Emergency ICU ward monitoring data processing system based on big data

Abstract

The invention discloses an emergency ICU ward monitoring data processing system based on big data, and relates to the technical field of big data processing, the monitoring data processing system comprises a data collection module, an abnormity marking module, a real-time data analysis module, an abnormity evaluation module and an early warning information generation module, and the modules are in electric signal connection. According to the emergency ICU ward monitoring data processing system based on big data, by analyzing vital sign data of a patient and equipment operation data, once abnormal fluctuation is found, early warning information is immediately generated and sent to medical staff, it can be ensured that the medical staff know the abnormal condition of the patient in the first time, so that processing measures are rapidly taken, and the medical staff are prevented from being damaged. Compared with a traditional manual monitoring mode, the system has the advantages that the response time is greatly shortened, the first-aid efficiency is improved, and meanwhile, the system can also provide detailed monitoring data and analysis reports to help medical staff to judge the illness state more accurately and formulate a more accurate treatment scheme.

Description

Technical Field

[0001] The present invention relates to the technical field of big data processing, and in particular to an emergency ICU ward monitoring data processing system based on big data. Background Art

[0002] The emergency ICU ward mainly treats patients whose lives are endangered or who have potential high-risk factors due to dysfunction of one or more organs and systems for various reasons. The conditions of these patients are often complex and changeable, requiring continuous or near-continuous observation, diagnosis and treatment, and monitoring. The ICU ward is equipped with a large number of advanced physiological monitors, pacemaker defibrillator monitors and other equipment to monitor the patient's vital signs in real time, including blood oxygen, heart rate, electrocardiogram, etc., and continuously generate a large amount of time series data. In the face of critically ill patients, early detection and intervention are indispensable means to prevent the disease from endangering the patient's life. Therefore, the emergency ICU ward has an urgent need for the real-time, accuracy and intelligence level of monitoring data processing.

[0003] The existing monitoring mechanism of emergency ICU wards focuses on monitoring. How to analyze the monitoring data and evaluate the development trend of patients' conditions to effectively convey early warning information is the problem we need to solve. To this end, a monitoring data processing system for emergency ICU wards based on big data is proposed. Summary of the invention

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: an emergency ICU ward monitoring data processing system based on big data, the monitoring data processing system includes a data collection module, an abnormal marking module, a real-time data analysis module, an abnormal evaluation module and an early warning information generation module, wherein the modules are connected by electrical signals;

[0005] The data collection module is used to collect data corresponding to patients in the ICU ward, including patients' vital signs data and equipment operation data, and perform preprocessing operations on the collected data;

[0006] The anomaly marking module uses a statistical anomaly detection algorithm to compare the preprocessed data with a preset standard value threshold, determine the anomaly value and mark it;

[0007] The real-time data analysis module, in combination with the abnormal marking results, uses stream processing technology to analyze the collected data and detect abnormal fluctuations in the patient's vital signs data and equipment operation data;

[0008] The abnormality assessment module, based on machine learning algorithms and historical data, combined with real-time data analysis results, assesses the severity of abnormalities in the emergency ICU ward, provides medical staff with a more comprehensive assessment of patient conditions, and assists in formulating more accurate treatment plans;

[0009] The warning information generation module generates warning information according to the abnormal evaluation results, and sends it to medical staff with detailed monitoring data and analysis reports, so that medical staff can quickly understand the status of the ICU ward and take corresponding treatment measures.

[0010] Preferably, the data collection module comprises a data acquisition unit, a data preprocessing unit and a data storage unit, wherein the units are connected by electrical signals;

[0011] The data acquisition unit is responsible for collecting the patient's vital signs data and equipment operation data from various equipment and systems in the emergency ICU ward;

[0012] The data preprocessing unit is used to clean, convert and merge the collected raw data, and convert unstructured data (voice recordings, image data, etc.) into structured data to facilitate subsequent analysis and processing;

[0013] The data storage unit adopts a distributed storage system (Hadoop HDFS) to store the collected data efficiently and securely.

