CN118766423A - A critical care status alarm method and system based on big data monitoring - Google Patents

Abstract

The present invention discloses a critical care state alarm method and system based on big data monitoring, which relates to the field of critical care. The critical care state alarm method based on big data monitoring includes the following steps: S1, obtaining patient parameter information and obtaining critical care device configuration requirements; S2, empowering and prioritizing the configuration critical care device group; S3, obtaining thresholds and influencing parameters and setting graded alarm influencing rules; S4, setting alarm adjustment rules and optimizing adjustments; S5, predicting monitoring state evolution prediction parameters and optimizing monitoring state evolution prediction parameters; S6, obtaining alarm evolution prediction difference parameters and alarm evolution prediction adjustment requirements; S7, outputting advanced monitoring state evolution warning parameters and optimized monitoring state alarm information. The present invention formulates targeted monitoring plans by analyzing the patient's parameter information in detail to ensure that each patient can receive the most suitable monitoring measures for their condition.

Description

A critical care status alarm method and system based on big data monitoring

Technical Field

The present invention relates to the field of intensive care, and in particular to an intensive care status alarm method and system based on big data monitoring.

Background Art

Big data monitoring plays a vital role in many fields, especially in health care, environmental monitoring, financial market analysis, etc. Big data monitoring provides instant insights by collecting and analyzing data in real time, which helps to detect problems, trends or abnormal behaviors in a timely manner. In the field of healthcare, it helps medical teams identify changes in patient conditions early, implement early warnings, and take timely intervention measures to improve treatment outcomes and patient safety.

The critical care status alarm system can monitor the patient's vital signs and important medical indicators, such as heart rate, blood pressure, respiratory rate, etc. in real time. When the indicators exceed the normal range, the system will immediately issue an alarm, allowing medical staff to respond quickly and intervene in time, greatly improving the patient's survival rate and treatment effect. Through continuous monitoring of the patient's status and real-time alarms, medical staff can take measures before the condition worsens and avoid serious health problems or complications.

However, the existing intensive care status alarm method based on big data monitoring does not classify the alarms when it is used, so that the existing intensive care status alarm method based on big data monitoring cannot accurately reflect the real-time status of the patient when it is used. At the same time, the existing intensive care status alarm method based on big data monitoring does not sort the monitoring priorities of the intensive care devices when it is used, so that the patient cannot clearly understand the monitoring focus when using the intensive care device, which affects the efficiency of the use of the intensive care status alarm method based on big data monitoring.

Currently, no effective solution has been proposed for the problems in the related technologies.

Summary of the invention

In view of the problems in the related technology, the present invention proposes an intensive care status alarm method and system based on big data monitoring to overcome the above-mentioned technical problems existing in the existing related technology.

To this end, the specific technical solution adopted by the present invention is as follows:

According to one aspect of the present invention, a critical care status alarm method based on big data monitoring is provided, comprising the following steps:

S1. Obtain patient parameter information, analyze the patient parameter information to set a critical care plan, and obtain critical care device configuration requirements based on the critical care plan;

S2. configuring a critical care device group according to the critical care device configuration requirements, assigning weights based on the critical care device group configuration results, and generating a priority ranking result of critical care devices in the critical care device group according to the assignment of weights to the critical care device group;

S3. acquiring, based on the intensive care plan, individual device hierarchical alarm thresholds and intensive care device change impact parameters of the intensive care devices in the intensive care device group, and setting hierarchical alarm impact rules based on the individual device hierarchical alarm thresholds and intensive care device impact parameters;

S4. Setting alarm adjustment rules according to the priority ranking results of the intensive care device and the graded alarm impact rules, and optimizing and adjusting the monitoring status alarm information based on the alarm adjustment rules to obtain optimized monitoring status alarm information;

S5. Preset alarm evolution prediction rules, analyze monitoring state alarm information and optimize monitoring state evolution prediction parameters of monitoring state alarm information and optimize monitoring state evolution prediction parameters through alarm evolution prediction rules;

S6. Compare the monitoring state evolution prediction parameters and the optimized monitoring state evolution prediction parameters, obtain the alarm evolution prediction difference parameters, and set the alarm evolution prediction difference parameter adjustment threshold, compare the alarm evolution prediction difference parameter adjustment threshold with the alarm evolution prediction difference parameter, and obtain the alarm evolution prediction adjustment requirement;

S7. Based on the alarm evolution prediction adjustment requirements, optimize and adjust the optimized monitoring state evolution prediction parameters, obtain advanced monitoring state evolution warning parameters, output the advanced monitoring state evolution warning parameters and the optimized monitoring state alarm information, and build an alarm database and a warning database.

As a preferred solution, obtaining the individual device hierarchical alarm threshold and the intensive care device change influence parameter of the intensive care device in the intensive care device group based on the intensive care plan, and setting the hierarchical alarm influence rule based on the individual device hierarchical alarm threshold and the intensive care device influence parameter includes the following steps:

S31. Analyze the critical care plan, obtain the monitoring devices required for the critical care, and integrate the monitoring devices to obtain a critical care device group;

S32, analyzing the critical care indicators of each critical care device in the critical care device group, and setting individual device graded alarm thresholds of the critical care devices based on the critical care indicators;

S33, analyzing the monitoring device associated parameters of the critical care devices within the critical care device group, and calculating the critical care device change impact parameters based on the monitoring device associated parameters;

S34. Integrate the individual device graded alarm thresholds and the critical care device change impact parameters, formulate graded alarm impact rules based on the integration results, and verify and optimize the graded alarm impact rules.

As a preferred solution, analyzing the critical care index of each critical care device in the critical care device group and setting the individual device graded alarm threshold of the critical care device based on the critical care index includes the following steps:

S321, analyzing medical detection parameters of the intensive care unit, setting intensive care health thresholds according to the medical detection parameters, and setting intensive care indicators of each intensive care unit based on the intensive care health thresholds;

S322, evaluating the health impact of the critical care indicator, setting the critical care indicator emergency rule according to the health impact, and setting the initial device classification alarm threshold based on the critical care indicator emergency rule;

S323, presetting standard individual parameters and individual grading adjustment rules, obtaining characteristic individual parameters according to the patient parameter information, comparing the standard individual parameters with the characteristic individual parameters, and obtaining individual difference parameters;

S324: Match the individual classification adjustment rule with the individual difference parameter, and optimize and adjust the initial device classification alarm threshold according to the matching result to obtain the individual device classification alarm threshold.

As a preferred solution, analyzing the monitoring device associated parameters of the intensive care devices within the intensive care device group, and calculating the intensive care device change influencing parameters based on the monitoring device associated parameters includes the following steps:

S331, obtaining historical monitoring data of the intensive care device, and analyzing related parameters of the intensive care device based on the historical monitoring data;

S332, presetting causal rules and timing rules, and optimizing and adjusting the associated parameters based on the causal rules and timing rules to obtain the associated parameters of the monitoring device of the intensive care unit;

S333. Construct an association interaction model based on the associated parameters of the monitoring device, verify and optimize the association interaction model, and use the verified and optimized association interaction model to calculate the parameters affecting changes in the intensive care unit.

