Autonomous management system and method for patient data

Abstract

The invention relates to a data storage system, in particular to an autonomous management system and method for patient data. The patient end comprises a data acquisition module which is used for acquiring original data and converting the original data into structured data; the data integration module is used for carrying out data standardization and data normalization on the structured data; the data storage module is used for encrypting and storing the structured data; and the data analysis module is used for analyzing the structured data and generating a visual chart and risk assessment information. Compared with the prior art, the problems that in the prior art, a patient does not have the ability to regularize data, and a doctor does not have the ability to grasp complete historical data of the patient are solved, data of the whole life cycle of the patient can be integrated and analyzed, the doctor can comprehensively grasp the health dynamic state of the patient, and the patient experience is improved. Important support is provided for precise diagnosis and treatment of ovarian cancer.

Description

Technical Field

[0001] The present invention relates to a data storage system, and more particularly to an autonomous management system and method for patient data. Background Art

[0002] Ovarian cancer is the most complex and has the worst prognosis among gynecological malignancies. Since the early symptoms of ovarian cancer are often not obvious, patients are mostly in the middle and late stages at the time of diagnosis. Due to its long course, treatment and follow-up management run through the entire life cycle of the patient. Ovarian cancer patients may also experience multiple relapses and multiple surgeries, and need to receive different comprehensive treatments (such as chemotherapy, radiotherapy, targeted therapy, immunotherapy, etc.). Moreover, as the treatment progresses, data such as the patient's health status, treatment response, and disease progression are numerous and the changes are relatively complex.

[0003] During the treatment process, patients need to undergo multiple examinations regularly, including imaging examinations (such as B-ultrasound, CT, MRI), tumor marker detections (such as CA-125, HE4, etc.), and evaluations of other blood indicators. These data are often scattered among different medical institutions. However, due to the restrictions of data compliance and privacy protection, data intercommunication cannot be achieved among medical institutions. And patients themselves usually lack the ability to regularize data, and doctors can only obtain the examination data at a certain point in time, lacking the mastery of the patient's complete historical data. This results in doctors being unable to comprehensively grasp the patient's condition, thus affecting the accuracy of diagnosis and the effectiveness of treatment decisions. For example, the gradual increase of tumor markers such as CA-125 and HE4 may imply the risk of recurrence, but due to data loss or poor management, these key changes are often not noticed in time.

[0004] Therefore, a comprehensive data management and analysis based on the patient's entire life cycle is proposed, which can not only better track the patient's disease course, but also help doctors detect potential health risks in time and make more accurate and personalized treatment decisions. Summary of the Invention

[0005] The purpose of the present invention is to provide an autonomous management system and method for patient data to solve at least one of the above problems, so as to solve the problems in the prior art that patients themselves lack the ability to regularize data and doctors lack the mastery of the patient's complete historical data. This solution realizes the intelligent integration and analysis of the data of the patient's entire life cycle, helps doctors comprehensively master the patient's health dynamics, and provides important support for the precise diagnosis and treatment of ovarian cancer.

[0006] The purpose of the present invention is achieved through the following technical solutions:

[0007] The first aspect of the present invention discloses an autonomous management system for patient data, including a patient terminal;

[0008] The described patient terminal includes:

[0009] A data acquisition module, which is used to obtain raw data and convert the raw data into structured data;

[0010] A data integration module, which is used to standardize and regularize the structured data;

[0011] A data storage module, which is used to encrypt and store the data after regular processing;

[0012] A data analysis module, which is used to analyze the data after regular processing, generate visual charts and risk assessment information.

[0013] Preferably, the data acquisition module includes a data upload port, an OCR sub-module and an NLP sub-module;

[0014] The data upload port is used to obtain the raw data uploaded by the user;

[0015] The OCR sub-module is used to extract the text information in the raw data;

[0016] The NLP sub-module is used to perform natural language processing on the extracted text information and convert it into structured data.

[0017] Preferably, the raw data includes medical record records, imaging examination results, tumor marker detection results and blood index examination results.

[0018] Preferably, the data integration module includes a data standardization sub-module and a data regularization sub-module;

[0019] The data standardization sub-module is used to screen and standardize the structured data;

[0020] The data regularization sub-module is used to integrate the data after standardization processing and establish an electronic medical record sorted by time dimension.

[0021] Preferably, the data storage module includes an encryption sub-module and a storage sub-module;

[0022] The encryption sub-module is used to encrypt the data after regular processing using the national cryptography algorithm;

[0023] The storage sub-module is used to store the encrypted data, including local storage, cloud storage, distributed storage and blockchain storage.