[0014] Preferably, in the data collection module, the process of acquiring data in the ICU ward includes:

[0015] Establish connections between the data acquisition unit and various medical equipment (monitors, ventilators, infusion pumps, etc.) and information systems (electronic medical record systems, doctor's order systems, etc.) in the emergency ICU ward to ensure real-time data transmission. The data acquisition unit captures the patient's vital signs data and equipment operation data from the connected devices and systems through a preset interface (API). For monitor data, capture the patient's heart rate, blood pressure, body temperature, and blood oxygen saturation vital signs data; for ventilator data, capture the ventilator's operating parameters, including respiratory rate, tidal volume, and airway pressure; for infusion pump data, capture the flow rate, total amount, and remaining amount data of the infusion pump; for information system data, capture the patient's medical records and doctor's order information from the electronic medical record system and doctor's order system;

[0016] The data preprocessing unit checks the collected raw data, identifies and deletes noise, duplicates and invalid data, fills in missing data through interpolation methods, converts data from different sources and formats into a unified format and standard for subsequent analysis and processing, and merges data from different devices and systems according to patient ID and timestamp key fields to form a complete patient data record;

[0017] The data storage unit is used to receive the preprocessed data for preliminary inspection and verification. The Hadoop HDFS distributed storage system is used to store and manage the data. The data is distributed on different nodes according to the vital signs data and equipment operation data type to achieve load balancing and fault tolerance.

[0018] Preferably, the abnormal marking module includes a feature extraction unit and an abnormal feature marking unit;

[0019] The feature extraction unit is used to perform feature analysis on the pre-processed vital sign data and equipment operation data, and extract evaluation features of the vital sign and equipment operation respectively;

[0020] The abnormal feature marking unit compares the extracted vital signs and the evaluation features of the equipment operation with the standard value threshold, identifies the abnormal features and marks them.

[0021] Preferably, in the abnormality marking module, the abnormal value determination and marking process includes:

[0022] Extract pre-processed vital sign data and equipment operation data from the data collection module, and perform feature analysis on the pre-processed data to identify features reflecting the patient status and equipment operation status;

[0023] Extract evaluation features of vital signs and equipment operation from the results of feature analysis. The evaluation features of vital signs include heart rate, blood pressure, body temperature, and blood oxygen saturation. The evaluation features of equipment operation include respiratory rate, tidal volume, and flow rate of the infusion pump.

[0024] Using the abnormal feature marking unit, a corresponding standard value threshold is set for each evaluation feature according to clinical nursing requirements, and the extracted evaluation feature is compared with the corresponding standard value threshold. According to the comparison result, the abnormal feature exceeding the threshold is identified, wherein the standard value threshold is set based on medical knowledge and the specific situation of the patient, and is used to determine whether the data point is within the normal range;

[0025] The identified abnormal features are marked, including the type of abnormality (too high, too low, abnormal fluctuation), and the timestamp of the abnormality is recorded so that medical staff can accurately understand the time when the abnormality occurred.

[0026] Preferably, in the real-time data analysis module, the abnormal fluctuation detection process of vital sign data and equipment operation data includes:

[0027] Receive the pre-processed vital sign data and equipment operation data, as well as the corresponding abnormal marking results, from the abnormal marking module, and focus on analyzing the data marked as abnormal;

[0028] Stream processing technology is used to divide the real-time data stream into continuous time windows. Each window contains data within a fixed time period (1 minute). In each time window, the collected data is calculated and analyzed in real time to detect the change trend of the data.

[0029] According to the real-time values ​​and change trends of vital signs data such as heart rate, blood pressure, body temperature, and blood oxygen saturation, statistical methods are used to calculate the abnormal fluctuation index of vital signs, analyze the degree of deviation of vital signs data from the normal range, and output the abnormal fluctuation index of vital signs and its abnormal trend (increasing, decreasing, stable);

[0030] According to the real-time values ​​and changing trends of the equipment operation data of the ventilator's respiratory rate, tidal volume, and infusion pump flow rate, a statistical method is used to calculate the equipment operation abnormal fluctuation index, determine the abnormal type of equipment operation (excessive respiratory rate, abnormal infusion pump flow rate), and output the equipment operation abnormal fluctuation index and its abnormal type.

