Medical comprehensive management cloud platform based on blockchain technology

Through the blockchain technology comprehensive medical management cloud platform, the problem of inconsistent and decentralized medical data formats is solved, unified data collection, in-depth analysis and visual reporting are realized, and the efficiency and accuracy of medical data management and diagnosis and treatment are improved.

CN117976166BActive Publication Date: 2024-11-19ANHUI CLARIVATE DIGITAL TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410145952.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-02-02
Publication Date
2024-11-19
Estimated Expiration
2044-02-02

AI Technical Summary

Technical Problem

In the existing medical management system, the format of medical data is not unified and scattered, which makes it difficult to collect, store and process data, and it is impossible to effectively integrate and utilize data, and there is a lack of in-depth analysis of patient medical records, medical images and medical data. , affects the accuracy and efficiency of diagnosis and treatment.

Method used

Adopt a comprehensive medical management cloud platform based on blockchain technology, and use the medical data acquisition module to collect and standardize data from different sources and formats, use the distributed storage module to store data, and set up patient case analysis in the data processing module. The image analysis and medical analysis unit is extracted and conducted in-depth analysis to generate visual diagnostic and treatment reports.

Benefits of technology

It realizes unified management and in-depth analysis of medical data, improves the efficiency and accuracy of data management, enhances the safety and reliability of data, helps doctors quickly and accurately understand the patient's condition, and improves the efficiency and accuracy of diagnosis and treatment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117976166B_ABST
    Figure CN117976166B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of medical management technology, and is used to solve the problems in traditional medical data management, such as inconsistent formats and scattered data, which lead to greater difficulties in data collection, storage and processing, and the inability to achieve effective integration and utilization of data. In addition, there is a lack of in-depth analysis and mining of medical data, which leads to the inability to quickly and accurately understand the patient's condition, affecting the accuracy and efficiency of diagnosis and treatment. Specifically, it is a medical comprehensive management cloud platform based on blockchain technology, including a medical data collection module, a medical data storage module, a medical data processing module and a display terminal. The present invention improves the management efficiency and accuracy of data by uniformly collecting and standardizing medical data from different source systems and different formats. Distributed storage is used to store medical data on multiple nodes to enhance data security. Through in-depth analysis and mining of various data, and the use of visual display, the efficiency and accuracy of diagnosis and treatment are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of medical management technology, and in particular to a medical comprehensive management cloud platform based on blockchain technology. Background Art

[0002] With the continuous development and progress of medical technology, the management and utilization of medical data has become increasingly important. However, there are many problems in the existing medical management system. For example, in traditional medical data processing and management, data from different source systems such as medical institutions, patients and drug suppliers often have problems such as inconsistent formats and scattered data, which makes data collection, storage and processing difficult and makes it impossible to effectively integrate and utilize data. In addition, traditional medical data processing methods may lack in-depth analysis and mining of patient medical records, medical images and pharmaceutical data, resulting in doctors being unable to quickly and accurately understand the patient's condition, affecting the accuracy and efficiency of diagnosis and treatment.

[0003] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0004] The purpose of the present invention is to provide a medical comprehensive management cloud platform based on blockchain technology to solve the problems raised by the above background technology.

[0005] The object of the present invention can be achieved by the following technical solutions: A medical integrated management cloud platform based on blockchain technology includes: a medical data collection module for collecting medical data from various source systems and uniformly collecting and standardizing medical data from different source systems and different formats, thereby completing the unified collection of medical data, and each source system includes medical institutions, patients, and drug suppliers;

[0006] A medical data storage module is used to perform distributed storage of collected medical data, thereby distributing and storing the medical data on multiple nodes;

