Neurological critical patient monitoring system based on artificial intelligence and multi-modal data fusion

Abstract

The invention discloses a neurological critical patient monitoring system based on artificial intelligence and multi-modal data fusion, and relates to the technical field of intelligent monitoring, in the system, vital signs and medical record information of a neurological critical patient are obtained from existing medical monitoring equipment and an electronic medical record system and displayed in real time; different medical prediction models are utilized to perform different predictions according to the multi-modal monitoring data, and prediction results obtained by the different medical prediction models are displayed in real time; when the current key monitoring index of the neurological critical patient exceeds an early warning threshold value or prediction results obtained by different medical prediction models meet a preset early warning condition, a real-time early warning result display module is used for carrying out real-time early warning on medical staff; and finally, the data in the monitoring process is stored through a data storage and export module so as to be packaged and exported when further analysis is needed. The method is of great significance in improving the medical level of the neurointensive care unit, accelerating the illness response speed and improving the treatment efficiency.

Description

Technical Field

[0001] The present application relates to the field of intelligent monitoring technology, and in particular to a monitoring system for critically ill neurological patients based on artificial intelligence and multimodal data fusion. Background Art

[0002] Neurocritical care medicine is a young discipline and a subspecialty of neurology that has rapidly emerged in recent years. Its goal is to integrate neurology and critical care medicine, provide comprehensive, systematic and high-quality medical monitoring and treatment for patients with neurological critical diseases, improve the success rate of treatment and survival rate, and improve the prognosis of patients with neurological critical diseases. The disease spectrum of patients admitted to NICU mainly includes: severe ischemic stroke such as large-area cerebral infarction and basilar artery apex syndrome, large-volume cerebral hemorrhage, brainstem hemorrhage, etc., as well as perioperative management of some special operations such as minimally invasive puncture hematoma removal, neurointervention, intravenous thrombolysis, and external ventricular drainage. Studies based on large samples have shown that compared with non-specialized intensive care, specialized neurocritical care management can significantly reduce the mortality rate of critically ill patients and improve the prognosis of neurological function. However, with the advancement of medical technology, the demand for neurocritical care is increasing, and traditional monitoring methods are obviously unable to meet the needs of efficient and precise medical care. Summary of the invention

[0003] The purpose of this application is to provide a neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion, which can improve the efficiency and accuracy of neurological critical care patient monitoring and shorten the disease response time.

[0004] To achieve the above objectives, this application provides the following solutions: In the first aspect, the present application provides a neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion, including: a routine monitoring information display module, a prediction model result display module, an indicator display and parameter adjustment module, a real-time warning result display module, and a data storage and export module.

[0005] The conventional monitoring information display module is used to connect with existing medical monitoring equipment and electronic medical record systems to obtain and display multimodal monitoring data of critically ill neurological patients in real time; the multimodal monitoring data includes vital signs and medical record information.

[0006] The prediction model result display module is used to use different medical prediction models to make different predictions based on the multimodal monitoring data of critically ill neurological patients, and to display the prediction results obtained by different medical prediction models in real time.

[0007] The indicator display and parameter adjustment module is used to display the current key monitoring indicators and warning thresholds of critically ill neurological patients, and the key monitoring indicators and warning thresholds can be changed as needed.

[0008] The real-time warning result display module is used to provide real-time warnings to medical staff when the current key monitoring indicators of critically ill neurological patients exceed the warning threshold or the prediction results obtained by different medical prediction models meet the preset warning conditions.

[0009] The data storage and export module is used to store the vital signs of critically ill neurological patients, the medical records of critically ill neurological patients, the prediction results obtained by different medical prediction models, the current key monitoring indicators, warning thresholds, and real-time warning records, and package and export them when further analysis is required.

[0010] Optionally, the medical monitoring equipment includes: an electrocardiogram monitor, a blood pressure monitor and a thermometer; the vital signs of critically ill neurological patients include: heart rate, blood pressure and body temperature.

