Multi-center medical equipment big data cloud platform based on cloud-side-end architecture

Abstract

The invention provides a multi-center medical equipment big data cloud platform based on a cloud-edge-end architecture. The multi-center medical equipment big data cloud platform comprises a cloud computing layer, an edge computing layer and a terminal equipment layer, the cloud computing layer comprises a data storage and management module, a data analysis and machine learning module and a data sharing and interaction module; the edge computing layer comprises a plurality of edge computing devices, and the edge computing devices are located in a hospital and are in communication connection with the cloud computing layer; the terminal equipment layer comprises a plurality of terminal equipment, the terminal equipment comprises medical detection equipment, intelligent diagnosis and treatment equipment and wearable equipment, and the terminal equipment is in communication connection with at least one edge computing equipment. The cloud-edge-end architecture has good expansibility, computing nodes or storage resources can be dynamically increased according to requirements, the cloud-edge-end architecture adapts to continuously increasing medical data volume, and sustainable development and efficient operation of the platform are guaranteed.

Description

Technical Field

[0001] The present invention belongs to the field of digital platforms, and specifically relates to a multi-center medical equipment big data cloud platform based on a cloud-edge-end architecture. Background Art

[0002] With the rapid development of modern medical equipment, medical data, especially the massive data from a variety of testing and diagnosis equipment, has shown explosive growth. Especially in the real-time processing and analysis of multi-dimensional data such as imaging data, patient vital signs, and diagnostic reports, traditional medical data management systems have gradually exposed problems such as high transmission delay, insufficient computing resources, and complex data storage and management when facing the scale of big data. Although traditional centralized cloud computing provides powerful computing power and large-scale data storage capabilities, it is limited by network conditions and bandwidth in terms of data transmission and real-time response. Especially when sharing data and remote diagnosis between multi-center medical institutions, data transmission delays will seriously affect the efficiency of diagnosis and treatment and the timeliness of patient care, and due to the limited terminal processing capabilities, it also faces information security issues. Summary of the invention

[0003] In order to solve the problems in the prior art, the present invention provides a multi-center medical equipment big data cloud platform based on a cloud-edge-end architecture, including a cloud computing layer, an edge computing layer, and a terminal device layer; The cloud computing layer includes: data storage and management module, data analysis and machine learning module, data sharing and interaction module; The edge computing layer includes a plurality of edge computing devices, which are located in the hospital and are communicatively connected to the cloud computing layer; Each of the edge computing devices includes: a real-time data processing module, a data filtering and preprocessing module, and a privacy protection and data security module; The terminal device layer includes multiple terminal devices, including medical detection equipment, intelligent diagnosis and treatment equipment, and wearable devices. The terminal devices are communicatively connected to at least one edge computing device.

[0004] The present invention can produce the following beneficial effects through the above technical solution: The medical data collected by the terminal devices are preliminarily processed, screened and compressed through edge computing devices, which reduces the volume of original data transmission, alleviates the burden of cloud computing, improves the real-time and efficiency of data processing, and significantly reduces transmission delays, especially in large-scale imaging data processing scenarios.

[0005] Edge devices can perform certain computing tasks locally, such as feature extraction and data filtering, to ensure low-latency processing of medical data. For medical applications that require rapid response, such as vital sign monitoring, edge computing can provide instant feedback, greatly improving diagnosis and treatment efficiency.

[0006] By performing data peaking, throttling, and intelligent screening at the edge computing layer, the amount of irrelevant or redundant data transmission is reduced. Especially in the case of poor network conditions, edge computing devices can further optimize bandwidth utilization through batch transmission and priority transmission strategies to ensure priority transmission of critical data.

[0007] By performing data encryption, anonymization, and privacy enhancement processing on edge devices, the security of patients' sensitive data during transmission and storage is ensured. At the same time, the application of differential privacy technology further enhances data privacy protection and reduces the risk of data leakage.

[0008] The powerful computing and storage capabilities of the cloud support data integration and sharing among multi-center medical institutions, provide a unified medical data platform, promote collaborative diagnosis and data sharing among medical institutions, and improve the utilization efficiency of medical resources.

[0009] Through cloud-based machine learning and artificial intelligence algorithms, the platform can conduct in-depth analysis of medical data, provide personalized diagnosis and treatment recommendations, disease predictions, and clinical decision support, and improve the accuracy of diagnosis and treatment outcomes.

