Early warning system for emergency of critical patient

By designing an early warning system for sudden outbreaks in critically ill patients, identifying vital signs and monitoring indicators related to the condition, automatically triggering alarms and analyzing processing efficiency and data transmission accuracy, the problem of information overload is solved and rapid and accurate risk identification and management is achieved. , improves medical efficiency and quality.

CN118983112APending Publication Date: 2024-11-19WUXI NO 2 PEOPLES HOSPITAL
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202410851985.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-28
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

In the prior art, the monitoring data of critically ill patients is large, resulting in information overload, and key information may be buried or ignored, affecting accurate assessment and timely intervention.

Method used

Design an early warning system for sudden outbreaks in critically ill patients, including clinical data acquisition module, automatic warning module, comprehensive evaluation module, abnormal division module and processing module. By identifying the vital signs and monitoring indicators related to the disease, setting the warning threshold, and automatically Trigger the alarm, analyze the processing efficiency and data transmission accuracy, divide the abnormality degree, and carry out corresponding management.

Benefits of technology

实现了快速准确识别和应对患者风险,提高了医疗效率和质量,为医护人员提供可靠的数据支持,确保患者安全和健康。

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118983112A_ABST
    Figure CN118983112A_ABST
Patent Text Reader

Abstract

The invention discloses a critical patient emergency early warning system, and relates to the technical field of critical patient monitoring, and the critical patient emergency early warning system collects clinical data of a critical patient, identifies vital signs and monitoring indexes related to patient deterioration, and sets an early warning threshold value of each monitoring index. When the monitoring data exceed a preset early warning threshold value, the system automatically triggers an alarm; comprehensively analyzing the processing efficiency stability of the monitoring data and the transmission accuracy of the monitoring data after the alarm is triggered, and evaluating the abnormal degree of the critical patient in the monitoring data processing process; according to the evaluation result, the abnormal degree is divided into serious abnormity, general abnormity and slight abnormity, and corresponding management is carried out on the abnormal degrees; the abnormal degree of the managed critical patient monitoring data in the processing process is further analyzed, so that the medical quality and safety are improved, the medical risk is reduced, the medical efficiency is improved, personalized medical management is achieved, and the medical cost is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of critically ill patient monitoring, and in particular to an early warning system for sudden illness of critically ill patients. Background Art

[0002] Early warning of sudden illness in critically ill patients means identifying early signs that may indicate changes in the patient's condition through a series of observations and tests before the patient's condition worsens. These signs may include abnormal changes in vital signs, such as increased heart rate and respiratory rate, fluctuations in blood pressure, etc.; as well as changes in clinical manifestations, such as increased pain and changes in consciousness. By identifying these early warning signals in a timely manner, medical staff can take appropriate measures to conduct more effective interventions and treatments, which will help reduce the risk of worsening of the patient's condition and increase the success rate of treatment.

[0003] In the medical environment, achieving early warning of sudden illness in critically ill patients requires the comprehensive use of various monitoring technologies and clinical experience to establish a systematic evaluation and monitoring mechanism. This includes regular monitoring of patients' vital signs, using advanced life support systems to monitor patients' physiological parameters in real time, and combining clinical observation and evaluation of patients' conditions by medical staff. In addition, it is necessary to establish a complete data recording and analysis system to record and analyze patients' monitoring data in real time to detect abnormal changes and respond in a timely manner. The comprehensive use of these means can effectively improve the ability to identify and respond to early warning of sudden illness in critically ill patients, and provide more powerful support for patients' treatment and rehabilitation.

[0004] The prior art has the following deficiencies:

[0005] In the existing technology, for critically ill patients, the monitoring data may be very large, including vital signs monitoring, laboratory test results, etc., and medical staff need to process a large amount of information. In this case, information overload may occur, causing key information to be buried or ignored, thus affecting the accurate assessment of the patient's condition and timely intervention. Summary of the invention

[0006] The purpose of the present invention is to provide an early warning system for sudden illness in critically ill patients to overcome the deficiencies in the background technology.