[0011] Optionally, the medical prediction models include: outcome prediction model, mortality prediction model, mRS score prediction model, transfer time prediction model, and different complication risk prediction models; each of the above medical prediction models provides the medical team with predictions about the future health status of critically ill neurological patients through artificial intelligence and machine learning algorithms.

[0012] Optionally, when making predictions, the medical prediction model may also obtain information manually input by medical staff to predict the future health status of the neurological critically ill patient based on the information manually input by the medical staff and the vital signs of the neurological critically ill patient.

[0013] Optionally, key monitoring indicators are monitoring indicators that are crucial to the condition assessment of critically ill neurological patients; key monitoring indicators include cerebral blood flow autoregulation parameters and electroencephalogram parameters; the indicator display and parameter adjustment module is specifically used to: use charts to display the changes of each key monitoring indicator over time, to help medical staff quickly identify any abnormal changes in the patient's condition, and to provide a brief description and explanation for each key monitoring indicator, to help medical staff quickly understand the clinical significance of each key monitoring indicator and how to use these data to assess the patient's condition.

[0014] Optionally, the indicator display and parameter adjustment module includes: an authority determination submodule and a parameter adjustment recording submodule; the authority determination submodule is used to ensure that only authorized medical staff can change the current key monitoring indicators and warning thresholds; the parameter adjustment recording submodule is used to record the historical adjustment information of key monitoring indicators and warning thresholds in real time; the historical adjustment information includes the adjusted key monitoring indicators, adjustment values, adjustment time and adjustment personnel.

[0015] Optionally, all data stored in the data storage and export module are encrypted during the storage process to ensure the security and privacy of patient information, and the data is automatically backed up regularly to a secure remote server or cloud storage service to prevent data loss or damage; the data storage and export module provides export methods in multiple data formats when packaging and exporting data; data formats include: CSV, PDF and Excel.

[0016] Optionally, in the data storage and export module, TLS / SSL encryption algorithm or AES-256 encryption algorithm is used to encrypt all stored data.

[0017] Optionally, the real-time warning result display module can intuitively provide real-time warnings to medical staff by using different colors, icons or pop-up windows on the user interface; the real-time warning result display module can also push notifications to relevant medical staff via SMS, email or mobile application.

[0018] Optionally, the real-time warning result display module is also used to notify members of different levels of the medical team according to the severity of the warning, ensuring that appropriate professionals can take timely action.

[0019] According to the specific embodiments provided in this application, this application discloses the following technical effects: The present application provides a monitoring system for critically ill neurological patients based on artificial intelligence and multimodal data fusion, comprising: a routine monitoring information display module, a prediction model result display module, an indicator display and parameter adjustment module, a real-time warning result display module, and a data storage and export module; wherein, through the routine monitoring information display module, the vital signs and medical history information of critically ill neurological patients can be obtained from existing medical monitoring equipment and electronic medical record systems and displayed in real time; then, through the prediction model result display module, different predictions are made according to the vital signs of critically ill neurological patients using different medical prediction models, and the prediction results obtained by different medical prediction models are displayed in real time; and through the real-time warning result display module, when the current key monitoring indicators of critically ill neurological patients exceed the warning threshold or the prediction results obtained by different medical prediction models meet the preset warning conditions, real-time warnings are given to medical staff; finally, through the data storage and export module, the vital signs of critically ill neurological patients, the medical history information of critically ill neurological patients, the prediction results obtained by different medical prediction models, the current key monitoring indicators, the warning threshold, and the real-time warning records are stored, and packaged and exported when further analysis is required. The above solution of this application solves the problem that traditional monitoring methods can no longer meet the needs of efficient and accurate medical care. By using artificial intelligence technology, a comprehensive monitoring system for critically ill neurological patients is established, which can improve the efficiency and accuracy of monitoring of critically ill neurological patients, shorten the disease response time, strengthen risk management, and improve patient safety; it is conducive to promoting the effective use of medical resources and improving the overall service level of the hospital. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 A schematic diagram of the functional modules of a neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion provided in one embodiment of the present application.