[0024] Preferably, the data analysis module includes a trend analysis and display sub-module and an intelligent risk assessment sub-module;

[0025] The described trend analysis and display sub-module is used to generate a visual chart of data change trends;

[0026] The described intelligent risk assessment sub-module is used to conduct risk assessment through an artificial intelligence model and generate health warning information. The artificial intelligence model includes a survival analysis model and a recurrence prediction model.

[0027] Preferably, the autonomous management system further includes a doctor terminal;

[0028] The patient terminal further includes a data sharing module, which is used to encrypt and transmit the processed data to the doctor terminal and receive data source information from the doctor terminal;

[0029] The doctor terminal includes a data interaction module and a data calling module;

[0030] The data interaction module is used to receive the processed data from the patient terminal, perform desensitization processing and encrypted storage; the data interaction module is also used to transmit data source information to the patient terminal;

[0031] The data calling module is used to retrieve the desensitized data.

[0032] Preferably, the data sharing module and the data interaction module perform data transmission through an encrypted channel in a trusted execution environment.

[0033] Preferably, the data interaction module includes a data desensitization sub-module and an encrypted storage sub-module;

[0034] The data desensitization sub-module is used to desensitize the processed data;

[0035] The encrypted storage sub-module is used to encrypt and store the desensitized data.

[0036] The second aspect of the present invention discloses an autonomous management method for patient data, which uses any one of the above-mentioned autonomous management systems;

[0037] The autonomous management method is as follows:

[0038] The patient uploads the original data from at least one source to the data collection module through the patient terminal. The data collection module converts the original data into structured data and then transmits it to the data integration module. The data integration module standardizes and regularizes the structured data and then transmits it to the data storage module. The data storage module encrypts and stores the processed data. The data analysis module retrieves data from the data storage module for analysis and generates a visual chart and risk assessment information.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] With the help of the intelligent system, after multiple data entries and follow-ups, doctors can directly view the trend charts of indicators, greatly improving the efficiency of diagnosis and treatment. Through the integration and analysis of patient data throughout the life cycle, the system helps doctors comprehensively understand the health dynamics of patients and provides important support for the precise diagnosis and treatment of ovarian cancer.

[0041] Specifically, it includes:

[0042] 1. Efficiently integrate and manage the health data of ovarian cancer patients

[0043] 1) Provide efficient data collection tools, including the standardization of common data for ovarian cancer (such as tumor markers, imaging data, pathological reports, etc.), uniformly manage the examination data of patients in different medical institutions, and establish a complete medical record file for ovarian cancer.

[0044] 2) Provide innovative data collection tools that automatically identify unstructured data such as paper medical records and test reports through OCR (Optical Character Recognition) technology and NLP (Natural Language Processing) technology, and convert them into structured electronic medical records. This tool supports patients to independently upload and manage multi-source data and can achieve data standardization conversion across multiple institutions and formats.

[0045] 3) Support data recording at each treatment stage of patients, such as surgery, chemotherapy, and targeted therapy, to form a medical record data file throughout the life cycle.

[0046] 2. Intelligent trend analysis and auxiliary diagnosis support

[0047] 1) The system generates trend curves of relevant indicators (such as CA-125, HE4, imaging changes) based on the patient's historical data, provides abnormal warnings and auxiliary diagnosis suggestions to help doctors detect recurrence risks in a timely manner.

[0048] 2) Combine artificial intelligence models (such as survival analysis, recurrence prediction models) to conduct personalized risk assessments for patients and assist doctors in formulating precise treatment strategies.

[0049] 3. Ensure the secure sharing and compliant operation of health data

[0050] 1) Support patients to share their medical record data with doctors for diagnosis, treatment, and research use under authorization.

