Remote monitoring and early warning method and system for intensive care unit

Abstract

The invention discloses a remote monitoring and early warning method and system for an intensive care unit, and relates to the field of remote monitoring and early warning, and the method comprises the following steps: continuously collecting vital sign data of a patient through vital sign monitoring equipment of the intensive care unit; analyzing the vital sign data of the patient in real time by using a state level tree algorithm, and generating an early warning signal according to an analysis result; classifying the early warning signals based on a signal level bucket algorithm, and determining a signal transmission rule; and transmitting the early warning signal to a remote monitoring center according to the signal transmission rule. According to the method, the vital sign data of the patient in the intensive care unit are analyzed in real time by using the state level tree algorithm, and the vital sign data of the patient can be effectively classified and indexed by constructing high-speed and low-speed signal level buckets and formulating detailed signal transmission rules, the signal level is dynamically adjusted, and the transmission of emergency signals is preferentially guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of medical monitoring, and in particular to an intensive care unit remote monitoring early warning method and system. Background Art

[0002] In the modern medical monitoring system, signal devices play a vital role. They are responsible for transmitting key information of patients' vital signs to medical staff. Taking the intensive care unit as an example, the signal devices used usually include various physiological sign monitoring equipment and supporting communication equipment. Traditional signal devices are mainly based on wired connections and standard communication protocols, which can stably transmit basic vital sign data of critically ill patients, such as heart rate, blood oxygen saturation, etc. However, with the development of medical technology and the increase in monitoring needs, traditional signal devices have shown obvious limitations in data processing capabilities, transmission efficiency and remote monitoring. In particular, in terms of large-scale, real-time data processing and high-speed, reliable remote communications, existing technologies often cannot meet the requirements of efficient and accurate medical monitoring.

[0003] Current signal device technology has the problem of low processing efficiency when faced with complex and large amounts of medical data. In particular, in the process of real-time analysis of vital signs data and generation of warning signals, traditional signal devices often cannot respond quickly; in addition, existing signal transmission methods mostly rely on traditional wired or wireless communication technologies, which may encounter delays and instability problems when facing urgent or important medical data transmission. In terms of network resource management, traditional signal devices lack an efficient dynamic adjustment mechanism and cannot perform intelligent scheduling based on the urgency of the signal and the transmission priority, resulting in the inability to guarantee the timely transmission of emergency signals at critical moments.

[0004] These problems directly affect the timeliness and accuracy of early warning responses in medical monitoring, which may in turn have a negative impact on the patient's treatment effect. Therefore, there is an urgent need for a remote monitoring early warning technology that can improve data processing speed and accuracy, make early warning signal generation more timely, and improve signal transmission efficiency and stability, especially the ability to respond quickly in emergency situations, so as to solve the obvious deficiencies of existing technologies in real-time data analysis capabilities, rapid generation of early warning signals, and ensuring timely transmission of emergency signals.

[0005] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0006] In response to the problems in the related technology, the present invention proposes a remote monitoring early warning method and system for intensive care units, which has the advantages of making the early warning signal generation more timely and improving the transmission efficiency and stability of the signal, thereby solving the obvious deficiencies in the existing technology in real-time data analysis capabilities, rapid generation of early warning signals and ensuring timely transmission of emergency signals.

[0007] To this end, the specific technical solution adopted by the present invention is as follows: According to one aspect of the present invention, a remote monitoring early warning method for an intensive care unit is provided, and the remote monitoring early warning method for an intensive care unit comprises the following steps: S1. Continuously collect the patient's vital signs data through the vital signs monitoring equipment in the intensive care unit; S2. Analyze the patient's vital sign data in real time using the state level tree algorithm and generate an early warning signal based on the analysis results; S3, classify the warning signals based on the signal level bucket algorithm and determine the signal transmission rules; S4. According to the signal transmission rules, the warning signal is transmitted to the remote monitoring center.

[0008] Furthermore, using the state level tree algorithm to analyze the collected data in real time and generating an early warning signal according to the analysis result includes the following steps: S21. construct a state-level main tree based on the patient's vital signs data; S22, selecting a time segment length to divide the collected vital sign data into continuous time segment data; S23, performing comprehensive analysis and status marking on the data in each time slice, and generating three status level subtrees based on the status marking; S24, using the state mark as the key value of the state level subtree, updating the state level main tree and outputting the result; S25. Execute steps S22 to S24 in a loop, and generate a warning signal based on the output results.

[0009] Further, constructing the state level main tree based on the collected data includes the following steps: S211. Create an empty multi-branch balanced search tree for indexing all the patient's vital sign data history records; S212, defining the key of each node in the multi-branch balanced search tree as a combination of a unique identifier of the patient and a timestamp of the corresponding data history record; S213. Insert the patient's vital sign data into the multi-branch balanced search tree according to the defined index key to obtain the state-level main tree.

