Emergency path intelligent generation and management system based on big data

Abstract

The invention discloses an emergency path intelligent generation and management system based on big data, and relates to the technical field of emergency big data processing, and the system comprises a disease trigger module which is used for triggering an emergency request through a networking channel, carrying out the automatic positioning according to the networking channel, and deploying an ambulance closest to the positioning; the data uploading module is used for automatically uploading the acquired disease information of the patient and real-time ambulance positioning information through a network; the risk assessment module is used for assessing the risk of the patient based on multi-dimensional parameters according to the acquired disease information of the patient and automatically dividing risk levels; the first-aid path generation module is used for selecting a target medical resource and target positioning according to the risk level of the patient in combination with a time sensitive threshold value and surrounding medical resource information, and automatically generating a first-aid transportation path through the target positioning and ambulance positioning information after receiving the patient; and the planning adjustment module is used for tracking in real time, implementing core quality control index over-limit early warning and providing an improvement scheme.

Description

Technical Field

[0001] This invention relates to the field of emergency medical big data processing technology, specifically to an emergency medical route intelligent generation and management system based on big data. Background Technology

[0002] Among patients with acute myocardial infarction, 58.7% chose to seek medical attention independently, while 10.8% called 120 (emergency services). This resulted in a 179.1-minute extension of the symptom-to-first medical contact (S-to-FMC) time for STEMI patients, exceeding the 120-minute golden treatment window. Quality control indicators were not consistently applied throughout the process. At key time points, such as the first medical contact to wire (FMC-to-W) time and the door to wire (D-to-W) time, real-time monitoring and dynamic intervention were lacking, leading to unstable target achievement rates. Furthermore, technological bottlenecks exist; traditional emergency response pathways rely on human experience and judgment, failing to incorporate real-time data for dynamic adjustments and accurately matching patient risk levels with resource allocation.

[0003] Therefore, in order to effectively shorten the emergency response time for patients, it is necessary to propose an intelligent emergency route generation and management system based on big data. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent emergency route generation and management system based on big data, which solves the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A big data-based intelligent emergency route generation and management system includes:

[0007] The onset triggering module is used to trigger emergency requests through network channels, automatically locate the affected area based on the network channel, and dispatch the nearest ambulance.

[0008] The data upload module is used to automatically upload patient illness information and real-time ambulance location information obtained through the network;

[0009] The risk assessment module is used to assess patient risk based on multi-dimensional parameters and automatically classify risk levels according to the acquired patient disease information.

[0010] The emergency route generation module is used to select target medical resources and target location based on the patient's risk level, combined with time-sensitive thresholds and surrounding medical resource information. It automatically generates an emergency transport route using the target location and the ambulance's location information after picking up the patient.

[0011] The planning and adjustment module is used for real-time tracking, implementing early warnings for exceeding core quality control indicators, and providing improvement solutions.

[0012] Furthermore, the disease onset triggering module includes:

[0013] The mobile terminal triggering submodule is used to allow patients or their families to trigger emergency requests with one click via an emergency APP or emergency mini-program installed on a mobile terminal.

[0014] The primary healthcare institution linkage triggering submodule is used to enable village clinics and community treatment points, which are primary healthcare institutions, to remotely share patients' condition and test data with target medical resources through network linkage.

[0015] Furthermore, the data upload module includes:

[0016] The pre-hospital data upload submodule is used to collect vital signs data and verbal descriptions of the patient's condition on the ambulance and transmit them to the target medical resources in real time via wireless network.

[0017] The in-hospital data upload submodule is used to connect with HIS, LIS, and PACS systems to automatically obtain patients' electronic medical records, historical test results, and historical imaging data; and automatically record key time points of patients through smart wristbands or UWB base stations.

[0018] The external data upload submodule is used to connect to the regional medical resource database of the patient's location in order to dynamically optimize the allocation of medical resources.

[0019] Furthermore, the risk assessment module includes:

[0020] The multi-dimensional parameter assessment submodule is used to automatically classify risk levels based on chest pain characteristics, ECG ST segment changes, troponin levels, and vital signs.

[0021] The risk level dynamic adjustment submodule is used to determine whether the risk level needs to be upgraded based on real-time monitoring of changes in the patient's condition. If so, the patient's risk level is dynamically upgraded and the corresponding medical resources are prepared in advance.