As a preferred solution, building an associated interaction model based on associated parameters of the monitoring device, verifying and optimizing the associated interaction model, and using the verified and optimized associated interaction model to calculate the parameters affecting changes in the intensive care device include the following steps:

S3331. Define the impact of changes in monitoring device parameters required to be calculated by the associated interaction model, and clean the associated parameters of the monitoring device;

S3332. Obtain characteristic parameters of the post-cleaning monitoring device correlation parameters through statistical analysis, construct a correlation interaction model based on the characteristic parameters, and cross-validate the correlation interaction model;

S3333. Use the cross-validated correlation interaction model to calculate the parameters affecting changes in the intensive care unit, and verify and optimize the parameters affecting changes in the intensive care unit.

As a preferred solution, the characteristic parameters of the post-cleaning monitoring device correlation parameters are obtained through statistical analysis, and the calculation formula for constructing the correlation interaction model based on the characteristic parameters is:

Among them, S is the impact value of the change of critical care equipment;

N is the total number of characteristic parameters;

is the influence value of the i-th feature in the feature parameters;

F _i is the influence value of the feature parameter excluding the i-th feature.

As a preferred solution, comparing the monitoring state evolution prediction parameters and optimizing the monitoring state evolution prediction parameters, obtaining the alarm evolution prediction difference parameters, and setting the alarm evolution prediction difference parameter adjustment threshold, comparing the alarm evolution prediction difference parameter adjustment threshold with the alarm evolution prediction difference parameter, and obtaining the alarm evolution prediction adjustment requirement includes the following steps:

S61, presetting a difference analysis rule, and comparing the monitoring state evolution prediction parameter and optimizing the monitoring state evolution prediction parameter through the difference analysis rule to obtain a difference analysis result;

S62, according to the difference analysis result, extracting the difference parameters, and obtaining the alarm evolution prediction difference parameters of the difference analysis result;

S63, setting and verifying the alarm evolution prediction difference parameter adjustment threshold according to the patient parameter information;

S64. Adjust the threshold and alarm evolution prediction difference parameters based on the verified alarm evolution prediction difference parameters, obtain the alarm evolution prediction adjustment requirements through comparative analysis, and formulate an adjustment strategy based on the alarm evolution prediction adjustment requirements.

As a preferred solution, according to the difference analysis results, by extracting the difference parameters, obtaining the alarm evolution prediction difference parameters of the difference analysis results includes the following steps:

S621, generating a difference parameter extraction index according to the difference analysis result, and extracting a difference feature parameter of the difference analysis result based on the evaluation difference parameter extraction index;

S622, performing a difference impact analysis according to the difference characteristic parameters to obtain a difference parameter impact of the difference characteristic parameters, and generating a difference characteristic parameter adjustment plan based on the difference parameter impact;

S623: verify the difference characteristic parameter adjustment scheme, and adjust the difference characteristic parameters based on the verified difference characteristic parameter adjustment scheme to obtain the alarm evolution prediction difference parameters.

As a preferred solution, adjusting the threshold and the alarm evolution prediction difference parameter based on the verified alarm evolution prediction difference parameter, obtaining the alarm evolution prediction adjustment requirement through comparative analysis, and formulating an adjustment strategy based on the alarm evolution prediction adjustment requirement includes the following steps:

S641, comparing the alarm evolution prediction difference parameter adjustment threshold with the alarm evolution prediction difference parameter, and identifying the comparison out-of-range parameter according to the comparison result;

S642, analyzing and comparing out-of-range parameters, obtaining adjustment requirements, and setting alarm evolution prediction adjustment requirements based on the adjustment requirements;

S643. Develop adjustment strategies based on the forecast of alarm evolution and adjustment needs, and verify and optimize the adjustment strategies through feasibility assessment.

According to another aspect of the present invention, there is provided an intensive care status alarm system based on big data monitoring, the system comprising:

A parameter acquisition module is used to acquire patient parameter information, analyze the patient parameter information to set a critical care plan, and acquire critical care device configuration requirements based on the critical care plan;

A weighted ranking module, used to configure a critical care device group according to the critical care device configuration requirements, to grant weights based on the critical care device group configuration results, and to generate a priority ranking result of critical care devices in the critical care device group according to the weighted status of the critical care device group;

A hierarchical alarm module, for obtaining, based on the intensive care plan, individual device hierarchical alarm thresholds and intensive care device change impact parameters of intensive care devices in the intensive care device group, and setting hierarchical alarm impact rules based on the individual device hierarchical alarm thresholds and intensive care device impact parameters;

An optimization and adjustment module, used to set alarm adjustment rules according to the priority sorting results of the intensive care device and the graded alarm impact rules, and optimize and adjust the monitoring state alarm information based on the alarm adjustment rules to obtain optimized monitoring state alarm information;

An early warning prediction module is used to preset alarm evolution prediction rules, analyze monitoring state alarm information and optimize monitoring state evolution prediction parameters of monitoring state alarm information and optimize monitoring state evolution prediction parameters through alarm evolution prediction rules;

An early warning optimization module is used to compare and optimize monitoring state evolution prediction parameters, obtain alarm evolution prediction difference parameters, set alarm evolution prediction difference parameter adjustment thresholds, compare the alarm evolution prediction difference parameter adjustment thresholds with the alarm evolution prediction difference parameters, and obtain alarm evolution prediction adjustment requirements;

Output alarm module, used to optimize and adjust the optimized monitoring state evolution prediction parameters based on the alarm evolution prediction adjustment requirements, obtain advanced monitoring state evolution warning parameters, output advanced monitoring state evolution warning parameters and optimized monitoring state alarm information, and build an alarm database and a warning database;

The parameter acquisition module, the weighted sorting module, the graded alarm module, the optimization and adjustment module, the early warning prediction module, the early warning optimization module and the output alarm module are connected in sequence.

The beneficial effects of the present invention are:

1. The present invention formulates targeted monitoring plans by analyzing the patient's parameter information in detail to ensure that each patient can receive the most suitable monitoring measures for his or her condition, and sets the graded alarm thresholds of individual devices according to the patient's parameters, combined with the change-affecting parameters of the intensive care device, accurately reflects the patient's real-time status and reduces the possibility of false alarms.

2. The present invention rationally utilizes medical resources by prioritizing and weighting the intensive care device group to ensure that critically ill patients can obtain necessary monitoring devices in a timely manner, and dynamically adjusts the monitoring strategy and resource allocation to respond to changes in the patient's condition by continuously monitoring, analyzing and predicting the patient's condition evolution.

3. The present invention adopts an automated monitoring and alarm system to reduce errors in human judgment, improve the accuracy and response speed of monitoring, and identify potential deterioration of the disease by predicting the evolution of alarms, so as to take preventive measures and avoid the occurrence of serious complications. At the same time, the construction of an alarm database and an early warning database helps to accumulate experience and knowledge in intensive care, provide data support for medical staff, and help them make more accurate and well-founded decisions. Through continuous data analysis and model optimization, the effectiveness of the monitoring plan is continuously improved, and continuous improvement and optimization of the intensive care process is achieved.

BRIEF DESCRIPTION OF THE DRAWINGS

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.