[0010] Furthermore, the comprehensive analysis includes: threshold range determination, mutation detection and long-term trend analysis; Among them, threshold range determination is used to set the threshold range of each vital sign data according to medical standards and individual patient conditions; mutation detection is used to observe the rate of change of vital sign data through differential detection and identify mutation points; long-term trend analysis is used to analyze the long-term trend of the patient's vital sign data using time series analysis technology. By considering the results of the above three analysis methods and combining the experience and professional knowledge of clinicians, the patient's vital sign status is judged; Status tags include: normal, abnormal, and emergency; The three status level subtrees correspond to different status tags, including: The first level subtree indicates that the vital signs data are normal; The second level subtree indicates that the vital sign data is abnormal and needs attention; The third level subtree indicates that the vital sign data indicates an emergency situation and requires immediate action.

[0011] Further, using the state mark as the key value of the state level subtree, updating the state level main tree and outputting the result includes the following steps: S241, for the state-level subtree marked as normal, add the data of each node in the first-level subtree to the state-level main tree, and ignore the data if it already exists; S242, for the state level subtree whose state is marked as abnormal, search for the state level subtree whose state is marked as normal in the corresponding time slice, and update the state mark to abnormal. If not found, check the corresponding node in the state level main tree, and update the state mark from normal to abnormal. S243. For the status level subtree whose status is marked as urgent, search for the status level subtree whose status is marked as abnormal in the corresponding time slice, update the status mark to urgent, delete the status mark of the corresponding node in the status level main tree and output the result. If not found, check the corresponding node in the status level main tree and update the status marked as abnormal to urgent.

[0012] Furthermore, classifying the warning signal based on the signal level bucket algorithm and determining the signal transmission rule includes the following steps: S31, constructing a high-speed signal level bucket and a low-speed signal level bucket, and setting the signal transmission rate and signal flow size of the two signal level buckets; S32, classifying the priority of the warning signal and marking the color based on the classification result; S33. Formulate signal transmission rules based on the marking color.

[0013] Furthermore, constructing a high-speed signal level bucket and a low-speed signal level bucket, and setting the signal transmission rate and signal flow size of the two signal level buckets includes the following steps: S311. Construct a high-speed signal level bucket and a low-speed signal level bucket. The signal level bucket is used to manage and schedule the transmission of warning signals, and each time a signal is transmitted, the corresponding signal level is consumed. S312, set the average signal rate V C and the peak signal rate V P , where V C Indicates the transmission rate of the low-speed signal level bucket to the warning signal, V P Indicates the transmission rate of the high-speed signal level bucket to the warning signal, and V P >V C ; S313, set the average flow size S C and peak flow rate S P , where S C Indicates the maximum signal flow size of the low-speed signal level bucket, S P Indicates the maximum signal flow size of the high-speed signal level bucket.

[0014] Furthermore, the priority classification of the warning signals and the color marking based on the classification results include the following steps: S321, initialize the signal levels of the high-speed signal level bucket and the low-speed signal level bucket, so that the signal level of the low-speed signal level bucket is D C =S C , the signal level of the high-speed signal level barrel is D P =S P ; S322, evaluate the non-emergency F of the received warning signal, and compare whether the non-emergency F is greater than the signal level D of the high-speed signal level bucket P If yes, the warning signal is marked as green, and the signal levels of the high-speed signal level bucket and the low-speed signal level bucket remain unchanged; S323: Compare whether the non-emergency F is greater than the signal level D of the low-speed signal level bucket C If yes, the warning signal is marked as yellow, and the signal level D of the high-speed signal level bucket is updated. P =D P -F, the signal level of the low-speed signal level bucket remains unchanged, otherwise the warning signal is marked red, and the signal level of the high-speed signal level bucket is updated D P =D P -F, update the signal level D of the low-speed signal level bucket C =D C -F.

[0015] Furthermore, formulating a signal transmission rule based on the marking color includes the following steps: S331: Formulate signal transmission rules based on the marking color. For warning signals marked in red, the peak signal rate V P transmission; S332: For the warning signal marked as yellow, according to the average signal rate V C Transmission: When the red signal transmission is in the off-peak period, the yellow warning signal transmission rate is temporarily increased, and does not exceed the peak signal rate V P ; S333: For warning signals marked as green, according to the average signal rate V C transmission; S334: V C As the rate of increase continues to increase the signal level of the low-speed signal level bucket, V P As the signal level of the high-speed signal level bucket that continues to increase the rate cycle, when the signal level bucket reaches the maximum signal level, the excess signal level is discarded, among which the maximum signal level of the low-speed signal level bucket is D C =S C , the maximum signal level of the high-speed signal level bucket D P =S P .

[0016] According to another aspect of the present invention, there is also provided an intensive care unit remote monitoring early warning system, the intensive care unit remote monitoring early warning system comprising: A real-time monitoring module is used to continuously collect patients’ vital signs data through vital signs monitoring equipment in the intensive care unit; A signal generation module is used to analyze the patient's vital sign data in real time using a state level tree algorithm and generate an early warning signal based on the analysis results; A signal transmission module is used to classify warning signals based on a signal level bucket algorithm and determine signal transmission rules; A remote monitoring module is used to transmit the warning signal to the remote monitoring center according to the signal transmission rules; Among them, the real-time monitoring module is connected to the signal transmission module through the signal generation module, and the signal transmission module is connected to the remote monitoring module.