[0007] The medical data processing module is provided with a patient case analysis unit, a patient image analysis unit, and a patient medicine analysis unit, wherein the patient case analysis unit is based on the medical data and extracts the patient's electronic medical record therefrom, thereby processing the case data, obtaining the medical record data table and the disease diagnosis prediction and determination level corresponding to the patient, and displaying and explaining them through the display terminal; the patient image analysis unit is based on the medical data and extracts the patient's medical image data therefrom, thereby performing image lesion analysis, obtaining the image lesion conclusion report corresponding to the patient, and displaying and explaining them through the display terminal; the patient medicine analysis unit is based on the medical data and extracts the patient's medical data therefrom, thereby performing medical condition assessment analysis, obtaining the patient's corresponding diagnosis and treatment status conclusion report, and visually displays the patient's diagnosis and treatment status conclusion report through the display terminal;

[0008] The display terminal is used to display and explain the medical record data table corresponding to the patient, the disease diagnosis prediction judgment level, the image lesion conclusion report and the diagnosis and treatment status conclusion report.

[0009] Preferably, the medical data from different sources and in different formats are uniformly collected and standardized, and the specific analysis process is as follows:

[0010] 2-1. Data interface and integration: Establish data interfaces with various data sources. The data interfaces can adopt standardized data formats and transmission protocols. Data in different formats can be converted through data conversion tools or custom scripts, thereby integrating them into a unified data set.

[0011] 2-2. Data cleaning and preprocessing: The collected data is cleaned and preprocessed through data cleaning algorithms and rules, and the data cleaning algorithms and rules include removing duplicate data, correcting erroneous data, and filling missing data;

[0012] 2-3. Data standardization and coding: standardize and code data from different sources, specifically, code diagnosis, surgery, and drug information;

[0013] 2-4. Data quality control: By setting data rules and algorithms, we can filter out data that meets the requirements, and perform error correction and supplementation, that is, complete data quality control during the data collection process. Data quality control includes data verification, logic checking, and outlier processing;

[0014] 2-5. Data security and privacy protection: By using encrypted transmission, access control, and data desensitization technology during data collection and processing, we can protect data security and privacy and ensure that sensitive information is not accessed and used without authorization.

[0015] Preferably, the collected medical data is distributedly stored in the following manner:

[0016] 3-1. Data segmentation: The medical data is segmented according to certain rules to obtain a number of shards. When the medical data is segmented according to certain rules, it can be determined based on the characteristics of the data and the access mode;

[0017] 3-2. Node selection: Each shard is stored as an independent storage unit on one or more nodes. Appropriate nodes can be selected to store the sharded data according to the distributed storage architecture, and are usually selected based on factors such as node load, availability, and network latency.

[0018] 3-3. Data copy: Create multiple copies of important data and store each copy on a different node;

[0019] 3-4. Data consistency: Set up a distributed consistency protocol to ensure that data remains consistent on different nodes;

[0020] 3-5. Data access: When accessing data, the node where the distributed stored data is located is located through hash algorithms or shard indexes, and data is read and written.

[0021] 3-6. Data redundancy storage: Keep redundant copies of important data and store them on different nodes.

[0022] Preferably, the case data processing, the specific analysis process is as follows:

[0023] Based on the processed medical data, the electronic medical record data of the patient is retrieved from the medical data, and the disease type, symptom severity, and treatment cycle of the patient are extracted from the electronic medical record data to form a medical record data table of the patient, and the medical record data table of the patient is visually displayed through a display terminal;

[0024] Extracting characteristic parameters related to the patient's condition from the electronic medical record data, wherein the characteristic parameters related to the patient's condition include a medical history index, a surgical index, and a symptom index;

[0025] Among them, the medical history index is used to express the comprehensive feedback of the medical history level of the patient's family medical history and the medical history level of the patient's past medical history. If the medical history level of the patient's family medical history is A1, and the medical history level of the patient's past medical history is A2, then the patient's medical history index is: bs=(A1×q1+A2×q2) / 2, where q1 and q2 are weight factors respectively;