[0007] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: an early warning system for sudden illness in critically ill patients, characterized by comprising a clinical data acquisition module, an automatic warning module, a comprehensive evaluation module, an abnormal classification module and a processing module;

[0008] Clinical data acquisition module: determine the vital signs and monitoring indicators of critically ill patients, collect clinical data of critically ill patients, and identify vital signs and monitoring indicators related to the deterioration of the patient's condition;

[0009] Automatic warning module: According to the patient's vital signs and monitoring indicators related to the deterioration of the condition, the warning threshold of each monitoring indicator is set. When the monitoring data exceeds the preset warning threshold, the system automatically triggers an alarm;

[0010] Comprehensive evaluation module: conducts a comprehensive analysis of the processing efficiency and stability of monitoring data after the alarm is triggered, as well as the transmission accuracy of monitoring data, and evaluates the degree of abnormality in the processing of critically ill patients' monitoring data;

[0011] Abnormal classification module: According to the evaluation results, the abnormal degree in the process of critically ill patients' monitoring data processing is divided into severe abnormality, general abnormality, and minor abnormality, and they are managed accordingly;

[0012] Processing module: Further analyze the abnormality of the monitoring data processing of critically ill patients after management to improve the level and quality of monitoring data processing.

[0013] In a preferred embodiment, in the automatic warning module, when the monitoring data exceeds the preset warning threshold, the system automatically triggers an alarm, specifically including:

[0014] Determine the physiological indicators and monitoring indicators related to the patient's condition deterioration, and define the monitoring indicator set X = {x1, x2, ..., xn}, where xi represents the i-th monitoring indicator;

[0015] Collect historical data sets D = {d1, d2, ..., dm}, where each di contains the value of the monitoring indicator and related information, and define the warning threshold Ti for each monitoring indicator xi;

[0016] During the real-time monitoring process, for each monitoring indicator xi, the monitoring system will continuously obtain the latest patient data xnew. When xnew is greater than Ti, an early warning signal is generated to notify medical staff for further processing; when xnew is less than or equal to Ti, no early warning signal is generated.

[0017] In a preferred embodiment, in the comprehensive evaluation module, the correlation between the alarm response time and the data processing speed is analyzed to obtain the processing efficiency fluctuation index of the monitoring data, and the processing efficiency stability of the monitoring data after the alarm is triggered is evaluated. The method for obtaining the processing efficiency fluctuation index is:

[0018] Collect the alarm triggering time and the time data of medical staff processing monitoring data, and construct the collected data into a time series;

[0019] For each alarm, the time difference between the time when the medical staff processes the monitoring data and the time when the alarm is triggered is calculated, that is, the response time. The specific calculation expression is: RT = TP-TA; where TP is the time when the medical staff processes the monitoring data, TA is the alarm trigger time, and RT is the response time;

[0020] The standard deviation is used to calculate the processing efficiency fluctuation index. The specific calculation expression is: In the formula, ER et is the processing efficiency fluctuation index, RT a is the ath response time, indicating the time difference between the time when the medical staff processes the monitoring data and the time when the corresponding alarm is triggered. YT is the average of all response times, indicating the average response time of the medical staff to process the monitoring data, and N is the number of response times.

[0021] In a preferred embodiment, in the comprehensive evaluation module, the accuracy of the monitoring data after the alarm is triggered is analyzed, the abnormality of the monitoring data during the transmission process is determined, the transmission frequency outlier index of the monitoring data is obtained, and the transmission accuracy of the monitoring data is evaluated. The method for obtaining the transmission frequency outlier index is:

[0022] Obtain the transmission timestamp of the monitoring data from the monitoring system. For the timestamps t1, t2, ..., tn, calculate the transmission time interval Δti = ti + 1 - ti between adjacent time points, where i = 1, 2, ..., n - 1, ti represents the timestamp of the monitoring data transmission, and construct the transmission time interval Δti into a feature vector, represented as T = [Δt1, Δt2, ..., Δtn - 1];

[0023] The local outlier factor value of each eigenvector Ti is calculated using the LOF algorithm and expressed as: LOF(xi), where i = 1, 2, ..., n-1; the average value of the LOF value is calculated, and the specific calculation expression is: Where μLOF is the average value of LOF values. The standard value is calculated based on the average value of LOF values, that is, the transmission frequency outlier index is calculated. The specific calculation expression is: In the formula, EP mb is the transmission frequency outlier index.

[0024] In a preferred embodiment, the processing efficiency fluctuation index and the transmission frequency outlier index are normalized, and the abnormal evaluation coefficient in the critically ill patient monitoring data processing process is calculated based on the normalized processing efficiency fluctuation index and the transmission frequency outlier index.

