tuning and application specialization Dataset screening: Screen out follow-up-related data from medical data, such as patient medical records, diagnostic reports, follow-up records, etc. These data can be used to fine-tune the language model to better understand text information in the medical field.

[0050] Model structure adjustment: According to the characteristics of medical follow-up, it may be necessary to adjust the structure of the language model to better adapt to text processing tasks in the medical field. For example, specific layers or mechanisms related to medical knowledge can be considered to improve the model's performance in the medical field.

[0051] Parameter adjustment: For the follow-up task in the medical field, the parameters of the language model can be fine-tuned to better adapt to the characteristics of medical text data. For example, hyperparameters such as the learning rate and regularization parameter can be adjusted.

[0052] Transfer learning: Use a pre-trained language model for transfer learning on medical follow-up tasks. Fine-tuning can be performed on the basis of the pre-trained model, or part of the structure of the pre-trained model can be used for medical follow-up tasks.

[0053] Verification and adjustment: By using a validation dataset in the medical field, the fine-tuned language model is verified and adjusted to ensure its performance and stability in medical follow-up tasks.

[0054] Application specialization: For the specific needs of medical follow-up, the fine-tuned language model can be specialized. For example, according to the characteristics of different diseases and the needs of patients, the model can be customized and adjusted to better support medical follow-up tasks.

[0055] 4. Real-time information processing and response Real-time data reception: The system needs to be able to receive various data from medical follow-up in real time, including patients' medical records, diagnostic reports, follow-up records, etc. These data can be obtained through medical information systems, sensor devices, or input by patients themselves.

[0056] Real-time information processing: After receiving the data, the system needs to be able to process the text information in real time, including natural language processing, data cleaning, entity recognition, sentiment analysis, etc. This can be achieved by leveraging large language models for semantic understanding and information extraction to better understand patients' needs and conditions.

[0057] Real-time decision-making and response: The system needs to be able to make real-time decisions and responses based on the processed information. For example, based on patients' symptoms and follow-up records, intelligent follow-up suggestions, medication suggestions, lifestyle guidance, etc. can be automatically generated and patients' needs and questions can be responded to in a timely manner.

[0058] Real-time communication and interaction: The system needs to support real-time medical information exchange and interaction. By integrating instant messaging tools, speech recognition technology, etc., real-time communication between doctors and patients can be achieved to better support medical follow-up tasks.

[0059] Real-time monitoring and feedback: The system needs to be able to monitor patients' conditions and feedback information in real time, including patients' feedback during follow-up, physiological parameter monitoring data, etc. Through real-time analysis and processing by large language models, patients' conditions can be better understood and the follow-up plan can be adjusted in a timely manner.

[0060] 5. Interactive and context understanding capabilities Context understanding capabilities: The system needs to be able to understand and analyze patients' context and contextual information to better grasp patients' needs and conditions. This can be achieved by introducing context-aware dialogue management technology and dialogue state tracking technology, enabling the system to understand patients' needs and questions at different stages and be able to make reasonable responses and interactions.

[0061] Interactive Design: The system needs to support interactive conversations with patients. This can be achieved by introducing dialogue management technology and multi-turn dialogue design to better understand the implied meaning and emotional needs of patients and enable more intelligent communication and interaction.

[0062] Emotion Recognition and Response: The system needs to have the ability to recognize emotions, understand and analyze the emotional state of patients to better conduct emotional communication and response. This can be achieved with the help of the emotion analysis capabilities of large language models, enabling the system to more intelligently understand and respond to the emotional needs of patients.

[0063] Context Persistence: The system needs to be able to achieve the persistence of dialogue context to better understand and respond to patients' needs in multi-turn conversations. This can be achieved by introducing dialogue history management and context storage technology, enabling the system to better track and understand the previous communication content and needs of patients, and thus make more personalized and targeted responses.