[0026] The surgical index is used to indicate the comprehensive feedback of the risk level of all surgeries performed on the patient in a unit time. When evaluating the risk level of the surgery corresponding to the patient, the risk level of the surgery is generally fed back by the length of the surgery. The risk level of all surgeries performed on the patient in a unit time is recorded as FX. i, According to the formula , thereby calculating the surgical index szl corresponding to the patient;

[0027] The symptom index is used to represent the data value of the number of symptom types that the patient has in the current period, where headache, fever, cough, vomiting, etc. are all represented as symptom types;

[0028] The values ​​of the medical history index, surgical index and symptom index in the characteristic parameters related to the patient's condition are extracted and calculated and analyzed. According to the formula JZB=k1×bs+k2×szl+k3×zzl, the patient's disease prediction coefficient JZB is calculated, where zzl represents the symptom index, and k1, k2, and k3 represent weight factors respectively;

[0029] The patient's disease prediction coefficient is matched with the disease diagnosis prediction judgment level corresponding to the disease prediction coefficient, thereby obtaining the disease diagnosis prediction judgment level corresponding to the patient, and the patient's disease diagnosis prediction judgment level is visualized through a display terminal.

[0030] Preferably, the specific analysis process of the image lesion analysis is as follows:

[0031] The medical imaging data of the patient is retrieved from the medical data, and the lesion characteristics and lesion degree of the patient are extracted from the medical imaging data, and they are marked as bz and bc respectively, and the two data are normalized and analyzed, and the patient's imaging evaluation coefficient Iac is obtained according to the formula Iac=a1×bz+a2×bc, where a1 and a2 are respectively represented as normalization factors;

[0032] The patient's image assessment coefficient is matched with the lesion conclusion report corresponding to the image assessment coefficient, thereby obtaining the image lesion conclusion report corresponding to the patient, and the patient's lesion conclusion report is visualized through a display terminal.

[0033] Preferably, the specific analysis process of the medical condition assessment analysis is as follows:

[0034] Retrieving the patient's medical data from the medical data, and extracting the patient's drug type, dosage, and usage method from the medical data, matching the patient's drug type with the drug diagnosis and treatment level corresponding to the drug type, thereby obtaining the patient's drug diagnosis and treatment level, and performing a comprehensive average calculation of the drug diagnosis and treatment levels corresponding to all drug types of the patient, thereby obtaining the patient's drug index, which is recorded as yz;

[0035] Based on the drug type, the usage mode of the corresponding drug type is obtained, where the usage mode includes the number of times of use and the usage cycle, which are marked as sc and zq respectively, and the two data are normalized and analyzed. According to the formula sz=a3×sc+a4×zq, the usage index sz of the patient's corresponding drug type is calculated, where a3 and a4 are respectively represented as normalization factors;

[0036] The values ​​of the drug index, dosage and usage index corresponding to the patient are extracted, and substituted into the preset data model for calculation and analysis. According to the set data model zl=b1×yz+b2×yl+b3×sz, the patient's medical diagnosis and treatment evaluation coefficient zl is output, wherein yl represents the dosage corresponding to the patient, b1, b2, and b3 represent weight factors respectively, and the patient's medical evaluation coefficient is compared with the diagnosis and treatment status conclusion report corresponding to the medical evaluation coefficient, thereby outputting the patient's diagnosis and treatment status conclusion report, and visually displaying the patient's diagnosis and treatment status conclusion report through the display terminal.

[0037] Beneficial effects of the present invention:

[0038] The present invention can uniformly collect and standardize medical data from different sources and in different formats from various source systems through the medical data collection module, thereby realizing unified management of medical data and improving the efficiency and accuracy of data management.

[0039] The present invention adopts distributed storage technology through a medical data storage module to store medical data on multiple nodes, thereby enhancing the security and reliability of the data and facilitating the storage and backup of the data.

[0040] The present invention can extract the patient's electronic medical record based on medical data through the patient medical record analysis unit, process the medical record data, and predict the disease diagnosis level, which helps doctors quickly understand the patient's condition and make a more accurate diagnosis and treatment plan.