[0051] 2) Provide data sharing records and traceability functions, allowing patients to understand the usage of data and enhancing patients' trust in data management and use. Description of the Drawings

[0052] Figure 1 It is a schematic structural diagram of the self-management system;

[0053] In the figure: 100 - patient side; 110 - data acquisition module; 120 - data integration module; 130 - data storage module; 140 - data analysis module; 150 - data sharing module; 111 - data upload port; 112 - OCR sub-module; 113 - NLP sub-module; 121 - data standardization sub-module; 122 - data regularization sub-module; 131 - encryption sub-module; 132 - storage sub-module; 141 - trend analysis and display sub-module; 142 - intelligent risk assessment sub-module; 200 - doctor side; 210 - data interaction module; 220 - data call module; 211 - data desensitization sub-module; 212 - encrypted storage sub-module. Detailed implementation mode

[0054] The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0055] Embodiment 1

[0056] An autonomous management system for patient data, as Figure 1 shown, includes a patient side 100;

[0057] The patient side 100 described above includes:

[0058] A data acquisition module 110, which is used to obtain raw data and convert the raw data into structured data;

[0059] A data integration module 120, which is used to perform data standardization and data regularization on the structured data;

[0060] A data storage module 130, which is used to encrypt and store the data after the regularization process;

[0061] A data analysis module 140, which is used to analyze the data after the regularization process, generate visual charts and risk assessment information.

[0062] More specifically, in this embodiment:

[0063] The system architecture diagram is as shown in the appendix Figure 1 shown. The overall architecture of the system is divided into two parts: the patient side 100 and the doctor side 200. Among them, the core management and analysis functions of medical record data are all completed on the patient side 100.

[0064] The patient side 100 includes a data acquisition module 110, a data integration module 120, a data storage module 130, a data analysis module 140 and a data sharing module 150.

[0065] The data acquisition module 110 further includes a data upload port 111, an OCR sub-module 112, and an NLP sub-module 113. Among them, the data upload port 111 is used to obtain the original data uploaded by the user, such as the photos taken by the user (including paper medical records, test reports, imaging examination results, tumor marker test results, blood index test results, etc.), the uploaded electronic documents (including electronic medical records, test reports, imaging examination results, tumor marker test results, blood index test results, etc.). The OCR sub-module 112 is used to identify and extract the text information (unstructured data) in the original data by means of optical character recognition. The NLP sub-module 113 is used to perform natural language processing on the extracted text information and convert it into structured data for subsequent management and analysis.

[0066] The data integration module 120 further includes a data standardization sub-module 121 and a data regularization sub-module 122. The data standardization sub-module 121 is used to screen and standardize the structured data. It determines the required data according to the suggestions of ovarian cancer experts, including the types of indicators that ovarian cancer patients should pay attention to, standard units, normal range of values, etc., and screens out the required data from the structured data processed by the data acquisition module 110, and then standardizes and processes it into data with a consistent format. The data regularization sub-module 122 is used to regularize and integrate the multi-source data after standardization processing, and establish an electronic medical record sorted by time dimension.

[0067] The data storage module 130 further includes an encryption sub-module 131 and a storage sub-module 132. The encryption sub-module 131 is used to encrypt the processed data using the national encryption algorithm. It can automatically generate a key by the device or the patient provides an encryption password to ensure the security of the data in the static storage state, and only the authorized party can decrypt and access it. The storage sub-module 132 is used to store the encrypted data, including local storage, cloud storage, distributed storage, and blockchain storage. The encrypted data is stored locally on the patient side 100 to form the patient's historical medical record file. At the same time, it also supports cloud encrypted storage, which can further ensure the high availability and reliability of the data, or, perform backup through distributed storage to ensure the availability and anti-tampering of the data.

[0068] The data analysis module 140 further includes a trend analysis display submodule 141 and an intelligent risk assessment submodule 142; the trend analysis display submodule 141 is used to generate a visual chart of data change trends. The data analysis module 140 retrieves the encrypted data stored in the data storage module 130, and generates a trend curve of key indicators changing over time based on the patient's electronic medical record data established in advance, such as tumor markers such as CA-125 and HE4. By providing visual interfaces such as data charts and supporting key indicator screening, it can quickly and effectively help patients understand their health changes, or directly provide and display them to doctors for auxiliary diagnosis during medical consultation; the intelligent risk assessment submodule 142 is used to perform risk assessment and generate health warning information through artificial intelligence models. The artificial intelligence models it uses include survival analysis models and recurrence prediction models. Risk assessment is performed based on established patient electronic medical records to provide patients with health warning information such as disease recurrence.

[0069] The data sharing module 150 is used to encrypt and transmit the regularly processed data (retrieved from the data storage module 130) to the doctor end 200 and receive data tracing information from the doctor end 200. At the same time, the data sharing module 150 will also receive data sharing application requests from the doctor end 200, and then the patient can choose whether to authorize the establishment of the patient's electronic medical record data to be shared with the designated doctor (the doctor who initiates the request) according to his own wishes. The setting of data tracing can record each time the data is shared, used, retrieved, etc. (including the visitor's identity, access time, access content and operation behavior), so that the use of the shared data can be easily traced to ensure transparent management of the data.