[0022] Figure 2 A schematic diagram of the contents that need to be considered for implementing the routine monitoring information display function in a neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion provided in one embodiment of the present application.

[0023] Figure 3 A schematic diagram of the contents that need to be considered in implementing the prediction model result display function in a neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion provided in one embodiment of the present application.

[0024] Figure 4 A schematic diagram of the contents that need to be considered for implementing the indicator display and parameter adjustment functions in a neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion provided in one embodiment of the present application.

[0025] Figure 5 A schematic diagram of the contents that need to be considered for realizing the real-time warning result display function in a neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion provided in one embodiment of the present application.

[0026] Figure 6 A schematic diagram of the contents that need to be considered in implementing data storage and export functions in a neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion provided in one embodiment of the present application.

[0027] Figure 7 A schematic diagram of the technical framework adopted in a neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion provided in one embodiment of the present application.

[0028] Figure 8 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0030] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0031] In an exemplary embodiment, Figure 1 As shown, a neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion is provided, including: a routine monitoring information display module 101, a prediction model result display module 102, an indicator display and parameter adjustment module 103, a real-time warning result display module 104 and a data storage and export module 105.

[0032] The conventional monitoring information display module 101 is used to connect with existing medical monitoring equipment and electronic medical record systems to obtain and display multimodal monitoring data of critically ill neurological patients in real time; the multimodal monitoring data includes vital signs and medical record information. Medical monitoring equipment includes: electrocardiogram monitor, sphygmomanometer and thermometer; accordingly, the vital signs of critically ill neurological patients obtained include: heart rate, blood pressure and body temperature.

[0033] The routine monitoring information display function is one of the core functions of the monitoring system, which is designed to provide real-time monitoring of the patient's vital signs and key medical information. This function ensures that medical staff can obtain the patient's heart rate, blood pressure, body temperature and other basic vital signs information in real time, as well as important medical scores such as the NIHSS (National Institutes of Health Stroke Scale) score, which is crucial for assessing the patient's health status and formulating treatment plans.

[0034] like Figure 2 As shown in the figure, the following points need to be considered for the realization of the general monitoring information display function: (1) Data collection: Automatically collect patients’ vital signs and medical history information by interfacing with the hospital’s existing monitoring equipment and electronic medical record systems. These devices may include electrocardiogram monitors, blood pressure monitors, thermometers, and tools for recording NIHSS scores.

[0035] (2) Data integration: The collected data needs to be integrated and formatted so that it can be displayed uniformly on the monitoring system. This may include data cleaning (removing noise or erroneous readings), normalization (ensuring that the data format is consistent), and merging (combining data from different sources into a single record for the patient).

[0036] (3) Real-time update: To ensure the real-time nature of information, the monitoring system will set a data update frequency, which may range from a few seconds to a few minutes, depending on the type of monitoring equipment and monitoring needs. For example, heart rate and blood pressure may require more frequent updates, while evaluation indicators such as NIHSS scores may be updated less frequently.

[0037] (4) User interface design: Design a clear and intuitive user interface to ensure that medical staff can quickly identify and interpret the displayed information. Abnormal values ​​or important warnings, such as abnormal heart rate, high / low blood pressure, etc., should be highlighted on the interface so that medical staff can quickly take appropriate measures.

[0038] (5) Data visualization: Data visualization tools such as charts and trend lines are provided to help medical staff understand the changing trends of patients’ health status over time. For example, through time series graphs of blood pressure and heart rate, medical staff can easily identify any sudden changes in the patient’s condition.