[0041] The present invention provides doctors with more intuitive and accurate analysis results by performing lesion analysis on medical imaging data, which helps in early detection and accurate diagnosis of diseases.

[0042] The present invention extracts the patient's medical data based on the medical data through the patient medical analysis unit, performs medical condition evaluation and analysis, and provides a comprehensive diagnosis and treatment status conclusion report for the doctor. This helps the doctor to fully understand the patient's condition and formulate a more scientific and effective treatment plan.

[0043] The present invention visualizes the patient's medical record data table, disease diagnosis prediction and determination level, image lesion conclusion report and diagnosis and treatment status conclusion report, making it convenient for doctors to quickly understand and judge the patient's condition, thereby improving the efficiency and accuracy of diagnosis and treatment.

[0044] In summary, the present invention can improve the efficiency and quality of medical services and provide doctors and patients with more convenient and accurate diagnosis and treatment services through unified data management, distributed storage, case data processing and disease prediction, medical image analysis, medical condition assessment and visual display. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The present invention will be further described below in conjunction with the accompanying drawings.

[0046] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] See also Figure 1 As shown, the present invention is a medical comprehensive management cloud platform based on blockchain technology, including: a medical data acquisition module, a medical data storage module, a medical data processing module, and the medical data processing module is provided with a patient case analysis unit, a patient image analysis unit, a patient medicine analysis unit and a display terminal.

[0049] The medical data collection module is used to collect medical data from various source systems and to uniformly collect and standardize medical data from different source systems and in different formats. The specific analysis process is as follows:

[0050] 2-1. Data interface and integration: Establish data interfaces with various data sources. The data interfaces can adopt standardized data formats and transmission protocols. Data in different formats can be converted through data conversion tools or custom scripts, thereby integrating them into a unified data set.

[0051] 2-2. Data cleaning and preprocessing: The collected data is cleaned and preprocessed through data cleaning algorithms and rules, and the data cleaning algorithms and rules include removing duplicate data, correcting erroneous data, and filling missing data;

[0052] 2-3. Data standardization and coding: standardize and code data from different sources, specifically, code diagnosis, surgery, and drug information;

[0053] 2-4. Data quality control: By setting data rules and algorithms, we can filter out data that meets the requirements, and perform error correction and supplementation, that is, complete data quality control during the data collection process. Data quality control includes data verification, logic checking, and outlier processing;

[0054] 2-5. Data security and privacy protection: In the process of data collection and processing, encryption transmission, access control, and data desensitization technologies are used to protect the security and privacy of data and ensure that sensitive information is not accessed and used without authorization;

[0055] In specific cases, the above methods and technologies can achieve unified collection and standard processing of data from different sources and formats, providing a reliable data foundation for subsequent data analysis and application. At the same time, it is necessary to cooperate with the providers of various data sources to ensure timely update and accuracy of data;

[0056] It should also be noted that medical institutions are one of the largest sources of medical data, including hospitals, clinics, and health centers. The medical data collected from medical institutions include electronic medical records, diagnostic information, examination reports, prescription information, and treatment records. These data are usually stored in the database or system of medical institutions in a structured or unstructured form. Through the medical data collection module, these data are uniformly collected and converted into a standardized format to facilitate subsequent data processing and analysis. For example, an electronic medical record data, after data cleaning, format conversion and other steps, is converted into a standardized format to facilitate subsequent disease classification, diagnosis and analysis and other applications.

[0057] Patients are another important source of medical data. The data reported by patients include health status, medical history, medication, and living habits. These data are usually collected through online questionnaires, telephone surveys, mobile applications, etc. Through the medical data collection module, these data are uniformly collected and converted into a standardized format to facilitate subsequent data processing and analysis. For example, the patient health data collected through a mobile application is converted into a standardized format after data cleaning, format conversion and other steps, which is convenient for subsequent health status analysis, disease prediction and other applications.

