New-generation medical equipment integration engine

Abstract

The invention discloses a new-generation medical equipment integration engine, which comprises an equipment data standardization module used for automatically identifying and converting various equipment data formats; the equipment data standardization module can process various medical equipment data such as HL7, DICOM and MODBUS through a built-in multi-protocol analyzer and convert the medical equipment data into a uniform standard format, so that the consistency and interoperability of the data are ensured; the real-time data processing engine module is used for collecting, transmitting and processing the data of the medical equipment in real time; the intelligent analysis and decision support module is used for performing intelligent analysis on the data from the medical equipment through deep learning and time sequence analysis technologies; a micro-service architecture design module; and a multi-level security mechanism module. The device data can be deeply analyzed and predicted, the accuracy of diagnosis and treatment decisions can be improved, early warning can be achieved, and the safety of patients is ensured.

Description

Technical Field

[0001] The present invention relates to the field of medical information technology, and in particular to a new generation of medical equipment integration engine. Background Art

[0002] Most current medical equipment integration systems rely on traditional interfaces and protocols (such as HL7, DICOM, etc.) to connect with hospital information systems (HIS). These systems are often faced with challenges such as complex data sources, diverse equipment types, and inconsistent communication standards. Hospital medical equipment such as monitors, imaging equipment, ventilators, and blood analyzers often come from different suppliers. Each device has its own independent interface and data format, making it difficult to share and integrate data between devices. In addition, existing integration systems usually rely on specific platforms and lack cross-platform capabilities, which increases maintenance costs and deployment difficulties. Summary of the invention

[0003] The purpose of the present invention is to provide a new generation of medical device integration engine to solve the above-mentioned problems existing in the prior art.

[0004] The present invention aims to solve the deficiencies of existing medical equipment integration systems in terms of standardization, real-time performance, intelligent analysis, system scalability and cross-platform support, and to design and implement a new generation of medical equipment integration engine. This engine can seamlessly integrate medical equipment data from different sources, provide real-time and intelligent data analysis and decision support, and can run across platforms, supporting multiple system environments such as Windows, Linux, ARM, etc., to ensure its wide applicability in various medical environments.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] A next-generation medical device integration engine, including:

[0007] Equipment data standardization module is used to automatically identify and convert multiple equipment data formats. Through the built-in multi-protocol parser, the equipment data standardization module can process HL7, DICOM, MODBUS and other medical equipment data and convert them into a unified standard format to ensure data consistency and interoperability.

[0008] Real-time data processing engine module, used for real-time collection, transmission and processing of data from medical equipment;

[0009] Intelligent analysis and decision support module, which uses deep learning and time series analysis technology to intelligently analyze data from medical devices;

[0010] Microservice architecture design module;

[0011] Multi-level security mechanism module: including data transmission encryption, access control, identity authentication, etc., to ensure the security and compliance of medical device data during transmission and sharing.

[0012] Preferably, the device data standardization module includes:

[0013] Protocol parsing library, used to implement data format recognition and parsing;

[0014] Data format conversion module, used to convert data in different formats into target standard formats;

[0015] The data format verification module is used to verify the converted data to ensure the integrity, consistency and accuracy of the data and prevent format errors or data loss;

[0016] Field mapping module, used to standardize the mapping of device data.

[0017] Preferably, the device data standardization module further includes:

[0018] Data storage and sharing module, which is used to store standardized data in a unified data warehouse and supports interoperability with hospital information systems and electronic medical record systems to ensure data accessibility and sharing;

[0019] Abnormal data processing and fault-tolerance mechanism module, used for abnormal data that occurs during parsing or conversion. The system should be able to automatically perform fault-tolerance processing and generate alarm logs;

[0020] System monitoring and performance optimization module, which is used to monitor the performance of data collection, analysis, conversion and other processes, ensure the efficient operation of the system, optimize the data processing process and reduce delays;

[0021] The data security and privacy protection module is used to encrypt the stored and transmitted data to ensure the security and privacy of the data during transmission.

[0022] Preferably, the real-time data processing engine module includes:

[0023] The data acquisition and streaming module obtains real-time data through device interfaces or sensors, and uses streaming data transmission technology to transmit the data to the processing engine in real time to ensure the rapid flow of data;

[0024] Data preprocessing and formatting module: During data transmission, Apache Flink is used to perform basic cleaning and formatting of raw data to ensure that the data conforms to a unified standard format for subsequent processing.

[0025] Real-time data stream analysis and processing module, which uses the real-time stream processing engine to calculate and analyze data, supports data aggregation and complex event processing operations to extract valuable information, provide early warning and decision support;

[0026] Real-time decision support and reasoning module: Provide decision support based on real-time data: Combine real-time processed data with medical knowledge base or AI model to provide real-time decision support;

[0027] Real-time data storage and query module: Store processed data in real time and support fast query: Processed data needs to be stored in real time and support efficient query to ensure that medical staff can quickly access data for decision-making when needed.