[0022] Furthermore, the emergency route generation module includes:

[0023] The emergency route planning submodule is used to determine the time-sensitive threshold corresponding to emergency care and the surrounding medical resource points with emergency care conditions based on the patient's condition. It selects the medical resource point with the shortest distance from the surrounding medical resource points with emergency care conditions as the target medical resource and plans an emergency route to reach the target medical resource.

[0024] The route optimization submodule is used to determine the route priority of emergency routes by using the global acute coronary event registration score (GRACE score) of the rule base and a machine learning model, and to use the emergency route with the highest priority as the emergency transport route.

[0025] The "Skip Inefficient Steps" submodule is used for program optimization of target medical resources. For high-risk patients, based on the currently known condition, it guides them to skip inefficient routine waiting procedures during emergency visits.

[0026] Furthermore, the planning adjustment module includes:

[0027] The tracking and early warning submodule is used to determine the core quality control indicators of emergency medical services. It evaluates whether the emergency medical transport route meets the requirements of the core quality control indicators based on real-time tracking. If the requirements are exceeded, an early warning is triggered and improvement suggestions are pushed.

[0028] The emergency medical resources dynamic adjustment submodule is used to track the dynamics of target medical resources and road conditions in real time. If the target medical resources are occupied, a new available target medical resource is identified and the emergency medical transport route is redefined. If the road conditions indicate that the emergency medical transport route is congested, the route is dynamically adjusted according to the road conditions to obtain the adjusted emergency medical transport route.

[0029] Furthermore, the risk assessment module includes

[0030] The emergency transport tracking submodule is used to continuously acquire the patient's vital signs during emergency transport by connecting with the emergency equipment on the ambulance.

[0031] The parameter change curve generation submodule is used to draw corresponding vital sign curves based on the patient's vital signs obtained from the emergency transport tracking submodule.

[0032] The risk tracking submodule is used to assess whether the risk situation has changed based on the patient's vital signs curve. If so, the risk level is adjusted accordingly.

[0033] Furthermore, the emergency route planning submodule includes:

[0034] The medical resource candidate area determination unit is used to obtain medical resource points in the patient's location through network connection, determine the time-sensitive threshold corresponding to emergency treatment based on the patient's condition, and select the area range where the transportation time is less than the patient's emergency treatment time-sensitive threshold as the candidate area for medical resource points in combination with the real-time traffic status obtained through the network.

[0035] The initial medical resource selection unit is used to determine the necessary emergency conditions based on the patient's condition, eliminate medical resource points in the candidate area that do not meet the emergency conditions, and obtain medical resource points that meet the emergency conditions for the patient's condition.

[0036] The reference time determination unit is used to obtain the average advance preparation time of similar cases in the past at medical resource points that meet the emergency conditions. It compares the required advance preparation time with the estimated time to reach the corresponding medical resource point and takes the longer time as the reference time.

[0037] The target medical resource and emergency route determination unit is used to select the medical resource points in the candidate area that meet the emergency conditions with the shortest reference time as the target medical resource, and the shortest transportation route corresponding to the target medical resource as the emergency route.

[0038] Furthermore, it also includes a collaborative interaction module, used to establish real-time interactive communication between the ambulance and the target medical resource provider, promptly share the real-time vital signs of the patient in the ambulance with the target medical resource provider; send collaborative requests to the target medical resource provider, urging the target medical resource provider to start relevant emergency preparations in advance according to the collaborative requests; and support real-time video communication between the ambulance and the target medical resource provider.

[0039] Furthermore, the planning adjustment module includes:

[0040] The path weight generation submodule is used to model the local traffic network using graph neural networks, predict the travel delays at different time periods and different road nodes, and assign dynamic weights to emergency routes based on the travel delays.

[0041] The training data acquisition submodule is used to collect historical traffic data, emergency records, and traffic police dispatch logs of local roads to build a multi-dimensional training set;

[0042] The route evaluation submodule is used to combine the type and urgency of the emergency rescue mission to recommend a set of route candidates with predicted delay labels to dispatchers and the system.

[0043] The emergency route correction submodule is used to perform weighted analysis on candidate routes in the route candidate set based on dynamic weights, and determine whether the emergency route needs to be adjusted based on the analysis results.