FIG1 is a method flow chart of a critical care status alarm method based on big data monitoring according to an embodiment of the present invention;

FIG2 is a system block diagram of an intensive care status alarm system based on big data monitoring according to an embodiment of the present invention.

In the figure:

1. Parameter acquisition module; 2. Weighted sorting module; 3. Grading alarm module; 4. Optimization and adjustment module; 5. Early warning prediction module; 6. Early warning optimization module; 7. Output alarm module.

DETAILED DESCRIPTION

The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. 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.

According to an embodiment of the present invention, a critical care status alarm method and system based on big data monitoring are provided.

The present invention is now further described in conjunction with the accompanying drawings and specific embodiments. According to one embodiment of the present invention, as shown in FIG1 , the intensive care state alarm method based on big data monitoring according to an embodiment of the present invention includes the following steps:

S1. Obtain patient parameter information, analyze the patient parameter information to set a critical care plan, and obtain critical care device configuration requirements based on the critical care plan;

Specifically, the patient's vital signs and other relevant health data are collected through various medical testing equipment and sensors, such as electrocardiographs, blood pressure monitors, pulse oximeters, etc., and historical health data is obtained through the patient's electronic health records, including past medical history, drug allergy history, surgical history, etc., and the patient's subjective symptom description, living habits, family medical history, etc. are collected.

Patient data collected from different sources are integrated together and necessary preprocessing is performed, such as data cleaning and format unification. Statistical analysis, machine learning, or artificial intelligence algorithms are then used to analyze the patient's parameter information, identify the severity of the disease, disease patterns, and possible risk factors, and have doctors, nurses, pharmacists, and other professionals participate in case discussions. Monitoring plans are set based on comprehensive consideration of analysis results and clinical experience. Based on the patient's specific situation and analysis results, a personalized intensive care plan is formulated, including monitoring frequency, specific treatment measures, and drug therapy. Possible changes in the patient's condition are anticipated, and response measures are preset for possible situations. Based on the intensive care plan, the required type of monitoring equipment is determined, such as ventilators, continuous renal replacement therapy devices, central venous pressure monitoring devices, etc. The urgency and priority of use of each device are evaluated based on the severity of the patient's condition and the requirements of the monitoring plan.

S2. configuring a critical care device group according to the critical care device configuration requirements, assigning weights based on the critical care device group configuration results, and generating a priority ranking result of critical care devices in the critical care device group according to the assignment of weights to the critical care device group;

Specifically, according to the requirements of the intensive care plan, the type and quantity of monitoring devices required, such as ventilators, monitors, infusion pumps, etc., are determined. When configuring the device group, the compatibility and integration between different devices need to be considered to ensure the smooth operation of the monitoring system. Each device in the intensive care device group is given a corresponding weight based on its clinical importance in patient treatment and monitoring. For example, for patients with respiratory failure, the weight of the ventilator may be higher than other devices.

The urgency of the equipment in improving the patient's condition is also an important factor in empowerment, and higher weights should be given to devices with high urgency. Based on the assigned weight and the priority of the equipment, the importance of each device is comprehensively evaluated to generate a priority ranking result for the devices in the intensive care device group. The priority ranking results should be dynamically adjusted according to changes in the patient's condition and actual usage. If a device fails or the patient's condition changes, the priority of the device needs to be re-evaluated. Based on the priority ranking results, the configuration and use of the intensive care device should be arranged to ensure that key devices can be put into use first.

S3. acquiring, based on the intensive care plan, individual device hierarchical alarm thresholds and intensive care device change impact parameters of the intensive care devices in the intensive care device group, and setting hierarchical alarm impact rules based on the individual device hierarchical alarm thresholds and intensive care device impact parameters;

Specifically, obtaining the individual device hierarchical alarm threshold and the intensive care device change influence parameter of the intensive care device in the intensive care device group based on the intensive care plan, and setting the hierarchical alarm influence rule based on the individual device hierarchical alarm threshold and the intensive care device influence parameter includes the following steps:

S31. Analyze the critical care plan, obtain the monitoring devices required for the critical care, and integrate the monitoring devices to obtain a critical care device group;

Specifically, analyze the patient's condition, medical history, treatment response, and specific monitoring needs, determine the basis for the required monitoring device, and based on the patient's specific situation and treatment goals, clarify the monitoring goals that need to be achieved, such as maintaining stable vital signs, monitoring specific health parameters, etc., identify key health parameters and indicators that need to be closely monitored, such as heart rate, blood pressure, blood oxygen saturation, etc.

Based on the monitoring objectives and key parameters obtained through analysis, determine the type of monitoring device needed to meet these needs. For example, for patients who need to monitor heart function, an electrocardiogram monitor may be needed. Select monitoring devices with reliable performance and good user feedback to ensure the accuracy of monitoring data and the stability of the equipment. Select devices that can be integrated with existing medical information systems, such as electronic health record systems, and integrate the selected monitoring devices into a collaborative system to ensure that data between different devices can be interconnected to provide comprehensive monitoring for patients. Based on the patient's actual monitoring needs, set appropriate operating parameters and alarm thresholds for each device to ensure that the monitoring device group can provide accurate and timely monitoring and alarms.

S32, analyzing the critical care indicators of each critical care device in the critical care device group, and setting individual device graded alarm thresholds of the critical care devices based on the critical care indicators;

Specifically, analyzing the critical care indicators of each critical care device in the critical care device group and setting the individual device graded alarm threshold of the critical care device based on the critical care indicators includes the following steps:

S321, analyzing medical detection parameters of the intensive care unit, setting intensive care health thresholds according to the medical detection parameters, and setting intensive care indicators of each intensive care unit based on the intensive care health thresholds;

Specifically, determining medical test parameters is crucial for monitoring patient conditions, such as heart rate, blood pressure, blood oxygen saturation, respiratory rate, etc., studying the normal range of each parameter and its changing trends under different conditions, and understanding the impact of different patients, such as age, gender and underlying diseases, on the normal range of these parameters.

Based on medical guidelines and patient-specific conditions, health thresholds are set for each key medical test parameter to determine whether the patient's health condition requires special attention or intervention. At the same time, the thresholds are adjusted according to the patient's specific conditions, such as existing diseases, treatment response, etc. For example, for patients with a history of heart disease, the heart rate threshold may need to be specially set.

Assign each medical test parameter to the corresponding monitoring device, such as an ECG monitor for monitoring heart rate and rhythm, and a sphygmomanometer for monitoring blood pressure, and set monitoring standards for each device, including when to trigger an alarm, to ensure that all monitoring devices can work together to monitor the patient's comprehensive condition. When necessary, data and alarms should be shared between devices.

S322, evaluating the health impact of the critical care indicator, setting the critical care indicator emergency rule according to the health impact, and setting the initial device classification alarm threshold based on the critical care indicator emergency rule;

Specifically, the patient's monitoring data is collected through monitoring equipment or medical record systems, and the collected data is analyzed, including comparison with baseline ranges and trend analysis, to determine whether there are any health impacts. Emergency rules for intensive care indicators are formulated based on the standards or professional guidelines of medical institutions, such as determining what actions to take in cases of too fast or too slow heart rate, abnormal respiratory rate, etc.