[0058] Drug suppliers are another source system of medical data, including drug manufacturers and wholesalers. The medical data collected from drug suppliers mainly includes drug information, sales records, and inventory management. These data are usually stored in the database or system of drug suppliers in a structured or unstructured form. Through the medical data collection module, these data are uniformly collected and converted into a standardized format to facilitate subsequent data processing and analysis. For example, a drug sales record data may need to go through data cleaning, format conversion and other steps to convert it into a standardized format to facilitate subsequent drug sales trend analysis, inventory management and other applications.

[0059] In summary, the transformation of medical data is mainly achieved through the medical data collection module, which includes two main steps: unified collection and standardized processing. In this way, the accuracy and reliability of the data can be ensured, providing a basis for subsequent medical management and services.

[0060] The medical data storage module is used to store the collected medical data in a distributed manner. The specific method is as follows:

[0061] 3-1. Data segmentation: Medical data is segmented according to certain rules to obtain several shards. When the medical data is segmented according to certain rules, it can be determined according to the characteristics and access patterns of the data, such as by patient ID, time range, and medical institution;

[0062] 3-2. Node selection: Each shard is treated as an independent storage unit and stored on one or more nodes. Appropriate nodes can be selected to store the sharded data according to the distributed storage architecture. The selection is usually made based on factors such as node load, availability, and network latency to achieve load balancing and fault tolerance.

[0063] 3-3. Data copy: Create multiple copies of important data and store each copy on a different node. The purpose is to obtain backup data from other nodes when a node fails to ensure data availability. The number of data copies and the replication strategy can be determined based on system requirements and available resources;

[0064] 3-4. Data consistency: Set up a distributed consistency protocol to ensure that data remains consistent on different nodes. The data consistency protocol can ensure data reliability and credibility, and improve the maintainability and scalability of the system.

[0065] 3-5. Data access: When accessing data, the node where the distributed stored data is located is located through hash algorithms or shard indexes, and data is read and written.

[0066] 3-6. Data redundancy storage: Redundant copies are kept for important data and stored on different nodes. This allows for quick switching to other nodes when a node fails, ensuring data availability and service continuity. Data redundancy storage can improve the system's fault tolerance and reduce fault recovery time.

[0067] In specific cases, the above methods can realize the distributed storage of medical data and improve the reliability and availability of data. At the same time, this storage method can also improve the scalability and fault tolerance of data and adapt to the storage and processing needs of large-scale data. In practical applications, appropriate distributed storage solutions can be selected according to specific needs, and optimized and adjusted.

[0068] The medical data processing module is provided with a patient case analysis unit, a patient image analysis unit, and a patient medicine analysis unit. The patient case analysis unit is based on medical data and extracts the patient's electronic medical record from it, thereby processing the case data. The specific analysis process is as follows:

[0069] Based on the processed medical data, the electronic medical record data of the patient is retrieved from the medical data, and the disease type, symptom severity, and treatment cycle of the patient are extracted from the electronic medical record data to form a medical record data table of the patient, and the medical record data table of the patient is visually displayed through a display terminal;

[0070] Extracting characteristic parameters related to the patient's condition from the electronic medical record data, wherein the characteristic parameters related to the patient's condition include a medical history index, a surgical index, and a symptom index;

[0071] Among them, the medical history index is used to express the comprehensive feedback of the medical history level of the patient's family medical history and the medical history level of the patient's past medical history. If the medical history level of the patient's family medical history is A1, and the medical history level of the patient's past medical history is A2, then the patient's medical history index is: bs=(A1×q1+A2×q2) / 2, where q1 and q2 are weight factors respectively;

[0072] The surgical index is used to indicate the comprehensive feedback of the risk level of all surgeries performed on the patient in a unit time. When evaluating the risk level of the surgery corresponding to the patient, the risk level of the surgery is generally fed back by the length of the surgery. The risk level of all surgeries performed on the patient in a unit time is recorded as FX. i, According to the formula , thereby calculating the surgical index szl corresponding to the patient;