[0010] The cloud-edge-end architecture has good scalability and can dynamically add computing nodes or storage resources according to demand, adapt to the growing amount of medical data, and ensure the sustainable development and efficient operation of the platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0012] Figure 1 It is a schematic diagram of the structure of the present invention. DETAILED DESCRIPTION

[0013] Below, the invention is preferably described in conjunction with the accompanying drawings and specific implementation methods.

[0014] This embodiment solves the above problem through the following steps: In one embodiment, reference Figure 1The present invention provides a multi-center medical device big data cloud platform based on a cloud-edge-end architecture, which aims to achieve efficient collection, real-time processing, secure storage and intelligent analysis of data from various medical devices through the collaborative work of cloud computing, edge computing and end devices.

[0015] The platform includes a cloud computing layer, an edge computing layer, and a terminal device layer.

[0016] In the present invention, the cloud computing layer refers to a data processing and storage center deployed in the cloud, which has large-scale data storage capabilities and high-performance computing capabilities. The cloud computing layer is used to receive processed data from the edge computing layer and the terminal device layer, and further perform in-depth data analysis, long-term storage, and cross-center data sharing. Through the cloud computing layer, multi-device data from different medical centers can be integrated, analyzed, and mined to provide intelligent diagnosis support and medical decision-making recommendations based on big data.

[0017] The edge computing layer refers to computing nodes deployed near medical devices, which are responsible for preliminary processing and analysis of data collected by terminal devices. The edge computing layer reduces the load of the cloud computing layer through local processing capabilities, while ensuring low-latency transmission and real-time response of key medical data. The edge computing layer can pre-process high-frequency data, such as patient vital signs data, filter irrelevant data and pass valuable information to the cloud computing layer, thereby reducing bandwidth usage.

[0018] The terminal device layer refers to medical equipment that is in direct contact with patients or located in medical facilities, and is used to collect patients' physiological data or provide medical services. The terminal device layer includes various medical monitoring devices, diagnostic devices, or wearable devices, such as electrocardiographs, blood oxygen monitors, smart bracelets, etc. The terminal device layer is connected to the edge computing layer through built-in or external communication modules to upload and process the collected medical data in real time. The cloud computing layer includes: a data storage and management module, a data analysis and machine learning module, and a data sharing and interaction module.

[0019] The data storage and management module is used to save data collected from different devices and terminals through a distributed storage system; this module is used to save data collected from different devices and terminals through a distributed storage system, ensure the safe and stable storage of large-scale medical data, and have efficient data retrieval and management capabilities. The data storage and management module can store medical data in various formats, including but not limited to patient vital signs data, imaging data, diagnostic records and related medical reports.

[0020] Specifically, the data storage and management module adopts a storage solution based on the Hadoop Distributed File System (HDFS). HDFS has the characteristics of distributed storage and data redundancy. It divides medical data into multiple data blocks and stores them on different storage nodes, thereby achieving data reliability and high availability. In this solution, each data block is stored in multiple copies to meet the data recovery needs when a single node fails. At the same time, HDFS supports parallel processing of large-scale data, which can improve the storage and access efficiency of massive medical data.

[0021] In addition, the data storage and management module also includes a management solution based on a NoSQL database, such as using Cassandra or MongoDB for fast data access and retrieval. NoSQL databases have high scalability and flexible data model design, and are suitable for storing medical data in heterogeneous formats, especially for high-concurrency access scenarios, ensuring efficient data access in a multi-center medical device environment.

[0022] The data analysis and machine learning module is used to use cloud computing resources to analyze medical data through machine learning technology to support clinical decision-making and medical research. This module uses high-performance computing resources in the cloud to analyze and process medical data by applying advanced machine learning algorithms, aiming to provide support for clinical decision-making and medical research. The data analysis and machine learning module can extract features from a variety of medical data uploaded by terminal devices and edge computing layers, identify trends, predict disease risks, and generate personalized diagnosis and treatment recommendations.

[0023] Specifically, the data analysis and machine learning module adopts a solution based on the Apache Spark distributed computing framework. This solution uses Spark's parallel processing capabilities to perform distributed analysis on large-scale medical data, and is particularly suitable for processing high-dimensional medical imaging data, time series data, and structured and unstructured medical record data. The MLlib machine learning library in Spark can be used to train and deploy machine learning models, including linear regression, decision trees, random forests, support vector machines (SVM) and other algorithms, to help predict patient health conditions, classify diseases, and evaluate treatment effects.

