A method and system for generating an emergency intervention plan
Through the comparison of emergency assessment models and historical data, combined with machine learning algorithms and emergency intervention strategy library, a specific emergency intervention plan is generated, which solves the problem of insufficient analysis capabilities and decision-making support in existing systems, and improves the accuracy and effectiveness of emergency responses .
Patent Information
- Application Number
- CN202411328368.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-24
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-09-24
AI Technical Summary
Existing emergency data processing systems have limited analytical capabilities and decision support, are difficult to adapt to complex and changeable emergency situations, and have failed to make full use of historical data to improve emergency response strategies.
By obtaining emergency monitoring data, using pre-established emergency assessment models to generate a preliminary evaluation report, and comparing it with historical data, using machine learning algorithms to predict future trends and goals, and combining with the emergency intervention strategy library to formulate specific emergency intervention plans.
It improves the accuracy and pertinence of emergency monitoring and intervention, enhances the scientificity and effectiveness of emergency management, and can respond quickly and reduce losses.
Smart Images

Figure CN118863597B_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the field of data processing technology, and in particular to a method and system for generating an emergency intervention plan. Background Art
[0002] With the development of social economy and the advancement of technology, people are facing more and more emergencies such as natural disasters and man-made accidents. In these emergency situations, how to effectively collect and analyze emergency monitoring data and make quick and accurate decisions based on it has become an important technical requirement. Emergency management departments need an efficient data processing system to assist them in grasping the development of events, assessing risks, and taking timely actions to reduce losses.
[0003] Currently, many places have adopted automated monitoring systems and data analysis tools to process emergency data. These systems are usually able to automatically collect information from various sensors and other data sources, and perform preliminary processing on the data through preset rules or algorithms. However, the functions of these systems are often limited to simple data aggregation and preliminary screening, lacking in-depth data analysis capabilities and intelligent decision support.
[0004] Although the existing emergency data processing solutions have improved the speed of emergency response to a certain extent, there are still some shortcomings:
[0005] Limited analytical capabilities: Existing systems mainly rely on fixed rules and algorithms, which cannot adapt to complex and changing emergency situations and find it difficult to generate in-depth analytical results.
[0006] Inadequate decision support: The lack of an effective mechanism to convert preliminary emergency assessment results into specific emergency recommendations makes it difficult for decision makers to quickly develop appropriate intervention measures.
[0007] Insufficient use of historical data: Existing systems rarely make full use of historical emergency monitoring data and are unable to improve current emergency response strategies by learning from historical data. Summary of the invention
[0008] The embodiments of the present application provide a method and system for generating an emergency intervention plan to solve the problems existing in the above-mentioned background technology.
[0009] In the first aspect, an embodiment of the present application provides a method for generating an emergency intervention plan, comprising: obtaining emergency monitoring data; using a pre-established emergency assessment model to analyze the emergency monitoring data to generate a preliminary emergency assessment report; comparing the preliminary emergency assessment report with historical emergency monitoring data to generate emergency recommendations; using a pre-created emergency intervention strategy library to formulate a specific emergency intervention plan based on the emergency recommendations.
[0010] Furthermore, a pre-established emergency assessment model is used to analyze the emergency monitoring data to generate a preliminary emergency assessment report, including: converting the emergency monitoring data into standardized emergency monitoring data; based on the standardized emergency monitoring data and a preset risk function, calculating the risk function value corresponding to each standardized emergency monitoring data, wherein the risk function value is used to characterize the risk level of each standardized emergency monitoring data; and inputting the risk function value corresponding to each standardized emergency monitoring data as input information into a pre-trained emergency assessment model to obtain a preliminary emergency assessment report output by the emergency assessment model.
[0011] Furthermore, the expression of the preset risk function is:
[0012] ;
[0013] in, For the Emergency monitoring data in time The risk function value corresponding to the measured value of For the Emergency monitoring data in time The measured value of For the Emergency monitoring data in time The average value of No. Emergency monitoring data in time The standard deviation of , and For the The preset weights corresponding to the emergency monitoring data are: For the Emergency monitoring data in time The instantaneous rate of change, For the Emergency monitoring data in time The average value of the instantaneous rate of change, For the seasonal cycle of emergency monitoring data;
[0014] The expression of the pre-trained emergency assessment model is:
[0015] ;
[0016] in, for The dynamic emergency risk index at each moment, is the total number of emergency monitoring data, For the Emergency monitoring data in The dynamic weight corresponding to the moment, , For the Emergency monitoring data in time The measured value of For the Emergency monitoring data in time The average value of No. Emergency monitoring data in time The standard deviation of For the Emergency monitoring data in time The seasonal adjustment factor is For time Time Emergency monitoring data and The interaction weights between emergency monitoring data, For the Emergency monitoring data and The interaction effect function between emergency monitoring data, .