[0017] The beneficial effects of the present invention are: (1) The present invention uses a state-level tree algorithm to analyze the vital signs data of patients in the intensive care unit in real time. By constructing a state-level main tree and three state-level subtrees, the vital signs data of patients are effectively classified and indexed, thereby achieving fast and accurate data retrieval and state evaluation. In an emergency, it can quickly generate an early warning signal to provide medical personnel with immediate early warning information. At the same time, by constructing high-speed and low-speed signal level buckets and setting detailed signal transmission rules, it can dynamically adjust the signal level and give priority to the transmission of emergency signals, which not only ensures the immediate transmission of important signals, but also avoids the waste of network resources, thereby improving the application efficiency and stability of the communication network in remote monitoring of intensive care.

[0018] (2) By introducing the state-level tree algorithm, the present invention can process and analyze the vital signs data of patients in the intensive care unit in real time, which not only improves the efficiency of data processing, but also enhances the accuracy of warning signal generation. By constructing a state-level main tree and three state-level subtrees, the patient's vital signs data can be effectively retrieved and the state evaluated quickly and accurately. In an emergency, a warning signal can be quickly generated to provide medical personnel with immediate warning information. By dividing the time slice data and performing a comprehensive analysis, the present method not only focuses on the data changes at a single time point, but also takes into account the long-term trend, thereby more comprehensively evaluating the patient's health status and improving the accuracy of remote monitoring.

[0019] (3) By applying the signal level bucket algorithm, the present invention proposes transmission rules for warning signals of different emergency levels, ensuring the response speed and reliability of the intensive care unit remote monitoring system at critical moments, making the transmission of warning signals more efficient and orderly; at the same time, by constructing high-speed and low-speed signal level buckets and automatically adjusting them according to the signal level consumption after transmission, the present invention further optimizes the classification and transmission process of warning signals. This mechanism ensures that emergency warning signals can be transmitted first, while effectively utilizing network resources and reducing the occupation of network bandwidth by non-emergency signals. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 It is a flowchart of a remote monitoring early warning method for an intensive care unit according to an embodiment of the present invention; Figure 2 The invention is a principle block diagram of a remote monitoring and early warning system for an intensive care unit according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention and are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in the field should be able to understand other possible implementations and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0023] According to an embodiment of the present invention, a remote monitoring early warning method and system for an intensive care unit are provided.

[0024] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to one embodiment of the present invention, a remote monitoring early warning method for an intensive care unit is provided, and the remote monitoring early warning method for an intensive care unit comprises the following steps: S1. Continuously collect the patient's vital signs data through the vital signs monitoring equipment in the intensive care unit; Specifically, first select high-precision vital signs monitoring equipment suitable for the intensive care unit environment, including heart rate monitors, blood pressure monitors, blood oxygen saturation meters and respiratory rate machines, and then reasonably arrange the location of the monitoring equipment according to the spatial layout of the intensive care unit to ensure that the sensors of the equipment can be properly connected to the corresponding parts of the patient, such as the heart rate monitoring belt fixed on the chest, the blood pressure cuff wrapped around the upper arm, and each device is connected to the central monitoring network through a wireless connection. After the pre-arrangement is completed, the vital signs monitoring equipment can collect the patient's vital signs data in real time and automatically send the collected data to the central monitoring network without manual intervention.

[0025] S2. Analyze the patient's vital sign data in real time using the state level tree algorithm and generate an early warning signal based on the analysis results; Specifically, the state-level tree algorithm is a multi-branch balanced search tree algorithm, which overcomes the defect that the traditional binary search tree algorithm can only store a small amount of data. In the multi-branch balanced search tree, all key-value pairs are stored in leaf nodes, and non-leaf nodes only store navigation data. It expands the nodes to accommodate multiple child nodes, thereby reducing the height of the tree and improving the search efficiency. It can make full use of the node space, improve the efficiency of data processing, and there is no need to traverse the entire tree, which improves the performance in interval query scenarios.

[0026] Specifically, a state-level main tree is constructed based on the collected data. An empty multi-branch balanced search tree is created as the data structure of the state-level main tree to index all the patient's vital signs data history records. The key of each node in the multi-branch balanced search tree is defined as a combination of the patient's unique identifier (such as medical record number) and the timestamp of the corresponding data history record to ensure that each record has a unique index. The patient's vital signs data collected in real time are inserted into the multi-branch balanced search tree according to the defined index key to form the state-level main tree. An appropriate time segment length (such as 1 minute) is selected to divide the continuously collected vital signs data into continuous time segments.