[0024] In practical applications, the module generates personalized disease prediction models by training a large amount of historical medical data. For example, the LSTM (Long Short-Term Memory Network) model based on time series data can be used to predict cardiovascular diseases. By analyzing the patient's continuous electrocardiogram data, abnormal heart rhythms can be predicted in real time and warnings can be issued in advance. In addition, the module can also provide doctors with recommended diagnosis and treatment plans based on patient data to improve the accuracy and efficiency of medical services.

[0025] Data sharing and interaction module, used to transmit analysis results and / or processed data back to the edge or terminal device. This module is used to transmit cloud analysis results and / or processed data back to the edge computing layer or terminal device to ensure the real-time and effective use of medical data, and support data interaction and collaboration between multi-center medical institutions. Through this module, medical equipment and medical personnel can obtain the diagnosis results, medical advice and related data support of cloud analysis in a timely manner, improving the efficiency and accuracy of diagnosis and treatment.

[0026] Specifically, the data sharing and interaction module adopts a solution based on RESTful API (Representational State Transfer). Through RESTful API, edge computing nodes or terminal devices can request data from the cloud in a standardized way, and the cloud server returns the analysis results or processed data to the requester in a structured format (such as JSON or XML) according to the request. This solution has high compatibility and flexibility and is suitable for cross-platform data transmission between different devices.

[0027] In addition, the data sharing and interaction module further integrates message queue technology (such as Apache Kafka) to ensure the real-time and stability of data transmission. Kafka can handle large-scale message streams, support concurrent data requests and feedback between multi-center medical institutions, and ensure that the analysis results are synchronously transmitted between multiple devices in different medical centers. Through this module, edge devices can receive the analysis results returned from the cloud in the first time, perform necessary local processing or present them to doctors, and support medical scenarios such as remote monitoring and real-time diagnosis.

[0028] The edge computing layer includes a plurality of edge computing devices, which are located in the hospital and are in communication connection with the cloud computing layer. Each edge computing device includes: a real-time data processing module, a data filtering and preprocessing module, and a privacy protection and data security module.

[0029] Each edge computing device is located in a hospital or medical institution and is connected to the cloud computing layer through a communication network. Each edge computing device includes the following modules: The real-time data processing module is used to receive and process real-time medical data from terminal devices to ensure that the data is quickly responded to and preliminarily processed locally. This module can process continuous streaming data such as electrocardiograms, blood pressure monitoring, and imaging data in real time through efficient computing capabilities. Specifically, the real-time data processing module uses multi-threaded parallel processing technology, combined with hardware accelerators (such as GPUs or FPGAs) to ensure rapid processing of large-scale data, and uses stream processing frameworks (such as Apache Flink or Storm) to achieve efficient processing and analysis of time-sensitive medical data.

[0030] The data filtering and preprocessing module is used to filter, clean and format the collected raw medical data to reduce the transmission of irrelevant or redundant data to the cloud. This module optimizes data transmission efficiency by formatting and compressing data, and removes noise data and redundant information through local algorithms. The specific implementation method includes a filtering mechanism based on a rule engine to automatically identify data that is not related to medical analysis, such as repeated measurement results, noise interference signals, etc., to ensure that the cloud only receives filtered valid data. At the same time, the data preprocessing module uses edge machine learning models to perform preliminary data analysis and feature extraction, reduce the dimension of the data, and improve transmission and processing efficiency.

[0031] The privacy protection and data security module is used to protect patient medical data from being leaked during processing and transmission of edge computing devices, ensuring data security and compliance. This module can encrypt data and perform data anonymization and privacy enhancement operations locally. The specific implementation methods include using the Advanced Encryption Standard (AES-256) to encrypt, store and transmit all sensitive data, and using data access control mechanisms (such as role-based access control, RBAC) to limit access rights to data. In addition, the privacy protection module integrates a differential privacy algorithm to fuzzy sensitive data during data processing, ensuring that sensitive data is still effectively protected even if the edge device is hacked.

[0032] Through the integration of the above modules, edge computing devices can effectively process medical data locally while ensuring data security and privacy protection, providing high-quality pre-processed data for further analysis before transmission to the cloud computing layer.