[0064] 6. System Integration and Interface Design Data Interface Design: The system needs to be able to exchange and share data with the patient information management system, diagnostic system, and medical record system of medical institutions. Therefore, appropriate data interfaces need to be designed to ensure that the system can obtain and update patients' medical information and feedback follow-up results and suggestions to the medical record system.

[0065] Dialogue Interface Design: The system needs to be able to interact with patients in natural language conversations. Therefore, appropriate dialogue interfaces need to be designed so that the system can understand patients' needs and questions and make intelligent responses and exchanges. This may involve the design of aspects such as speech recognition interfaces, natural language processing interfaces, and dialogue management interfaces.

[0066] Multi-Platform Adaptation: Considering that patients may use different devices for follow-up communication, the system needs to have the ability to adapt to multiple platforms and be able to interact stably and smoothly on different devices. Therefore, appropriate interfaces and adaptation solutions need to be designed to ensure that the system can be effectively docked and communicated on different devices.

[0067] Security and Privacy Protection: In system integration and interface design, issues such as data security and privacy protection need to be considered to ensure that the system can securely exchange data and transmit information and protect patients' privacy information from being leaked or misused.

[0068] 7. Scalability and Maintainability Modular design: The system is divided into multiple independent modules, and each module is responsible for a specific function or task. Such a design can make the system easier to expand and maintain because when modifying the system or adding new functions, only specific modules need to be concerned, without affecting the entire system.

[0069] Use standardized interfaces: Standardized interfaces are adopted for communication between various modules within the system, which can ensure a lower coupling degree between modules and facilitate the expansion and maintenance of the system. For example, adopting RESTful API interfaces can make the system more flexible and scalable.

[0070] Introduce automated testing: Establish a comprehensive automated testing framework, including unit testing, integration testing, and end-to-end testing, to ensure that each module and function of the system can be tested quickly and accurately, which helps to guarantee the maintainability and scalability of the system.

[0071] Adopt a suitable technical architecture: Select a suitable technical architecture and design pattern, such as a microservices architecture, an event-driven architecture, etc., which can improve the scalability and maintainability of the system and make it easier to expand new functions and handle larger loads.

[0072] Continuous integration and continuous delivery: Introduce continuous integration and continuous delivery tools to ensure that each modification of the system can be built, tested, and deployed quickly and automatically, which helps to guarantee the stability and maintainability of the system.

[0073] Advantages of the present invention: Personalized service: The intelligent system based on the large language model can understand and analyze the user's description of the condition and provide personalized medical advice and health management solutions, improving the quality and efficiency of medical services.

[0074] Data-driven decision-making: The system can analyze the user's personal health data, discover potential health risks, and provide preventive measures to help users better manage their health.

[0075] Doctor assistance: The system can present the user's questions and condition descriptions to doctors to assist doctors in diagnosis and treatment suggestions, improving the work efficiency and accuracy of doctors.

[0076] Provide convenient services: Users can interact with the system through the mobile App and the web version, and obtain medical advice and health management services anytime and anywhere.

[0077] Data security and privacy protection: The system ensures the full protection of the user's personal health data through the security and privacy protection module, in line with relevant privacy regulations and requirements.

[0078] Stronger natural language processing ability: The intelligent medical follow-up system based on large language models can more accurately understand patients' natural language inputs, including spoken and written language, and can better identify patients' needs and problems.

[0079] Intelligent recommendations and suggestions: The system can provide personalized health advice and treatment plans based on patients' health conditions and historical records to help patients better manage their health.

[0080] Real-time data analysis: The system can analyze patients' health data in real time, including physical signs, biochemical indicators, etc., to promptly detect abnormal conditions and issue warnings.

[0081] Automated follow-up and tracking: The system can automatically send follow-up reminders and tracking messages to help doctors better manage patients' follow-up plans and improve the timeliness and efficiency of follow-up.

[0082] Intelligent knowledge base: The system can integrate rich medical knowledge and clinical experience to provide doctors with more comprehensive reference materials to help them better serve patients.