[0028] Preferably, the real-time data processing engine module also includes:

[0029] Real-time monitoring and alarm module: monitor the real-time data processing process, detect anomalies in time and issue alarms: monitor the health of data stream processing in real time, ensure the stability of data stream and processing engine, and issue alarms when failures or anomalies occur;

[0030] The data consistency and fault-tolerance processing module is used to ensure the consistency and fault-tolerance of data in multiple nodes and multiple systems: in a high-concurrency real-time data processing environment, it ensures the accuracy and consistency of data and can restore processing in the event of a system failure.

[0031] Preferably, the real-time data processing engine module also includes:

[0032] System expansion and high availability design to ensure high availability and scalability of the system under high load: Design the system architecture to support horizontal expansion to ensure that the system can still operate efficiently when the amount of data increases dramatically;

[0033] The data security and privacy protection module ensures data security and privacy protection during real-time data processing: encryption and access control measures are taken during data transmission and processing to ensure the security of sensitive data.

[0034] Preferably, the intelligent analysis and decision support module includes:

[0035] The data acquisition and preprocessing module is used to collect historical data and real-time data of medical equipment and perform preprocessing: connect with the equipment through the interface, obtain the patient's physiological data in real time, and preprocess the data;

[0036] Feature extraction and data conversion module, extracting key information from raw data: Performing feature engineering on the raw data collected by the device, extracting key physiological indicators such as heart rate, respiratory rate, and blood oxygen saturation, and converting the data to adapt to the input requirements of the AI ​​model;

[0037] AI model training and optimization: training and optimizing AI models based on historical data: using historical data to train deep learning models to learn the relationship between patient conditions and physiological indicators; optimizing the accuracy of the model and using cross-validation methods to select the optimal model;

[0038] The real-time prediction and analysis module performs instant prediction and analysis based on real-time data: inputs real-time monitoring data into the trained AI model to perform instant prediction and disease change analysis, and judges the patient's health risks based on the prediction results.

[0039] Preferably, the intelligent analysis and decision support module also includes:

[0040] Early warning and intelligent diagnosis and treatment suggestion module, which generates early warning of the disease and provides intelligent diagnosis and treatment suggestions: Based on the prediction results, the system automatically generates early warning signals of disease changes and provides intelligent diagnosis and treatment suggestions to support medical staff in making decisions at critical moments;

[0041] The personalized diagnosis and treatment plan generation module generates personalized diagnosis and treatment plans based on the patient's historical data and real-time data: using the patient's personalized information and combining it with real-time monitoring data to provide patients with personalized diagnosis and treatment plans;

[0042] Multimodal data fusion and analysis module, which integrates data from different devices and sensors for comprehensive analysis: Integrate data from different devices and combine them with other clinical data for multimodal analysis to obtain more accurate predictions and diagnosis and treatment recommendations;

[0043] Real-time feedback and optimization module, which provides feedback and optimizes the model based on actual usage: Through the feedback from medical staff and changes in the actual condition of patients, the AI ​​model is continuously adjusted and optimized to improve the accuracy of prediction;

[0044] Data security and privacy protection module ensures that medical data is protected throughout the entire process: encryption and privacy protection measures are taken during data collection, storage, processing and transmission to ensure the security of patients' personal information and medical data;

[0045] The model deployment and maintenance module deploys the trained model into a real-time environment and performs regular maintenance: deploying the AI ​​model into a production environment to ensure that it can provide real-time prediction and decision support in actual scenarios; at the same time, regularly updating and optimizing the model based on new data.

[0046] Preferably, data transmission encryption is used to ensure that medical device data will not be stolen or tampered with during transmission, and encryption technology is used to ensure the confidentiality and integrity of the data;

[0047] Access control is used to control data access rights and ensure that only authorized personnel can access sensitive information: set corresponding data access rights according to different user roles to ensure that personnel at different levels can only access data within their authorized scope;

[0048] Authentication is used to ensure the legitimacy of the identity of data accessors: Authentication is performed before data access to confirm whether the requester is an authorized user and to prevent unauthorized users from accessing sensitive data.

[0049] Preferably, the streaming data transmission technology is: Apache Kafka.

[0050] The beneficial effects of the present invention are:

[0051] The new generation of medical equipment integration engine of the present invention has the following advantages:

[0052] 1. Multi-protocol support and data standardization: The present invention can support multiple medical device communication protocols and realize unified conversion of device data through adaptive standardization modules, which greatly improves the interoperability and compatibility of device data and surpasses the reliance on a single protocol in existing systems.

[0053] 2. Real-time and high efficiency: Compared with the batch processing mode of the prior art, the present invention adopts a streaming processing engine, which can realize real-time transmission and processing of data, greatly reducing data delay and ensuring the real-time response requirements of medical equipment.

[0054] 3. Intelligent analysis capability: By integrating AI and deep learning models, the present invention can conduct in-depth analysis and prediction of device data, which can not only improve the accuracy of diagnosis and treatment decisions, but also achieve early warning to ensure patient safety.