[0027] Specifically, the data in each time slice is comprehensively analyzed and marked with status, and three state-level subtrees are generated based on the status marking. The comprehensive analysis includes three aspects: threshold range determination, according to medical standards and individual patient conditions, the normal threshold range of each vital sign parameter is set to determine whether the data exceeds the threshold; mutation detection, through differential operation to detect the change rate of vital sign data, identify possible mutation points or abnormal fluctuations; long-term trend analysis, using time series analysis technology to analyze the long-term change trend of the patient's vital sign data, and find the gradual abnormal change pattern. Considering the results of the above three analysis methods and combining the experience and knowledge of professional doctors in the intensive care unit, a comprehensive judgment is made on the patient's vital sign status in the time slice, and the status markings are given: normal, abnormal, and emergency. Based on different status markings, three state-level subtrees are generated. The first-level subtree indicates that the patient's vital sign data in the corresponding time slice is normal, the second-level subtree indicates that the patient's vital sign data in the corresponding time slice is abnormal and needs to be paid special attention to, and the third-level subtree indicates that the patient's vital sign data in the corresponding time slice indicates an emergency and immediate rescue measures need to be taken.

[0028] Specifically, with the status mark as the key value, the information of the status level subtree is updated to the status level main tree, and the analysis results are output. For the data of the first level subtree, it is directly added to the corresponding node of the main tree. If the data already exists, it is ignored. For the data of the second level subtree, first find out whether there is a first level mark at the corresponding time slice position in the main tree. If so, it is updated to abnormal. If not, an abnormal mark is directly added. For the data of the third level subtree, first find out whether there is a second level mark at the corresponding time slice position in the main tree. If so, it is updated to emergency, and the node information is output as a warning signal; if there is no second level mark, an emergency mark is directly added, and a warning signal is output. Through the above steps, the state level tree algorithm can be used to efficiently process a large amount of vital signs data, and realize real-time monitoring and graded warning of patients' health status.

[0029] S3, classify the warning signals based on the signal level bucket algorithm and determine the signal transmission rules; Specifically, the signal level bucket algorithm is a token bucket algorithm. The token bucket algorithm is a network traffic shaping and rate limiting technology. It controls the data transmission rate by simulating a token bucket. The core idea of ​​the algorithm is: the system generates tokens at a certain rate (token generation rate) and stores them in a token bucket. Each token represents a data unit that can be sent. When data needs to be sent, first check whether there are enough tokens in the token bucket. If so, remove the corresponding number of tokens from the bucket and send the data. Otherwise, the data needs to wait until there are enough tokens in the bucket. At the same time, the capacity of the bucket is limited. If the token bucket is full when a new token is generated, the newly generated token will be discarded. The token bucket algorithm can control the rate at which data is sent, while also allowing a certain degree of burst transmission.

[0030] Specifically, a high-speed signal level bucket and a low-speed signal level bucket are constructed, and the signal transmission rate and signal flow size of the two signal level buckets are set. The high-speed signal level bucket and the low-speed signal level bucket are used to manage and schedule the transmission of warning signals. After each signal transmission, the corresponding signal level (token number) will decrease. Set the average signal rate V C and the peak signal rate V P , where V C Indicates the transmission rate of the low-speed signal level bucket to the warning signal, V P Indicates the transmission rate of the high-speed signal level bucket to the warning signal, and V P >V C , set the average flow size S C and peak flow rate S P , where S C Indicates the maximum signal flow size of the low-speed signal level bucket, S P Indicates the maximum signal flow size of the high-speed signal level bucket.

[0031] Specifically, the warning signals are prioritized and marked with colors based on the classification results, and the signal levels of the high-speed signal level bucket and the low-speed signal level bucket are initialized so that the signal level D of the low-speed signal level bucket is C =S C , the signal level of the high-speed signal level barrel is D P =S P , evaluate the non-emergency F of the received warning signal, and compare whether the non-emergency F is greater than the signal level D of the high-speed signal level bucket P If yes, the warning signal is marked as green, and the signal levels of the high-speed signal level bucket and the low-speed signal level bucket remain unchanged. Compare whether the non-emergency F is greater than the signal level D of the low-speed signal level bucket. C If yes, the warning signal is marked as yellow, and the signal level D of the high-speed signal level bucket is updated. P =DP -F, the signal level of the low-speed signal level bucket remains unchanged. Otherwise, the warning signal is marked red, and the signal level of the high-speed signal level bucket is updated D P =D P -F, update the signal level D of the low-speed signal level bucket C =D C -F.

[0032] Specifically, signal transmission rules are formulated based on the marking color. For warning signals marked as red, the peak signal rate V P For yellow warning signals, the average signal rate V C When the red signal transmission is in the off-peak period, the yellow warning signal transmission rate is temporarily increased, but not exceeding the peak signal rate V P For warning signals marked as green, according to the average signal rate V C Transmission, with V C The rate at which the signal level of the low-speed signal level bucket is increased periodically is V P The signal level of the high-speed signal level bucket is periodically increased at a rate until the maximum value is reached, and the signal level is kept unchanged. Through the above steps, the signal level bucket algorithm can be used to classify warning signals according to their urgency, and corresponding transmission rules can be formulated to ensure that warning signals with high urgency can be transmitted faster, thereby responding to the patient's critical condition in a timely manner.