[0025] In a preferred embodiment, in the abnormality classification module, according to the evaluation results, the abnormality degree in the critically ill patient monitoring data processing process is divided into severe abnormality, general abnormality, and slight abnormality, specifically:

[0026] Compare the abnormal assessment coefficient obtained during the processing of the critically ill patient monitoring data with the gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and compare the abnormal assessment coefficient with the first standard threshold and the second standard threshold respectively;

[0027] If the abnormality assessment coefficient is greater than the second standard threshold, the degree of abnormality in the processing of critically ill patient monitoring data is classified as severe abnormality; if the abnormality assessment coefficient is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the degree of abnormality in the processing of critically ill patient monitoring data is classified as general abnormality; if the abnormality assessment coefficient is less than the first standard threshold, the degree of abnormality in the processing of critically ill patient monitoring data is classified as minor abnormality.

[0028] In a preferred embodiment, in the processing module, the abnormal degree in the process of processing the critically ill patient monitoring data after management is further analyzed, the abnormal assessment coefficients in the process of processing the critically ill patient monitoring data within a period of time are continuously collected, and the abnormal assessment coefficients in the process of processing the critically ill patient monitoring data collected are used to establish a corresponding data set, and the abnormal assessment coefficients in the process of processing the critically ill patient monitoring data in the set are compared and analyzed with the abnormal assessment coefficient reference threshold, and the risk index in the process of processing the critically ill patient monitoring data is calculated. The specific calculation expression is: Where RW pk is the risk index, H is the number of abnormal evaluation coefficients collected within a period of time, k is the label of the abnormal evaluation coefficient, TF rb It is the reference threshold of the abnormal assessment coefficient.

[0029] In a preferred embodiment, the acquired risk index is compared with a risk index reference threshold; if the risk index is greater than or equal to the risk index reference threshold, a warning signal is generated; if the risk index is less than the risk index reference threshold, no warning signal is generated.

[0030] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0031] 1. The present invention collects clinical data of critically ill patients, identifies vital signs and monitoring indicators related to the worsening of the patient's condition, and sets a warning threshold for each monitoring indicator. When the monitoring data exceeds the preset warning threshold, the system automatically triggers an alarm; a comprehensive analysis is conducted on the processing efficiency and stability of the monitoring data after the alarm is triggered, as well as the transmission accuracy of the monitoring data, to evaluate the degree of abnormality in the processing of critically ill patients' monitoring data; based on the evaluation results, the degree of abnormality is divided into severe abnormality, general abnormality, and minor abnormality, and each is managed accordingly. The system can quickly and accurately identify and respond to risks that patients may face, realize personalized medical management, and provide patients with safer, more efficient, and more considerate medical services.

[0032] 2. By comprehensively comparing the risk index with the preset reference threshold, the system can quickly determine whether there is a potential risk in the monitoring data processing process after management, and take corresponding early warning measures to ensure the safety and health of patients. This method effectively improves medical efficiency and quality, provides more reliable data support for medical staff, and provides patients with safer and more efficient medical services. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0034] Figure 1 The present invention is a flow chart of the method.

[0035] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] Example 1, please refer to Figure 1 , 2 As shown, the early warning system for sudden illness in critically ill patients described in this embodiment includes a clinical data acquisition module, an automatic warning module, a comprehensive evaluation module, an abnormal classification module and a data processing module;

[0038] Clinical data acquisition module: determine the vital signs and monitoring indicators of critically ill patients, collect clinical data of critically ill patients, and identify vital signs and monitoring indicators related to the deterioration of the patient's condition;

[0039] Automatic warning module: According to the patient's vital signs and monitoring indicators related to the deterioration of the condition, the warning threshold of each monitoring indicator is set. When the monitoring data exceeds the preset warning threshold, the system automatically triggers an alarm;

[0040] Comprehensive evaluation module: conducts a comprehensive analysis of the processing efficiency and stability of monitoring data after the alarm is triggered, as well as the transmission accuracy of monitoring data, and evaluates the degree of abnormality in the processing of critically ill patients' monitoring data;

[0041] Abnormal classification module: According to the evaluation results, the abnormal degree in the process of critically ill patients' monitoring data processing is divided into severe abnormality, general abnormality, and minor abnormality, and they are managed accordingly;

[0042] Data processing module: further analyze the abnormality of the monitoring data processing of critically ill patients after management to improve the level and quality of monitoring data processing.