[0031] Preferably, the calculation expression of the abnormal fluctuation index of vital signs is:

[0032] ;

[0033] in, is the abnormal fluctuation index of vital signs, is the actual heart rate value, The standard value of heart rate is 60-100 beats / min for normal adults. is the actual blood pressure value, expressed as systolic pressure, The standard value of blood pressure is 90-139 mmHg for normal adults. is the actual body temperature value, The standard value of body temperature is 36.0-37.0℃ for normal adults. is the actual blood oxygen saturation value, The standard value of blood oxygen saturation is 95%-100% for normal adults. When it is close to 0, it means that the vital signs data are very close to the standard value and there is no obvious abnormal fluctuation. When it is close to 1, it means that the vital sign data deviates greatly from the standard value and there is obvious abnormal fluctuation;

[0034] The calculation expression of the equipment operation abnormal fluctuation index is:

[0035] ;

[0036] in, is the abnormal fluctuation index of equipment operation. is the actual ventilator respiratory rate value, is the standard value of the ventilator respiratory rate, is the actual tidal volume value, is the standard value of tidal volume, is the actual infusion pump flow rate value, is the standard value of the infusion pump flow rate. When it is close to 0, it means that the equipment operation data is very close to the standard value, and there is no obvious abnormal fluctuation. When it is close to 1, it means that the equipment operation data deviates greatly from the standard value and there are obvious abnormal fluctuations.

[0037] Preferably, in the abnormality assessment module, the assessment process of the severity of the abnormality in the emergency ICU ward includes:

[0038] Extract patient vital signs data and equipment operation data, and obtain historical data associated with patient vital signs data and equipment operation data, and integrate them into a unified data set for subsequent processing;

[0039] Perform feature extraction on the data in the data set, extract the characteristics of heart rate variability and blood pressure fluctuation range from the vital signs data, and extract the characteristics of equipment failure frequency and abnormal alarm from the equipment operation data to obtain a feature data set, and divide the feature data set into a training set and a test set;

[0040] Use the data in the training set combined with the neural network model to build an anomaly assessment model, and use the test set data to evaluate the trained anomaly assessment model. By adjusting the model parameters, the performance of the model is optimized and the accuracy of anomaly detection is improved.

[0041] The trained anomaly assessment model is used to detect anomalies in real-time data. According to the detection results, the abnormal assessment coefficient is calculated by combining the abnormal fluctuation index of vital signs and the abnormal fluctuation index of equipment operation, and the severity of the abnormality in the emergency ICU ward is analyzed. According to the size and change trend of the abnormal assessment coefficient, the severity and cause of the abnormality are analyzed. The abnormal data is further identified and marked through the abnormal marking module, and the abnormal fluctuation index of vital signs and the abnormal fluctuation index of equipment operation are calculated to detect abnormal fluctuations in the data, and then the severity of the abnormality in the ICU ward is comprehensively evaluated to provide medical staff with a comprehensive assessment of the patient's condition.

[0042] Preferably, the calculation expression of the abnormality assessment coefficient is:

[0043] ;

[0044] in, is the abnormal assessment coefficient, It is the abnormal fluctuation index of vital signs, which reflects the degree of deviation of vital signs data from the normal range. It is the equipment operation abnormal fluctuation index, which reflects the deviation degree of equipment operation data from the normal range. When it is close to 0, it means that the vital signs and equipment operation data are close to the standard value, and there is no obvious abnormal fluctuation. When it is close to 1, it means that the vital signs and equipment operation data deviate greatly from the standard values ​​and there are obvious abnormal fluctuations. By combining the radical and logarithmic functions, the sensitivity to the degree of deviation is enhanced, so that even slight deviations can be reflected in the coefficient. At the same time, the exponential function ensures that the output of the coefficient is always within the range of 0 to 1.

[0045] Preferably, in the warning information generation module, the generation and generation process of the warning information includes:

[0046] Analyze the received abnormal assessment results, including abnormal assessment coefficient, abnormal type, abnormal location key information, and set warning thresholds according to medical standards. When the abnormal assessment coefficient exceeds the warning threshold, generate warning information;

[0047] Generate warning information based on abnormality assessment results. The warning information includes the warning type (abnormal vital signs, abnormal equipment operation, etc.) and specific abnormal data. Collect detailed monitoring data and analysis reports related to the warning, including the time, duration, abnormal value, and trend of the abnormality.

[0048] Format warning information and related data to ensure that the information is clear and easy to understand, so that medical staff can quickly grasp the situation, and send warning information and detailed reports to medical staff through communication channels (hospital internal communication system, mobile devices, email);

[0049] Record the time when medical staff receive the warning information and the time when they respond to it, so as to facilitate subsequent review and process improvement, and track the response of medical staff to the warning information and changes in the patient's condition to ensure that the warning information is handled in a timely and effective manner.