[0033] S4. According to the signal transmission rules, the warning signal is transmitted to the remote monitoring center.

[0034] Specifically, the communication network infrastructure, including routers and gateways, is pre-installed in the hospital to ensure that the intensive care unit area has sufficient communication network coverage. In the intensive care unit, the generated warning signal is first packaged according to the predetermined data format, including patient information, vital signs data, status mark and timestamp, and then the packaged warning signal is sent to the communication network through the communication terminal equipment. According to the signal transmission rules, the communication network is scheduled according to the priority of the warning signal, and the red warning is transmitted at the fastest speed, followed by the yellow warning, and the green warning is transmitted at a regular speed. In the remote monitoring center, a communication receiving device is installed to continuously monitor and receive the warning signal from the intensive care unit, and according to the level and content of the signal, the warning information is displayed in a striking manner on the monitoring screen, and the sound and light alarm is triggered to remind the medical staff and critical medicine experts on duty. The critical medicine experts maintain instant communication with the on-site personnel of the intensive care unit through the equipped communication equipment, and are ready to provide remote guidance and support according to the warning signal at any time, so that the remote monitoring center can be informed of the critical situation of the patients in the intensive care unit in time, and save precious life. Time.

[0035] In one embodiment, using the state level tree algorithm to analyze the collected data in real time and generating an early warning signal according to the analysis result includes the following steps: S21. construct a state-level main tree based on the patient's vital signs data; S22, selecting a time segment length to divide the collected vital sign data into continuous time segment data; S23, performing comprehensive analysis and status marking on the data in each time slice, and generating three status level subtrees based on the status marking; S24, using the state mark as the key value of the state level subtree, updating the state level main tree and outputting the result; S25. Execute steps S22 to S24 in a loop, and generate a warning signal based on the output results.

[0036] In one embodiment, constructing a state level main tree based on the collected data includes the following steps: S211. Create an empty multi-branch balanced search tree for indexing all the patient's vital sign data history records; S212, defining the key of each node in the multi-branch balanced search tree as a combination of a unique identifier of the patient and a timestamp of the corresponding data history record; S213. Insert the patient's vital sign data into the multi-branch balanced search tree according to the defined index key to obtain the state-level main tree.

[0037] In one embodiment, the comprehensive analysis includes: threshold range determination, mutation detection and long-term trend analysis; Among them, threshold range determination is used to set the threshold range of each vital sign data according to medical standards and individual patient conditions; mutation detection is used to observe the rate of change of vital sign data through differential detection and identify mutation points; long-term trend analysis is used to analyze the long-term trend of the patient's vital sign data using time series analysis technology. By considering the results of the above three analysis methods and combining the experience and professional knowledge of clinicians, the patient's vital sign status is judged; Status tags include: normal, abnormal, and emergency; The three status level subtrees correspond to different status tags, including: The first level subtree indicates that the vital signs data are normal; The second level subtree indicates that the vital sign data is abnormal and needs attention; The third level subtree indicates that the vital sign data indicates an emergency situation and requires immediate action.

[0038] In one embodiment, using the state mark as the key value of the state level subtree, updating the state level main tree and outputting the result includes the following steps: S241, for the state-level subtree marked as normal, add the data of each node in the first-level subtree to the state-level main tree, and ignore the data if it already exists; S242, for the state level subtree whose state is marked as abnormal, search for the state level subtree whose state is marked as normal in the corresponding time slice, and update the state mark to abnormal. If not found, check the corresponding node in the state level main tree, and update the state mark from normal to abnormal. S243. For the status level subtree whose status is marked as urgent, search for the status level subtree whose status is marked as abnormal in the corresponding time slice, update the status mark to urgent, delete the status mark of the corresponding node in the status level main tree and output the result. If not found, check the corresponding node in the status level main tree and update the status marked as abnormal to urgent.

[0039] In one embodiment, classifying the warning signal based on the signal level bucket algorithm and determining the signal transmission rule includes the following steps: S31, constructing a high-speed signal level bucket and a low-speed signal level bucket, and setting the signal transmission rate and signal flow size of the two signal level buckets; S32, classifying the priority of the warning signal and marking the color based on the classification result; S33. Formulate signal transmission rules based on the marking color.

[0040] In one embodiment, constructing a high-speed signal level bucket and a low-speed signal level bucket, and setting the signal transmission rate and signal flow size of the two signal level buckets includes the following steps: S311. Construct a high-speed signal level bucket and a low-speed signal level bucket. The signal level bucket is used to manage and schedule the transmission of warning signals, and each time a signal is transmitted, the corresponding signal level is consumed. S312, set the average signal rate V C and the peak signal rate V P , where V C Indicates the transmission rate of the low-speed signal level bucket to the warning signal, V P Indicates the transmission rate of the high-speed signal level bucket to the warning signal, and V P> V C ; S313, set the average flow size S C and peak flow rate S P , where S C Indicates the maximum signal flow size of the low-speed signal level bucket, S P Indicates the maximum signal flow size of the high-speed signal level bucket.