[0044] Compared with the prior art, the beneficial effects of the present invention are:

[0045] This invention dynamically optimizes the emergency care pathway for chest pain patients by integrating patient risk stratification, emergency procedure quality control indicators, and multi-source data in real time, shortening the time interval from onset to effective treatment. For high-risk patients arriving at the emergency department, due to their high risk level and the dynamic sharing of real-time test data, they can be guided to skip the inefficient routine waiting process and directly proceed to critical emergency stages, such as the catheterization lab. According to assessments, this invention can reduce the time from when a patient enters the hospital to when the guidewire is inserted from 45 minutes to 22 minutes, thereby significantly improving the efficiency of emergency care for high-risk patients and thus improving their survival rate and prognosis. Attached Figure Description

[0046] Figure 1 This is a schematic diagram of the emergency route intelligent generation and management system based on big data according to the present invention. Detailed Implementation

[0047] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0048] To resolve the existing issues, please refer to Figure 1 This embodiment provides the following technical solution:

[0049] A big data-based intelligent emergency route generation and management system includes:

[0050] The onset triggering module is used to trigger emergency requests through network channels, automatically locate the affected area based on the network channel, and dispatch the nearest ambulance.

[0051] The data upload module is used to automatically upload patient illness information and real-time ambulance location information obtained through the network;

[0052] The risk assessment module is used to assess patient risk based on multi-dimensional parameters and automatically classify risk levels according to the acquired patient disease information.

[0053] The emergency route generation module is used to select target medical resources and target location based on the patient's risk level, combined with time-sensitive thresholds and surrounding medical resource information. It automatically generates an emergency transport route using the target location and the ambulance's location information after picking up the patient.

[0054] The planning and adjustment module is used for real-time tracking, implementing early warnings for exceeding core quality control indicators, and providing improvement solutions.

[0055] This invention utilizes a cloud-based big data platform to trigger an emergency response mechanism when a patient experiences symptoms. Through data upload and sharing, and risk assessment, it searches for nearby medical resources that meet the criteria for emergency care based on the patient's location. It then plans, tracks, and optimizes emergency response routes in real time, integrating patient risk stratification, emergency process quality control indicators, and multi-source data to dynamically optimize emergency response routes for chest pain patients, shortening the time interval from onset of symptoms to effective treatment. For high-risk patients arriving at the emergency department, due to their higher risk level and the dynamic sharing of real-time test data, they can be guided to skip inefficient routine waiting procedures and directly proceed to critical emergency stages, such as the catheterization lab. Evaluations show that this invention can reduce the time from a patient entering the hospital to guidewire passage from 45 minutes to 22 minutes, thereby significantly improving the efficiency of emergency care for high-risk patients and ultimately increasing their survival rate and prognosis.

[0056] Based on the foregoing embodiments, the disease triggering module includes:

[0057] The mobile terminal triggering submodule is used to allow patients or their families to trigger emergency requests with one click via an emergency APP or emergency mini-program installed on a mobile terminal.

[0058] The primary healthcare institution linkage triggering submodule is used to enable village clinics and community treatment points, which are primary healthcare institutions, to remotely share patients' condition and test data with target medical resources through network linkage.

[0059] This system can communicate with multiple terminals of various types via the network, such as personal handheld mobile terminals (mobile phones, tablets, etc.) and desktop terminals (desktop computers) in primary healthcare institutions (village clinics and community treatment points). It allows patients or their families to trigger emergency requests with one click, and also enables primary healthcare institutions to trigger emergency responses based on the patient's condition. This helps ensure that patients are included in the emergency response process as soon as they fall ill, reducing delays in emergency care.

[0060] Based on the foregoing embodiments, the data upload module includes:

[0061] The pre-hospital data upload submodule is used to collect vital signs data and verbal descriptions of the patient's condition on the ambulance and transmit them to the target medical resources in real time via wireless network.

[0062] The in-hospital data upload submodule is used to connect to the HIS, LIS, and PACS systems to automatically acquire patients' electronic medical records, historical test results, and historical imaging data; and to automatically record key time points of patients through smart wristbands or UWB base stations. Among them, the HIS (Hospital Information System) is the hospital information system, the LIS (Laboratory Information System) is the laboratory information system, and the PACS (Picture Archiving and Communication System) is the medical image archiving and communication system.

[0063] The external data upload submodule is used to connect to the regional medical resource database of the patient's location in order to dynamically optimize the allocation of medical resources.

[0064] This system, connected via wireless network, can transmit real-time examination data collected from patients at primary healthcare institutions and / or in ambulances to a big data platform for sharing with target medical resource providers. It can also retrieve patients' past medical history and treatment records, allowing medical personnel at the target healthcare resource providers to gain a more comprehensive understanding of the patient's condition in advance, enabling them to make early predictions and emergency preparations, thereby shortening pre-emergency waiting times. Furthermore, the existence of the preceding test data provides the foundational data for bypassing routine examinations after admission, which can shorten the time required for subsequent in-hospital emergency care, improving emergency efficiency and patient survival rates.