[0039] The prediction model result display module 102 is used to use different medical prediction models to make different predictions based on the multimodal monitoring data of neurological critical patients, and to display the prediction results obtained by different medical prediction models in real time. The medical prediction models include: outcome prediction model, mortality prediction model, mRS score prediction model, transfer time prediction model, and different complication risk prediction models; each of the above medical prediction models provides the medical team with predictions about the future health status of neurological critical patients through artificial intelligence and machine learning algorithms. In addition, when making predictions, the medical prediction model can also obtain information manually entered by medical staff to predict the future health status of neurological critical patients based on the information manually entered by medical staff and the vital signs of neurological critical patients.

[0040] The prediction model result display function is an advanced function that aims to use the collected monitoring information and the data entered by medical staff to provide the medical team with predictions about the patient's future health status through artificial intelligence and machine learning algorithms. It usually includes but is not limited to outcome prediction, mortality rate, modified Rankin Scale (mRS) score, expected transfer time, and risk prediction of complications such as cerebral hemorrhage, deep vein thrombosis (DVT), cerebral edema, early neurological deterioration (END), sepsis, pulmonary infection, disseminated intravascular coagulation (DIC), gastrointestinal bleeding and shock.

[0041] like Figure 3 As shown in the figure, the following points need to be considered for the realization of the prediction model result display function: (1) Model development and integration: This function is achieved by developing new or integrating existing medical prediction models. These prediction models are trained based on historical medical data and can analyze patients’ vital signs, laboratory test results, medical images and other information to predict patients’ future health status and the risk of potential complications.

[0042] (2) Data processing: Some medical prediction models need to receive real-time data from monitoring equipment and information manually input by medical staff, such as patients' living habits, family medical history, etc. The system must be able to process this data, including cleaning and normalization, and extracting features that are useful for the prediction model.

[0043] (3) Real-time display of prediction results: The prediction results need to be displayed in real time on the monitoring system, showing various predictions in the form of charts, scores or text, such as the percentage of mortality, the prediction interval of mRS score, and the risk level of complications. The system should also provide a function to explain the prediction results to help medical staff understand and use these predictions.

[0044] (4) Model accuracy and reliability: It is crucial to ensure the accuracy and reliability of the prediction model. This requires collaboration with medical research institutions and experts to continuously optimize and calibrate the model using the latest medical research results and clinical data. The performance of the model should be evaluated regularly to ensure that its prediction results meet the needs of clinical practice.

[0045] (5) User interaction design: The display of prediction results should be designed to be intuitive and easy to understand, so that medical staff can quickly obtain and understand important prediction information. In addition, an appropriate user interface should be provided to allow medical staff to adjust model inputs based on clinical judgment to obtain more personalized prediction results.

[0046] The indicator display and parameter adjustment module 103 is used to display the current key monitoring indicators and warning thresholds of the neurological critical patients, and can change the key monitoring indicators and warning thresholds as needed. The key monitoring indicators are monitoring indicators that are crucial to the condition assessment of the neurological critical patients; the key monitoring indicators include cerebral blood flow automatic adjustment parameters and electroencephalogram parameters.

[0047] In this embodiment, the indicator display and parameter adjustment module 103 is specifically used to: use charts to display the changes of various key monitoring indicators over time, help medical staff quickly identify any abnormal changes in the patient's status, and provide brief descriptions and explanations for each key monitoring indicator to help medical staff quickly understand the clinical significance of each key monitoring indicator and how to use these data to assess the patient's condition. In order to ensure the security and traceability of the system, the indicator display and parameter adjustment module 103 also includes: an authority determination submodule and a parameter adjustment record submodule; the authority determination submodule is used to ensure that only authorized medical staff can change the current key monitoring indicators and warning thresholds; the parameter adjustment record submodule is used to record the historical adjustment information of the key monitoring indicators and warning thresholds in real time; the historical adjustment information includes the adjusted key monitoring indicators, adjustment values, adjustment time and adjustment personnel.