[0041] In one embodiment, the priority classification of the warning signal and the color marking based on the classification result include the following steps: S321, initialize the signal levels of the high-speed signal level bucket and the low-speed signal level bucket, so that the signal level of the low-speed signal level bucket is D C =S C , the signal level of the high-speed signal level barrel is D P =S P ; S322, evaluate the non-emergency F of the received warning signal, and compare whether the non-emergency F is greater than the signal level D of the high-speed signal level bucket P If yes, the warning signal is marked as green, and the signal levels of the high-speed signal level bucket and the low-speed signal level bucket remain unchanged; S323: Compare whether the non-emergency F is greater than the signal level D of the low-speed signal level bucket C If yes, the warning signal is marked as yellow, and the signal level D of the high-speed signal level bucket is updated. P =D P -F, the signal level of the low-speed signal level bucket remains unchanged, otherwise the warning signal is marked red, and the signal level of the high-speed signal level bucket is updated D P =D P -F, update the signal level D of the low-speed signal level bucket C =D C -F.

[0042] In one embodiment, formulating a signal transmission rule based on a marker color includes the following steps: S331: Formulate signal transmission rules based on the marking color. For warning signals marked in red, the peak signal rate V P transmission; S332: For the warning signal marked as yellow, according to the average signal rate V C Transmission: When the red signal transmission is in the off-peak period, the yellow warning signal transmission rate is temporarily increased, and does not exceed the peak signal rate V P ; S333: For warning signals marked as green, according to the average signal rate V C transmission; S334: V C As the rate of increase continues to increase the signal level of the low-speed signal level bucket, V P As the signal level of the high-speed signal level bucket that continues to increase the rate cycle, when the signal level bucket reaches the maximum signal level, the excess signal level is discarded, among which the maximum signal level of the low-speed signal level bucket is D C =S C , the maximum signal level of the high-speed signal level bucket DP =S P .

[0043] In order to facilitate understanding of the above technical scheme of the present invention, the following is a specific explanation taking the intensive care unit of a central hospital as an example: a 62-year-old patient was admitted to the intensive care unit of the hospital due to multiple fractures caused by a serious car accident. According to the implementation scheme of the present invention, the hospital first installed advanced vital signs monitoring equipment for the patient in the intensive care unit, continuously collected the patient's vital signs data, and uploaded it to the hospital's data center in real time through the built-in communication module. Then, the state level tree algorithm is used to process the massive monitoring data from the intensive care unit in real time. The algorithm first preprocesses and extracts features from the original data, then constructs a state level main tree, and dynamically updates the tree structure according to changes in the data. At the same time, the algorithm conducts a comprehensive analysis of the data of each time segment, automatically generates the patient's health status mark (normal, abnormal, emergency) and attaches it to the state level subtree. When the patient's vital signs data is abnormal, the system will automatically generate warning signals of different levels, and use the signal level bucket algorithm to mark it according to the urgency of the warning signal. Green, yellow and red, differentiated transmission strategies are formulated based on the marking colors; in the early morning of the third day when the patient was admitted to the intensive care unit, the monitoring equipment detected a sudden abnormal change in the patient's heart rate and immediately issued a red warning signal to the remote monitoring center. The remote monitoring center is equipped with a number of experienced critical care medicine experts who monitor the warning information from the intensive care unit in real time through a large screen. After receiving the red warning, the expert team immediately activated the emergency response mechanism, established a high-definition video connection with the intensive care unit using the communication network, determined that the patient was at risk of post-traumatic cardiac arrest, and immediately and remotely guided the on-site medical staff to perform cardiac cardioversion and rescue, saving the patient's precious life; the application of the present invention greatly improves the signal transmission efficiency and monitoring quality of the intensive care unit, and transmits warning information in real time through the communication network, so that medical staff can discover changes in the patient's condition in the first time and strive for golden rescue time. In addition, the intervention of the remote expert team also makes up for the shortage of critical care medicine talents in grassroots hospitals and effectively improves the treatment level of difficult and critically ill patients.

[0044] like Figure 2 According to another embodiment of the present invention, a remote monitoring and early warning system for an intensive care unit is provided. The remote monitoring and early warning system for an intensive care unit includes: A real-time monitoring module 1, used to continuously collect the patient's vital sign data through the vital sign monitoring equipment in the intensive care unit; The signal generation module 2 is used to analyze the patient's vital sign data in real time using the state level tree algorithm and generate an early warning signal according to the analysis results; The signal transmission module 3 is used to classify the warning signal based on the signal level bucket algorithm and determine the signal transmission rules; The remote monitoring module 4 is used to transmit the warning signal to the remote monitoring center according to the signal transmission rules; The real-time monitoring module 1 is connected to the signal transmission module 3 via the signal generation module 2 , and the signal transmission module 3 is connected to the remote monitoring module 4 .