[0070] The doctor end 200 includes a data interaction module 210 and a data calling module 220. The data interaction module 210 is used to receive the data after regular processing from the patient end 100 and perform desensitization processing and encrypted storage, and is also used to transmit data source information to the patient end 100; the data calling module 220 is used to retrieve the desensitized data and initiate a data sharing application request to the patient end 100.

[0071] The data interaction module 210 further includes a data desensitization sub-module 211 and an encrypted storage sub-module 212; the data desensitization sub-module 211 is used to desensitize the regularized data. The information that needs to be desensitized includes at least privacy data such as name, ID number, mobile phone number, and medical record number. By removing or replacing them with feature codes / identification codes, the privacy of patients is protected, thereby reducing the risk of data leakage. These desensitized data can be further used for scientific research purposes; the encrypted storage sub-module 212 is used to encrypt and store the desensitized data. In the same way as the data storage module 130, it uses the national cryptographic algorithm for encryption and adopts at least one of local storage, cloud storage, distributed storage, and blockchain storage for data storage. The data sharing module 150 and the data interaction module 210 perform data transmission through an encrypted channel in a trusted execution environment. Specifically, the system realizes the protection of keys and authorization logic based on the trusted execution environment technology. During the data sharing transmission process, end-to-end encryption technology (such as the TLS / SSL protocol) is adopted for transmission, and then the transmitted data will be encrypted. Only the authorized recipient can decrypt the data, thereby ensuring that the data itself is not leaked during the data sharing process, only verifying the authenticity and availability of the data, realizing the protection of data security, and ensuring that the data will not be stolen or tampered with on the transmission link.

[0072] The data call module 220 retrieves the desensitized information from the encrypted storage sub-module 212 of the data interaction module 210 for scientific research use, thereby meeting the need of doctors to collect complete diagnosis and treatment history data of patients when conducting some medical research. In addition, the data call module 220 also sends a data sharing application request to the patient terminal 100. For example, doctors can initiate relevant research projects on the doctor terminal 200 application. After improving the project information (such as project objectives, requirements, department or doctor information, etc.), the system will generate corresponding data item requirements according to the needs filled in by the doctor; then the doctor can publish the data item requirements in the system and display them to the patient, and the patient decides on the patient terminal 100 whether to authorize a specific doctor to obtain their corresponding data.

[0073] Relying on a complete data security protection chain and a patient authorization system, the system enables doctors to apply for data from patients in a safe and compliant manner, thereby obtaining more complete multi-center medical data in a controllable, auditable, and traceable manner on the premise of ensuring patient data security, and improving the level of medical research.

[0074] The autonomous management method of this system is as follows:

[0075] The patient uploads raw data from at least one source to the data acquisition module 110 through the patient terminal 100. The data acquisition module 110 converts the raw data into structured data and transmits it to the data integration module 120. The data integration module 120 standardizes and regularizes the structured data and transmits it to the data storage module 130. The data storage module 130 encrypts and stores the regularized data. The data analysis module 140 retrieves data from the data storage module 130 for analysis to generate visual charts and risk assessment information.

[0076] The doctor issues a data sharing application request to the patient through the data calling module 220 of the doctor's end 200, and the patient selects the data range according to his / her will to authorize the data on the patient's end 100; after the patient agrees to the authorization, an encrypted transmission channel will be established between the corresponding doctor's end 200 and the patient's end 100 based on the trusted execution environment, and the data sharing module 150 retrieves the specified data in the data storage module 130 and transmits it to the data interaction module 210. After receiving the data, the data interaction module 210 performs desensitization processing and encrypts the data for storage; the doctor retrieves the desensitized data from the data interaction module 210 through the data calling module 220 as needed. The data calling module 220 of the doctor's end 200 will record all relevant information such as data retrieval and usage records, and return data source information to the corresponding patient's end 100 through the data interaction module 210.

[0077] Example 2

[0078] The system of this embodiment is basically the same as that of Embodiment 1, with the main difference being that blockchain technology is used in this embodiment to improve the security and transparency of data sharing. Specifically, in this embodiment, the encrypted data of both the patient end 100 and the doctor end 200 are stored in blockchain to further improve the security and transparency of the data sharing process. Through the decentralized and tamper-proof characteristics of blockchain, the patient's medical record data sharing can be recorded in the blockchain network, and each data access and operation can be tracked and audited. Through the system, patients can clearly understand when, by whom, and for what purpose the data was accessed, which greatly enhances the transparency and trust of data sharing. This will provide stronger security for the management and use of medical data.