[0050] The present invention provides an emergency ICU ward monitoring data processing system based on big data, which has the following beneficial effects:

[0051] 1. The emergency ICU ward monitoring data processing system based on big data analyzes the patient's vital signs data and equipment operation data. Once abnormal fluctuations are found, it immediately generates warning information and sends it to medical staff. It can ensure that medical staff are aware of the patient's abnormal condition at the first time and take prompt measures to deal with it. Compared with traditional manual monitoring methods, it greatly shortens the response time and improves emergency rescue efficiency. At the same time, the system can also provide detailed monitoring data and analysis reports to help medical staff more accurately judge the condition and formulate more precise treatment plans.

[0052] 2. The emergency ICU ward monitoring data processing system based on big data further identifies and marks abnormal data through the abnormal marking module, calculates the abnormal fluctuation index of vital signs and the abnormal fluctuation index of equipment operation, detects abnormal fluctuations in data, and then comprehensively evaluates the severity of abnormalities in the ICU ward, providing medical staff with a comprehensive patient condition assessment, real-time monitoring of patient conditions and a rapid response mechanism, which greatly improves patient safety and optimizes treatment outcomes.

[0053] 3. The emergency ICU ward monitoring data processing system based on big data provides medical staff with a comprehensive assessment of the patient's condition, including abnormal fluctuations in vital signs and abnormal equipment operation status, providing strong support for medical staff to formulate treatment plans. Medical staff can formulate personalized treatment plans based on the system's analysis results and the patient's actual situation. In addition, the system can also provide historical data comparison and analysis to help medical staff understand the patient's condition development trend, so as to make more accurate judgments and further improve the quality of medical care. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 This is a module structure diagram of an emergency ICU ward monitoring data processing system based on big data of the present invention;

[0055] Figure 2 The flowchart of determining and marking abnormal values ​​of the present invention is as follows;

[0056] Figure 3 This is a flow chart of abnormal fluctuation detection of vital sign data and equipment operation data of the present invention;

[0057] Figure 4 This is a flow chart for evaluating the severity of abnormalities in the emergency ICU ward of the present invention. DETAILED DESCRIPTION

[0058] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present invention are provided for the purpose of illustration and description, and are not intended to be exhaustive or to limit the present invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention, and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses.

[0059] The first embodiment, as Figure 1 , Figure 2 As shown, the present invention provides a technical solution: an emergency ICU ward monitoring data processing system based on big data, the monitoring data processing system includes a data collection module, an abnormal marking module, a real-time data analysis module, an abnormal evaluation module and an early warning information generation module, wherein the modules are connected by electrical signals;

[0060] The data collection module is used to collect the data of the corresponding patients in the ICU ward, including the patients' vital signs data and equipment operation data, and perform pre-processing operations on the collected data;

[0061] Furthermore, the data collection module includes a data collection unit, a data preprocessing unit and a data storage unit, wherein the units are connected by electrical signals. The data collection unit is responsible for collecting the patient's vital signs data and equipment operation data from various equipment and systems in the emergency ICU ward. The data preprocessing unit is used to clean, convert and merge the collected raw data to eliminate noise, outliers and duplicates in the data, improve the quality and availability of the data, and convert unstructured data (voice recordings, image data, etc.) into structured data for subsequent analysis and processing. The data storage unit uses a distributed storage system (Hadoop HDFS) to store the collected data efficiently and securely.

[0062] Furthermore, in the data collection module, the process of acquiring data in the ICU ward includes:

[0063] The data acquisition unit is connected to various medical equipment (monitors, ventilators, infusion pumps, etc.) and information systems (electronic medical record systems, doctor's order systems, etc.) in the emergency ICU ward to ensure real-time data transmission. The data acquisition unit captures the patient's vital signs data and equipment operation data from the connected devices and systems through the preset interface (API). For monitor data, the patient's heart rate, blood pressure, body temperature, and blood oxygen saturation vital signs data are captured. For ventilator data, the ventilator's operating parameters are captured, including respiratory rate, tidal volume, and airway pressure. For infusion pump data, the flow rate, total amount, and remaining amount data of the infusion pump are captured. For information system data, the patient's medical records and doctor's order information are captured from the electronic medical record system and doctor's order system. The collected raw data is checked through the data preprocessing unit to identify and delete noise, duplicates and invalid data. For missing data, the data is filled by interpolation method, and the data from different sources and formats are converted into a unified format and standard for subsequent analysis and processing. The data from different devices and systems are merged according to the patient ID and timestamp key fields to form a complete patient data record. The preprocessed data is received by the data storage unit for preliminary inspection and verification. The distributed storage system (Hadoop HDFS) is used to store and manage the data, and the data is distributed on different nodes according to the type of data (vital signs data, equipment operation data) to achieve load balancing and fault tolerance.