[0045] To sum up, with the help of the above-mentioned technical scheme of the present invention, the present invention uses the state level tree algorithm to analyze the vital signs data of patients in the intensive care unit in real time, and effectively classifies and indexes the vital signs data of patients by constructing a state level main tree and three state level subtrees, thereby realizing fast and accurate data retrieval and state evaluation, and can quickly generate warning signals in emergency situations to provide medical personnel with immediate warning information. At the same time, by constructing high-speed and low-speed signal level buckets and setting detailed signal transmission rules, the signal level can be dynamically adjusted to give priority to the transmission of emergency signals, which not only ensures the instant transmission of important signals, but also avoids the waste of network resources, and improves the application efficiency and stability of communication networks in remote monitoring of intensive care. By introducing the state level tree algorithm, the present invention can process and analyze the vital signs data of patients in the intensive care unit in real time, which not only improves the efficiency of data processing, but also enhances the accuracy of warning signal generation. With the help of constructing a state level main tree and three state level subtrees, the present invention can quickly generate warning signals in emergency situations to provide medical personnel with immediate warning information. At the same time, by constructing high-speed and low-speed signal level buckets and setting detailed signal transmission rules, the signal level can be dynamically adjusted to give priority to the transmission of emergency signals, which not only ensures the instant transmission of important signals, but also avoids the waste of network resources, and improves the application efficiency and stability of communication networks in intensive care remote monitoring. The state-level subtree can effectively retrieve and evaluate the patient's vital signs data quickly and accurately, and can quickly generate warning signals in emergency situations to provide medical personnel with immediate warning information. By dividing the time slice data and performing comprehensive analysis, this method not only focuses on the data changes at a single time point, but also takes into account the long-term trends, thereby more comprehensively evaluating the patient's health status and improving the accuracy of remote monitoring. By applying the signal level bucket algorithm, the present invention proposes transmission rules for warning signals of different urgency levels, ensuring the response speed and reliability of the intensive care unit remote monitoring system at critical moments, making the transmission of warning signals more efficient and orderly. In addition, by constructing high-speed and low-speed signal level buckets and automatically adjusting them according to the signal level consumption after transmission, the present invention further optimizes the classification and transmission process of warning signals. This mechanism ensures that emergency warning signals can be transmitted first, while effectively utilizing network resources and reducing the occupation of network bandwidth by non-emergency signals.

[0046] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A remote monitoring early warning method for an intensive care unit, characterized in that: The intensive care unit remote monitoring early warning method comprises the following steps: S1. Continuously collect the patient's vital signs data through the vital signs monitoring equipment in the intensive care unit; S2. Analyze the patient's vital sign data in real time using the state level tree algorithm and generate an early warning signal based on the analysis results; S3, classify the warning signals based on the signal level bucket algorithm and determine the signal transmission rules; S4. According to the signal transmission rules, the warning signal is transmitted to the remote monitoring center.

2. The intensive care unit remote monitoring early warning method according to claim 1, characterized in that: The method of analyzing the patient's vital sign data in real time using the state level tree algorithm and generating an early warning signal according to the analysis result includes the following steps: S21. construct a state-level main tree based on the patient's vital signs data; S22, selecting a time segment length to divide the collected vital sign data into continuous time segment data; S23, performing comprehensive analysis and status marking on the data in each time slice, and generating three status level subtrees based on the status marking; S24, using the state mark as the key value of the state level subtree, updating the state level main tree and outputting the result; S25. Execute steps S22 to S24 in a loop, and generate a warning signal based on the output results.

3. The intensive care unit remote monitoring early warning method according to claim 2, characterized in that: The construction of the state level main tree based on the patient's vital signs data comprises the following steps: S211. Create an empty multi-branch balanced search tree for indexing all the patient's vital sign data history records; S212, defining the key of each node in the multi-branch balanced search tree as a combination of a unique identifier of the patient and a timestamp of the corresponding data history record; S213. Insert the patient's vital sign data into the multi-branch balanced search tree according to the defined index key to obtain the state-level main tree.

4. The intensive care unit remote monitoring early warning method according to claim 3, characterized in that: The comprehensive analysis includes: threshold range determination, mutation detection and long-term trend analysis; Among them, threshold range determination is used to set the threshold range of each vital sign data according to medical standards and individual patient conditions; mutation detection is used to observe the rate of change of vital sign data through differential detection and identify mutation points; long-term trend analysis is used to analyze the long-term trend of the patient's vital sign data using time series analysis technology. By considering the results of the above three analysis methods and combining the experience and professional knowledge of clinicians, the patient's vital sign status is judged; The status marks include: normal, abnormal, and emergency; The three state level subtrees correspond to different state tags, including: The first level subtree indicates that the vital signs data are normal; The second level subtree indicates that the vital sign data is abnormal and needs attention; The third level subtree indicates that the vital sign data indicates an emergency situation and requires immediate action.