[0043] Among them, in the clinical data acquisition module, the vital signs and monitoring indicators of critically ill patients are determined, the clinical data of critically ill patients are collected, and the vital signs and monitoring indicators related to the deterioration of the patient's condition are identified, specifically:

[0044] First, determine the vital signs and indicators that need to be monitored, including but not limited to: heart rate, respiratory rate, blood pressure, body temperature, blood oxygen saturation, mental state, urine output and other physiological parameters. In addition, the patient's laboratory test results, such as blood biochemical indicators, blood gas analysis, electrolyte levels, etc., should also be considered.

[0045] Collect clinical data from critically ill patients, including vital signs monitoring data and laboratory test results. This can be collected automatically through modern medical equipment and information systems, or through manual recording.

[0046] Analyze the collected clinical data, focusing on the vital signs and monitoring indicators related to the patient's condition deterioration. Use statistical methods and data mining techniques to identify the characteristics and patterns associated with the patient's adverse clinical events.

[0047] Among them, data mining technology is used to find the correlation between physiological characteristics and monitoring indicators related to adverse clinical events of patients, including:

[0048] First, clinical data including physiological characteristics and monitoring indicators are collected. These data can come from sources such as hospital information systems, electronic medical records, vital signs monitoring instruments, laboratory test results, etc. The collected data is cleaned and preprocessed, including removing duplicate data, processing missing values, outliers and noise data, to ensure data quality and accuracy.

[0049] From all physiological characteristics and monitoring indicators, select features that may be associated with adverse clinical events in patients. This can be guided by expert knowledge and domain experience, or feature selection algorithms can be used to automatically select the most relevant features. The selected features are transformed and standardized to have similar scales and distributions for subsequent data mining analysis.

[0050] Select appropriate data mining techniques and models to discover the correlation between physiological characteristics and monitoring indicators. Commonly used data mining techniques include association rule mining, cluster analysis, classification and prediction, etc.

[0051] Use the selected data mining model to train and evaluate the processed data. By dividing the data set into a training set and a test set, use the training set to train the model, and then use the test set to evaluate the performance and accuracy of the model.

[0052] Analyze the trained data mining model to find the association rules or patterns between physiological characteristics and monitoring indicators. These rules or patterns may include the combination of specific physiological characteristics, the interaction relationship between indicators, etc.

[0053] Interpret the mined association rules or patterns, understand the correlation between physiological characteristics and monitoring indicators, and their relationship with patients' adverse clinical events. According to the mining results, formulate corresponding prevention strategies and intervention measures to reduce the incidence of adverse clinical events.

[0054] Based on the analysis results, vital signs and monitoring indicators that may indicate a worsening of the patient's condition are identified. These indicators may appear as abnormal values, trend changes, or specific patterns, such as increased heart rate, rapid breathing, decreased blood pressure, decreased oxygen saturation, etc.

[0055] Automatic warning module: According to the vital signs and monitoring indicators related to the deterioration of the patient's condition, the warning threshold of each monitoring indicator is set. When the monitoring data exceeds the preset warning threshold, the system automatically triggers the alarm.

[0056] Based on medical knowledge and the characteristics of the deterioration of the condition, determine the physiological indicators and monitoring indicators related to the deterioration of the patient's condition. These indicators may include heart rate, respiratory rate, blood pressure, body temperature, blood oxygen saturation, etc. Define the monitoring indicator set X = {x1, x2, ..., xn}, where xi represents the i-th monitoring indicator.

[0057] Collect historical data sets D = {d1, d2, ..., dm}, where each di contains the value of the monitoring indicator and related information; for each monitoring indicator xi, define the warning threshold Ti, which can be determined by statistical methods or based on clinical guidelines.

[0058] During the real-time monitoring process, for each monitoring indicator xi, the monitoring system will continuously obtain the latest patient data xnew. When xnew is greater than Ti, an early warning signal is generated to notify medical staff for further processing; when xnew is less than or equal to Ti, no early warning signal is generated.

[0059] Comprehensive evaluation module: conducts a comprehensive analysis of the processing efficiency and stability of monitoring data after the alarm is triggered, as well as the transmission accuracy of monitoring data, and evaluates the degree of abnormality in the processing of critically ill patients' monitoring data;

[0060] Analyzing the efficiency of monitoring data processing after an alarm is triggered means evaluating the speed and efficiency of medical staff in processing monitoring data after receiving the alarm. Determine the time it takes from the alarm being triggered to the time medical staff begin processing monitoring data. A shorter response time usually means that medical staff are able to recognize changes in the patient's condition more quickly and take appropriate intervention measures. Analyze the speed at which medical staff process monitoring data. This includes evaluating how quickly and accurately they analyze data, identify anomalies, make decisions, and implement intervention measures. Comprehensively analyze the time it takes from the alarm being triggered to the time medical staff begin processing monitoring data and the speed at which medical staff process monitoring data, and evaluate the stability of the efficiency of monitoring data processing after the alarm is triggered.