[0048] The indicator display and parameter adjustment function is designed to provide a comprehensive view of various monitoring indicators that are critical to the assessment of the patient's condition in the neurointensive care unit. These indicators include cerebral blood flow autoregulation parameters Mx, electroencephalogram (aEEG) parameters, etc., which are extremely important for monitoring brain activity and blood flow status. This function also allows medical staff to adjust monitoring parameters according to the patient's specific condition, such as adjusting the warning threshold, so as to more accurately monitor and respond to changes in patients.

[0049] like Figure 4 As shown in the figure, the following points need to be considered for the realization of indicator display and parameter adjustment functions: (1) Real-time data display: Design an intuitive user interface to display the current values ​​and historical trends of key monitoring indicators in real time. For example, charts can be used to display the changes in Mx parameters and aEEG parameters over time to help medical staff quickly identify any abnormal changes in the patient's status.

[0050] (2) Indicator explanation: Provide a brief description and explanation for each monitoring indicator to help medical staff understand the clinical significance of each indicator and how to use this data to assess the patient's condition.

[0051] (3) Monitoring parameter adjustment: Allows medical staff to adjust monitoring parameters directly through the interface, such as modifying warning thresholds. These adjustments can be made based on the patient’s current condition and treatment response to provide a more personalized monitoring plan.

[0052] (4) Permission management: Ensure that only authorized medical staff can adjust monitoring parameters. This can be achieved through user login and role-based access control to ensure system security and data accuracy.

[0053] (5) Parameter adjustment records: The system automatically records the history of all parameter adjustments, including the adjusted parameters, adjustment values, adjustment time, and adjustment personnel. This helps with subsequent data analysis and review to ensure the rationality and necessity of each adjustment.

[0054] (6) Intelligent recommendations: The system can provide medical staff with intelligent recommendations for parameter adjustments based on the monitoring data and the output of the predictive model. For example, if the system detects that the patient's Mx parameter shows a decrease in the autoregulation of cerebral blood flow, it can recommend lowering the alarm threshold of the target blood pressure in order to more closely monitor the patient's condition.

[0055] (7) Feedback loop: By analyzing the patient’s response to parameter adjustments, the system continuously learns and optimizes, improving the accuracy of parameter adjustment recommendations and forming a feedback loop for continuous improvement.

[0056] The real-time warning result display module 104 is used to provide real-time warnings to medical staff when the current key monitoring indicators of critically ill neurological patients exceed the warning threshold or the prediction results obtained by different medical prediction models meet the preset warning conditions. In this embodiment, the real-time warning result display module 104 can intuitively provide real-time warnings to medical staff by using different colors, icons or pop-ups on the user interface; the real-time warning result display module 104 can also push notifications to relevant medical staff via text messages, emails or mobile applications. In another embodiment, the real-time warning result display module 104 is also used to notify members of different levels of the medical team according to the severity of the warning to ensure that appropriate professionals can take timely action.

[0057] The real-time warning result display function is committed to using real-time data analysis and prediction models to promptly identify and notify the medical team of serious health risks that patients may face. This includes but is not limited to emergency medical situations such as bleeding and shock, with the goal of improving the patient's treatment effect and survival rate through timely intervention.

[0058] like Figure 5 As shown in the figure, the following points need to be considered for the implementation of the real-time warning result display function: (1) Risk assessment: First, warning thresholds are set for various health risks based on historical data and clinical experience. These thresholds are based on the risk levels determined when the predictive model analyzes real-time data (such as vital signs, laboratory test results, etc.).

[0059] (2) Personalized configuration: Allows medical staff to adjust warning thresholds and conditions based on the patient's specific situation or the specific needs of the ward. This ensures that the sensitivity and specificity of the warning system meet actual needs.

[0060] (3) User interface: In the user interface of the monitoring system, visual elements such as colors, icons or pop-ups are used to intuitively display warning information. For example, for high-risk warnings, a red warning symbol can be used, while for medium risks, yellow can be used.

[0061] (4) Detailed information and guidance: In addition to basic warning indications, it also provides information about warning conditions, recommended clinical response measures, and further diagnostic suggestions when necessary.