And based on the medical institution's policies and professional guidelines, determine the initial device classification alarm thresholds for different critical care indicators so that alarms can be triggered and appropriate actions can be taken when they are outside the normal range.

S323, presetting standard individual parameters and individual grading adjustment rules, obtaining characteristic individual parameters according to the patient parameter information, comparing the standard individual parameters with the characteristic individual parameters, and obtaining individual difference parameters;

Specifically, the patient's monitoring data is collected through monitoring equipment or medical record systems, and the collected data is analyzed, including comparison with baseline ranges and trend analysis, to determine whether there are any health impacts. Emergency rules for intensive care indicators are formulated based on the standards or professional guidelines of medical institutions, such as determining what actions to take in cases of too fast or too slow heart rate, abnormal respiratory rate, etc.

Based on institutional policies and professional guidelines, determine initial device classification alarm thresholds for different critical care indicators so that alarms can be triggered and appropriate actions can be taken when they are outside normal ranges.

S324: Match the individual classification adjustment rule with the individual difference parameter, and optimize and adjust the initial device classification alarm threshold according to the matching result to obtain the individual device classification alarm threshold.

Specifically, statistical analysis methods or machine learning algorithms are used to analyze the relationship between individual difference parameters and health impacts, determine which individual difference parameters have a more significant impact on critical care indicators, and formulate individual grading adjustment rules based on the analysis results. That is, according to the characteristics of the individual difference parameters, the initial device grading alarm threshold is adjusted. For example, for older patients, a more relaxed alarm threshold may be required. The formulated individual grading adjustment rules are then applied to a certain number of patient data to verify their accuracy and effectiveness.

S33, analyzing the monitoring device associated parameters of the critical care devices within the critical care device group, and calculating the critical care device change impact parameters based on the monitoring device associated parameters;

Specifically, analyzing the monitoring device associated parameters of the intensive care devices within the intensive care device group, and calculating the intensive care device change impact parameters based on the monitoring device associated parameters includes the following steps:

S331, obtaining historical monitoring data of the intensive care device, and analyzing related parameters of the intensive care device based on the historical monitoring data;

Specifically, use the data provided by the intensive care unit to export or connect to the medical record system to obtain historical monitoring data, including key monitoring indicators such as heart rate, respiratory rate, blood pressure, body temperature, etc., clean and preprocess the collected historical monitoring data, including processing missing values, outliers and standardized data formats to ensure data accuracy and consistency, select associated parameters related to intensive care indicators based on medical knowledge and research purposes, including blood oxygen saturation, blood sugar level, carbon dioxide concentration, etc., use statistical methods or machine learning technology to establish an association model to analyze the relationship between monitoring indicators and the selected association parameters, and use linear regression, decision tree and other methods to select an appropriate model based on data characteristics.

The established association model is validated, and a portion of the historical monitoring data is used to evaluate the accuracy and generalization ability of the model. The results of the association model are analyzed to understand the relationship between monitoring indicators and association parameters. The established association model is applied to actual patient monitoring to provide more comprehensive information and earlier intervention opportunities, and the model is updated regularly to reflect changes in medical practice and patient characteristics.

S332, presetting causal rules and timing rules, and optimizing and adjusting the associated parameters based on the causal rules and timing rules to obtain the associated parameters of the monitoring device of the intensive care unit;

Specifically, based on medical knowledge and clinical experience, formulate rules for possible causal relationships between monitoring indicators, such as certain drugs may affect patients' blood pressure or heart rate, and determine the temporal relationship between monitoring indicators and related parameters, that is, the time sequence and impact delay between them, such as changes in certain physiological parameters may appear before changes in other parameters. Use statistical analysis or machine learning technology to analyze and verify the formulated causal rules and timing rules.

According to the analysis results of causal rules and timing rules, the settings of associated parameters are adjusted to reflect the relationship between monitoring indicators, such as adjusting blood pressure parameters affected by drugs according to causal rules, or adjusting time delay parameters according to timing rules. The optimized associated parameters are applied to actual monitoring data to verify their accuracy and effectiveness, and the parameters are adjusted according to the verification results to improve their adaptability and accuracy.

S333. Construct an association interaction model based on the associated parameters of the monitoring device, verify and optimize the association interaction model, and use the verified and optimized association interaction model to calculate the parameters affecting changes in the intensive care unit.

Specifically, constructing an associated interaction model based on associated parameters of a monitoring device, verifying and optimizing the associated interaction model, and using the verified and optimized associated interaction model to calculate the parameters affecting changes in the intensive care device include the following steps:

S3331. Define the impact of changes in monitoring device parameters required to be calculated by the associated interaction model, and clean the associated parameters of the monitoring device;

Specifically, the associated parameters related to the monitoring indicators are selected, including drug use, physiological status, therapeutic intervention, etc., to ensure that the selected parameters have potential influence. According to medical knowledge and research purposes, an associated interaction model is established to describe the mathematical relationship between the changes in monitoring device parameters and the selected associated parameters, and to determine the influence factor of each associated parameter on the monitoring indicator, that is, the degree to which the parameter change affects the change in the monitoring indicator.

Data cleaning is performed on the associated parameters of the monitoring device, including processing missing values, outliers and ensuring data consistency. According to the established association interaction model, the associated parameters of the monitoring device are standardized in order to compare the impact of different parameters on the monitoring indicators. This is achieved by mapping the parameter values to the same scale. The established association interaction model is validated using an independent data set or cross-validation method to ensure its applicability and accuracy on different data sets.

S3332. Obtain characteristic parameters of the post-cleaning monitoring device correlation parameters through statistical analysis, construct a correlation interaction model based on the characteristic parameters, and cross-validate the correlation interaction model;

Specifically, the characteristic parameters of the post-cleaning monitoring device correlation parameters are obtained through statistical analysis, and the calculation formula for constructing the correlation interaction model based on the characteristic parameters is:

Among them, S is the impact value of the change of critical care equipment;

N is the total number of characteristic parameters;

is the influence value of the i-th feature in the feature parameters;

F _i is the influence value of the feature parameter excluding the i-th feature.

S3333. Use the cross-validated correlation interaction model to calculate the parameters affecting changes in the intensive care unit, and verify and optimize the parameters affecting changes in the intensive care unit.

Specifically, the cross-validated association interaction model is applied to the actual monitoring data to calculate the influencing parameters of changes in intensive care units, ensuring that the data used do not overlap with the data set during model development, avoiding overfitting and verifying the generalization ability of the model. The established association interaction model is used to calculate the association parameters in the actual monitoring data to obtain the influencing parameters on intensive care indicators. The calculated influencing parameters of changes in intensive care units are compared with the actual observed patient data to verify the accuracy and reliability of the model. Statistical indicators such as mean square error and correlation coefficient are used to evaluate the model's fit and predictive ability.

Based on the validation results, the correlation interaction model is optimized and adjusted to improve its prediction accuracy for parameters affecting changes in critical care devices, including the need to adjust the model structure, parameter settings, or use more complex algorithms to handle specific situations.