5. The intensive care unit remote monitoring early warning method according to claim 4, characterized in that: The method of using the state mark as the key value of the state level subtree, updating the state level main tree and outputting the result comprises the following steps: S241, for the state-level subtree marked as normal, add the data of each node in the first-level subtree to the state-level main tree, and ignore the data if it already exists; S242, for the state level subtree whose state is marked as abnormal, search for the state level subtree whose state is marked as normal in the corresponding time slice, and update the state mark to abnormal. If not found, check the corresponding node in the state level main tree, and update the state mark from normal to abnormal. S243. For the status level subtree whose status is marked as urgent, search for the status level subtree whose status is marked as abnormal in the corresponding time slice, update the status mark to urgent, delete the status mark of the corresponding node in the status level main tree and output the result. If not found, check the corresponding node in the status level main tree and update the status marked as abnormal to urgent.

6. The intensive care unit remote monitoring early warning method according to claim 1, characterized in that: The method of classifying the warning signal based on the signal level bucket algorithm and determining the signal transmission rule includes the following steps: S31, constructing a high-speed signal level bucket and a low-speed signal level bucket, and setting the signal transmission rate and signal flow size of the two signal level buckets; S32, classifying the priority of the warning signal and marking the color based on the classification result; S33. Formulate signal transmission rules based on the marking color.

7. The intensive care unit remote monitoring early warning method according to claim 6, characterized in that: The process of constructing a high-speed signal level bucket and a low-speed signal level bucket and setting the signal transmission rate and signal flow size of the two signal level buckets includes the following steps: S311. Construct a high-speed signal level bucket and a low-speed signal level bucket. The signal level bucket is used to manage and schedule the transmission of warning signals, and each time a signal is transmitted, the corresponding signal level is consumed. S312, set the average signal rate V C and the peak signal rate V P , where V C Indicates the transmission rate of the low-speed signal level bucket to the warning signal, V P Indicates the transmission rate of the high-speed signal level bucket to the warning signal, and V P >V C ; S313, set the average flow size S C and peak flow rate S P , where S C Indicates the maximum signal flow size of the low-speed signal level bucket, S P Indicates the maximum signal flow size of the high-speed signal level bucket.

8. The intensive care unit remote monitoring early warning method according to claim 7, characterized in that: The step of prioritizing the warning signals and marking the colors based on the classification results includes the following steps: S321, initialize the signal levels of the high-speed signal level bucket and the low-speed signal level bucket, so that the signal level of the low-speed signal level bucket is D C =S C , the signal level of the high-speed signal level barrel is D P =S P ; S322, evaluate the non-emergency F of the received warning signal, and compare whether the non-emergency F is greater than the signal level D of the high-speed signal level bucket P If yes, the warning signal is marked as green, and the signal levels of the high-speed signal level bucket and the low-speed signal level bucket remain unchanged; S323: Compare whether the non-emergency F is greater than the signal level D of the low-speed signal level bucket C If yes, the warning signal is marked as yellow, and the signal level D of the high-speed signal level bucket is updated. P =D P -F, the signal level of the low-speed signal level bucket remains unchanged, otherwise the warning signal is marked red, and the signal level of the high-speed signal level bucket is updated D P =D P -F, update the signal level D of the low-speed signal level bucket C =D C -F.

9. The intensive care unit remote monitoring early warning method according to claim 8, characterized in that: The signal transmission rule formulated based on the marking color comprises the following steps: S331: Formulate signal transmission rules based on the marking color. For warning signals marked in red, the peak signal rate V P transmission; S332: For the warning signal marked as yellow, according to the average signal rate V C Transmission: When the red signal transmission is in the off-peak period, the yellow warning signal transmission rate is temporarily increased, and does not exceed the peak signal rate V P ; S333: For warning signals marked as green, according to the average signal rate V C transmission; S334: V C As the rate of increase continues to increase the signal level of the low-speed signal level bucket, V P As the signal level of the high-speed signal level bucket that continues to increase the rate cycle, when the signal level bucket reaches the maximum signal level, the excess signal level is discarded, among which the maximum signal level of the low-speed signal level bucket is D C =S C , the maximum signal level of the high-speed signal level bucket D P =S P .

10. An intensive care unit remote monitoring early warning system, used to implement the intensive care unit remote monitoring early warning method according to any one of claims 1 to 9, characterized in that: The intensive care unit remote monitoring early warning system includes: A real-time monitoring module, which is used to continuously collect the patient's vital sign data through the vital sign monitoring equipment in the intensive care unit; A signal generation module is used to analyze the patient's vital sign data in real time using a state level tree algorithm and generate an early warning signal based on the analysis results; A signal transmission module is used to classify warning signals based on a signal level bucket algorithm and determine signal transmission rules; A remote monitoring module is used to transmit the warning signal to the remote monitoring center according to the signal transmission rules; Wherein, the real-time monitoring module is connected to the signal transmission module through the signal generation module, and the signal transmission module is connected to the remote monitoring module.

Images