[0055] 4. Cross-platform compatibility: The present invention supports different operating systems and hardware environments such as Windows, Linux and ARM, has a high degree of cross-platform compatibility, can adapt to the technical needs of different medical institutions, and reduces the deployment and operation and maintenance costs of the system.

[0056] 5. High scalability and flexibility: Based on the microservice architecture design, the system can be flexibly expanded. Whether it is connecting new devices or expanding new functional modules, it can be quickly adapted and deployed, with scalability that exceeds the existing integrated system. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 This is the architecture diagram of the new generation medical equipment integration engine of the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation methods described herein are only used to explain the present invention and are not used to limit the present invention.

[0059] Reference Figure 1 A new generation of medical device integration engine shown, including:

[0060] The device data standardization module is used to automatically identify and convert various device data formats; through the built-in multi-protocol parser, the device data standardization module can process HL7, DICOM, MODBUS and other medical device data, and convert them into a unified standard format to ensure data consistency and interoperability.

[0061] The real-time data processing engine module is used to collect, transmit and process the data of medical equipment in real time, which greatly reduces the delay of data transmission. Whether it is the real-time data of monitoring equipment or the real-time output of imaging equipment, the system can ensure almost no delay in response speed and ensure the timeliness of medical decision-making.

[0062] Intelligent analysis and decision support module, the present invention integrates AI models, and intelligently analyzes data from medical devices through deep learning and time series analysis technology. For example, the system can predict changes in patients' conditions, issue warnings, and provide intelligent diagnosis and treatment suggestions for medical staff based on historical data and real-time monitoring data of equipment such as ventilators and ECG monitors.

[0063] Microservice architecture design module: In order to improve the flexibility and scalability of the system, the present invention adopts a microservice architecture. Each functional module (such as data standardization, intelligent analysis, real-time processing, etc.) is independently deployed and independently scalable, allowing the system to easily access new devices or functional modules, ensuring that it has high adaptability and continuous evolution capabilities.

[0064] Cross-platform support: A significant advantage of the present invention is that it has cross-platform operation capabilities, supporting Windows, Linux and ARM architecture device environments. Through containerization (such as Docker) or virtualization-based technologies, the system can be easily deployed in different hardware and operating system environments, ensuring seamless application in various hospitals and medical institutions.

[0065] Multi-level security mechanism module: The present invention also integrates a multi-level security mechanism, including data transmission encryption, access control, identity authentication, etc., to ensure the security and compliance of medical device data during transmission and sharing.

[0066] Preferably, the device data standardization module includes:

[0067] Protocol parsing library, used to implement data format recognition and parsing;

[0068] Data format conversion module, used to convert data in different formats into target standard formats;

[0069] The data format verification module is used to verify the converted data to ensure the integrity, consistency and accuracy of the data and prevent format errors or data loss;

[0070] Field mapping module, used to standardize the mapping of device data.

[0071] Preferably, the device data standardization module further includes:

[0072] Data storage and sharing module, which is used to store standardized data in a unified data warehouse and supports interoperability with hospital information systems and electronic medical record systems to ensure data accessibility and sharing;

[0073] Abnormal data processing and fault-tolerance mechanism module, used for abnormal data that occurs during parsing or conversion. The system should be able to automatically perform fault-tolerance processing and generate alarm logs;

[0074] System monitoring and performance optimization module, which is used to monitor the performance of data collection, analysis, conversion and other processes, ensure the efficient operation of the system, optimize the data processing process and reduce delays;

[0075] The data security and privacy protection module is used to encrypt the stored and transmitted data to ensure the security and privacy of the data during transmission.

[0076] In this embodiment, the implementation steps of the device data standardization module and the technologies used in combination are as follows:

[0077] 1). Data collection and protocol identification

[0078] Automatically identify device data formats: Automatically identify the data formats output by different devices (such as monitors, CT scanners, blood glucose meters, etc.) through a multi-protocol parser, such as HL7, DICOM, MODBUS, etc., and perform preliminary data analysis.

[0079] Technology used: Data format recognition and parsing based on protocol parsing library (such as HL7Parser, DICOM library, MODBUS protocol stack).

[0080] 2). Data format conversion

[0081] Convert data from different devices into a unified format: Convert the identified data into a unified standard format (such as FHIR, JSON, XML, etc.) for subsequent processing and integration.

[0082] Technologies used: Use data transformation tools (such as Apache Camel, XSLT) or custom transformation logic (such as Pandas library in Python) to transform data in different formats into the target standard format.

[0083] 3). Data verification and consistency check

[0084] Ensure the consistency and accuracy of data formats: Verify the converted data to ensure its integrity, consistency and accuracy to prevent format errors or data loss.

[0085] Technologies used: Use JSON Schema and XML Schema to verify data structure, and regular expressions (RegEx) to verify data consistency.

[0086] 4). Data mapping and standardization

[0087] Standardize mapping of device-specific fields: Map device-specific data fields (such as device number, measurement unit, timestamp, etc.) to a unified standard format to ensure that data fields of different devices can be unified under the standard system.