[0073] The symptom index is used to represent the data value of the number of symptom types that the patient has in the current period, where headache, fever, cough, vomiting, etc. are all represented as symptom types;

[0074] The values ​​of the medical history index, surgical index and symptom index in the characteristic parameters related to the patient's condition are extracted and calculated and analyzed. According to the formula JZB=k1×bs+k2×szl+k3×zzl, the patient's disease prediction coefficient JZB is calculated, where zzl represents the symptom index, and k1, k2, and k3 represent weight factors respectively;

[0075] The patient's disease prediction coefficient is matched with the disease diagnosis prediction judgment level corresponding to the disease prediction coefficient, thereby obtaining the disease diagnosis prediction judgment level corresponding to the patient, and the patient's disease diagnosis prediction judgment level is visualized through a display terminal.

[0076] The patient image analysis unit extracts the patient's medical image data based on the medical data and performs image lesion analysis. The specific analysis process is as follows:

[0077] The medical imaging data of the patient is retrieved from the medical data, and the lesion characteristics and lesion degree of the patient are extracted from the medical imaging data, and they are marked as bz and bc respectively, and the two data are normalized and analyzed, and the patient's imaging evaluation coefficient Iac is obtained according to the formula Iac=a1×bz+a2×bc, where a1 and a2 are respectively represented as normalization factors;

[0078] The patient's image assessment coefficient is matched with the lesion conclusion report corresponding to the image assessment coefficient, thereby obtaining the image lesion conclusion report corresponding to the patient, and the patient's lesion conclusion report is visualized through a display terminal.

[0079] The patient medical analysis unit extracts the patient's medical data from the medical data and performs medical condition evaluation and analysis. The specific analysis process is as follows:

[0080] Retrieving the patient's medical data from the medical data, and extracting the patient's drug type, dosage, and usage method from the medical data, matching the patient's drug type with the drug diagnosis and treatment level corresponding to the drug type, thereby obtaining the patient's drug diagnosis and treatment level, and performing a comprehensive average calculation of the drug diagnosis and treatment levels corresponding to all drug types of the patient, thereby obtaining the patient's drug index, which is recorded as yz;

[0081] Based on the drug type, the usage mode of the corresponding drug type is obtained, where the usage mode includes the number of times of use and the usage cycle, which are marked as sc and zq respectively, and the two data are normalized and analyzed. According to the formula sz=a3×sc+a4×zq, the usage index sz of the patient's corresponding drug type is calculated, where a3 and a4 are respectively represented as normalization factors;

[0082] Extract the values ​​of the drug index, dosage and usage index corresponding to the patient, and substitute them into the preset data model for calculation and analysis. According to the set data model zl=b1×yz+b2×yl+b3×sz, the patient's medical diagnosis and treatment evaluation coefficient zl is output, where yl represents the dosage corresponding to the patient, b1, b2, and b3 represent weight factors respectively. The patient's medical evaluation coefficient and the diagnosis and treatment status conclusion report corresponding to the medical evaluation coefficient are compared to output the patient's diagnosis and treatment status conclusion report, and the patient's diagnosis and treatment status conclusion report is visualized through the display terminal;

[0083] The display terminal is used to display and explain the medical record data table corresponding to the patient, the disease diagnosis prediction judgment level, the image lesion conclusion report and the diagnosis and treatment status conclusion report.

[0084] The present invention improves the management efficiency and accuracy of data by uniformly collecting and standardizing medical data from different source systems and formats. At the same time, the distributed storage technology is used to store medical data on multiple nodes, which enhances the security and reliability of the data. In addition, by deeply analyzing and mining the patient's electronic medical records, medical images and pharmaceutical data, useful information such as the patient's medical record data table, disease diagnosis prediction and judgment level, image lesion conclusion report and diagnosis and treatment status conclusion report are obtained, and visualized through the display terminal. This helps doctors quickly understand the patient's condition, formulate a more scientific and effective diagnosis and treatment plan, and improve the efficiency and accuracy of diagnosis and treatment.