[0033] Through the integration of the above modules, edge computing devices can effectively process medical data locally while ensuring data security and privacy protection, providing high-quality pre-processed data for further analysis before transmission to the cloud computing layer.

[0034] The imaging data generated by medical equipment is very large and time-consuming to transmit. Furthermore, the data preprocessing module applies edge machine learning models to perform preliminary data analysis and feature extraction, reduce the dimension of the data, and improve transmission and processing efficiency. Specifically, it includes: Perform preliminary processing of the model on the edge device, including convolution operations of the first few layers (such as edge detection of image data, low-level feature extraction, etc.). Although the calculation of the convolution layer is complex, for images or other sensor data, the intermediate results it produces are smaller than the original data and are suitable for edge computing.

[0035] The edge device uploads the intermediate results to the cloud, which completes the deep feature extraction and final classification or regression tasks. The cloud has sufficient computing resources and can handle more complex model calculations.

[0036] The model is segmented based on the number of convolutional layers or network depth. For example, the first few convolutional blocks of ResNet are placed on the edge device to extract preliminary features, and the subsequent deep convolution and fully connected layers are left to the cloud for execution.

[0037] To further optimize processing performance on edge devices, it may be necessary to use model compression techniques (such as quantization, pruning, or distillation) to reduce the amount of computation and model size to adapt them to the processing capabilities of edge devices.

[0038] After receiving input data (such as medical images), the edge device first performs the first few layers of the model to convert the data into intermediate feature representations. This process can include the following steps: The image data undergoes preprocessing operations such as standardization, noise reduction or image enhancement to make it meet the input requirements of the model.

[0039] The processed image or signal data is used as the input of the model and enters the initial convolution layer of the model.

[0040] The edge device performs the first few layers of convolution operations of the model, such as edge detection, contour extraction, color distribution analysis, etc., to extract low-level features. Through the convolution layer and pooling layer, the raw data is converted into a more concise feature representation to reduce the data volume.

[0041] For example, in medical image processing, several layers of convolution can be performed on MRI or CT images to extract the main shape and texture features and map these features into a smaller amount of data.

[0042] Intermediate features are usually much smaller than the original data, making them easier to transmit. The amount of data transmitted can be further compressed using feature compression algorithms (such as sparse processing and low-dimensional embedding).

[0043] The intermediate results obtained by feature extraction on the edge device can be transmitted to the cloud through the network. In order to reduce transmission delay and bandwidth usage, the following measures can be adopted: Use efficient transmission protocols, such as gRPC or HTTP / 2, to reduce transmission overhead, and use streaming technology to upload a portion of features immediately after calculation to reduce waiting time.

[0044] Compress intermediate results, for example, using efficient data serialization formats such as Protobuf or Avro.

[0045] Design the transmission priority according to the importance of the data and the network conditions. For example, the edge device can upload the features of the key lesion area first, and the features of other non-critical parts can be uploaded later.

[0046] Implement incremental transmission: If the changes between some image frames are small, only the changed parts or incremental features are uploaded.

[0047] After receiving the intermediate feature representation from the edge device, the cloud continues to execute the subsequent parts of the model. Typically, this includes more complex feature extraction, fully connected layer operations, and final classification or regression analysis.

[0048] The cloud uses powerful computing resources to execute the remaining deep convolutional layers, fully connected layers, and other complex operations to generate the final classification results or prediction values.

[0049] For example, in medical image analysis, the cloud can further analyze the details of the image (such as the specific characteristics of the tumor) based on the features extracted by the edge device and generate the final diagnosis results.

[0050] After the cloud analysis is completed, the final results are returned to the edge device or other terminal device for use by doctors or medical staff.

[0051] The cloud can also save the analysis results and share them with other medical centers or related devices for further collaboration and diagnosis.

[0052] In practical applications, the network between edge devices and the cloud may be unstable, and a fault-tolerant mechanism needs to be designed to ensure the robustness of the system and the reliability of data transmission.

[0053] When the network is interrupted or the latency is too high, the edge device should have a certain amount of local processing power to perform more layers of model reasoning in temporary situations to ensure the most basic diagnostic capabilities. Then, when the network is restored, the data can be synchronized to the cloud.

[0054] By dynamically adjusting the number of model layers allocated between edge devices and the cloud, the computing location can be flexibly switched according to the real-time network status, edge device computing power, and the urgency of the task. For example, when the network is poor, the edge device can take on a few more layers of reasoning to reduce the amount of data transmitted.