[0061] The correlation between the alarm response time and the data processing speed is analyzed to obtain the processing efficiency fluctuation index of the monitoring data, and the processing efficiency stability of the monitoring data after the alarm is triggered is evaluated. The method for obtaining the processing efficiency fluctuation index is:

[0062] Collect the alarm trigger time and the time when the medical staff processes the monitoring data, and construct the collected data into a time series, which includes the alarm trigger time and the time when the medical staff processes the monitoring data. The unit of the time series can be seconds, minutes or hours, depending on the time granularity of the data.

[0063] For each alarm, the time difference between the time when the medical staff processes the monitoring data and the time when the alarm is triggered is calculated, that is, the response time. The specific calculation expression is: RT = TP-TA; where TP is the time when the medical staff processes the monitoring data, TA is the alarm trigger time, and RT is the response time;

[0064] The standard deviation is used to calculate the processing efficiency fluctuation index. The standard deviation measures the degree of deviation of each data point in the data set from the average value, thereby reflecting the volatility of the data. The specific calculation expression is: In the formula, ER et is the processing efficiency fluctuation index, RT a is the ath response time, which indicates the time difference between the time when the medical staff processes the monitoring data and the time when the corresponding alarm is triggered, YT is the average of all response times, which indicates the average response time of the medical staff to process the monitoring data, and N is the number of response times;

[0065] The larger the processing efficiency fluctuation index, the greater the volatility of the processing efficiency, that is, the speed at which medical staff process monitoring data varies and fluctuates greatly. This may result in the time to process monitoring data sometimes being fast and sometimes slow, lacking stability. Therefore, the larger the processing efficiency fluctuation index, it usually indicates a higher degree of abnormality in the processing of critically ill patient monitoring data.

[0066] Inconsistent response: There are differences in the response speed of medical staff at different times or in different situations, resulting in fluctuations in the time to process monitoring data.

[0067] Time-consuming processing: Some monitoring data may require more time to analyze or process. For example, when an abnormal situation occurs, additional inspection or intervention is required, resulting in reduced processing efficiency.

[0068] Workload: The workload of medical staff is uneven, resulting in fluctuations in the speed of processing monitoring data. For example, during peak hours or emergency situations, medical staff may need to process more monitoring data, resulting in reduced processing efficiency.

[0069] Analyze the accuracy of monitoring equipment, determine possible errors in data collection and possible errors in data transmission and storage, to ensure that the collected monitoring data is accurate and reliable.

[0070] Analyze the accuracy of the monitoring data after the alarm is triggered, determine the degree of abnormality of the monitoring data during transmission, obtain the transmission frequency outlier index of the monitoring data, and evaluate the transmission accuracy of the monitoring data. The method for obtaining the transmission frequency outlier index is:

[0071] Obtain the transmission timestamp or time series data of the monitoring data from the monitoring system. For timestamps t1, t2, ..., tn, calculate the transmission time interval Δti = ti + 1 - ti between adjacent time points, where i = 1, 2, ..., n-1, ti represents the timestamp of the monitoring data transmission, and construct the transmission time interval Δti into a feature vector, expressed as T = [Δt1, Δt2, ..., Δtn-1];

[0072] The local outlier factor value of each eigenvector Ti is calculated using the LOF algorithm and expressed as: LOF(xi), where i = 1, 2, ..., n-1; the average value of the LOF value is calculated, and the specific calculation expression is: Where μLOF is the average value of LOF values. The standard value is calculated based on the average value of LOF values, that is, the transmission frequency outlier index is calculated. The specific calculation expression is: In the formula, EP mb is the transmission frequency outlier index.

[0073] Unstable data transmission: A large transmission frequency outlier index indicates that the transmission frequency of the monitoring data fluctuates greatly, that is, the data transmission process is unstable. This may be caused by factors such as transmission delay, data loss, network failure or system error.

[0074] More transmission anomalies: A larger outlier index indicates that there are more anomalies in the monitoring data transmission process. These anomalies may include data transmission interruption, transmission errors, data loss or repeated transmission, which affect the integrity and accuracy of the monitoring data.