[0088] Technology used: Standardized mapping of device data through field mapping tables or rule engines such as Drools.

[0089] 5). Data storage and sharing

[0090] Store standardized data and support interoperability: Store standardized data in a unified data warehouse and support interoperability with systems such as hospital information systems (HIS) and electronic medical records (EMR) to ensure data accessibility and sharing.

[0091] Technologies used: MySQL and MongoDB are used to store standardized data, and FHIR and RESTful API interfaces are used to share data with other systems.

[0092] 6). Abnormal data processing and fault tolerance mechanism

[0093] Process abnormal data and perform fault-tolerant processing: For abnormal data that appears during the parsing or conversion process (such as format incompatibility, data loss, etc.), the system should be able to automatically perform fault-tolerant processing and generate an alarm log.

[0094] Technologies used: Use exception handling mechanisms (such as try-catch), error logs (such as Log4j), and automatic alarm systems (such as Prometheus and Grafana) for real-time monitoring and early warning.

[0095] 7). System monitoring and performance optimization

[0096] Real-time monitoring of data processing flow: Monitor the performance of data collection, analysis, conversion and other processes to ensure efficient operation of the system, optimize the data processing flow and reduce delays.

[0097] Technologies used: Monitor system performance through monitoring tools (such as Prometheus, Grafana), and use caching technology (such as Redis) to improve processing efficiency and reduce database pressure.

[0098] 8) Security and privacy protection

[0099] Protect the security of medical data: Encrypt stored and transmitted data to ensure the security and privacy of data during transmission.

[0100] Technology used: Use national secret SM2 and SM4 encryption algorithms to encrypt data to ensure the privacy and security of patient data.

[0101] The device data standardization module automatically identifies a variety of device data formats and uses technologies such as protocol analysis, data conversion, format verification, field mapping, storage and sharing to standardize device data from different sources and ensure data consistency, interoperability, security and efficiency.

[0102] Preferably, the real-time data processing engine module includes:

[0103] The data collection and streaming module collects medical device data in real time and streams it: real-time data is obtained through device interfaces or sensors, and streaming data transmission technology (such as Apache Kafka) is used to transmit the data to the processing engine in real time to ensure the rapid flow of data.

[0104] Technology used: Apache Kafka is used as a message queue to achieve high-throughput, low-latency data transmission, supporting real-time collection and transmission of medical device data.

[0105] The data preprocessing and formatting module preprocesses and standardizes real-time data: During data transmission, Apache Flink performs basic cleaning and formatting on the original data to ensure that the data conforms to a unified standard format for subsequent processing.

[0106] Technology used: Use Apache Flink or Apache Beam to clean, filter, and transform real-time data streams to ensure data consistency and processability.

[0107] The real-time data stream analysis and processing module performs real-time analysis and processing on the transmitted data: it uses the real-time stream processing engine to calculate and analyze the data, supports operations such as data aggregation and complex event processing (CEP) to extract valuable information for early warning and decision support.

[0108] Technologies used: Apache Flink is used for streaming data processing, supporting real-time window computing, time series analysis, and event-driven processing. Flink CEP can be used to identify real-time complex event patterns.

[0109] Real-time decision support and reasoning module: Provide decision support based on real-time data: Combine real-time processed data with medical knowledge base or AI model to provide real-time decision support, such as clinical warning, diagnosis and treatment recommendations, risk assessment, etc.

[0110] Technology used: Integrate machine learning models or deep learning inference engines (such as TensorFlow, PyTorch), combine with real-time data for fast inference, and provide real-time decision-making recommendations for medical personnel.

[0111] Real-time data storage and query module: Store processed data in real time and support fast query: Processed data needs to be stored in real time and support efficient query to ensure that medical staff can quickly access data for decision-making when needed.

[0112] Technologies used: Use efficient data storage systems (such as Apache HBase, Cassandra) for real-time data storage to ensure low latency and high concurrency for data queries.

[0113] Preferably, the real-time data processing engine module also includes:

[0114] Real-time monitoring and alarm module: monitor the real-time data processing process, detect anomalies in time and issue alarms: monitor the health of data stream processing in real time, ensure the stability of data stream and processing engine, and issue alarms when failures or anomalies occur;

[0115] Technologies used: Use Prometheus and Grafana for system monitoring, track the performance of components such as Kafka and Flink, and use Alertmanager for abnormal alarms.

[0116] The data consistency and fault-tolerance processing module is used to ensure the consistency and fault-tolerance of data in multiple nodes and multiple systems: in a high-concurrency real-time data processing environment, it ensures the accuracy and consistency of data and can restore processing in the event of a system failure.

[0117] Technologies used: Kafka's distributed transactions and Flink's state management mechanism are used to ensure data consistency and fault tolerance. Flink Checkpointing and Kafka's message idempotence mechanism ensure data reliability.