[0017] Furthermore, the method also includes: obtaining the historical emergency behavior data; based on the dynamic emergency risk index and the historical emergency behavior data, using a machine learning algorithm to predict the emergency trend in the future; using the emergency trend and emergency goals to generate emergency recommendations, wherein.
[0018] Furthermore, based on the dynamic emergency risk index and the historical emergency behavior data, a machine learning algorithm is used to predict the emergency trend in the future, including: using a long short-term memory network or a variant model, and introducing an external data source, combining the emergency monitoring data and the historical emergency behavior data, to predict the emergency trend in the future.
[0019] Furthermore, the emergency trends and emergency goals are used to generate emergency recommendations, including: generating an emergency intervention plan based on the emergency trends and the emergency goals using a genetic algorithm or a reinforcement learning algorithm; combining the emergency intervention plan with environmental factors to screen out initial emergency recommendations; and adjusting and optimizing the initial emergency recommendations based on priority and feasibility to form the emergency recommendations.
[0020] Furthermore, the method also includes: obtaining the indicator baseline range corresponding to the real-time value of each of the emergency monitoring data, and filtering out abnormal values that exceed the baseline range to generate corrected emergency monitoring data; and / or calculating the rate of change of the real-time value of each of the emergency monitoring data and the value at the previous moment, and filtering out abnormal values whose rate of change exceeds a preset threshold to generate corrected emergency monitoring data.
[0021] In the second aspect, an embodiment of the present application provides a system for generating an emergency intervention plan, including: an acquisition unit for acquiring emergency monitoring data; a first generation unit for analyzing the emergency monitoring data using a pre-established emergency assessment model to generate a preliminary emergency assessment report; a second generation unit for comparing the preliminary emergency assessment report with historical emergency monitoring data to generate emergency recommendations; and a feedback unit for using a pre-created emergency intervention strategy library to formulate a specific emergency intervention plan based on the emergency recommendations.
[0022] In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the method described in the first aspect above.
[0023] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, which, when executed by a computer, implements the method described in the first aspect above.
[0024] In an embodiment of the present invention, emergency monitoring data is acquired; a pre-established emergency assessment model is used to analyze the emergency monitoring data to generate a preliminary emergency assessment report; the preliminary emergency assessment report is compared with historical emergency monitoring data to generate emergency recommendations; a pre-created emergency intervention strategy library is used to formulate a specific emergency intervention plan based on the emergency recommendations, and an emergency data processing method is used to formulate a specific and targeted emergency intervention plan based on the plan, so as to better meet the needs of precise emergency management, improve the effectiveness of emergency monitoring and intervention, and provide more scientific and effective emergency support means.
[0025] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0027] Figure 1 A flowchart of a method for generating an emergency intervention plan provided in an embodiment of the present application;
[0028] Figure 2 A schematic diagram of a system for generating an emergency intervention plan provided in an embodiment of the present application;
[0029] Figure 3 A schematic diagram of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0030] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. 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.
[0031] Embodiment 1:
[0032] According to an embodiment of the present invention, an embodiment of a method for generating an emergency intervention plan is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0033] Figure 1 is a flow chart of a method for generating an emergency intervention plan according to an embodiment of the present invention, such as Figure 1 As shown, the method comprises the following steps:
[0034] Step S102, obtaining emergency monitoring data;
[0035] Step S104, using a pre-established emergency assessment model to analyze the emergency monitoring data and generate a preliminary emergency assessment report;
[0036] Step S106, comparing the preliminary emergency assessment report with historical emergency monitoring data to generate emergency recommendations;
[0037] Step S108, using the pre-created emergency intervention strategy library, formulate a specific emergency intervention plan according to the emergency suggestions.
[0038] The above emergency data include public health information data, socio-economic data, medical treatment information data and basic geographic data. The above steps are described in detail below using medical treatment information data as an example.