[0065] Based on the foregoing embodiments, the risk assessment module includes:

[0066] The multi-dimensional parameter assessment submodule is used to automatically classify risk levels based on chest pain characteristics, ECG ST segment changes, troponin levels, and vital signs.

[0067] The risk level dynamic adjustment submodule is used to determine whether the risk level needs to be upgraded based on real-time monitoring of changes in the patient's condition. If so, the patient's risk level is dynamically upgraded and the corresponding medical resources are prepared in advance.

[0068] This system can automatically classify the risk level of a patient's condition by analyzing data from multi-dimensional parameters of the patient's examination. Through dynamic tracking and real-time data sharing, it can determine whether the risk level of the patient's condition needs to be adjusted according to changes in the situation. If it is determined that the risk level can be reduced, there is no need to adjust the emergency response strategy. If it is determined that the risk level needs to be upgraded, the corresponding medical resources will be activated in advance to accelerate preparation after the upgrade.

[0069] Based on the foregoing embodiments, the emergency route generation module includes:

[0070] The emergency route planning submodule is used to determine the time-sensitive threshold corresponding to emergency care and the surrounding medical resource points with emergency care conditions based on the patient's condition. It selects the medical resource point with the shortest distance from the surrounding medical resource points with emergency care conditions as the target medical resource and plans an emergency route to reach the target medical resource.

[0071] The route optimization submodule is used to determine the route priority of emergency routes by using the global acute coronary event registration score (GRACE score) of the rule base and a machine learning model, and to use the emergency route with the highest priority as the emergency transport route.

[0072] The "Skip Inefficient Steps" submodule is used for program optimization of target medical resources. For high-risk patients, based on the currently known condition, it guides them to skip inefficient routine waiting procedures during emergency visits.

[0073] This system's emergency route planning encompasses both ambulance transport route planning and hospital admission procedure optimization. It selects suitable medical resource points by comparing emergency conditions to avoid transporting patients to medical resource points without the corresponding emergency conditions. Through the selection of medical resource points and routes, combined with optimization algorithm models, it determines the emergency transport route. For high-risk patients, based on the currently known condition, it guides them to skip inefficient routine waiting procedures during emergency visits.

[0074] Based on the foregoing embodiments, the planning adjustment module includes:

[0075] The tracking and early warning submodule is used to determine the core quality control indicators of emergency medical services. It evaluates whether the emergency medical transport route meets the requirements of the core quality control indicators based on real-time tracking. If the requirements are exceeded, an early warning is triggered and improvement suggestions are pushed.

[0076] The emergency medical resources dynamic adjustment submodule is used to track the dynamics of target medical resources and road conditions in real time. If the target medical resources are occupied, a new available target medical resource is identified and the emergency medical transport route is redefined. If the road conditions indicate that the emergency medical transport route is congested, the route is dynamically adjusted according to the road conditions to obtain the adjusted emergency medical transport route.

[0077] This system can track and evaluate emergency transport routes in real time. In traffic congestion, it can trigger warnings and push improvement suggestions based on whether the core quality control indicators of emergency care exceed the limits. The system can also dynamically adjust ambulance routes through real-time traffic data and can work with traffic control departments to open green channels and adjust emergency transport routes, effectively ensuring that emergency care is provided to patients as quickly as possible.

[0078] Based on the foregoing embodiments, the risk assessment module includes

[0079] The emergency transport tracking submodule is used to continuously acquire the patient's vital signs during emergency transport by connecting with the emergency equipment on the ambulance.

[0080] The parameter change curve generation submodule is used to draw corresponding vital sign curves based on the patient's vital signs obtained from the emergency transport tracking submodule.

[0081] The risk tracking submodule is used to assess whether the risk situation has changed based on the patient's vital signs curve. If so, the risk level is adjusted accordingly.

[0082] This system tracks patients during emergency transport, continuously acquiring their vital signs and plotting corresponding vital sign curves. These curves can be dynamically displayed on connected devices, allowing medical personnel to understand the patient's condition more intuitively and in real time. Based on the vital sign curves, the system assesses whether there are any changes in risk, enabling timely adjustments to risk levels and emergency response strategies.