[0085] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. A medical integrated management cloud platform based on blockchain technology, characterized by: include: The medical data collection module is used to collect medical data from various source systems and uniformly collect and standardize medical data from different source systems and in different formats, thereby completing the unified collection of medical data. The various source systems include medical institutions, patients, and drug suppliers; uniformly collect and standardize medical data from different source systems and in different formats. The specific analysis process is as follows: 2-1. Data interface and integration: Establish data interfaces with various data sources. The data interfaces adopt standardized data formats and transmission protocols. Data in different formats are converted through data conversion tools or custom scripts, thereby integrating them into a unified data set. 2-2. Data cleaning and preprocessing: The collected data is cleaned and preprocessed through data cleaning algorithms and rules, and the data cleaning algorithms and rules include removing duplicate data, correcting erroneous data, and filling missing data; 2-3. Data standardization and coding: standardize and code data from different sources, specifically, code diagnosis, surgery, and drug information; 2-4. Data quality control: By setting data rules and algorithms, we can filter out data that meets the requirements, and perform error correction and supplementation, that is, complete data quality control during the data collection process. Data quality control includes data verification, logic checking, and outlier processing; 2-5. Data security and privacy protection: In the process of data collection and processing, encryption transmission, access control, and data desensitization technologies are used to protect the security and privacy of data and ensure that sensitive information is not accessed and used without authorization; The medical data storage module is used to perform distributed storage of the collected medical data, thereby distributing the medical data on multiple nodes; the specific method is: 3-1. Data segmentation: Medical data is segmented according to certain rules to obtain several shards. When the medical data is segmented according to certain rules, it is determined according to the characteristics and access patterns of the data, and is divided according to patient ID, time range, and medical institution; 3-2. Node selection: Each shard is treated as an independent storage unit and stored on one or more nodes. Appropriate nodes are selected to store the sharded data according to the distributed storage architecture. The selection is usually also made based on the node load, availability, and network latency factors to achieve load balancing and fault tolerance. 3-3. Data copy: Create multiple copies of important data and store each copy on a different node. The purpose is to obtain backup data from other nodes when a node fails to ensure data availability. The number of data copies and the replication strategy are determined according to system requirements and available resources. 3-4. Data consistency: Set up a distributed consistency protocol to ensure that data remains consistent on different nodes. The data consistency protocol ensures data reliability and credibility, and improves system maintainability and scalability. 3-5. Data access: When accessing data, the node where the distributed stored data is located is located through hash algorithm or shard index method, and the data is read and written; 3-6. Data redundancy storage: Reserve redundant copies for important data and store them on different nodes. In this way, when a node fails, it can quickly switch to other nodes to ensure data availability and service continuity. The medical data processing module is provided with a patient case analysis unit, a patient image analysis unit, and a patient medicine analysis unit, wherein the patient case analysis unit is based on the medical data and extracts the patient's electronic medical record therefrom, thereby processing the case data to obtain the medical record data table and disease diagnosis prediction and determination level corresponding to the patient; the patient image analysis unit is based on the medical data and extracts the patient's medical image data therefrom, thereby performing image lesion analysis to obtain the image lesion conclusion report corresponding to the patient; the patient medicine analysis unit is based on the medical data and extracts the patient's medical data therefrom, thereby performing medical condition assessment analysis to obtain the patient's corresponding diagnosis and treatment status conclusion report, and visually displays the patient's diagnosis and treatment status conclusion report through the display terminal; The display terminal is used to display and explain the medical record data table corresponding to the patient, the disease diagnosis prediction and judgment level, the image lesion conclusion report and the diagnosis and treatment status conclusion report; The specific analysis process of the case data processing is as follows: Based on the processed medical