[0064] The anomaly marking module uses a statistical anomaly detection algorithm to compare the preprocessed data with the preset standard value threshold, determine the anomaly value and mark it;

[0065] Furthermore, the abnormal marking module includes a feature extraction unit and an abnormal feature marking unit, the feature extraction unit is used to perform feature analysis on the pre-processed vital signs data and equipment operation data, respectively extracting evaluation features of vital signs and equipment operation, and the abnormal feature marking unit compares the extracted vital signs and equipment operation evaluation features with the standard value threshold, identifies abnormal features and marks them;

[0066] Furthermore, in the abnormality marking module, the abnormal value determination and marking process includes:

[0067] Extract pre-processed vital signs data and equipment operation data from the data collection module, perform feature analysis on the pre-processed data, identify features reflecting the patient status and equipment operation status, and extract evaluation features of vital signs and equipment operation from the results of feature analysis, wherein the evaluation features of vital signs include heart rate, blood pressure, body temperature, and blood oxygen saturation, and the evaluation features of equipment operation include respiratory rate, tidal volume, and flow rate of the infusion pump of the ventilator. Use the abnormal feature marking unit to set a corresponding standard value threshold for each evaluation feature according to clinical nursing requirements, and compare the extracted evaluation features with the corresponding standard value threshold. According to the comparison results, identify abnormal features that exceed the threshold, wherein the standard value threshold is set based on medical knowledge and the specific situation of the patient, and is used to determine whether the data point is within the normal range. Mark the identified abnormal features, including marking the type of abnormality (too high, too low, abnormal fluctuation), and record the timestamp of the abnormality so that medical staff can accurately understand the time point when the abnormality occurred;

[0068] The real-time data analysis module combines the abnormal marking results and uses stream processing technology to analyze the collected data to detect abnormal fluctuations in the patient's vital signs data and equipment operation data;

[0069] The abnormality assessment module, based on machine learning algorithms and historical data, combined with real-time data analysis results, assesses the severity of abnormalities in the emergency ICU ward, provides medical staff with a more comprehensive assessment of patient conditions, and assists in formulating more accurate treatment plans;

[0070] The warning information generation module generates warning information based on the abnormal assessment results and sends it to medical staff with detailed monitoring data and analysis reports so that they can quickly understand the status of the ICU ward and take appropriate measures.

[0071] The second embodiment is based on the first embodiment. Figure 3 , Figure 4 As shown, in the real-time data analysis module, the abnormal fluctuation detection process of vital sign data and equipment operation data includes:

[0072] Receive the pre-processed vital signs data and equipment operation data, as well as the corresponding abnormal marking results, from the abnormal marking module, focus on analyzing the data marked as abnormal, use stream processing technology to divide the real-time data stream into continuous time windows, each window contains data within a fixed time period (1 minute), and in each time window, perform real-time calculation and analysis on the collected data to detect the change trend of the data. According to the real-time values ​​and change trends of the vital signs data of heart rate, blood pressure, body temperature, and blood oxygen saturation, use statistical methods to calculate the vital signs abnormal fluctuation index, analyze the degree of deviation of the vital signs data from the normal range, and output the vital signs abnormal fluctuation index and its abnormal trend (increasing, decreasing, stable). According to the real-time values ​​and change trends of the equipment operation data of the ventilator respiratory rate, tidal volume, and infusion pump flow rate, use statistical methods to calculate the equipment operation abnormal fluctuation index, judge the abnormal type of equipment operation (excessive respiratory rate, abnormal infusion pump flow rate), and output the equipment operation abnormal fluctuation index and its abnormal type;

[0073] Furthermore, the calculation expression of the abnormal fluctuation index of vital signs is:

[0074] ;

[0075] in, is the abnormal fluctuation index of vital signs, is the actual heart rate value, The standard value of heart rate is 60-100 beats / min for normal adults. is the actual blood pressure value, expressed as systolic pressure, The standard value of blood pressure is 90-139 mmHg for normal adults. is the actual body temperature value, The standard value of body temperature is 36.0-37.0℃ for normal adults. is the actual blood oxygen saturation value, The standard value of blood oxygen saturation is 95%-100% for normal adults. When it is close to 0, it means that the vital signs data are very close to the standard value and there is no obvious abnormal fluctuation. When it is close to 1, it means that the vital sign data deviates greatly from the standard value and there is obvious abnormal fluctuation;