[0118] Preferably, the real-time data processing engine module also includes:

[0119] System expansion and high availability design to ensure high availability and scalability of the system under high load: Design the system architecture to support horizontal expansion to ensure that the system can still operate efficiently when the amount of data increases dramatically;

[0120] Technologies used: Distributed architecture is adopted, and Kubernetes is used for containerized deployment to ensure high availability and scalability of the system. Both Kafka and Flink support distributed processing and can effectively process large-scale data.

[0121] The data security and privacy protection module ensures data security and privacy protection during real-time data processing: encryption and access control measures are taken during data transmission and processing to ensure the security of sensitive data.

[0122] Technologies used: Use the national secret SM2 and SM4 encryption algorithms to protect data transmission and storage, and combine OAuth2.0 and RBAC for access control to ensure that only authorized users can access sensitive data.

[0123] The real-time data processing engine uses Apache Kafka for streaming data transmission, Apache Flink for real-time analysis and processing, and combines efficient data storage and query systems to achieve real-time collection, analysis and decision support for medical equipment data, ensuring the timeliness of medical decisions and efficient flow of data. At the same time, through real-time monitoring, fault-tolerant processing and data security measures, the high availability, data consistency and security of the system are ensured.

[0124] Preferably, the intelligent analysis and decision support module includes:

[0125] The data acquisition and preprocessing module is used to collect historical data and real-time data of medical equipment and perform preprocessing: connect with the equipment (such as ventilator, ECG monitor, etc.) through the interface to obtain the patient's physiological data in real time and preprocess the data (such as denoising, filling missing values, and data standardization).

[0126] Technology used: Use data collection tools and protocols (such as HL7, FHIR, DICOM), combined with Python's data processing libraries (such as Pandas, Numpy) for data preprocessing.

[0127] The feature extraction and data conversion module extracts key information from the raw data: performs feature engineering on the raw data collected by the device, extracts key physiological indicators such as heart rate, respiratory rate, and blood oxygen saturation, and converts the data to adapt to the input requirements of the AI ​​model.

[0128] Techniques used: Machine learning libraries such as Scikit-learn are used for feature extraction, and time series analysis methods (such as sliding windows and Fourier transform) are used to extract key time series features.

[0129] AI model training and optimization: Train and optimize AI models based on historical data: Use historical data to train deep learning models (such as LSTM, GRU) to learn the relationship between the patient's condition and physiological indicators; optimize the accuracy of the model and use cross-validation methods to select the optimal model;

[0130] Techniques used: Use TensorFlow or PyTorch to train deep learning models, use LSTM (Long Short-Term Memory Network) and GRU (Gated Recurrent Unit) to process time series data, and use K-fold cross-validation to optimize the model.

[0131] The real-time prediction and analysis module performs instant prediction and analysis based on real-time data: inputs real-time monitoring data into the trained AI model to perform instant prediction and disease change analysis, and judges the patient's health risks based on the prediction results.

[0132] Technologies used: Use TensorFlow Serving or ONNX Runtime for real-time reasoning and inference of AI models, combined with time series analysis methods for dynamic prediction.

[0133] Preferably, the intelligent analysis and decision support module also includes:

[0134] Early warning and intelligent diagnosis and treatment suggestion module, which generates early warning of the disease and provides intelligent diagnosis and treatment suggestions: Based on the prediction results, the system automatically generates early warning signals of disease changes and provides intelligent diagnosis and treatment suggestions to support medical staff in making decisions at critical moments;

[0135] Technology used: Combining the output of rule engines (such as Drools) and deep learning models to generate specific clinical warning information and recommendations.

[0136] The personalized diagnosis and treatment plan generation module generates personalized diagnosis and treatment plans based on the patient's historical data and real-time data: using the patient's personalized information (such as medical history, drug allergies, clinical symptoms, etc.) combined with real-time monitoring data to provide patients with personalized diagnosis and treatment plans;

[0137] Technologies used: Generate customized treatment plans for patients based on AI recommendation systems (such as collaborative filtering, content-based) and deep learning methods.

[0138] The multimodal data fusion and analysis module integrates data from different devices and sensors for comprehensive analysis: it integrates data from different devices (such as ECG monitors, ventilators, blood glucose meters, etc.) and combines them with other clinical data (such as imaging data, laboratory results) for multimodal analysis to obtain more accurate predictions and treatment recommendations.

[0139] Technology used: Use multimodal learning (such as Transformer model, Multimodal Neural Networks) to fuse different types of data for comprehensive analysis.

[0140] Real-time feedback and optimization module, which provides feedback and optimizes the model based on actual usage: Through feedback from medical staff and changes in the patient's actual condition, the AI ​​model is continuously adjusted and optimized to improve the accuracy of the prediction.

[0141] Technology used: Use online learning and incremental learning techniques to enable the model to update and optimize itself based on new data. Use A / B testing to compare and verify different model versions.

[0142] The data security and privacy protection module ensures that medical data is securely protected throughout the entire process: encryption and privacy protection measures are taken during data collection, storage, processing and transmission to ensure the security of patients' personal information and medical data.