[0039] Medical treatment information data refers to various relevant information collected during emergency medical treatment, including but not limited to patients' vital signs (such as heart rate (HR), blood pressure (BP), oxygen saturation (SpO2), etc.), laboratory test results, imaging test results, medical history records, etc. These data are usually automatically or manually entered into the central database through the Hospital Information System (HIS), Electronic Health Record (EHR) and other related medical equipment.
[0040] In the embodiment of the present application, for example, an emergency center receives a request for emergency treatment from a car accident victim and immediately initiates an emergency response mechanism. The emergency personnel first use a portable medical device to measure the patient's vital signs and transmit these data to the hospital's HIS system in real time through a mobile medical terminal. At the same time, the emergency personnel also enter the patient's preliminary diagnosis information (for example, suspected craniocerebral injury and multiple fractures).
[0041] The emergency assessment model is a pre-trained machine learning model or expert system that is used to assess the patient's condition based on the emergency monitoring data collected in real time and generate a preliminary emergency assessment report, which includes an assessment of the severity of the patient's condition, recommended priority treatment items, etc.
[0042] The emergency assessment module in the HIS system uses a pre-trained machine learning model (e.g., a classifier based on a support vector machine (SVM)) to assess the severity of the patient's condition based on the received vital sign data and preliminary diagnosis information. Assume that the model output shows that the patient is a high-risk patient and needs to be prepared for surgery immediately. This conclusion will form part of the preliminary emergency assessment report.
[0043] Historical emergency monitoring data refers to relevant information from similar cases in the past, including treatment processes, drugs used, final results, etc. By comparing and analyzing the preliminary emergency assessment report with historical data, more targeted emergency recommendations can be generated to guide subsequent treatment work.
[0044] Further review of historical cases in the EHR system revealed several cases similar to the current patient’s. By comparing the treatment and results of these cases, the system recommended that the patient be immediately scheduled for a CT scan to confirm intracranial hemorrhage and that a neurosurgeon be contacted for consultation.
[0045] The emergency intervention strategy library contains a variety of standard operating procedures (SOPs) for different types of emergency medical events. Based on the emergency recommendations generated in the previous step, the system will select the most appropriate intervention measures from this library and formulate a specific emergency intervention plan.
[0046] In the embodiment of the present application, according to the above emergency suggestions, an emergency treatment process suitable for patients with craniocerebral injury is selected from the SOP library. The process includes but is not limited to: immediately performing a CT scan, preparing the operating room, notifying the anesthesia department and the neurosurgery team to stand by, and preparing necessary rescue drugs and equipment. These steps constitute a specific emergency intervention plan.
[0047] Through the above steps, an efficient medical emergency response system can be built to ensure rapid and accurate response in emergency situations and provide the best treatment plan.
[0048] In an embodiment of the present invention, the emergency monitoring data is analyzed using a pre-established emergency assessment model to generate a preliminary emergency assessment report, including:
[0049] Converting the emergency monitoring data into standardized emergency monitoring data;
[0050] Based on the standardized emergency monitoring data and the preset risk function, a risk function value corresponding to each standardized emergency monitoring data is calculated, wherein the risk function value is used to characterize the risk level of each standardized emergency monitoring data;
[0051] The risk function value corresponding to each standardized emergency monitoring data is input as input information into a pre-trained emergency assessment model to obtain a preliminary emergency assessment report output by the emergency assessment model.
[0052] The above content is explained below using medical treatment information data as an example.
[0053] For example, the emergency center receives a call for emergency treatment from a car accident victim. The emergency personnel use a portable medical device to measure the patient's heart rate of 120 beats per minute, blood pressure of 100 / 60 mmHg, and blood oxygen saturation of 92%. For ease of processing, these data are standardized, for example, the heart rate is converted to a Z-score value (heart rate minus the mean heart rate and divided by the standard deviation), and the blood pressure and blood oxygen saturation are also converted accordingly.
[0054] The preset risk function is a mathematical expression used to quantify the risk of standardized emergency monitoring data. By substituting the standardized data into the function, a risk score can be obtained, which represents the risk level of a specific health parameter.