[0079] Example 3

[0080] The system of this embodiment is basically the same as that of Embodiment 1. The main difference is that each patient terminal 100 further includes a remote follow-up management module to support the remote health management of ovarian cancer patients after treatment. The remote follow-up management module can regularly retrieve the inspection reports of key indicators and the results of daily detection indicators (such as weight, blood pressure, heart rate, etc.) from the data storage module 130 according to the patient's authorization, and establish a trend chart of indicator changes in the time dimension to help doctors track the patient's recovery progress in real time. Doctors can obtain the data results of the remote follow-up management module through the authorized doctor terminal 200. In addition, doctors can also set health warning thresholds in the system. Once abnormal data (such as rapid weight loss or too high blood pressure) is detected, the system will automatically generate a warning alert and notify the doctor and the patient to arrange remote consultation or further examinations in a timely manner. This remote follow-up management mode effectively reduces the need for patients to frequently go to the hospital, improves the quality of life of patients, and also enhances the doctor's continuous monitoring ability for patients.

[0081] Application Example 1

[0082] Patient Li had multiple blood index examinations (such as CA-125, HE4, etc.) and imaging examinations in different medical institutions. These data were scattered in various hospitals and were difficult to comprehensively utilize. Patient Li used the medical record data self-management system of Embodiment 1 of the present invention. After each examination, the hospital report was uploaded by taking screenshots or photos and converted into an electronic medical record. The system standardized the data and integrated the multi-source data from different medical institutions into a unified platform.

[0083] One year later, Li went to a well-known hospital in Shanghai to find an expert for a reexamination. He used the patient terminal 100 application in the system to directly show all the examination data and the generated trend analysis chart of the past year to the expert. Through the trend analysis display module and the complete medical record file, the expert quickly understood the changes in Li's condition and the trend of key indicators. The intelligent risk assessment module provided by the system also prompted the possible recurrence risk. Based on these detailed data, the expert was able to accurately evaluate Li's current condition and give personalized treatment suggestions. Therefore, Li obtained a timely and effective treatment plan.

[0084] Application Example 2

[0085] Doctor Sun is conducting a cutting-edge research on the treatment methods of ovarian cancer and needs to collect historical case data of a large number of ovarian cancer patients nationwide. However, the data in this hospital is relatively limited and discontinuous, making it difficult to meet the research needs. For this reason, Sun used the system of Embodiment 1 of the present invention to create a research project and sent a data application request to patient users through the doctor terminal 200 of the system.

[0086] Patient users in the system received the data application and reviewed the data sharing security instructions, confirming that the data would be transmitted and stored in an encrypted and desensitized manner throughout the process to ensure privacy. After understanding and agreeing to the sharing terms, some patient users chose to authorize the use of their medical record data for Sun's research project.

[0087] After obtaining sufficient authorization, Sun obtained the anonymized patient medical history data through the system's data sharing module 150 and medical research data collection module. Through the system's research project management function, Sun can safely conduct in-depth analysis of these anonymized data to conduct relevant scientific research, ultimately providing more powerful theoretical and data support for the treatment of ovarian cancer.

[0088] The originality of this invention lies in the realization of autonomous management, cross-institutional integration, intelligent analysis and secure sharing of patient medical record data, meeting the needs of patients for self-health management and physician-assisted diagnosis and treatment.

[0089] 1. Patient self-management and cross-institutional data integration:

[0090] 1) Compared with the existing technology, the present invention allows patients to upload and manage cross-institutional health data independently, breaking the limitation of data silos between medical institutions. It supports the full data cycle management of ovarian cancer patients from diagnosis, treatment to follow-up, which is not achieved by many existing systems.

[0091] 2) Through OCR and NLP technology, unstructured medical record information is converted into standardized electronic medical records, realizing the integration and standardized processing of multi-source data.

[0092] 2. Intelligent trend analysis and auxiliary diagnosis support:

[0093] 1) Use artificial intelligence technology to perform trend analysis on patients’ health data, such as the changing trends of key tumor markers such as CA-125 and HE4, to help doctors quickly diagnose the condition.

[0094] 2) Personalized risk assessment based on historical data and AI models provides doctors with auxiliary diagnosis and treatment suggestions to improve the accuracy of diagnosis.