[0055] Distributed reasoning of cloud-edge models distributes the computing tasks of deep learning models between the edge and the cloud, which can reduce the pressure of data transmission and make full use of the computing resources of the edge and the cloud. The edge device is responsible for preliminary feature extraction, and the cloud performs complex reasoning and analysis, thereby reducing dependence on network transmission while maintaining efficient processing. This method is particularly suitable for real-time processing of large-scale medical data, such as image analysis, patient monitoring and other scenarios.

[0056] The terminal device layer includes multiple terminal devices, including medical detection equipment, intelligent diagnosis and treatment equipment, and wearable devices. The terminal devices are communicatively connected to at least one edge computing device.

[0057] Medical testing equipment refers to professional equipment used to collect physiological data of patients, including but not limited to electrocardiographs, blood pressure monitors, blood oxygen saturation detectors, etc., which can provide high-precision vital signs data. Each medical testing equipment includes the following modules: Data acquisition module, which integrates multiple sensors to collect patients' physiological signals in real time, such as ECG signals, blood pressure, blood oxygen saturation, etc. Specific implementation methods include electrode sensors (for ECG monitoring), optical sensors (for measuring blood oxygen saturation), air pressure sensors (for monitoring blood pressure), etc. These sensors continuously monitor patients' health data with high precision and high frequency to ensure the accuracy of medical data.

[0058] The data transmission module is used to transmit the collected medical data to the edge computing device. The module has multiple communication methods, such as wired connection (such as Ethernet) or wireless communication (such as Wi-Fi, Bluetooth, ZigBee), to ensure data reliability and low latency. The data transmission module also has the function of automatically selecting the optimal communication protocol to ensure the stability of data transmission, especially in hospital environments with complex network conditions.

[0059] The local data storage module is used to temporarily store data when data transmission is limited or the device network is interrupted to ensure that medical data is not lost. The module backs up data through flash memory until the network is restored and the connection with the edge computing device is reestablished. At the same time, the local storage module regularly cleans up old data to ensure the continuous operation of the device.

[0060] Intelligent diagnosis and treatment equipment refers to equipment with diagnostic and treatment functions, including but not limited to remote ultrasound machines, intelligent diagnosis and treatment robots, portable CT scanners, etc., which can perform intelligent diagnosis and treatment tasks by combining data analysis and machine learning technology. Each intelligent diagnosis and treatment equipment includes the following modules: Intelligent diagnosis module, which integrates intelligent algorithms for preliminary analysis and diagnosis of collected medical data. For example, remote ultrasound equipment can use image processing algorithms based on convolutional neural networks (CNN) to automatically identify and mark abnormal areas in ultrasound images; while portable CT scanners can use deep learning models to quickly classify scanned images and generate preliminary diagnosis results. The intelligent diagnosis module can provide doctors with instant feedback and improve diagnostic efficiency.

[0061] Treatment feedback module, which is used to perform treatment operations or intervention measures after diagnosis. Specifically, the intelligent diagnosis and treatment robot can accurately implement treatment operations such as minimally invasive surgery and drug injection based on the diagnosis results through the robotic arm and control system. This module ensures the accuracy and safety of the treatment process through real-time data monitoring and feedback mechanisms, and uploads treatment data to the edge computing device in real time through the data transmission module.

[0062] Data sharing module, through which intelligent diagnosis and treatment equipment shares diagnosis data and treatment results with edge computing devices and other medical devices. Specific implementation methods include interfaces based on RESTful APIs, or the use of message queue technology (such as Apache Kafka) to ensure real-time data synchronization and interaction between multiple devices, thereby supporting remote diagnosis and treatment and multi-center collaboration.

[0063] Wearable devices refer to portable devices used to continuously monitor the health status of patients, such as smart bracelets, smart watches, portable ECG monitors, etc. These devices are portable and low-power, suitable for patients to wear for a long time in their daily lives and monitor their health status in real time. Each wearable device includes the following modules: The sensor module is used to monitor the user's various physiological indicators in real time, such as heart rate, blood pressure, body temperature, exercise status, etc. The module integrates multiple sensors, such as accelerometers, optical heart rate sensors, and temperature sensors, to ensure that the patient's health data can be continuously collected. These sensors can automatically adjust the collection frequency according to the wearer's behavior changes, thereby extending the battery life of the device.