S34. Integrate the individual device graded alarm thresholds and the critical care device change impact parameters, formulate graded alarm impact rules based on the integration results, and verify and optimize the graded alarm impact rules.

Specifically, the graded alarm thresholds of individual devices are integrated with the parameters affecting changes in intensive care devices to ensure that the data formats and units of the two are consistent. Based on the integrated data, graded alarm impact rules are formulated, that is, different individual grades are defined, such as adjusting the alarm thresholds according to the parameters affecting changes in intensive care devices, including setting weights, threshold adjustment ratios and other rules. The formulated graded alarm impact rules are verified using actual patient data, and the alarm thresholds after applying the rules are compared to see whether they are consistent with the actual patient conditions. The applicability of the rules in different scenarios is evaluated. Based on the verification results, the graded alarm impact rules are optimized and adjusted, including the need to adjust weights, update rule conditions, or consider introducing more individual difference parameters to improve the accuracy of the rules.

S4. Setting alarm adjustment rules according to the priority ranking results of the intensive care device and the graded alarm impact rules, and optimizing and adjusting the monitoring status alarm information based on the alarm adjustment rules to obtain optimized monitoring status alarm information;

Specifically, clarify the priority given to each intensive care unit based on its importance in patient treatment, classify alarms into different levels, such as low, medium, and high, and determine the urgency of the alarm based on changes in the patient's vital signs and potential risks. For high-priority monitoring devices, their alarm settings are more sensitive to ensure a rapid response to slight changes in the patient's condition. Based on the level of the alarm, set specific response measures for each level. For example, a high-level alarm may require immediate notification to a doctor, while a low-level alarm is recorded and evaluated by the nurse during routine inspections.

According to the actual monitoring situation and patient response, the alarm trigger threshold is refined or adjusted to avoid excessive alarms, alarm fatigue or missed reports. The alarm information from different monitoring devices is integrated and analyzed to avoid information silos, ensuring that medical staff can obtain the patient's comprehensive health status. The historical alarm data is analyzed using intelligent algorithms to identify patterns that truly require emergency response, thereby optimizing the response of the alarm system. By monitoring the operation of the system in real time and collecting feedback from medical staff, the alarm adjustment rules are continuously optimized, and the performance of the alarm system is regularly evaluated to ensure the accuracy and timeliness of alarm information while reducing unnecessary alarms.

S5. Preset alarm evolution prediction rules, analyze monitoring state alarm information and optimize monitoring state evolution prediction parameters of monitoring state alarm information and optimize monitoring state evolution prediction parameters through alarm evolution prediction rules;

Specifically, analyze past monitoring status alarm information, including the type of alarm, frequency, patient response, and measures taken, use statistical analysis and data mining techniques to identify common patterns and trends in alarm evolution, such as other alarm types that often follow certain specific alarms, and based on the identified patterns and trends, build mathematical or machine learning models to predict the evolution path of alarms, taking into account the patient's underlying health status and current monitoring data.

The alarm evolution prediction rules are applied in real time in the monitoring system to analyze the current alarm information, predict the possible evolution path, and evaluate the subsequent health risks and urgency based on the prediction results, so as to take timely preventive or intervention measures. Based on the feedback of the prediction model and the actual monitoring effect, the parameters in the model are optimized to improve the accuracy and reliability of the prediction, and the optimized prediction parameters are applied to the alarm system to achieve more accurate prediction of the evolution of the monitoring status.

Combined with the patient's real-time monitoring data, historical medical records, and external influencing factors such as environmental changes, comprehensive analysis is performed to optimize the prediction parameters. The latest advances in artificial intelligence and machine learning are used to continuously improve the performance of the prediction model so that it can more accurately predict the evolution of the monitoring status. The optimized alarm evolution prediction rules are implemented, their effects are continuously monitored, and feedback is collected. Based on the feedback and new data analysis results, the prediction rules and parameters are continuously iterated and optimized to respond to changes in patient conditions and medical environment.

S6. Compare the monitoring state evolution prediction parameters and the optimized monitoring state evolution prediction parameters, obtain the alarm evolution prediction difference parameters, and set the alarm evolution prediction difference parameter adjustment threshold, compare the alarm evolution prediction difference parameter adjustment threshold with the alarm evolution prediction difference parameter, and obtain the alarm evolution prediction adjustment requirement;

Specifically, comparing the monitoring state evolution prediction parameters and optimizing the monitoring state evolution prediction parameters, obtaining the alarm evolution prediction difference parameters, and setting the alarm evolution prediction difference parameter adjustment threshold, comparing the alarm evolution prediction difference parameter adjustment threshold with the alarm evolution prediction difference parameter, and obtaining the alarm evolution prediction adjustment requirement includes the following steps:

S61, presetting a difference analysis rule, and comparing the monitoring state evolution prediction parameter and optimizing the monitoring state evolution prediction parameter through the difference analysis rule to obtain a difference analysis result;

Specifically, determine the monitoring status evolution prediction parameters to be analyzed, such as predicting the trend of patient condition changes or the possibility of patient prognosis, and formulate differential analysis rules based on medical knowledge and clinical experience, that is, define the differential analysis method between monitoring status evolution prediction parameters, including comparing data at different time points or between different patients, and prepare data for monitoring status evolution prediction parameters, including historical monitoring data, basic patient information, etc., to ensure the quality and integrity of the data and the accuracy of differential analysis.

According to the established difference analysis rules, the monitoring status evolution prediction parameters are compared and analyzed, and statistical methods, machine learning algorithms, etc. are used for data processing and analysis. According to the difference analysis results, the settings or algorithms of the monitoring status evolution prediction parameters are optimized, including adjusting model parameters, updating model structure, or introducing new feature variables, etc., to verify whether the optimized monitoring status evolution prediction parameters can more accurately reflect the patient's actual condition changes or prognosis, and use historical data or actual patient data for verification.

S62, according to the difference analysis result, extracting the difference parameters, and obtaining the alarm evolution prediction difference parameters of the difference analysis result;

Specifically, according to the difference analysis result, obtaining the alarm evolution prediction difference parameter of the difference analysis result by difference parameter extraction includes the following steps:

S621, generating a difference parameter extraction index according to the difference analysis result, and extracting a difference feature parameter of the difference analysis result based on the evaluation difference parameter extraction index;

Specifically, according to the results of differential analysis, differential features related to the prediction parameters of the monitoring status evolution are identified, including prominent changes and trend differences in certain monitoring indicators. Based on the identified differential features, differential parameter extraction indicators are formulated, that is, the specific method of extracting these differential features from the monitoring data is determined, and the designed differential parameter extraction indicators are evaluated to determine their accuracy and reliability through discussions with medical experts and comparisons with actual patient data.

Using the difference parameter extraction indicators that have passed the evaluation, the difference feature parameters are extracted from the actual monitoring data to ensure that the extracted parameters can accurately reflect the important features in the difference analysis results. The extracted difference feature parameters are analyzed to deeply understand the difference characteristics between the monitoring status evolution prediction parameters.