[0095] 3. Data security and privacy protection:

[0096] 1) Through data sharing records and traceability functions, patients can be ensured to have controllable and transparent data usage, thus enhancing trust in data sharing.

[0097] 2) Data sharing strictly follows patient authorization, and data privacy and compliance operations are guaranteed during the sharing process.

[0098] The above description of the embodiments is provided to enable those of ordinary skill in the art to understand and use the invention. It is obvious that those skilled in the art can easily make various modifications to these embodiments and apply the general principles described herein to other embodiments without creative efforts. Therefore, the present invention is not limited to the above embodiments, and all improvements and modifications made by those skilled in the art without departing from the scope of the present invention according to the disclosure of the present invention should be within the protection scope of the present invention.

Claims

1. An autonomous management system for patient data, characterized in that: comprising a patient end (100); The patient end (100) comprises: A data acquisition module (110), used to acquire raw data and convert the raw data into structured data; A data integration module (120), used for standardizing and regularizing structured data; A data storage module (130) is used to encrypt and store the data after the regularization process; The data analysis module (140) is used to analyze the data after regularization and generate visual charts and risk assessment information.

2. The autonomous management system for patient data according to claim 1, characterized in that: The data acquisition module (110) comprises a data upload port (111), an OCR submodule (112) and an NLP submodule (113); The data upload port (111) is used to obtain the original data uploaded by the user; The OCR submodule (112) is used to extract text information from the original data; The NLP submodule (113) is used to perform natural language processing on the extracted text information and convert it into structured data.

3. The autonomous management system for patient data according to claim 1, characterized in that: The original data include medical records, imaging examination results, tumor marker test results and blood index test results.

4. The autonomous management system for patient data according to claim 1, characterized in that: The data integration module (120) includes a data standardization submodule (121) and a data regularization submodule (122); The data standardization submodule (121) is used to screen and standardize structured data; The data regularization submodule (122) is used to integrate the standardized data and establish an electronic medical record sorted by time dimension.

5. The autonomous management system for patient data according to claim 1, characterized in that: The data storage module (130) comprises an encryption submodule (131) and a storage submodule (132); The encryption submodule (131) is used to encrypt the data after the regularization process using a national encryption algorithm; The storage submodule (132) is used to store encrypted data, including local storage, cloud storage, distributed storage and blockchain storage.

6. The autonomous management system for patient data according to claim 1, characterized in that: The data analysis module (140) comprises a trend analysis and display submodule (141) and an intelligent risk assessment submodule (142); The trend analysis and display submodule (141) is used to generate a visual chart of data change trends; The intelligent risk assessment submodule (142) is used to perform risk assessment and generate health warning information through an artificial intelligence model, and the artificial intelligence model includes a survival analysis model and a recurrence prediction model.

7. The autonomous management system for patient data according to claim 1, characterized in that: The autonomous management system further comprises a doctor terminal (200); The patient end (100) further comprises a data sharing module (150) for encrypting and transmitting the regularly processed data to the doctor end (200) and receiving data source information from the doctor end (200); The doctor end (200) comprises a data interaction module (210) and a data calling module (220); The data interaction module (210) is used to receive the data after regular processing from the patient end (100) and perform desensitization processing and encrypted storage; the data interaction module (210) is also used to transmit data source information to the patient end (100); The data calling module (220) is used to retrieve the data after the desensitization process.

8. The autonomous management system for patient data according to claim 7, characterized in that: The data sharing module (150) and the data interaction module (210) perform data transmission in a trusted execution environment by establishing an encrypted channel.

9. The autonomous management system for patient data according to claim 7, characterized in that: The data interaction module (210) comprises a data desensitization submodule (211) and an encryption storage submodule (212); The data desensitization submodule (211) is used to perform desensitization processing on the data after the regularization processing; The encryption storage submodule (212) is used to encrypt and store the desensitized data.

10. A method for autonomous management of patient data, characterized in that: Adopting the autonomous management system as claimed in any one of claims 1 to 9; The autonomous management method is: The patient uploads raw data from at least one source to the data acquisition module (110) through the patient terminal (100); the data acquisition module (110) converts the raw data into structured data and transmits the data to the data integration module (120); the data integration module (120) performs data standardization and data regularization on the structured data and transmits the data to the data storage module (130); the data storage module (130) encrypts and stores the regularized data; The data analysis module (140) retrieves data from the data storage module (130) for analysis and generates visual charts and risk assessment information.

Images