[0055] The emergency assessment model is a pre-trained machine learning model or expert system that is used to assess the patient's condition based on a standardized risk function value and generate a preliminary emergency assessment report. This report may include an assessment of the severity of the patient's condition, recommended priority treatment items, etc. In an embodiment of the present application, the system inputs the standardized heart rate risk function value, blood pressure risk function value, and blood oxygen saturation risk function value into a pre-trained emergency assessment model. The model may be a neural network or other supervised learning model that has been trained with a large amount of medical data and can identify the emergency level corresponding to different risk combinations. The model outputs a preliminary emergency assessment report, indicating that the patient is at high risk and that immediate measures need to be taken to stabilize his vital signs and prepare for further examination and treatment. Through the above steps, an efficient medical emergency treatment system can be built to ensure that a quick and accurate response can be made in an emergency and provide the best treatment plan.
[0056] Preferably, the expression of the preset risk function is:
[0057] ;
[0058] in, For the Emergency monitoring data in time The risk function value corresponding to the measured value of For the Emergency monitoring data in time The measured value of For the Emergency monitoring data in time The average value of No. Emergency monitoring data in time The standard deviation of , and For the The preset weights corresponding to the emergency monitoring data are: For the Emergency monitoring data in time The instantaneous rate of change, For the Emergency monitoring data in time The average value of the instantaneous rate of change, For the seasonal cycle of emergency monitoring data;
[0059] The expression of the pre-trained emergency assessment model is:
[0060] ;
[0061] in, for The dynamic emergency risk index at each moment, is the total number of emergency monitoring data, For the Emergency monitoring data in The dynamic weight corresponding to the moment,
[0062] , For the Emergency monitoring data in time The measured value of For the Emergency monitoring data in time The average value of No. Emergency monitoring data in time The standard deviation of For the Emergency monitoring data in time The seasonal adjustment factor is For time Time Emergency monitoring data and The interaction weights between emergency monitoring data, For the Emergency monitoring data and The interaction effect function between emergency monitoring data, .
[0063] In an embodiment of the present invention, the method further includes:
[0064] Acquiring the historical emergency behavior data;
[0065] Based on the dynamic emergency risk index and the historical emergency behavior data, a machine learning algorithm is used to predict the emergency trend in the future;
[0066] Using the emergency trends and emergency goals, emergency recommendations are generated.
[0067] In the embodiment of the present invention, historical emergency behavior data refers to the handling records of similar medical emergencies that have occurred in the past, including but not limited to the response time of medical staff, the initial measures taken, the medical resources used, the patient's outcome, etc. These data can be extracted from the hospital's information system and used for subsequent analysis.
[0068] The treatment records of all patients with craniocerebral injury caused by traffic accidents in the past five years were retrieved from the hospital's Electronic Health Records (EHR) system. These records include the time when the patient arrived at the emergency room, changes in vital signs, initial treatment measures received, operation time, and hospitalization days.
[0069] The Dynamic Emergency Risk Index (DERI) is calculated through real-time monitoring data and a preset risk function to assess the severity of the current emergency. Combined with historical emergency behavior data, machine learning algorithms can be used to predict emergency trends in the future to help medical institutions prepare in advance.
[0070] The current patient's DERI is input into a pre-trained machine learning model together with historical emergency behavior data. This model may be a long short-term memory network (LSTM) because it is good at processing time series data. By analyzing past treatment cases, the model can predict the development trend of emergency situations that the current patient may face, such as how long it will take to stabilize the condition, whether emergency surgery is needed, etc.
[0071] Emergency goals refer to the ideal state or results that medical institutions hope to achieve, such as reducing patient waiting time, improving the success rate of treatment, etc. Based on the predicted emergency trends and emergency goals, the system can generate specific emergency recommendations to guide future emergency management work.
[0072] For example, the model predicts that the current patient needs to enter the operating room for surgery as soon as possible, otherwise his life may be in danger. Based on this prediction result and the hospital's emergency goal (starting surgery as quickly as possible), the system generates an emergency recommendation, suggesting that a green channel be opened immediately for the patient, various examinations be accelerated, and surgery be arranged as soon as possible.
[0073] Specifically, for example, a hospital receives a patient injured in a car accident. Initial examinations reveal that the patient has severe craniocerebral injury and requires immediate surgery. The following are the specific steps:
[0074] Obtaining emergency monitoring data: First responders used portable medical equipment to measure the patient's heart rate at 120 beats / minute, blood pressure at 100 / 60 mmHg, and blood oxygen saturation at 92%.
[0075] Standardized emergency monitoring data: Heart rate is standardized to Z(HR)=1.5, and blood pressure and blood oxygen saturation are also standardized.