[0062] (5) Notification system: When a warning condition is detected, the system can send a push notification to the relevant medical staff via SMS, email or mobile application. This ensures that the medical staff can be informed of potential emergencies in a timely manner even if they are not in front of the monitoring screen.

[0063] (6) Tiered response: Depending on the severity of the alert, notifications can be sent to different levels of the medical team, from frontline caregivers to specialists, ensuring that appropriate professionals can take timely action.

[0064] (7) Recording and review: All warning events will be recorded by the system to facilitate subsequent analysis and evaluation of the effectiveness of the warning system, while providing data support for clinical decision-making.

[0065] The data storage and export module 105 is used to store the vital signs of critically ill neurological patients, the medical records of critically ill neurological patients, the prediction results obtained by different medical prediction models, the current key monitoring indicators, warning thresholds, and real-time warning records, and package and export them when further analysis is required.

[0066] All data stored in the data storage and export module 105 are encrypted during the storage process to ensure the security and privacy of patient information, and the data is automatically backed up regularly to a secure remote server or cloud storage service to prevent data loss or damage. Specifically, in the data storage and export module 105, TLS / SSL encryption algorithm or AES-256 encryption algorithm is used to encrypt all stored data. When the data storage and export module 105 packages and exports data, it provides export methods in multiple data formats; data formats include: CSV (suitable for large-scale data analysis), PDF (suitable for reporting or presentation) and Excel (suitable for further processing).

[0067] The data storage and export function means that the system can store all data collected and generated by the monitoring system under the premise of ensuring data security and privacy protection, and allow users to export these data in various formats for further analysis, research or support for medical decision-making. This includes real-time monitoring data, early warning records, prediction model results, parameter adjustment history and other key information.

[0068] like Figure 6 As shown, the following points need to be considered for the implementation of data storage and export functions: (1) Security and privacy protection: All data must be encrypted during storage to ensure the security and privacy of patient information, using advanced encryption technologies such as TLS / SSL encryption algorithms and encryption algorithms that comply with industry standards, such as AES-256 encryption algorithms.

[0069] (2) Data backup and recovery: Regularly and automatically back up data to a secure remote server or cloud storage service to prevent data loss or corruption, and ensure an effective data recovery strategy to quickly restore data in the event of data loss or corruption.

[0070] (3) High availability: Load balancing and failover mechanisms are used to ensure high availability of the data storage system, thereby supporting the 24 / 7 uninterrupted operation needs of medical institutions.

[0071] (4) Flexible export options: It provides a simple and easy-to-use interface that allows users to select the data type, time range and format of the exported data as needed. It supports the export of multiple data formats, such as CSV (suitable for large-scale data analysis), PDF (suitable for reporting or presentation) and Excel (suitable for further processing).

[0072] (5) Data filtering and customization: Allows users to customize the exported data content, such as exporting only specific monitoring parameters or warning records, and provides powerful data filtering functions to help users quickly find the required data.

[0073] (6) Protect the security of exported data: Data security and privacy protection also need to be ensured during the export process. For example, the exported data files can be encrypted to ensure that only authorized users can access them.

[0074] (7) Export records and audits: Detailed logs of all data export operations are recorded, including export time, exporter, export content, etc., to support subsequent auditing and monitoring.

[0075] The project objectives of the above-designed neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion include: Signal Collection and Input: Develop systems that can collect vital sign signals (such as EEG, heart rate, blood pressure, etc.) from various medical devices.

[0076] Real-time monitoring: Collected signals are monitored in real time through artificial intelligence algorithms to accurately identify changes in the disease.

[0077] Early warning system: Establish an intelligent early warning system to promptly notify medical staff when potential risks arise in the course of a disease.

[0078] Risk prediction: Use machine learning and other technologies to predict the development trend of the disease and assist doctors in making more accurate diagnosis and treatment decisions.

[0079] Information storage and export: Build a secure information storage system to ensure data integrity and privacy, and provide convenient data export functions to support medical research and remote consultation.