[0064] The data transmission module transmits data to edge computing devices through low-power wireless communication technologies such as Bluetooth Low Energy (BLE), Wi-Fi or 5G networks. Wearable devices are usually battery-powered, so this module optimizes power consumption to ensure that data transmission efficiency is maintained while extending the device usage time.

[0065] The local data storage module is used to temporarily store data when the network connection is interrupted or the device is offline, and automatically synchronize to the edge computing device after the connection is restored. This module uses embedded memory for data storage and ensures efficient use of storage space through a circular storage mechanism.

[0066] The user feedback module is used to provide the wearer with instant health information or reminders through the device's display or vibration feedback device. For example, when the heart rate is abnormal or the blood oxygen saturation is too low, the device reminds the user through vibration or sound, and uploads the data to the edge computing device so that medical staff can intervene in time.

[0067] Through the collaborative work of medical detection equipment, intelligent diagnosis and treatment equipment and wearable devices in the terminal device layer, comprehensive monitoring and intelligent diagnosis and treatment of patients can be achieved. Various types of equipment maintain communication connection with at least one edge computing device, and ensure real-time processing and transmission of data through a distributed architecture, support multi-center medical collaboration and remote medical diagnosis, thereby improving diagnosis and treatment efficiency, optimizing resource allocation, and ensuring the timeliness and security of data.

[0068] The prior art mentioned in the above background technology section and the specific embodiment section of the present invention can be regarded as a part of the present invention, and is used to understand the meaning of some technical features or parameters. The protection scope of the present invention shall be based on the actual contents of the claims.

Claims

1. A multi-center medical equipment big data cloud platform based on cloud-edge-end architecture, characterized in that: The platform includes a cloud computing layer, an edge computing layer, and a terminal device layer; The cloud computing layer includes: data storage and management module, data analysis and machine learning module, data sharing and interaction module; The edge computing layer includes a plurality of edge computing devices, which are located in the hospital and are communicatively connected to the cloud computing layer; Each of the edge computing devices includes: a real-time data processing module, a data filtering and preprocessing module, and a privacy protection and data security module; The terminal device layer includes multiple terminal devices, including medical detection equipment, intelligent diagnosis and treatment equipment, and wearable devices. The terminal devices are communicatively connected to at least one edge computing device.

2. The multi-center medical equipment big data cloud platform based on cloud-edge-end architecture according to claim 1 is characterized in that: The data storage and management module is used to save data collected from different devices and terminals through a distributed storage system.

3. The multi-center medical equipment big data cloud platform based on cloud-edge-end architecture according to claim 1 is characterized in that: The data analysis and machine learning module is used to utilize cloud computing resources to analyze medical data through machine learning technology to support clinical decision-making and medical research.

4. The multi-center medical equipment big data cloud platform based on cloud-edge-end architecture according to claim 1, characterized in that: The data sharing and interaction module is used to transmit the analysis results and / or processed data back to the edge or terminal device.

5. The multi-center medical equipment big data cloud platform based on cloud-edge-end architecture according to claim 1, characterized in that: The real-time data processing module is used to receive and process real-time medical data from terminal devices to ensure that the data is quickly responded to and preliminarily processed locally.

6. The multi-center medical equipment big data cloud platform based on cloud-edge-end architecture according to claim 1, characterized in that: The data filtering and preprocessing module is used to filter, clean and format the collected raw medical data to reduce the transmission of irrelevant or redundant data to the cloud.

7. The multi-center medical equipment big data cloud platform based on cloud-edge-end architecture according to claim 1, characterized in that: The privacy protection and data security modules are used to protect patient medical data from being leaked during processing and transmission of edge computing devices, ensuring data security and compliance.

8. The multi-center medical equipment big data cloud platform based on cloud-edge-end architecture according to claim 1, characterized in that: The medical testing equipment refers to professional equipment used to collect physiological data of patients.

9. The multi-center medical equipment big data cloud platform based on cloud-edge-end architecture according to claim 1, characterized in that: The intelligent diagnosis and treatment equipment refers to equipment with diagnosis and treatment functions.

10. The multi-center medical equipment big data cloud platform based on cloud-edge-end architecture according to claim 1, characterized in that: The wearable device refers to a portable device used to continuously monitor a patient's health status.

Images