[0075] Increased data processing pressure: If the monitoring data transmission frequency is abnormally high, it may increase the pressure on medical staff to process monitoring data. They need to deal with data anomalies or failures more frequently, which may lead to decreased processing efficiency and delayed implementation of intervention measures.

[0076] Increased potential risks: Due to abnormally frequent data transmission, the real-time and accuracy of monitoring data may be affected, thereby increasing the risk of not detecting or intervening in time for changes in the patient's condition, which may have an adverse effect on the patient's health.

[0077] The processing efficiency fluctuation index and the transmission frequency outlier index are normalized, and the abnormal assessment coefficient in the processing of critically ill patient monitoring data is calculated based on the normalized processing efficiency fluctuation index and the transmission frequency outlier index.

[0078] For example, the present invention can use the following formula to calculate the abnormal evaluation coefficient in the process of critically ill patient monitoring data processing, and the calculation expression is: Where TF k is the abnormal evaluation coefficient, ER et is the processing efficiency fluctuation index, EP mb is the transmission frequency outlier index, a 1 、a 2 is the proportionality coefficient of the processing efficiency fluctuation index and the transmission frequency outlier index, and a 2 >a 1 >0.

[0079] Abnormality classification module: According to the evaluation results, the abnormality degree in the processing of critically ill patients' monitoring data is divided into severe abnormality, general abnormality, and minor abnormality, and they are managed accordingly.

[0080] Compare the abnormal assessment coefficient obtained during the processing of the critically ill patient monitoring data with the gradient standard threshold, the gradient standard threshold in the present application includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and compare the abnormal assessment coefficient with the first standard threshold and the second standard threshold respectively;

[0081] If the abnormality assessment coefficient is greater than the second standard threshold, the abnormality in the processing of critically ill patient monitoring data is classified as severe abnormality, and emergency measures should be taken immediately to intervene to ensure the safety and health of the patient. More medical staff resources need to be mobilized to strengthen the processing of monitoring data and intervention measures;

[0082] If the abnormality assessment coefficient is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the abnormality level in the critically ill patient monitoring data processing process is classified as general abnormality. Although the abnormality level is not as severe as that of a serious abnormality, measures still need to be taken to resolve it to avoid further deterioration. The medical process needs to be adjusted or the equipment settings optimized to improve the accuracy and efficiency of monitoring data transmission and processing;

[0083] If the abnormality assessment coefficient is less than the first standard threshold, the abnormality in the processing of critically ill patient monitoring data is classified as a minor abnormality. Although the abnormality is low, it still needs to be closely monitored and handled in a timely manner to prevent the problem from further expanding. Data quality control is required to check for possible problems in the data collection and transmission process and correct them in a timely manner. At the same time, strengthen the supervision and management of the monitoring data processing process to ensure data accuracy and reliability.

[0084] In this embodiment, by determining the vital signs and monitoring indicators of critically ill patients, clinical data of critically ill patients are collected, and vital signs and monitoring indicators related to the deterioration of the patient's condition are identified; according to the vital signs and monitoring indicators related to the deterioration of the patient's condition, the warning threshold of each monitoring indicator is set, and when the monitoring data exceeds the preset warning threshold, the system automatically triggers an alarm; after the alarm is triggered, the processing efficiency stability of the monitoring data and the transmission accuracy of the monitoring data are comprehensively analyzed to evaluate the abnormality in the processing of critically ill patients' monitoring data; according to the evaluation results, the abnormality in the processing of critically ill patients' monitoring data is divided into severe abnormality, general abnormality, and slight abnormality, and they are managed accordingly. Not only can optimizing the processing process of critically ill patients' monitoring data improve medical quality and safety, but it also reduces medical risks, improves medical efficiency, realizes personalized medical management, and reduces medical costs, which is of great significance to both patients and medical systems.

[0085] Embodiment 2, processing module: further analyzing the abnormality degree in the process of processing the monitoring data of the managed critically ill patients to improve the level and quality of the monitoring data processing.

[0086] Further analysis of the degree of abnormality in the processing of critically ill patient monitoring data means conducting an in-depth review and evaluation of the monitoring data to identify possible abnormalities and analyze the causes, patterns, and impact of the abnormalities. Through this process, targeted treatment suggestions can be put forward, and a continuous improvement mechanism can be established to continuously optimize the process and technology of monitoring data processing, thereby improving the level and quality of monitoring data processing and ensuring that patients receive safer and more effective medical services.