S622, performing a difference impact analysis according to the difference characteristic parameters to obtain a difference parameter impact of the difference characteristic parameters, and generating a difference characteristic parameter adjustment plan based on the difference parameter impact;

Specifically, statistical methods or machine learning techniques are used to analyze the relationship between the difference characteristic parameters and other monitoring indicators to determine their influence on the prediction of the evolution of the monitoring status. Based on the results of the difference impact analysis, the difference parameter influence of the difference characteristic parameters is obtained, that is, the degree of influence of different parameter changes on the difference characteristic parameters.

Based on the impact of differential parameters, an adjustment plan for differential characteristic parameters is formulated, including adjusting the threshold of monitoring indicators, optimizing treatment plans, changing monitoring strategies and other measures to improve the patient's monitoring status. When formulating the adjustment plan, it is necessary to consider the patient's specific situation, the availability of medical resources and the opinions of the medical team to ensure the feasibility and practicality of the adjustment plan. The formulated adjustment plan is applied to actual patient data to verify its effectiveness and feasibility, and the effectiveness of the adjustment plan is evaluated by monitoring changes in patient conditions and treatment outcomes.

S623: verify the difference characteristic parameter adjustment scheme, and adjust the difference characteristic parameters based on the verified difference characteristic parameter adjustment scheme to obtain the alarm evolution prediction difference parameters.

S63, setting and verifying the alarm evolution prediction difference parameter adjustment threshold according to the patient parameter information;

Specifically, obtain the patient's monitoring parameters, physiological indicators, medical history and other related information to ensure the integrity and accuracy of the data; determine the specific parameters that need to set adjustment thresholds based on the patient's parameter information and the influence of the differential characteristic parameters, including key monitoring indicators, physiological variables, etc.; formulate rules to describe how to dynamically adjust the thresholds of differential parameters based on the patient's parameter information; the rules include weight adjustment based on patient characteristics, dynamic update of baseline values, etc.

Apply the formulated adjustment threshold rules to actual patient data to verify their effect on the difference parameters of alarm evolution prediction, use experimental data or actual patient conditions to evaluate the rationality and applicability of the adjustment threshold, compare the prediction effect of monitoring status evolution before and after the application of the adjustment threshold, including indicators such as alarm accuracy and false negative rate, and ensure that the use of the adjustment threshold can improve the accuracy and timeliness of patient monitoring.

S64. Adjust the threshold and alarm evolution prediction difference parameter based on the verified alarm evolution prediction difference parameter, obtain the alarm evolution prediction adjustment requirement through comparison and analysis, and formulate an adjustment strategy based on the alarm evolution prediction adjustment requirement.

Specifically, adjusting the threshold and the alarm evolution prediction difference parameter based on the verified alarm evolution prediction difference parameter, obtaining the alarm evolution prediction adjustment requirement through comparison and analysis, and formulating an adjustment strategy based on the alarm evolution prediction adjustment requirement include the following steps:

S641, comparing the alarm evolution prediction difference parameter adjustment threshold with the alarm evolution prediction difference parameter, and identifying the comparison out-of-range parameter according to the comparison result;

S642, analyzing and comparing out-of-range parameters, obtaining adjustment requirements, and setting alarm evolution prediction adjustment requirements based on the adjustment requirements;

Specifically, identify parameters that exceed the normal range during the monitoring process, including monitored physiological indicators, instrument parameters, etc., analyze the out-of-range parameters, understand their possible causes and impacts, and make a comprehensive judgment based on the patient's medical history, clinical condition, and the working status of the equipment. Based on the analysis results, determine whether it is necessary to adjust the monitoring strategy or equipment settings. If the out-of-range parameters reflect a worsening of the patient's condition, it is necessary to adjust the treatment plan or increase the monitoring frequency.

Based on the determined adjustment needs, formulate corresponding adjustment plans, including adjusting alarm thresholds, changing monitoring strategies, adjusting treatment plans and other operations; according to the formulated adjustment plan, set alarm evolution prediction adjustment needs, which are achieved by updating the alarm system settings, adjusting the parameters of the monitoring equipment, etc.; apply the set alarm evolution prediction adjustment needs and monitor their effects in actual clinical applications.

S643. Develop adjustment strategies based on the forecast of alarm evolution and adjustment needs, and verify and optimize the adjustment strategies through feasibility assessment.

Specifically, predict adjustment needs based on the evolution of alarms and clarify required adjustments, including modifying monitoring parameter thresholds, adjusting treatment plans, changing monitoring frequencies, etc. Based on the identified adjustment needs, formulate corresponding adjustment strategies to ensure that the adjustment strategies can effectively meet the needs of patient monitoring and comply with the norms and standards of medical practice.

Conduct a feasibility assessment on the formulated adjustment strategy, consider its operability, cost-effectiveness, safety and other aspects in actual clinical applications, conduct an evaluation through discussions with the medical team, simulation experiments, etc., apply the formulated adjustment strategy to actual patients, and monitor its effectiveness; based on the verification results, optimize the adjustment strategy, adjust parameter settings, improve operating procedures or re-evaluate feasibility; continuously monitor the effectiveness of the adjustment strategy, and update and optimize it based on patient feedback and practical experience to ensure that the adjustment strategy is consistent with the development of medical practice and patient needs.

S7. Based on the alarm evolution prediction adjustment requirements, optimize and adjust the optimized monitoring state evolution prediction parameters, obtain advanced monitoring state evolution warning parameters, output the advanced monitoring state evolution warning parameters and the optimized monitoring state alarm information, and build an alarm database and a warning database.

Specifically, evaluate the performance of the current early warning system and identify areas for improvement, such as reducing false alarms and missed alarms, or improving the accuracy and timeliness of predictions. In-depth analysis of monitoring data, historical warning responses, and patient health outcomes is performed to identify the direction of parameter adjustment. Based on the analysis results, adjust the algorithm or parameters of the prediction model, such as improving the data processing process, introducing more advanced machine learning models, or adjusting the prediction threshold. In a safe test environment, run the model with new prediction parameters, compare performance improvements, and ensure that the new parameters do not introduce unexpected side effects. Once verified, apply the advanced warning parameters to the actual monitoring status evolution warning system to improve the accuracy and efficiency of the warning.

Ensure that the monitoring system can effectively integrate data from various monitoring devices, apply advanced warning parameters to real-time monitoring data, generate optimized monitoring status alarm information, and dynamically adjust the output of alarm information based on the prediction results of advanced warning parameters to ensure that the medical team can receive the most relevant and urgent alarms, and design an efficient database architecture for storing and managing alarm information and warning parameters, including data collection, storage, query and analysis mechanisms, store all generated alarm information and related warning parameters in the database, including real-time data and historical data, ensure data security and privacy, and implement strict data management policies and access control mechanisms.

Data is regularly extracted from the database for analysis and trend prediction, early warning parameters and alarm strategies are optimized, and information in the database is used to provide decision support, helping the medical team to better understand the evolution of the patient's condition and develop more effective treatments and interventions.