[0076] The calculation expression of equipment operation abnormal fluctuation index is:

[0077] ;

[0078] in, is the abnormal fluctuation index of equipment operation. is the actual ventilator respiratory rate value, is the standard value of the ventilator respiratory rate, is the actual tidal volume value, is the standard value of tidal volume, is the actual infusion pump flow rate value, is the standard value of the infusion pump flow rate. When it is close to 0, it means that the equipment operation data is very close to the standard value, and there is no obvious abnormal fluctuation. When it is close to 1, it means that the equipment operation data deviates greatly from the standard value and there is obvious abnormal fluctuation;

[0079] In the abnormality assessment module, the assessment process of the severity of abnormalities in the emergency ICU ward includes:

[0080] Extract patient vital signs data and equipment operation data, and obtain historical data associated with patient vital signs data and equipment operation data, and synthesize a unified data set for subsequent processing. Perform feature extraction on the data in the data set, extract the characteristics of heart rate variability and blood pressure fluctuation range from the vital signs data, and extract the characteristics of equipment failure frequency and abnormal alarm from the equipment operation data to obtain a feature data set, and divide the feature data set into a training set and a test set. Use the data in the training set in combination with the neural network model to build an abnormal evaluation model, and use the test set data to evaluate the trained abnormal evaluation model. By adjusting the parameters of the model, optimize the performance of the model and improve the accuracy of abnormal detection. Use the trained abnormal evaluation model to perform abnormal detection on real-time data. According to the test results, calculate the abnormal evaluation coefficient based on the abnormal fluctuation index of vital signs and the abnormal fluctuation index of equipment operation, analyze the severity of abnormalities in the emergency ICU ward, and analyze the severity and cause of abnormalities based on the size and change trend of the abnormal evaluation coefficient.

[0081] Furthermore, the calculation expression of the abnormal evaluation coefficient is:

[0082] ;

[0083] in, is the abnormal assessment coefficient, It is the abnormal fluctuation index of vital signs, which reflects the degree of deviation of vital signs data from the normal range. It is the equipment operation abnormal fluctuation index, which reflects the deviation degree of equipment operation data from the normal range. When it is close to 0, it means that the vital signs and equipment operation data are close to the standard value, and there is no obvious abnormal fluctuation. When it is close to 1, it means that the vital signs and equipment operation data deviate greatly from the standard value, and there are obvious abnormal fluctuations. By combining the root form and the logarithmic function, the sensitivity to the degree of deviation is enhanced, so that even slight deviations can be reflected in the coefficient. At the same time, the exponential function ensures that the output of the coefficient is always within the range of 0 to 1. The abnormal data is further identified and marked through the abnormal marking module, and the vital signs abnormal fluctuation index and the equipment operation abnormal fluctuation index are calculated to detect abnormal fluctuations in the data, thereby comprehensively evaluating the severity of abnormalities in the ICU ward and providing medical staff with a comprehensive assessment of the patient's condition.

[0084] In the warning information generation module, the generation and occurrence process of warning information includes:

[0085] Parse the received abnormal assessment results, including abnormal assessment coefficient, abnormal type, abnormal location key information, and set the warning threshold according to the medical standards. When the abnormal assessment coefficient exceeds the warning threshold, generate warning information. Generate warning information based on the abnormal assessment results. The warning information includes the warning type (abnormal vital signs, abnormal equipment operation, etc.) and specific abnormal data, and collect detailed monitoring data and analysis reports related to the warning, including the time, duration, abnormal value, and trend of the abnormality. Format the warning information and related data to ensure that the information is clear and easy to understand, so that medical staff can quickly grasp the situation, and send warning information and to medical staff through communication channels (hospital internal communication system, mobile devices, email). Detailed reports record the time when medical staff receive and respond to warning information, so as to facilitate subsequent review and improvement of processes, and track the response of medical staff to warning information and changes in patient conditions to ensure that warning information is handled in a timely and effective manner. By analyzing the patient's vital signs data and equipment operation data, once abnormal fluctuations are found, warning information is immediately generated and sent to medical staff, which can ensure that medical staff are aware of the patient's abnormal condition at the first time and take prompt measures to deal with it. Compared with traditional manual monitoring methods, it greatly shortens the response time and improves emergency rescue efficiency. At the same time, the system can also provide detailed monitoring data and analysis reports to help medical staff more accurately judge the condition and formulate more precise treatment plans.