[0087] The abnormal assessment coefficients in the process of processing the critically ill patient monitoring data within a period of time are continuously collected, and the corresponding data set is established for the abnormal assessment coefficients in the process of processing the critically ill patient monitoring data collected. The abnormal assessment coefficients in the process of processing the critically ill patient monitoring data in the set are compared and analyzed with the abnormal assessment coefficient reference threshold, and the risk index in the process of processing the critically ill patient monitoring data is calculated. The specific calculation expression is: Where RW pk is the risk index, H is the number of abnormal evaluation coefficients collected within a period of time, k is the label of the abnormal evaluation coefficient, TF rb is the reference threshold of the abnormal assessment coefficient.

[0088] The obtained risk index is compared with the risk index reference threshold; if the risk index is greater than or equal to the risk index reference threshold, it means that the possibility of risk in the processing of critically ill patient monitoring data after management is high, and an early warning signal is generated at this time to remind medical staff to pay attention to possible problems and take corresponding intervention measures; if the risk index is less than the risk index reference threshold, it means that the possibility of risk in the processing of critically ill patient monitoring data after management is low, and no early warning signal is generated at this time, and medical staff can continue the normal process of monitoring data processing without additional intervention measures.

[0089] In this embodiment, by continuously collecting and analyzing the abnormal assessment coefficients in the monitoring data processing process of critically ill patients over a period of time, and comparing the risk index with the preset risk index reference threshold, it is determined whether there is a risk in the monitoring data processing process after management. If the risk index is greater than or equal to the risk index reference threshold, an early warning signal will be triggered to alert medical staff to possible problems and take intervention measures. On the contrary, if the risk index is less than the risk index reference threshold, no early warning signal will be generated, and medical staff can continue the normal processing flow of monitoring data. This method helps to promptly discover and respond to potential risks, ensuring that patients receive safer and more efficient medical services.

[0090] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0091] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0092] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0093] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0094] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0095] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0096] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0097] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0098] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0099] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0100] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0101] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. An early warning system for sudden illness in critically ill patients, characterized by: It includes clinical data acquisition module, automatic warning module, comprehensive evaluation module, abnormal classification module and processing module; Clinical data acquisition module: determine the vital signs and monitoring indicators of critically ill patients, collect clinical data of critically ill patients, and identify vital signs and monitoring indicators related to the deterioration of the patient's condition; Automatic warning module: According to the patient's vital signs and monitoring indicators related to the deterioration of the condition, the warning threshold of each monitoring indicator is set. When the monitoring data exceeds the preset warning threshold, the system automatically triggers an alarm; Comprehensive evaluation module: conducts a comprehensive analysis of the processing efficiency and stability of monitoring data after the alarm is triggered, as well as the transmission accuracy of monitoring data, and evaluates the degree of abnormality in the processing of critically ill patients' monitoring data; Abnormal classification module: According to the evaluation results, the abnormal degree in the process of critically ill patients' monitoring data processing is divided into severe abnormality, general abnormality, and minor abnormality, and they are managed accordingly; Processing module: Further analyze the abnormality of the monitoring data processing of critically ill patients after management to improve the level and quality of monitoring data processing.

2. The early warning system for sudden illness in critically ill patients according to claim 1, characterized in that: In the automatic warning module, when the monitoring data exceeds the preset warning threshold, the system automatically triggers an alarm, including: Determine the physiological indicators and monitoring indicators related to the patient's condition deterioration, and define the monitoring indicator set X = {x1, x2, ..., xn}, where xi represents the i-th monitoring indicator; Collect historical data sets D = {d1, d2, ..., dm}, where each di contains the value of the monitoring indicator and related information, and define the warning threshold Ti for each monitoring indicator xi; During the real-time monitoring process, for each monitoring indicator xi, the monitoring system will continuously obtain the latest patient data xnew. When xnew is greater than Ti, an early warning signal is generated to notify medical staff for further processing; when xnew is less than or equal to Ti, no early warning signal is generated.