[0083] Based on the foregoing embodiments, the emergency route planning submodule includes:

[0084] The medical resource candidate area determination unit is used to obtain medical resource points in the patient's location through network connection, determine the time-sensitive threshold corresponding to emergency treatment based on the patient's condition, and select the area range where the transportation time is less than the patient's emergency treatment time-sensitive threshold as the candidate area for medical resource points in combination with the real-time traffic status obtained through the network.

[0085] The initial medical resource selection unit is used to determine the necessary emergency conditions based on the patient's condition, eliminate medical resource points in the candidate area that do not meet the emergency conditions, and obtain medical resource points that meet the emergency conditions for the patient's condition.

[0086] The reference time determination unit is used to obtain the average advance preparation time of similar cases in the past at medical resource points that meet the emergency conditions. It compares the required advance preparation time with the estimated time to reach the corresponding medical resource point and takes the longer time as the reference time.

[0087] The target medical resource and emergency route determination unit is used to select the medical resource points in the candidate area that meet the emergency conditions with the shortest reference time as the target medical resource, and the shortest transportation route corresponding to the target medical resource as the emergency route.

[0088] This system determines a time-sensitive threshold (i.e., the estimated time limit for emergency treatment) based on the patient's condition, using this as the maximum acceptable transport time. Combined with the ambulance's speed, it determines the range of medical resource points to select, i.e., the candidate area. Then, based on the patient's emergency needs, it filters candidate medical resources within the candidate area, eliminating those that do not meet the emergency treatment requirements, further narrowing the selection. Finally, it comprehensively considers the average advance preparation time required for emergency treatment at each medical resource point and the estimated delivery time to the corresponding medical resource point, taking the longer of the two as a reference time. The medical resource point with the shortest reference time is selected as the target medical resource. This solution reduces the amount of data processed, accelerates the data processing process, and saves emergency treatment time through multi-faceted comparison and screening.

[0089] Based on the aforementioned embodiments, a collaborative interaction module is also included, which is used to establish real-time interactive communication between the emergency vehicle and the target medical resource provider, promptly share the real-time vital signs of the patient in the emergency vehicle with the target medical resource provider; and send a collaborative request to the target medical resource provider, urging the target medical resource provider to start relevant emergency condition preparations in advance according to the collaborative request; and support real-time video communication between the emergency vehicle and the target medical resource provider.

[0090] This system, through its collaborative interaction module, facilitates real-time communication between emergency vehicles and target medical resources, enabling the sharing of patients' real-time vital signs. On one hand, this allows medical personnel in emergency vehicles to receive real-time guidance from target medical resources, ensuring patient safety during transport. On the other hand, it allows target medical resources to anticipate necessary emergency measures in advance and initiate relevant emergency preparations ahead of time, ensuring the timely implementation of substantive emergency care and improving the efficiency and effectiveness of emergency care.

[0091] Based on the foregoing embodiments, the planning adjustment module includes:

[0092] The path weight generation submodule is used to model the local traffic network using a graph neural network and to aggregate inter-node features using a graph convolutional neural network (GCN).

[0093]

[0094] in, Let represent the feature vector of node j at layer (n+1), which contains information such as historical travel time, real-time congestion index, and traffic control status; σ represents the activation function; N(j) represents the set of neighboring nodes of node j; d i and d j and are the degree of nodes i and j, respectively, which are the number of edges connecting nodes i and j to other nodes; w n This represents the weight matrix of the nth layer; b represents the feature vector of node j at the nth layer;n This represents the bias vector of the nth layer;

[0095] Predict traffic delays at different time periods and road nodes, and assign dynamic weights to emergency routes based on these delays; the following algorithm is used to express the traffic cost of each route:

[0096]

[0097] Where C(R) represents the objective function of the passage cost; e k The edge of the graph neural mesh is represented by t; the travel time of the edge is represented by t; the travel path is represented by R; f(e k ,t) represents the travel delay of the edge;

[0098] The training data acquisition submodule is used to collect historical traffic flow data, emergency records and traffic police dispatch logs of local roads, and construct a multi-dimensional training set for implementing traffic network model training;

[0099] The route evaluation submodule is used to combine the type and urgency of the emergency rescue mission to recommend a set of route candidates with predicted delay labels to dispatchers and the system.

[0100] The emergency route correction submodule is used to perform weighted analysis on candidate routes in the route candidate set based on dynamic weights, and determine whether the emergency route needs to be adjusted based on the analysis results.