[0076] Calculate risk function value: Calculate the risk function value using the preset risk function.
[0077] Generate a preliminary emergency assessment report: Input the risk function value into the pre-trained emergency assessment model. The model output indicates that the patient is at high risk and immediate measures are needed to stabilize vital signs.
[0078] Obtain historical emergency behavior data: Extract the treatment records of all patients with craniocerebral injuries caused by traffic accidents in the past five years from the EHR system.
[0079] Predicting emergency trends: The current patient’s DERI (based on the risk function value) is input into the LSTM model together with the historical emergency behavior data to predict that the patient needs surgery as soon as possible.
[0080] Generate emergency recommendations: Based on the prediction results and the hospital's emergency goals, the system recommends immediately opening a green channel for the patient, speeding up various examinations, and arranging surgery as soon as possible.
[0081] Through the above steps, hospitals can respond to emergencies quickly and accurately and take appropriate measures based on the predicted results.
[0082] In an embodiment of the present invention, based on the dynamic emergency risk index and the historical emergency behavior data, a machine learning algorithm is used to predict the emergency trend in the future period of time, including:
[0083] Use a long short-term memory network or a variant model, introduce an external data source, combine the emergency monitoring data and the historical emergency behavior data, and predict the emergency trend in the future.
[0084] Long Short-Term Memory Network (LSTM) is a special type of Recurrent Neural Network (RNN) that is particularly suitable for processing time series data. The LSTM model can remember information over a long time span, overcoming the gradient vanishing problem of traditional RNN. Variant models may include Gated Recurrent Unit (GRU) or other improved versions.
[0085] Introducing external data sources means that in addition to using traditional emergency monitoring data and historical emergency behavior data, other factors that may affect emergency trends are also combined, such as weather conditions, holidays, special events, etc. This additional information can help the model better understand the impact of environmental factors on emergency situations.
[0086] In the embodiment of the present application, the LSTM model is used to predict the emergency trend in the future. In addition, weather forecast data is introduced as one of the external data sources, because bad weather may lead to an increase in traffic accidents, which in turn affects the emergency pressure of the hospital.
[0087] Specifically, for example, a hospital receives a car accident victim, and preliminary examination shows that the patient has severe craniocerebral injury. The following are the specific implementation steps:
[0088] Obtaining emergency monitoring data: First responders use portable medical devices to measure the patient's vital signs, including a heart rate of 120 beats per minute, blood pressure of 100 / 60 mmHg, and blood oxygen saturation of 92%. These data are recorded and sent to the hospital's information system.
[0089] Standardize emergency monitoring data: Standardize these vital signs data, for example, convert heart rate into Z-score value, and blood pressure and blood oxygen saturation are also converted accordingly.
[0090] Calculate the risk function value: Use the preset risk function to calculate the risk function value corresponding to each standardized emergency monitoring data.
[0091] Generate a preliminary emergency assessment report: Input the risk function value into the pre-trained emergency assessment model. The model output indicates that the patient is at high risk and immediate measures are needed to stabilize vital signs and prepare for surgery.
[0092] Obtain historical emergency behavior data: Extract the treatment records of all patients with craniocerebral injuries caused by traffic accidents in the past five years from the EHR system, including the time the patient arrived at the emergency room, changes in vital signs, initial treatment measures received, operation time, number of days in hospital, etc.
[0093] Introducing external data sources: Assume that the weather forecast for the day shows that there will be heavy rain in the next 24 hours, which may lead to more traffic accidents. Therefore, weather forecast data is included in the analysis as one of the external data sources.
[0094] Use LSTM model to predict emergency trends: The current patient's DERI (based on risk function value), historical emergency behavior data, and weather forecast data are input into the pre-trained LSTM model. After training, the model can predict emergency trends in the future. For example, it is expected that the emergency department will receive more patients injured in traffic accidents in the next few hours.
[0095] Generate emergency suggestions: Based on the prediction results and the hospital's emergency goals (such as reducing patient waiting time and improving treatment efficiency), the system generates specific emergency suggestions, such as increasing the number of emergency doctors on duty, preparing operating rooms in advance, and notifying relevant departments to be prepared.
[0096] Through the above steps, hospitals can use advanced machine learning technology to predict future emergency trends and make reasonable resource allocations accordingly to improve the quality and efficiency of medical services.