data, the electronic medical record data of the patient is retrieved from the medical data, and the disease type, symptom severity, and treatment cycle of the patient are extracted from the electronic medical record data to form a medical record data table of the patient, and the medical record data table of the patient is visually displayed through a display terminal; Extracting characteristic parameters related to the patient's condition from the electronic medical record data, wherein the characteristic parameters related to the patient's condition include a medical history index, a surgical index, and a symptom index; Among them, the medical history index is used to express the comprehensive feedback of the medical history level of the patient's family medical history and the medical history level of the patient's past medical history. If the medical history level of the patient's family medical history is A1, and the medical history level of the patient's past medical history is A2, then the patient's medical history index is: bs=(A1×q1+A2×q2) / 2, where q1 and q2 are weight factors respectively; The surgical index is used to indicate the comprehensive feedback of the risk level of all surgeries performed on the patient in a unit time. When evaluating the risk level of the surgery corresponding to the patient, the risk level of the surgery is generally fed back by the length of the surgery. The risk level of all surgeries performed on the patient in a unit time is recorded as FX. i , according to the formula , thereby calculating the surgical index szl corresponding to the patient; The symptom index is used to represent the data value of the number of symptom types that the patient has in the current period, where headache, fever, cough, and vomiting are all represented as symptom types; The values ​​of the medical history index, surgical index and symptom index in the characteristic parameters related to the patient's condition are extracted and calculated and analyzed. According to the formula JZB=k1×bs+k2×szl+k3×zzl, the patient's disease prediction coefficient JZB is calculated, where zzl represents the symptom index, and k1, k2, and k3 represent weight factors respectively; Matching the patient's disease prediction coefficient with the disease diagnosis prediction judgment level corresponding to the disease prediction coefficient, thereby obtaining the disease diagnosis prediction judgment level corresponding to the patient, and visually displaying the patient's disease diagnosis prediction judgment level through a display terminal; The specific analysis process of the image lesion analysis is as follows: The medical imaging data of the patient is retrieved from the medical data, and the lesion characteristics and lesion degree of the patient are extracted from the medical imaging data, and they are marked as bz and bc respectively, and the two data are normalized and analyzed, and the patient's imaging evaluation coefficient Iac is obtained according to the formula Iac=a1×bz+a2×bc, where a1 and a2 are respectively represented as normalization factors; Matching the patient's image assessment coefficient with the lesion conclusion report corresponding to the image assessment coefficient, thereby obtaining the image lesion conclusion report corresponding to the patient, and visually displaying the patient's lesion conclusion report through a display terminal; The specific analysis process of the medical condition evaluation and analysis is as follows: Retrieving the patient's medical data from the medical data, and extracting the patient's drug type, dosage, and usage method from the medical data, matching the patient's drug type with the drug diagnosis and treatment level corresponding to the drug type, thereby obtaining the patient's drug diagnosis and treatment level, and performing a comprehensive average calculation of the drug diagnosis and treatment levels corresponding to all drug types of the patient, thereby obtaining the patient's drug index, which is recorded as yz; Based on the drug type, the usage mode of the corresponding drug type is obtained, where the usage mode includes the number of times of use and the usage cycle, which are marked as sc and zq respectively, and the two data are normalized and analyzed. According to the formula sz=a3×sc+a4×zq, the usage index sz of the patient's corresponding drug type is calculated, where a3 and a4 are respectively represented as normalization factors; The values ​​of the drug index, dosage and usage index corresponding to the patient are extracted, and substituted into the preset data model for calculation and analysis. According to the set data model zl=b1×yz+b2×yl+b3×sz, the patient's medical diagnosis and treatment evaluation coefficient zl is output, wherein yl represents the dosage corresponding to the patient, b1, b2, and b3 represent weight factors respectively, and the patient's medical evaluation coefficient is compared with the diagnosis and treatment status conclusion report corresponding to the medical evaluation coefficient, thereby outputting the patient's diagnosis and treatment status conclusion report, and visually displaying the patient's diagnosis and treatment status conclusion report through the display terminal.