According to another embodiment of the present invention, as shown in FIG2 , a critical care status alarm system based on big data monitoring includes:

Parameter acquisition module 1, used to acquire patient parameter information, analyze the patient parameter information to set a critical care plan, and acquire critical care device configuration requirements based on the critical care plan;

A weighting and sorting module 2 is used to configure a critical care device group according to the critical care device configuration requirements, weight the critical care device group configuration results, and generate a priority sorting result of the critical care devices in the critical care device group according to the weighting of the critical care device group;

A hierarchical alarm module 3, configured to obtain, based on the intensive care plan, individual device hierarchical alarm thresholds and intensive care device change influencing parameters of the intensive care devices in the intensive care device group, and to set hierarchical alarm influencing rules based on the individual device hierarchical alarm thresholds and intensive care device influencing parameters;

The optimization and adjustment module 4 is used to set alarm adjustment rules according to the priority sorting results of the intensive care device and the graded alarm impact rules, and optimize and adjust the monitoring state alarm information based on the alarm adjustment rules to obtain optimized monitoring state alarm information;

Early warning prediction module 5, used for presetting alarm evolution prediction rules, analyzing monitoring state alarm information and optimizing monitoring state evolution prediction parameters of monitoring state alarm information and optimizing monitoring state evolution prediction parameters through alarm evolution prediction rules;

The early warning optimization module 6 is used to compare the monitoring state evolution prediction parameters and optimize the monitoring state evolution prediction parameters, obtain the alarm evolution prediction difference parameters, and set the alarm evolution prediction difference parameter adjustment threshold, compare the alarm evolution prediction difference parameter adjustment threshold with the alarm evolution prediction difference parameter, and obtain the alarm evolution prediction adjustment requirement;

Output alarm module 7, used for optimizing and adjusting the optimized monitoring state evolution prediction parameters based on the alarm evolution prediction adjustment requirements, obtaining advanced monitoring state evolution warning parameters, outputting the advanced monitoring state evolution warning parameters and optimized monitoring state alarm information, and building an alarm database and a warning database;

The parameter acquisition module 1, the weighted ranking module 2, the graded alarm module 3, the optimization and adjustment module 4, the early warning prediction module 5, the early warning optimization module 6 and the output alarm module 7 are connected in sequence.

To sum up, with the help of the above-mentioned technical scheme of the present invention, the present invention formulates a targeted monitoring plan by analyzing the patient's parameter information in detail, ensuring that each patient can receive the monitoring measures that best suit their condition, and sets the graded alarm threshold of the individual device according to the patient's parameters, combined with the change in the intensive care device. The parameters affect the accurate reflection of the patient's real-time status and reduce the possibility of false alarms.

In addition, the present invention rationally utilizes medical resources by prioritizing and weighting the intensive care device group, ensuring that critically ill patients can receive necessary monitoring devices in a timely manner, and dynamically adjusts monitoring strategies and resource allocation to respond to changes in patient conditions by continuously monitoring, analyzing and predicting the patient's condition evolution.

In addition, the present invention adopts an automated monitoring and alarm system to reduce errors in human judgment, improve the accuracy and response speed of monitoring, and identify potential deterioration of the disease by predicting the evolution of alarms, so as to take preventive measures and avoid the occurrence of serious complications. At the same time, the construction of an alarm database and an early warning database helps to accumulate experience and knowledge in intensive care, provide data support for medical staff, and help them make more accurate and well-founded decisions. Through continuous data analysis and model optimization, the effectiveness of the monitoring plan is continuously improved, thereby achieving continuous improvement and optimization of the intensive care process.

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 (10)

1. The intensive care state alarm method based on big data monitoring is characterized by comprising the following steps of:

S1, acquiring patient parameter information, analyzing the patient parameter information to set an intensive care scheme, and acquiring an intensive care device configuration requirement based on the intensive care scheme;

S2, configuring an intensive care device group according to the configuration requirement of the intensive care device, giving weight based on the configuration result of the intensive care device group, and generating a priority ordering result of the intensive care devices in the intensive care device group according to the giving weight of the intensive care device group;

s3, acquiring individual device grading alarm thresholds and intensive care device change influence parameters of the intensive care devices in the intensive care device group based on the intensive care scheme, and setting grading alarm influence rules based on the individual device grading alarm thresholds and the intensive care device influence parameters;

S4, setting alarm adjustment rules according to the priority ordering result of the intensive care device and the hierarchical alarm influence rules, and optimizing and adjusting the monitoring state alarm information based on the alarm adjustment rules to acquire optimized monitoring state alarm information;

S5, presetting an alarm evolution prediction rule, and analyzing monitoring state evolution prediction parameters of monitoring state alarm information and optimized monitoring state alarm information and optimizing the monitoring state evolution prediction parameters through the alarm evolution prediction rule;

s6, comparing the monitored state evolution prediction parameters with the optimized monitored state evolution prediction parameters to obtain alarm evolution prediction difference parameters, setting an alarm evolution prediction difference parameter adjustment threshold, and comparing the alarm evolution prediction difference parameter adjustment threshold with the alarm evolution prediction difference parameters to obtain alarm evolution prediction adjustment requirements;

and S7, optimizing and adjusting the optimized monitoring state evolution prediction parameters based on the alarm evolution prediction adjustment requirement, acquiring advanced monitoring state evolution early warning parameters, outputting the advanced monitoring state evolution early warning parameters and the optimized monitoring state alarm information, and constructing an alarm database and an early warning database.

2. The intensive care status alert method based on big data monitoring as claimed in claim 1, wherein the acquiring individual device class alert thresholds and intensive care device variation influencing parameters of the intensive care devices in the intensive care device group based on the intensive care scheme and setting the class alert influencing rules based on the individual device class alert thresholds and the intensive care device influencing parameters comprises the steps of:

s31, analyzing an intensive care scheme, acquiring a monitoring device required by intensive care, and integrating the monitoring devices to acquire an intensive care device group;

S32, analyzing the intensive care indexes of each intensive care device in the intensive care device group, and setting individual device grading alarm thresholds of the intensive care devices based on the intensive care indexes;

S33, analyzing monitoring device related parameters of the intensive care devices in the intensive care device group, and calculating intensive care device change influencing parameters based on the monitoring device related parameters;

And S34, integrating the individual device grading alarm threshold value and the intensive care device change influence parameter, formulating a grading alarm influence rule based on the integration result, and verifying and optimizing the grading alarm influence rule.

3. The intensive care status alert method based on big data monitoring as claimed in claim 2, wherein analyzing the intensive care index of each of the intensive care devices in the intensive care device group and setting the individual device class alert threshold of the intensive care device based on the intensive care index comprises the steps of:

S321, analyzing medical detection parameters of the intensive care devices, setting an intensive care health threshold value through the medical detection parameters, and setting an intensive care index of each intensive care device based on the intensive care health threshold value;

s322, evaluating the health influence condition of the intensive care index, setting an emergency rule of the intensive care index according to the health influence condition, and setting an initial device grading alarm threshold value based on the emergency rule of the intensive care index;

S323, presetting standard individual parameters and individual grading adjustment rules, acquiring characteristic individual parameters according to patient parameter information, and comparing the standard individual parameters with the characteristic individual parameters to acquire individual difference parameters;

s324, matching the individual grading adjustment rule with the individual difference parameter, and optimally adjusting the initial device grading alarm threshold according to the matching result to obtain the individual device grading alarm threshold.