[0086] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field and related fields without creative work should fall within the scope of protection of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention are implemented according to the conventional means in the field unless otherwise specified and limited.

Claims

1. An emergency ICU ward monitoring data processing system based on big data, characterized in that: The monitoring data processing system includes a data collection module, an abnormality marking module, a real-time data analysis module, an abnormality assessment module and an early warning information generation module, wherein the modules are connected by electrical signals; The data collection module is used to collect data corresponding to patients in the ICU ward, including patients' vital signs data and equipment operation data, and perform preprocessing operations on the collected data; The anomaly marking module uses a statistical anomaly detection algorithm to compare the preprocessed data with a preset standard value threshold, determine the anomaly value and mark it; The real-time data analysis module, in combination with the abnormal marking results, uses stream processing technology to analyze the collected data and detect abnormal fluctuations in the patient's vital signs data and equipment operation data; The abnormality assessment module assesses the severity of abnormalities in the emergency ICU ward based on machine learning algorithms and historical data combined with real-time data analysis results; The warning information generation module generates warning information according to the abnormal evaluation results and sends an analysis report to medical staff.

2. According to the big data-based emergency ICU ward monitoring data processing system of claim 1, it is characterized by: The data collection module includes a data acquisition unit, a data preprocessing unit and a data storage unit, wherein the units are connected by electrical signals; The data acquisition unit is responsible for collecting the patient's vital signs data and equipment operation data from various equipment and systems in the emergency ICU ward; The data preprocessing unit is used to clean, convert and merge the collected raw data, and convert the unstructured data into structured data; The data storage unit adopts a distributed storage system to store the collected data.

3. According to the big data-based emergency ICU ward monitoring data processing system of claim 2, it is characterized by: In the data collection module, the process of acquiring data in the ICU ward includes: The data acquisition unit is connected to various medical devices and information systems in the emergency ICU ward. The data acquisition unit captures the patient's vital signs data and equipment operation data from the connected devices and systems through a preset interface. For monitor data, the patient's heart rate, blood pressure, body temperature, and blood oxygen saturation vital signs data are captured. For ventilator data, the ventilator's operating parameters, including respiratory rate, tidal volume, and airway pressure, are captured. For infusion pump data, the flow rate, total amount, and remaining amount data of the infusion pump are captured. For information system data, the patient's medical records and doctor's order information are captured from the electronic medical record system and doctor's order system; The data preprocessing unit checks the collected raw data and merges the data from different devices and systems according to the patient ID and timestamp key fields to form a complete patient data record; The data storage unit is used to receive the preprocessed data, perform preliminary inspection and verification, and use a distributed storage system to store and manage the data. According to the type of data, the data is distributed on different nodes to achieve load balancing and fault tolerance.

4. The big data-based emergency ICU ward monitoring data processing system according to claim 3 is characterized by: The abnormal marking module includes a feature extraction unit and an abnormal feature marking unit; The feature extraction unit is used to perform feature analysis on the pre-processed vital sign data and equipment operation data, and extract evaluation features of the vital sign and equipment operation respectively; The abnormal feature marking unit compares the extracted vital signs and the evaluation features of the equipment operation with the standard value threshold, identifies the abnormal features and marks them.

5. The big data-based emergency ICU ward monitoring data processing system according to claim 4 is characterized by: In the abnormality marking module, the abnormal value determination and marking process includes: Extract pre-processed vital sign data and equipment operation data from the data collection module, and perform feature analysis on the pre-processed data to identify features reflecting the patient status and equipment operation status; Extract evaluation features of vital signs and equipment operation from the results of feature analysis. The evaluation features of vital signs include heart rate, blood pressure, body temperature, and blood oxygen saturation. The evaluation features of equipment operation include respiratory rate, tidal volume, and flow rate of the infusion pump. Using the abnormal feature marking unit, a corresponding standard value threshold is set for each evaluation feature according to clinical nursing requirements, and the extracted evaluation feature is compared with the corresponding standard value threshold, and the abnormal features exceeding the threshold are identified according to the comparison results; The identified abnormal features are marked, including marking the type of abnormality and recording the timestamp of the abnormality.