[0083] In summary, the intelligent medical follow-up system based on large language models has significant improvements in aspects such as understanding patients' needs, personalized recommendations, data analysis, and knowledge base, and can better improve the efficiency and quality of medical follow-up. Brief Description of the Drawings

[0084] Figure 1 is a flowchart of an embodiment of the present invention. Detailed Embodiment

[0085] Please refer to Figure 1 shown, which is an embodiment of the present invention.

[0086] An intelligent medical follow-up system based on large language models includes a user interface layer, a speech recognition module, a natural language processing module, a medical knowledge base, a data management module, an intelligent recommendation module, a doctor assistance module, a data analysis module, and a security and privacy protection module.

[0087] The user interface layer mentioned above includes a mobile App and a web page, through which users can interact with the system, including filling out follow-up questionnaires, obtaining medical advice, etc.

[0088] The speech recognition module: is used to convert users' speech inputs into text form for the system to process and analyze.

[0089] The natural language processing module based on large language models is used to understand and process the text information input by users, including answering questions raised by users, analyzing users' disease descriptions, etc.

[0090] The medical knowledge base mentioned above includes medical literature, clinical guidelines, doctors' experience, etc., and is used to provide medical knowledge and suggestions for the system.

[0091] The data management module is used to manage users' personal health data, including medical records, examination reports, medication records, etc.

[0092] The intelligent recommendation module provides personalized medical suggestions and health management solutions for users based on their personal health data and the medical knowledge base.

[0093] The doctor assistance module is used to present users' questions and descriptions of their conditions to doctors to assist doctors in making diagnoses and providing treatment suggestions; The data analysis module is used to analyze users' health data to discover potential health risks and provide preventive measures.

[0094] The security and privacy protection module ensures that users' personal health data is fully protected and complies with relevant privacy regulations and requirements. ​​

Claims

1. An intelligent medical follow-up system based on a large language model, characterized by: It includes user interface layer, speech recognition module, natural language processing module, medical knowledge base, data management module, intelligent recommendation module, doctor assistance module, data analysis module and security and privacy protection module.

2. The intelligent medical follow-up system based on a large language model according to claim 1, characterized in that: The user interface layer includes a mobile app and a web page, through which users can interact with the system, including filling out follow-up questionnaires, obtaining medical advice, etc.

3. The intelligent medical follow-up system based on a large language model according to claim 1, characterized in that: The speech recognition module is used to convert the user's speech input into text form so that the system can process and analyze it.

4. The intelligent medical follow-up system based on a large language model according to claim 1, characterized in that: The natural language processing module is based on a large language model and is used to understand and process text information input by the user, including answering questions raised by the user, analyzing the user's description of the condition, etc.

5. The intelligent medical follow-up system based on a large language model according to claim 1, characterized in that: The medical knowledge base includes medical literature, clinical guidelines, physician experience, etc., which are used to systematically provide medical knowledge and advice.

6. The intelligent medical follow-up system based on a large language model according to claim 1, characterized in that: The data management module is used to manage the user's personal health data, including medical records, examination reports, medication records, etc.

7. The intelligent medical follow-up system based on a large language model according to claim 1, characterized in that: The intelligent recommendation module provides users with personalized medical advice and health management solutions based on their personal health data and medical knowledge base.

8. The intelligent medical follow-up system based on a large language model according to claim 1, characterized in that: The doctor assistance module is used to present the user's questions and condition descriptions to the doctor, and to assist the doctor in making diagnosis and treatment recommendations.

9. The intelligent medical follow-up system based on a large language model according to claim 1, characterized in that: The data analysis module is used to analyze the user's health data, discover potential health risks and provide preventive measures.

10. The intelligent medical follow-up system based on a large language model according to claim 1, characterized in that: The security and privacy protection module ensures that the user's personal health data is fully protected and complies with relevant privacy laws and regulations.

Images