4. The intensive care unit status alert method as claimed in claim 3, wherein the analyzing the monitoring unit associated parameters of the intensive care units within the intensive care unit group and calculating the intensive care unit change affecting parameters based on the monitoring unit associated parameters comprises the steps of:

S331, acquiring historical monitoring data of the intensive care device, and analyzing associated parameters of the intensive care device based on the historical monitoring data;

S332, presetting a causal rule and a time sequence rule, and optimizing and adjusting the association parameters based on the causal rule and the time sequence rule to obtain the monitoring device association parameters of the intensive care device;

S333, constructing a correlation interaction model based on the correlation parameters of the monitoring device, verifying and optimizing the correlation interaction model, and calculating the variation influence parameters of the intensive care device by adopting the correlation interaction model after verification and optimization.

5. The intensive care state alarm method based on big data monitoring as set forth in claim 4, wherein the steps of constructing a correlation interaction model based on the correlation parameters of the monitoring device, verifying and optimizing the correlation interaction model, and calculating the variation influence parameters of the intensive care device by using the correlation interaction model after verification and optimization include the steps of:

s3331, defining the monitoring device parameter change influence required to be calculated by the association interaction model, and cleaning the monitoring device association parameters;

s3332, acquiring characteristic parameters of the correlation parameters of the monitoring device after cleaning through statistical analysis, constructing a correlation interaction model based on the characteristic parameters, and carrying out cross verification on the correlation interaction model;

S3333, calculating the change influence parameters of the intensive care device by adopting the cross-validated association interaction model, and verifying and optimizing the change influence parameters of the intensive care device.

6. The method for alarming the intensive care state based on big data monitoring according to claim 5, wherein the calculation formula for obtaining the characteristic parameters of the relevant parameters of the monitoring device after cleaning based on the characteristic parameters and constructing the relevant interaction model is as follows:

S is an influence value of the change of the intensive care unit;

N is the total number of characteristic parameters;

is the ith in the characteristic parameters an influence value of the individual feature;

f _i is the influence value of the feature parameter excluding the ith feature.

7. The intensive care state alarm method based on big data monitoring according to claim 1, wherein the comparing the monitored state evolution prediction parameter and the optimized monitored state evolution prediction parameter to obtain an alarm evolution prediction difference parameter, setting an alarm evolution prediction difference parameter adjustment threshold, comparing the alarm evolution prediction difference parameter adjustment threshold with the alarm evolution prediction difference parameter, and obtaining an alarm evolution prediction adjustment requirement comprises the following steps:

s61, presetting a difference analysis rule, and comparing the monitoring state evolution prediction parameter with the optimized monitoring state evolution prediction parameter through the difference analysis rule to obtain a difference analysis result;

s62, according to a difference analysis result, acquiring an alarm evolution prediction difference parameter of the difference analysis result through difference parameter extraction;

S63, setting an alarm evolution prediction difference parameter adjustment threshold according to patient parameter information and verifying;

S64, adjusting a threshold value and an alarm evolution prediction difference parameter based on the verified alarm evolution prediction difference parameter, acquiring an alarm evolution prediction adjustment requirement through comparison analysis, and formulating an adjustment strategy based on the alarm evolution prediction adjustment requirement.

8. The intensive care state alarm method as claimed in claim 7, wherein the obtaining the alarm evolution prediction difference parameter of the difference analysis result through the difference parameter extraction according to the difference analysis result comprises the following steps:

s621, generating a difference parameter extraction index according to a difference analysis result, and extracting a difference characteristic parameter of the difference analysis result based on the estimated difference parameter extraction index;

S622, obtaining a difference parameter influence condition of the difference characteristic parameters through difference influence analysis according to the difference characteristic parameters, and generating a difference characteristic parameter adjustment scheme based on the difference parameter influence condition;

s623, verifying the difference characteristic parameter adjustment scheme, and adjusting the difference characteristic parameter based on the verified difference characteristic parameter adjustment scheme to obtain the alarm evolution prediction difference parameter.

9. The intensive care state alarm method as claimed in claim 7, wherein the adjusting of the threshold and the alarm evolution prediction difference parameters based on the verified alarm evolution prediction difference parameters acquires an alarm evolution prediction adjustment requirement through comparison analysis, and the formulating of an adjustment strategy based on the alarm evolution prediction adjustment requirement comprises the steps of:

s641, comparing the alarm evolution prediction difference parameter adjustment threshold with the alarm evolution prediction difference parameter, and identifying and comparing the out-of-range parameter according to the comparison result;

s642, analyzing and comparing the out-of-range parameters, acquiring an adjustment requirement, and setting an alarm evolution prediction adjustment requirement based on the adjustment requirement;

s643, formulating an adjustment strategy based on the alarm evolution prediction adjustment requirement, and verifying optimization of the adjustment strategy through feasibility assessment.

10. An intensive care state alarm system based on big data monitoring for implementing the intensive care state alarm method based on big data monitoring as set forth in any one of claims 1 to 9, characterized in that the system comprises:

the parameter acquisition module is used for acquiring patient parameter information, analyzing the patient parameter information, setting an intensive care scheme, and acquiring the configuration requirement of the intensive care device based on the intensive care scheme;

The weighting ordering module is used for configuring the intensive care device group according to the configuration requirement of the intensive care device, weighting the intensive care device group based on the configuration result of the intensive care device group, and generating a priority ordering result of the intensive care devices in the intensive care device group through the weighting condition of the intensive care device group;

The hierarchical alarm module is used for acquiring individual device hierarchical alarm thresholds and intensive care device change influence parameters of the intensive care devices in the intensive care device group based on the intensive care scheme, and setting hierarchical alarm influence rules based on the individual device hierarchical alarm thresholds and the intensive care device influence parameters;

The optimization adjustment module is used for setting alarm adjustment rules according to the priority ordering result of the intensive care device and the hierarchical alarm influence rules, and optimizing and adjusting the monitoring state alarm information based on the alarm adjustment rules to obtain optimized monitoring state alarm information;

The early warning prediction module is used for presetting an alarm evolution prediction rule, analyzing the monitored state evolution prediction parameters of the monitored state alarm information and the optimized monitored state alarm information through the alarm evolution prediction rule, and optimizing the monitored state evolution prediction parameters;

The early warning optimization module is used for comparing the monitoring state evolution prediction parameters with the optimized monitoring state evolution prediction parameters to obtain alarm evolution prediction difference parameters, setting an alarm evolution prediction difference parameter adjustment threshold value, and comparing the alarm evolution prediction difference parameter adjustment threshold value with the alarm evolution prediction difference parameters to obtain alarm evolution prediction adjustment requirements;

The output alarm module is used for optimizing and adjusting the optimized monitoring state evolution prediction parameters based on the alarm evolution prediction adjustment requirement, acquiring advanced monitoring state evolution early-warning parameters, outputting the advanced monitoring state evolution early-warning parameters and the optimized monitoring state alarm information, and constructing an alarm database and an early-warning database;

The parameter acquisition module, the weighting ordering module, the grading alarm module, the optimization adjustment module, the early warning prediction module, the early warning optimization module and the output alarm module are sequentially connected.