[0097] In the embodiment of the present invention, the emergency trend and the emergency target are used to generate emergency suggestions, including:
[0098] Generate an emergency intervention plan using a genetic algorithm or a reinforcement learning algorithm according to the emergency trend and the emergency goal;
[0099] Combine the emergency intervention plan with environmental factors to screen out initial emergency recommendations;
[0100] The initial emergency proposal is adjusted and optimized based on priority and feasibility to form the emergency proposal.
[0101] In the embodiment of the present invention, the emergency trend refers to the development direction of the emergency situation that may occur in the future period predicted based on historical data and current situation. The emergency goal refers to the goal that the medical institution hopes to achieve, such as reducing the waiting time of patients and improving the success rate of treatment. Genetic Algorithm (GA) and Reinforcement Learning (RL) are two common optimization algorithms that can be used to generate the optimal emergency intervention plan.
[0102] Genetic Algorithm: A search heuristic algorithm that imitates natural selection and genetic mechanisms. Through operations such as selection, crossover, and mutation, GA can find the optimal or nearly optimal solution in the solution space.
[0103] Reinforcement learning: is a machine learning method that learns to achieve a specific goal through trial and error. The RL agent interacts with the environment, tries different actions, and adjusts its behavior based on feedback to maximize some cumulative reward.
[0104] Specifically, a genetic algorithm is used to generate emergency intervention plans. The algorithm will take into account emergency trends (for example, an increase in the number of emergency patients in the next few hours) and emergency goals (such as shortening patient waiting time) and find the best resource allocation plan through a series of iterative processes.
[0105] The risk function value of the current patient, historical emergency behavior data, and weather forecast data are input into the pre-trained LSTM model. After training, the model can predict the emergency trend in the future. For example, it is expected that the emergency department will receive more patients injured in traffic accidents in the next few hours.
[0106] Generate emergency intervention plans using genetic algorithms: Genetic algorithms are used to generate multiple emergency intervention plans based on the predicted emergency trends and emergency goals (reducing patient waiting time). These plans may include increasing the number of emergency doctors on duty, preparing operating rooms in advance, and notifying relevant departments to prepare.
[0107] Combine environmental factors to filter initial emergency recommendations: Assume that the current weather forecast shows that there will be heavy rain in the next few hours, which may affect the efficiency of ambulance traffic. We combine the emergency intervention plan generated by the genetic algorithm with this environmental factor to filter out emergency recommendations that are still feasible under heavy rain conditions.
[0108] Adjust and optimize emergency recommendations: Consider priority and feasibility, and adjust the initial emergency recommendations. For example, give priority to critically ill patients entering the operating room, ensure that ambulances can safely deliver patients to the hospital before the rainstorm arrives, and allocate medical resources according to actual conditions. Through the above steps, hospitals can use advanced algorithms and technical means to predict future emergency trends, and make reasonable resource allocations accordingly to improve the quality and efficiency of medical services.
[0109] In an embodiment of the present invention, for example, the emergency department of a hospital receives multiple car accident victims, and preliminary examinations show that multiple patients have craniocerebral injuries and multiple fractures. The following are specific implementation steps:
[0110] Obtaining emergency monitoring data: First responders used portable medical equipment to measure the patient's vital signs, including a heart rate of 120 beats per minute, a blood pressure of 100 / 60 mmHg, and a blood oxygen saturation of 92%.
[0111] Get the metric baseline range and filter out outliers:
[0112] The baseline range of heart rate is 60-100 beats / minute, and the actual measured value is 120 beats / minute, which exceeds the baseline range and is therefore filtered out.
[0113] The baseline range of blood pressure was 120 / 80 mmHg, and the actual measured value was 100 / 60 mmHg, which was low but within the acceptable range and was retained.
[0114] The baseline range of blood oxygen saturation is above 95%, and the actual measured value is 92%, which is lower than the baseline range and is therefore filtered out.
[0115] After filtering through the baseline range, the corrected emergency monitoring data are: heart rate (filtered out), blood pressure 100 / 60 mmHg, and blood oxygen saturation (filtered out).
[0116] Calculate the rate of change and filter out outliers:
[0117] Assuming that the heart rate measured at the previous moment is 80 beats / minute, the current heart rate change rate is 50%, which exceeds the preset threshold of ±20%, so it is filtered out.
[0118] The blood pressure was 120 / 80 mmHg at the previous moment. The current blood pressure change is small, so it is maintained.