[0080] The technical framework required to implement the above-mentioned neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion is as follows: Figure 7 As shown, it includes: data collection layer, data processing layer, application layer and security layer.

[0081] (I) About the data collection layer Goal: To achieve efficient connection with various medical devices in the hospital (such as vital signs monitors, EEG machines, etc.) and automatically collect patients' physiological data.

[0082] Technical details include: (1) Interface standardization: Use common medical equipment interface standards, such as HL7 (Health Level Seven) or DICOM (Digital Imaging and Communications in Medicine), to achieve compatibility with equipment from different manufacturers.

[0083] (2) Data acquisition module: Develop a dedicated data acquisition module that can read and convert device data in real time and support multiple data formats and communication protocols.

[0084] (3) Preliminary data processing: Preliminary processing is performed when collecting data, such as timestamp marking, to ensure accurate synchronization of data.

[0085] (II) About the Data Processing Layer Goal: Ensure that the collected data is effectively processed and suitable for subsequent analysis and predictive models.

[0086] Technical details include: (1) High-performance servers: Deploy high-performance computing servers to support the processing and analysis of large amounts of data and ensure the system's responsiveness.

[0087] (2) Data cleaning and normalization: Use algorithms to remove noise, fill in missing values, normalize data, and improve data quality.

[0088] (3) Data analysis and feature extraction: Use advanced data analysis techniques (such as machine learning algorithms) to conduct in-depth analysis of data, extract key features, and provide support for early warning and prediction models.

[0089] (III) About the Application Layer Objective: To provide a user-friendly interface that enables medical staff to easily access monitoring data, history, and warning information.

[0090] Technical details include: (1) User interface (UI) design: Design a simple and intuitive UI to support medical staff to quickly understand patient status and system warnings.

[0091] (2) Historical data query: Provides efficient data retrieval function to facilitate users to query and compare historical monitoring data.

[0092] (3) Real-time warning display: Through real-time data analysis, when potential risks are detected, warning information is immediately displayed on the interface, and warning notifications can be configured to be sent.

[0093] (IV) About the security layer Goal: To ensure that all data collected, transmitted, and stored meets the highest security standards and protects patient privacy.

[0094] Technical details include: (1) Data encryption: Encrypt all transmitted and stored data, and use security protocols such as SSL / TLS to protect the data transmission process.

[0095] (2) Access control: Implement a role-based access control system to ensure that only authorized users can access sensitive data.

[0096] (3) Security Audit: Record all data access and operation logs to facilitate post-audit and monitoring of potential security threats.

[0097] Through the specific implementation of the above four-layer technical framework, the efficient and safe operation of the neurocritical patient monitoring system can be ensured, while providing strong data support and analysis capabilities for the neurocritical care unit, greatly improving the quality and efficiency of medical services.

[0098] It can be seen that the above solution provided in this embodiment solves the problem that traditional monitoring methods can no longer meet the needs of efficient and accurate medical care. By using artificial intelligence technology, a comprehensive monitoring system for critically ill neurological patients is established, which can improve the efficiency and accuracy of monitoring critically ill neurological patients, shorten the disease response time, strengthen risk management, and improve patient safety; it is conducive to promoting the effective use of medical resources and improving the overall service level of the hospital.

[0099] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, various functions of a neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion are realized.

[0100] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0101] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, which, when executed by a processor, implements the functions of the above-mentioned embodiments of the neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion.

[0102] In an exemplary embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the functions of the above-mentioned embodiments of the neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion.