6. The big data-based emergency ICU ward monitoring data processing system according to claim 5 is characterized by: In the real-time data analysis module, the abnormal fluctuation detection process of vital sign data and equipment operation data includes: Receive the pre-processed vital sign data and equipment operation data, as well as the corresponding abnormal marking results, from the abnormal marking module, and focus on analyzing the data marked as abnormal; Use stream processing technology to divide the real-time data stream into continuous time windows. Each window contains data within a fixed time period. In each time window, the collected data is calculated and analyzed in real time to detect the change trend of the data. According to the real-time values ​​and change trends of vital signs data such as heart rate, blood pressure, body temperature, and blood oxygen saturation, a statistical method is used to calculate the abnormal fluctuation index of vital signs, analyze the degree of deviation of vital signs data from the normal range, and output the abnormal fluctuation index of vital signs and its abnormal trend; According to the real-time values ​​and changing trends of the equipment operation data of the ventilator's respiratory rate, tidal volume, and infusion pump flow rate, a statistical method is used to calculate the equipment operation abnormal fluctuation index, determine the abnormal type of equipment operation, and output the equipment operation abnormal fluctuation index and its abnormal type.

7. The big data-based emergency ICU ward monitoring data processing system according to claim 6 is characterized by: The calculation expression of the abnormal fluctuation index of vital signs is: ； in, is the abnormal fluctuation index of vital signs, is the actual heart rate value, is the standard value of heart rate, is the actual blood pressure value, expressed as systolic pressure, is the standard value of blood pressure, is the actual body temperature value, is the standard value of body temperature, is the actual blood oxygen saturation value, is the standard value of blood oxygen saturation; The calculation expression of the equipment operation abnormal fluctuation index is: ； in, is the abnormal fluctuation index of equipment operation. is the actual ventilator respiratory rate value, is the standard value of the ventilator respiratory rate, is the actual tidal volume value, is the standard value of tidal volume, is the actual infusion pump flow rate value, It is the standard value of the infusion pump flow rate.

8. The big data-based emergency ICU ward monitoring data processing system according to claim 7 is characterized by: In the abnormality assessment module, the assessment process of the severity of the abnormality in the emergency ICU ward includes: Extract patient vital signs data and equipment operation data, and obtain historical data associated with patient vital signs data and equipment operation data to obtain a unified data set; Perform feature extraction on the data in the data set, extract the characteristics of heart rate variability and blood pressure fluctuation range from the vital signs data, and extract the characteristics of equipment failure frequency and abnormal alarm from the equipment operation data to obtain a feature data set, and divide the feature data set into a training set and a test set; Use the data in the training set combined with the neural network model to build an anomaly assessment model, and use the test set data to evaluate the trained anomaly assessment model, and optimize the model performance by adjusting the model parameters; The trained anomaly assessment model is used to detect anomalies in real-time data. Based on the detection results, the anomaly assessment coefficient is calculated by combining the abnormal fluctuation index of vital signs and the abnormal fluctuation index of equipment operation. The severity of the abnormalities in the emergency ICU ward is analyzed, and the severity and cause of the abnormalities are analyzed based on the size and change trend of the anomaly assessment coefficient.

9. The big data-based emergency ICU ward monitoring data processing system according to claim 8, characterized in that: The calculation expression of the abnormal evaluation coefficient is: ； in, is the abnormal assessment coefficient, is the abnormal fluctuation index of vital signs, is the abnormal fluctuation index of equipment operation. When it is close to 0, it means that the vital signs and equipment operation data are close to the standard value, and there is no obvious abnormal fluctuation. When it is close to 1, it means that the vital signs and equipment operation data deviate greatly from the standard values ​​and there are obvious abnormal fluctuations.

10. The big data-based emergency ICU ward monitoring data processing system according to claim 9, characterized in that: In the warning information generation module, the generation and generation process of the warning information includes: Analyze the received abnormal assessment results, including abnormal assessment coefficient, abnormal type, abnormal location key information, and set warning thresholds according to medical standards. When the abnormal assessment coefficient exceeds the warning threshold, generate warning information; Generate warning information based on the abnormality assessment results. The warning information includes the warning type and specific abnormal data, and collect detailed monitoring data and analysis reports related to the warning, including the time, duration, abnormal value, and trend of the abnormality; Format warning information and related data, and send warning information and detailed reports to medical staff through communication channels; Record the time when medical staff receive the warning information and the time when they respond, and track the medical staff's response to the warning information and changes in the patient's condition.

Images