3. The early warning system for sudden illness in critically ill patients according to claim 1, characterized in that: In the comprehensive evaluation module, the correlation between the alarm response time and the data processing speed is analyzed to obtain the processing efficiency fluctuation index of the monitoring data, and the processing efficiency stability of the monitoring data after the alarm is triggered is evaluated. The method for obtaining the processing efficiency fluctuation index is: Collect the alarm triggering time and the time data of medical staff processing monitoring data, and construct the collected data into a time series; For each alarm, the time difference between the time when the medical staff processes the monitoring data and the time when the alarm is triggered is calculated, that is, the response time. The specific calculation expression is: RT = TP-TA; where TP is the time when the medical staff processes the monitoring data, TA is the alarm trigger time, and RT is the response time; The standard deviation is used to calculate the processing efficiency fluctuation index. The specific calculation expression is: In the formula, ER et is the processing efficiency fluctuation index, RT a is the ath response time, indicating the time difference between the time when the medical staff processes the monitoring data and the time when the corresponding alarm is triggered. YT is the average of all response times, indicating the average response time of the medical staff to process the monitoring data, and N is the number of response times.

4. The early warning system for sudden illness in critically ill patients according to claim 1, characterized in that: In the comprehensive evaluation module, the accuracy of the monitoring data after the alarm is triggered is analyzed, the degree of abnormality of the monitoring data during transmission is determined, the transmission frequency outlier index of the monitoring data is obtained, and the transmission accuracy of the monitoring data is evaluated. The method for obtaining the transmission frequency outlier index is: Obtain the transmission timestamp of the monitoring data from the monitoring system. For the timestamps t1, t2, ..., tn, calculate the transmission time interval Δti = ti + 1 - ti between adjacent time points, where i = 1, 2, ..., n - 1, ti represents the timestamp of the monitoring data transmission, and construct the transmission time interval Δti into a feature vector, represented as T = [Δt1, Δt2, ..., Δtn - 1]; The local outlier factor value of each eigenvector Ti is calculated using the LOF algorithm and expressed as: LOF(xi), where i = 1, 2, ..., n-1; the average value of the LOF value is calculated, and the specific calculation expression is: Where μLOF is the average value of LOF values. The standard value is calculated based on the average value of LOF values, that is, the transmission frequency outlier index is calculated. The specific calculation expression is: In the formula, EP mb is the transmission frequency outlier index.

5. The early warning system for sudden illness in critically ill patients according to claim 1, characterized in that: The processing efficiency fluctuation index and the transmission frequency outlier index are normalized, and the abnormal assessment coefficient in the processing of critically ill patient monitoring data is calculated based on the normalized processing efficiency fluctuation index and the transmission frequency outlier index.

6. The early warning system for sudden illness in critically ill patients according to claim 5, characterized in that: In the abnormality classification module, according to the evaluation results, the degree of abnormality in the processing of critically ill patient monitoring data is divided into severe abnormality, general abnormality, and slight abnormality, specifically: Compare the abnormal assessment coefficient obtained during the processing of the critically ill patient monitoring data with the gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and compare the abnormal assessment coefficient with the first standard threshold and the second standard threshold respectively; If the abnormality assessment coefficient is greater than the second standard threshold, the degree of abnormality in the processing of critically ill patient monitoring data is classified as severe abnormality; if the abnormality assessment coefficient is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the degree of abnormality in the processing of critically ill patient monitoring data is classified as general abnormality; if the abnormality assessment coefficient is less than the first standard threshold, the degree of abnormality in the processing of critically ill patient monitoring data is classified as minor abnormality.

7. The early warning system for sudden illness in critically ill patients according to claim 1, characterized in that: In the processing module, the abnormal degree of the critically ill patient monitoring data processing after management is further analyzed, and the abnormal evaluation coefficients in the critically ill patient monitoring data processing within a period of time are continuously collected, and the abnormal evaluation coefficients in the critically ill patient monitoring data processing collected are used to establish a corresponding data set, and the abnormal evaluation coefficients in the critically ill patient monitoring data processing in the set are compared and analyzed with the abnormal evaluation coefficient reference threshold, and the risk index in the critically ill patient monitoring data processing is calculated. The specific calculation expression is: Where RW pk is the risk index, H is the number of abnormal evaluation coefficients collected within a period of time, k is the label of the abnormal evaluation coefficient, TF rb is the reference threshold of the abnormal assessment coefficient.

8. The early warning system for sudden illness in critically ill patients according to claim 7, characterized in that: Compare the acquired risk index with the risk index reference threshold; if the risk index is greater than or equal to the risk index reference threshold, generate a warning signal; If the risk index is less than the risk index reference threshold, no warning signal is generated.

Citation Information

Patent Citations

  • Internet-based electrocardiogram abnormity real-time monitoring system

    CN116649987A

  • Intelligent information management system for critical clinical patients

    CN117059245A