[0103] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0104] Those skilled in the art can understand that all or part of the functions in the above embodiments can be achieved by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the functions of the embodiments of the above systems. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0105] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0106] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0107] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the scheme and core ideas of this application; at the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion, characterized in that: include: Conventional monitoring information display module, prediction model result display module, indicator display and parameter adjustment module, real-time warning result display module, and data storage and export module; The conventional monitoring information display module is used to connect with existing medical monitoring equipment and electronic medical record systems to obtain and display multimodal monitoring data of critically ill neurological patients in real time; the multimodal monitoring data includes vital signs and medical record information; The prediction model result display module is used to use different medical prediction models to make different predictions based on the multimodal monitoring data of neurological critical patients, and to display the prediction results obtained by different medical prediction models in real time; The indicator display and parameter adjustment module is used to display the current key monitoring indicators and warning thresholds of neurological critical patients, and can change the key monitoring indicators and warning thresholds as needed; The real-time warning result display module is used to issue real-time warnings to medical staff when the current key monitoring indicators of critically ill neurological patients exceed the warning threshold or the prediction results obtained by different medical prediction models meet the preset warning conditions; The data storage and export module is used to store the vital signs of critically ill neurological patients, the medical records of critically ill neurological patients, the prediction results obtained by different medical prediction models, the current key monitoring indicators, warning thresholds, and real-time warning records, and to package and export them when further analysis is required.

2. The neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion according to claim 1 is characterized in that: The medical monitoring equipment includes: an electrocardiogram monitor, a sphygmomanometer and a thermometer; the vital signs of critically ill neurological patients include: heart rate, blood pressure and body temperature.

3. The neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion according to claim 1 is characterized in that: The medical prediction models include: outcome prediction model, mortality prediction model, mRS score prediction model, transfer time prediction model, and different complication risk prediction models; each of the above medical prediction models provides the medical team with predictions on the future health status of critically ill neurological patients through artificial intelligence and machine learning algorithms.

4. The neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion according to claim 3 is characterized in that: When making predictions, the medical prediction model can also obtain information manually input by medical staff to predict the future health status of the neurological critically ill patient based on the information manually input by the medical staff and the vital signs of the neurological critically ill patient.

5. The neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion according to claim 1 is characterized in that: The key monitoring indicators are monitoring indicators that are crucial to the condition assessment of critically ill neurological patients; the key monitoring indicators include cerebral blood flow automatic regulation parameters and electroencephalogram parameters; the indicator display and parameter adjustment module is specifically used to: use charts to display the changes of each key monitoring indicator over time, help medical staff quickly identify any abnormal changes in the patient's condition, and provide a brief description and explanation for each key monitoring indicator, so as to help medical staff quickly understand the clinical significance of each key monitoring indicator and how to use these data to assess the patient's condition.

6. The neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion according to claim 1 is characterized in that: The indicator display and parameter adjustment module includes: an authority determination submodule and a parameter adjustment recording submodule; the authority determination submodule is used to ensure that only authorized medical personnel can change the current key monitoring indicators and warning thresholds; the parameter adjustment recording submodule is used to record the historical adjustment information of key monitoring indicators and warning thresholds in real time; the historical adjustment information includes the adjusted key monitoring indicators, adjustment values, adjustment time and adjustment personnel.

7. The neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion according to claim 1 is characterized in that: All data stored in the data storage and export module are encrypted during storage to ensure the security and privacy of patient information, and the data is automatically backed up regularly to a secure remote server or cloud storage service to prevent data loss or damage; The data storage and export module provides export methods in multiple data formats when packaging and exporting data; The data formats include: CSV, PDF and Excel.

8. The neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion according to claim 7 is characterized in that: In the data storage and export module, TLS / SSL encryption algorithm or AES-256 encryption algorithm is used to encrypt all stored data.

9. The neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion according to claim 1, characterized in that: The real-time warning result display module can intuitively provide real-time warnings to medical staff by using different colors, icons or pop-up windows on the user interface; the real-time warning result display module can also push notifications to relevant medical staff via text messages, emails or mobile applications.

10. The neurological critical care patient monitoring system based on artificial intelligence and multimodal data fusion according to claim 1, characterized in that: The real-time warning result display module is also used to notify members of different levels of the medical team according to the severity of the warning, ensuring that appropriate professionals can take timely action.

Images