[0143] Technologies used: National secret SM2 and SM4 encryption algorithms are used for data protection, combined with OAuth 2.0 and RBAC for permission control.

[0144] The model deployment and maintenance module deploys the trained model into a real-time environment and performs regular maintenance: deploying the AI ​​model into a production environment to ensure that it can provide real-time prediction and decision support in actual scenarios; at the same time, regularly updating and optimizing the model based on new data.

[0145] Technologies used: Kubernetes for containerized deployment, and TensorFlow Serving or MLflow for model management and version control.

[0146] The intelligent analysis and decision support module combines deep learning, time series analysis, AI recommendation system and other technologies to conduct intelligent analysis based on real-time data from medical equipment, provide medical staff with disease prediction, early warning and intelligent diagnosis and treatment suggestions, and support the generation of personalized diagnosis and treatment plans. The module's real-time, intelligent and safe nature ensures accurate and timely medical decisions.

[0147] Preferably, 1) data transmission encryption, encrypting the security of medical data during transmission: used to ensure that medical device data will not be stolen or tampered with during transmission, and to ensure the confidentiality and integrity of data through encryption technology.

[0148] Technologies used: Use the national secret SM2 and SM4 encryption algorithms to encrypt data, and use TLS / SSL protocols to encrypt data transmission to ensure the security of data during transmission.

[0149] 2) Access control, which is used to control data access rights and ensure that only authorized personnel can access sensitive information: Set corresponding data access rights according to different user roles to ensure that personnel at different levels can only access data within their authorized scope.

[0150] Technologies used: Use the RBAC (role-based access control) model for access rights management, combined with ABAC (attribute-based access control) to provide more fine-grained permission control to ensure that users can only access data within their scope of responsibility.

[0151] 3) Authentication, used to ensure the legitimacy of the identity of the data accessor: Authentication is performed before data access to confirm whether the requester is an authorized user to prevent illegal users from accessing sensitive data.

[0152] Technologies used: OAuth 2.0 protocol is used for user authentication and authorization, combined with multi-factor authentication (MFA) to further enhance identity security. JWT (JSON Web Token) is used for identity credential delivery.

[0153] 4) Data storage encryption

[0154] Ensure security during data storage: Encrypt medical data stored in the database to prevent data leakage when the data is illegally accessed at the physical level or on the storage medium.

[0155] Technology used: Use the national secret SM4 algorithm to encrypt medical data in the database, combined with database transparent encryption (TDE) technology to ensure the security of data when it is stored at rest.

[0156] 5) Data de-identification and privacy protection

[0157] Protect patient privacy and prevent sensitive information from being leaked during data sharing: De-identify medical data to ensure that patients' personal identity information is not leaked during external sharing.

[0158] Technology used: Data desensitization technology is used to process sensitive information using de-identification and pseudonymization methods to ensure that patient privacy is not compromised when data is exchanged.

[0159] 6). Security audit and log management

[0160] Record and audit all data access operations to detect abnormal behavior in a timely manner: Record data access and generate audit logs for subsequent inspection and tracing, while promptly detecting illegal access or abnormal operations.

[0161] Technologies used: Use log management tools (such as ELK Stack, Splunk) to record all data access behaviors, and use SIEM (security information and event management) systems for real-time monitoring and alarms.

[0162] 7). Firewall and intrusion detection

[0163] Prevent malicious attacks and illegal access: Deploy firewalls and intrusion detection systems (IDS) to monitor data traffic and network activities to identify and block potential malicious attacks.

[0164] Technologies used: Use network firewalls (such as iptables), IDS / IPS systems (such as Snort, Suricata) to protect the network perimeter from external attacks.

[0165] 8). Data backup and recovery

[0166] Ensure data recovery in the event of data loss or damage: Back up data regularly and establish a data recovery mechanism to cope with recovery needs after system failure or data leakage.

[0167] Technologies used: Use backup solutions (such as Veeam, Acronis) to encrypt and back up data, and establish a disaster recovery plan (DRP) and business continuity plan (BCP) to ensure that data can be quickly restored in the event of a failure.

[0168] 9). Security vulnerability management and repair

[0169] Timely discover and repair security vulnerabilities in the system: regularly conduct security vulnerability scans and penetration tests, and promptly repair possible security vulnerabilities in the system to prevent malicious attackers from exploiting vulnerabilities to launch attacks.

[0170] Technologies used: Use tools such as OWASP ZAP and Burp Suite for vulnerability scanning and penetration testing, and use vulnerability management systems (such as Qualys) for vulnerability identification and repair.

[0171] 10). Compliance inspection and safety standards compliance

[0172] Ensure that data processing and storage comply with relevant regulations and standards: Ensure that the system meets the compliance requirements of medical data security, such as GDPR, HIPAA and other laws and regulations, and ensure that the data processing process meets the standards of privacy protection and data security.

[0173] Technology used: Use compliance checking tools (such as OneTrust) to conduct compliance audits to ensure that the system complies with regulations such as HIPAA and GDPR to ensure the legal processing of patient data.