[0119] The blood oxygen saturation at the previous moment was 98%, and the current change rate was −6.12%, which did not exceed the preset threshold and was retained.
[0120] After filtering the rate of change, the corrected emergency monitoring data are: heart rate (filtered), blood pressure 100 / 60 mmHg, and blood oxygen saturation 92%.
[0121] Through the above steps, hospitals can effectively identify and exclude outliers, thereby ensuring that subsequent analysis and decision-making are based on more reliable data.
[0122] Embodiment 2:
[0123] An embodiment of the present invention further provides a system for generating an emergency intervention plan, which is used to execute the method for generating an emergency intervention plan provided in the above content of the embodiment of the present invention. The following is a detailed introduction to the system for generating an emergency intervention plan provided in the embodiment of the present invention.
[0124] like Figure 2 As shown, Figure 2 The schematic diagram of the generation system of the above emergency intervention plan is as follows, wherein the system comprises:
[0125] An acquisition unit 10 is used to acquire emergency monitoring data;
[0126] A first generating unit 20 is used to analyze the emergency monitoring data using a pre-established emergency assessment model to generate a preliminary emergency assessment report;
[0127] A second generating unit 30 is used to compare the preliminary emergency assessment report with historical emergency monitoring data to generate emergency recommendations;
[0128] The feedback unit 40 is used to use the pre-created emergency intervention strategy library to formulate a specific emergency intervention plan according to the emergency suggestion.
[0129] Embodiment three:
[0130] The embodiment of the present invention further provides a computing device for executing a program of the method described in the first embodiment, such as Figure 3 As shown, the computing device may include a storage component 41 and a processing component 42;
[0131] The storage component 41 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 42 .
[0132] The processing component 42 may include one or more processors to execute computer instructions to complete all or part of the steps in the method of embodiment 1. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.
[0133] The storage component 41 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.
[0134] The display component 43 may be an electroluminescent (EL) element, a liquid crystal display or a micro display having a similar structure, or a retinal direct display or a similar laser scanning display.
[0135] Of course, a computing device may also include other components, such as input / output interfaces, communication components, etc.
[0136] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.
[0137] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.
[0138] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.
[0139] Embodiment 4:
[0140] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The method of the illustrated embodiment.
[0141] 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.
[0142] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.
[0143] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0144] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A method for generating an emergency intervention plan, It is characterized in that include: Acquiring medical treatment information data, wherein the medical treatment information data includes: the patient's vital signs, laboratory test results, imaging examination results and patient medical history records; Analyze the medical treatment information data using a pre-established emergency assessment model to generate a preliminary emergency assessment report; Comparing the preliminary emergency assessment report with historical medical treatment information data to generate emergency recommendations, wherein the historical medical treatment information data includes: treatment process, used drugs and final treatment results; Using a pre-created emergency intervention strategy library, formulate a specific emergency intervention plan based on the emergency recommendations, wherein the emergency intervention strategy library includes standard operating procedures for different types of emergency medical events; The medical treatment information data is analyzed using a pre-established emergency assessment model to generate a preliminary emergency assessment report, including: converting the medical treatment information data into standardized medical treatment information data; Based on the standardized medical treatment information data and a preset risk function, a risk function value corresponding to each standardized medical treatment information data is calculated, wherein the risk function value is used to characterize the risk level of each standardized medical treatment information data; Inputting the risk function value corresponding to each standardized medical treatment information data as input information into a pre-trained emergency assessment model to obtain a preliminary emergency assessment report output by the emergency assessment model; The expression of the preset risk function is: ; in, For the Medical treatment information data in time The risk function value corresponding to the measured value of For the Medical treatment information data in time The measured value of For the Medical treatment information data in time The average value of No. Medical treatment information data in time The standard deviation of , and For the The preset weight corresponding to each medical treatment information data, For the Medical treatment information data in time The instantaneous rate of change, For the Medical treatment information data in time The average value of the instantaneous rate of change, For the seasonal cycle of medical treatment information data; The expression of the pre-trained emergency assessment model is: ; in, for The dynamic emergency risk index at each moment, is the total number of medical treatment information data, For the Medical treatment information data The dynamic weight corresponding to the moment, , For the Medical treatment information data in time The measured value of For the Medical treatment information data in time The average value of No. Medical treatment information data in time The standard deviation of For the Medical treatment information data in time The seasonal adjustment factor is For time Time Medical treatment information data and The interaction weight between medical treatment information data, For the Medical treatment information data and The interaction effect function between medical treatment information data, .
2. The method according to claim 1, It is characterized in that The method further comprises: Obtain historical emergency behavior data; Based on the dynamic emergency risk index and the historical emergency behavior data, a machine learning algorithm is used to predict the emergency trend in the future; Using the emergency trends and emergency goals, emergency recommendations are generated.
3. The method according to claim 2, It is characterized in that Based on the dynamic emergency risk index and the historical emergency behavior data, a machine learning algorithm is used to predict the emergency trend in the future period of time, including: Use a long short-term memory network or a variant model, introduce an external data source, combine the medical treatment information data and the historical emergency behavior data, and predict the emergency trend in the future.
4. The method according to claim 2, It is characterized in that Using the emergency trends and emergency goals, generate emergency recommendations, including: Generate an emergency intervention plan using a genetic algorithm or a reinforcement learning algorithm according to the emergency trend and the emergency goal; Combine the emergency intervention plan with environmental factors to screen out initial emergency recommendations; The initial emergency proposal is adjusted and optimized based on priority and feasibility to form the emergency proposal.
5. The method according to claim 1, It is characterized in that The method further comprises: Obtaining the index baseline range corresponding to the real-time value of each of the medical treatment information data, and filtering out abnormal values beyond the baseline range to generate corrected medical treatment information data; and / or, The change rate between the real-time value of each medical rescue information data and the value at the previous moment is calculated, and abnormal values whose change rate exceeds a preset threshold are filtered out to generate corrected medical rescue information data.
6. A system for generating emergency intervention plans, It is characterized in that include: An acquisition unit, used for acquiring medical treatment information data, wherein the medical treatment information data includes: the patient's vital signs, laboratory test results, imaging examination results and patient medical history records; A first generating unit, configured to analyze the medical treatment information data using a pre-established emergency assessment model to generate a preliminary emergency assessment report; A second generating unit is used to compare the preliminary emergency assessment report with historical medical treatment information data to generate emergency suggestions, wherein the historical medical treatment information data includes: treatment process, used drugs and final treatment results; A feedback unit, configured to use a pre-created emergency intervention strategy library to formulate a specific emergency intervention plan according to the emergency suggestion, wherein the emergency intervention strategy library includes standard operating procedures for different types of emergency medical events; The medical treatment information data is analyzed using a pre-established emergency assessment model to generate a preliminary emergency assessment report, including: converting the medical treatment information data into standardized medical treatment information data; Based on the standardized medical treatment information data and a preset risk function, a risk function value corresponding to each standardized medical treatment information data is calculated, wherein the risk function value is used to characterize the risk level of each standardized medical treatment information data; Inputting the risk function value corresponding to each standardized medical treatment information data as input information into a pre-trained emergency assessment model to obtain a preliminary emergency assessment report output by the emergency assessment model; The expression of the preset risk function is: ; in, For the Medical treatment information data in time The risk function value corresponding to the measured value of For the Medical treatment information data in time The measured value of For the Medical treatment information data in time The average value of No. Medical treatment information data in time The standard deviation of , and For the The preset weight corresponding to each medical treatment information data, For the Medical treatment information data in time The instantaneous rate of change, For the Medical treatment information data in time The average value of the instantaneous rate of change, For the seasonal cycle of medical treatment information data; The expression of the pre-trained emergency assessment model is: ; in, for The dynamic emergency risk index at each moment, is the total number of medical treatment information data, For the The dynamic weight of each medical treatment information data at a time. , For the Medical treatment information data in time The measured value of For the Medical treatment information data in time The average value of No. Medical treatment information data in time The standard deviation of For the Medical treatment information data in time The seasonal adjustment factor is For time Time Medical treatment information data and The interaction weight between medical treatment information data, For the Medical treatment information data and The interaction effect function between medical treatment information data, .
7. A computing device, It is characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the method according to any one of claims 1 to 5.
8. A computer storage medium, It is characterized in that A computer program is stored, and when the computer program is executed by a computer, the method according to any one of claims 1 to 5 is implemented.
Citation Information
Patent Citations
Emergency communication intelligent emergency decision support system
CN110210697A
Geological disaster emergency management and decision-making system and method and readable storage medium
CN114399210A