[0174] The multi-layered security mechanism ensures the security, compliance and privacy protection of medical device data during transmission, storage and sharing by combining technologies such as data encryption, authentication, access control, auditing and privacy protection. These security measures ensure the confidentiality, integrity and availability of patient data while reducing potential security risks by comprehensively managing data flows, access rights, system vulnerabilities, etc.

[0175] Preferably, the streaming data transmission technology is: Apache Kafka.

[0176] By adopting the above technical solution disclosed in the present invention, the following beneficial effects are obtained:

[0177] The new generation of medical equipment integration engine of the present invention has the following advantages:

[0178] 1. Seamless integration of equipment data: Through adaptive standardized modules, medical devices of different brands and types can be easily integrated to ensure the uniformity of data formats.

[0179] 2. Real-time decision support: Through the streaming processing architecture, real-time collection and analysis of device data can be achieved, which significantly improves the response speed of medical device data and the real-time nature of diagnosis and treatment support.

[0180] 3. Intelligent analysis and early warning: The AI-driven intelligent analysis module can perform deep learning and prediction based on device data to provide more forward-looking medical advice and early warnings.

[0181] 4. Flexible system expansion: The microservice architecture design makes the system highly scalable, and can easily connect to new equipment and functions to support the long-term development of medical institutions.

[0182] 5. Cross-platform operation: The system can run efficiently on multiple platforms such as Windows, Linux, ARM, etc., ensuring its wide applicability in various medical environments.

[0183] 6. Enhanced security: Multi-level security mechanisms ensure the privacy and security of device data during transmission and storage, meeting global medical data security and compliance requirements.

[0184] Compared with the prior art, the new generation of medical device integration engine of the present invention has the following advantages:

[0185] 1. Multi-protocol support and data standardization: The present invention can support multiple medical device communication protocols and realize unified conversion of device data through adaptive standardization modules, which greatly improves the interoperability and compatibility of device data and surpasses the reliance on a single protocol in existing systems.

[0186] 2. Real-time and high efficiency: Compared with the batch processing mode of the prior art, the present invention adopts a streaming processing engine, which can realize real-time transmission and processing of data, greatly reducing data delay and ensuring the real-time response requirements of medical equipment.

[0187] 3. Intelligent analysis capability: By integrating AI and deep learning models, the present invention can conduct in-depth analysis and prediction of device data, which can not only improve the accuracy of diagnosis and treatment decisions, but also achieve early warning to ensure patient safety.

[0188] 4. Cross-platform compatibility: The present invention supports different operating systems and hardware environments such as Windows, Linux and ARM, has a high degree of cross-platform compatibility, can adapt to the technical needs of different medical institutions, and reduces the deployment and operation and maintenance costs of the system.

[0189] 5. High scalability and flexibility: Based on the microservice architecture design, the system can be flexibly expanded. Whether it is connecting new devices or expanding new functional modules, it can be quickly adapted and deployed, with scalability that exceeds the existing integrated system.

[0190] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be considered as the scope of protection of the present invention.

Claims

1. A new generation of medical device integration engine, characterized by: include: The device data standardization module is used to automatically identify and convert multiple device data formats; the device data standardization module can process HL7, DICOM, MODBUS and other medical device data through a built-in multi-protocol parser, and convert them into a unified standard format to ensure data consistency and interoperability; Real-time data processing engine module, used for real-time collection, transmission and processing of data from medical equipment; Intelligent analysis and decision support module, which uses deep learning and time series analysis technology to intelligently analyze data from medical devices; Microservice architecture design module; Multi-level security mechanism module: including data transmission encryption, access control, identity authentication, etc., to ensure the security and compliance of medical device data during transmission and sharing.

2. The new generation medical device integration engine according to claim 1, characterized in that: The device data standardization module includes: Protocol parsing library, used to implement data format recognition and parsing; Data format conversion module, used to convert data in different formats into target standard formats; The data format verification module is used to verify the converted data to ensure the integrity, consistency and accuracy of the data and prevent format errors or data loss; Field mapping module, used to standardize the mapping of device data.

3. The new generation medical device integration engine according to claim 2, characterized in that: The device data standardization module also includes: Data storage and sharing module, which is used to store standardized data in a unified data warehouse and supports interoperability with hospital information systems and electronic medical record systems to ensure data accessibility and sharing; Abnormal data processing and fault-tolerance mechanism module, used for abnormal data that occurs during parsing or conversion. The system should be able to automatically perform fault-tolerance processing and generate alarm logs; System monitoring and performance optimization module, which is used to monitor the performance of data collection, analysis, conversion and other processes, ensure the efficient operation of the system, optimize the data processing process and reduce delays; The data security and privacy protection module is used to encrypt the stored and transmitted data to ensure the security and privacy of the data during transmission.

4. The new generation medical device integration engine according to claim 1, characterized in that: The real-time data processing engine module includes: The data acquisition and streaming module obtains real-time data through device interfaces or sensors, and uses streaming data transmission technology to transmit the data to the processing engine in real time to ensure the rapid flow of data; Data preprocessing and formatting module: During data transmission, Apache Flink is used to perform basic cleaning and formatting of raw data to ensure that the data conforms to a unified standard format for subsequent processing. Real-time data stream analysis and processing module, which uses the real-time stream processing engine to calculate and analyze data, supports data aggregation and complex event processing operations to extract valuable information, provide early warning and decision support; Real-time decision support and reasoning module: Provide decision support based on real-time data: Combine real-time processed data with medical knowledge base or AI model to provide real-time decision support; Real-time data storage and query module: Store processed data in real time and support fast query: Processed data needs to be stored in real time and support efficient query to ensure that medical staff can quickly access data for decision-making when needed.

5. The new generation medical device integration engine according to claim 4, characterized in that: The real-time data processing engine module also includes: Real-time monitoring and alarm module: monitor the real-time data processing process, detect abnormalities in time and issue alarms: monitor the health of data stream processing in real time, ensure the stability of data stream and processing engine, and issue alarms when failures or abnormalities occur; The data consistency and fault-tolerance processing module is used to ensure the consistency and fault-tolerance of data in multiple nodes and multiple systems: in a high-concurrency real-time data processing environment, it ensures the accuracy and consistency of data and can restore processing in the event of a system failure.

6. The new generation medical device integration engine according to claim 5, characterized in that: The real-time data processing engine module also includes: System expansion and high availability design to ensure high availability and scalability of the system under high load: Design the system architecture to support horizontal expansion to ensure that the system can still operate efficiently when the amount of data increases dramatically; The data security and privacy protection module ensures data security and privacy protection during real-time data processing: encryption and access control measures are taken during data transmission and processing to ensure the security of sensitive data.

7. The new generation medical device integration engine according to claim 1, characterized in that: The intelligent analysis and decision support module includes: The data acquisition and preprocessing module is used to collect historical data and real-time data of medical equipment and perform preprocessing: connect with the equipment through the interface, obtain the patient's physiological data in real time, and preprocess the data; Feature extraction and data conversion module, extracting key information from raw data: Performing feature engineering on the raw data collected by the device, extracting key physiological indicators such as heart rate, respiratory rate, and blood oxygen saturation, and converting the data to adapt to the input requirements of the AI ​​model; AI model training and optimization: training and optimizing AI models based on historical data: using historical data to train deep learning models to learn the relationship between patient conditions and physiological indicators; optimizing the accuracy of the model and using cross-validation methods to select the optimal model; The real-time prediction and analysis module performs instant prediction and analysis based on real-time data: inputs real-time monitoring data into the trained AI model to perform instant prediction and disease change analysis, and judges the patient's health risks based on the prediction results.

8. The new generation medical device integration engine according to claim 7, characterized in that: The intelligent analysis and decision support module also includes: Early warning and intelligent diagnosis and treatment suggestion module, which generates early warning of the disease and provides intelligent diagnosis and treatment suggestions: Based on the prediction results, the system automatically generates early warning signals of disease changes and provides intelligent diagnosis and treatment suggestions to support medical staff in making decisions at critical moments; The personalized diagnosis and treatment plan generation module generates personalized diagnosis and treatment plans based on the patient's historical data and real-time data: using the patient's personalized information and combining it with real-time monitoring data to provide patients with personalized diagnosis and treatment plans; Multimodal data fusion and analysis module, which integrates data from different devices and sensors for comprehensive analysis: Integrate data from different devices and combine them with other clinical data for multimodal analysis to obtain more accurate predictions and diagnosis and treatment recommendations; Real-time feedback and optimization module, which provides feedback and optimizes the model based on actual usage: Through the feedback from medical staff and changes in the actual condition of patients, the AI ​​model is continuously adjusted and optimized to improve the accuracy of prediction; Data security and privacy protection module ensures that medical data is protected throughout the entire process: encryption and privacy protection measures are taken during data collection, storage, processing and transmission to ensure the security of patients' personal information and medical data; The model deployment and maintenance module deploys the trained model into a real-time environment and performs regular maintenance: deploying the AI ​​model into a production environment to ensure that it can provide real-time prediction and decision support in actual scenarios; at the same time, regularly updating and optimizing the model based on new data.

9. The new generation medical device integration engine according to claim 1, characterized in that: The data transmission encryption is used to ensure that the medical device data will not be stolen or tampered with during the transmission process, and the confidentiality and integrity of the data are protected by encryption technology; The access control is used to control the access rights of data and ensure that only authorized personnel can access sensitive information: set corresponding data access rights according to different user roles to ensure that personnel at different levels can only access data within their authorized scope; The identity authentication is used to ensure the legitimacy of the identity of the data accessor: identity authentication is performed before data access to confirm whether the requester is an authorized user, thereby preventing unauthorized users from accessing sensitive data.

10. The new generation medical device integration engine according to claim 4, characterized in that: The streaming data transmission technology is: Apache Kafka.

Images