[0101] This invention can also model the local traffic network using graph neural networks, train the model, and use the trained traffic network model to assist in weighted analysis of transport routes, predict and label route delays, and form a candidate set of routes with predicted delay labels. Combined with the route weights, it can analyze whether emergency routes need to be adjusted, thereby ensuring the efficiency and effectiveness of emergency routes.

[0102] The following is a brief explanation of the application process of this invention, using the example of a primary healthcare institution receiving patients.

[0103] When primary healthcare institutions such as village clinics, township health centers, and community treatment units receive patients with chest pain, they can transmit the patient's electrocardiogram (ECG) to a big data platform and share it with chest pain centers capable of coronary intervention. If the big data platform system determines that the patient has high-risk non-ST-segment elevation myocardial infarction (NSTEMI), it will automatically trigger emergency care and coordinate ambulance transfer. It will also notify the chest pain center (hospital) with coronary intervention capabilities to activate the catheterization lab, verify the availability of the catheterization lab, the interventional physician's schedule, and the estimated arrival time of the ambulance. If the FMC-to-W time exceeds the limit (above the quality control threshold), an automatic alarm will be triggered, and optimization suggestions will be pushed to the responsible department to adjust emergency preparations.

[0104] By enabling remote consultations and resource allocation between tertiary hospitals and primary hospitals through a cloud platform, high-risk patients can skip the routine waiting process and be directly guided to the catheterization lab after arriving at the emergency department of a tertiary hospital, based on their risk level and real-time test data from the primary hospital. This saves / shortens the time for admission procedures, reducing the time from the admission door to the guidewire passage from 45 minutes to 22 minutes.

[0105] In congested traffic environments, such as those caused by severe weather or traffic accidents, the system dynamically adjusts ambulance routes based on real-time traffic data and coordinates with traffic control departments to create green channels. Ambulances transmit data indicating which roads are congested, automatically planning alternative transport routes and coordinating with traffic police for traffic management when necessary. This is expected to reduce average arrival time by 40%.

[0106] The system of this invention can effectively reduce the time from the onset of symptoms to guidewire passage (S-to-W) from 250 minutes to 60 minutes.

[0107] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0108] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A big data-based intelligent emergency route generation and management system, characterized in that, include: The onset triggering module is used to trigger emergency requests through network channels, automatically locate the affected area based on the network channel, and dispatch the nearest ambulance. The data upload module is used to automatically upload patient illness information and real-time ambulance location information obtained through the network; The risk assessment module is used to assess patient risk based on multi-dimensional parameters and automatically classify risk levels according to the acquired patient disease information. The emergency route generation module is used to select target medical resources and target location based on the patient's risk level, combined with time-sensitive thresholds and surrounding medical resource information. It automatically generates an emergency transport route using the target location and the ambulance's location information after picking up the patient. The planning and adjustment module is used for real-time tracking, implementing early warnings for exceeding core quality control indicators, and providing improvement solutions.

2. The emergency medical route intelligent generation and management system based on big data as described in claim 1, characterized in that, The disease onset triggering module includes: The mobile terminal triggering submodule is used to allow patients or their families to trigger emergency requests with one click via an emergency APP or emergency mini-program installed on a mobile terminal. The primary healthcare institution linkage triggering submodule is used to enable village clinics and community treatment points, which are primary healthcare institutions, to remotely share patients' condition and test data with target medical resources through network linkage.

3. The emergency medical route intelligent generation and management system based on big data as described in claim 1, characterized in that, The data upload module includes: The pre-hospital data upload submodule is used to collect vital signs data and verbal descriptions of the patient's condition on the ambulance and transmit them to the target medical resources in real time via wireless network. The in-hospital data upload submodule is used to connect with HIS, LIS, and PACS systems to automatically obtain patients' electronic medical records, historical test results, and historical imaging data; and automatically record key time points of patients through smart wristbands or UWB base stations. The external data upload submodule is used to connect to the regional medical resource database of the patient's location in order to dynamically optimize the allocation of medical resources.

4. The emergency medical route intelligent generation and management system based on big data as described in claim 1, characterized in that, The risk assessment module includes: The multi-dimensional parameter assessment submodule is used to automatically classify risk levels based on chest pain characteristics, ECG ST segment changes, troponin levels, and vital signs. The risk level dynamic adjustment submodule is used to determine whether the risk level needs to be upgraded based on real-time monitoring of changes in the patient's condition. If so, the patient's risk level is dynamically upgraded and the corresponding medical resources are prepared in advance.

5. The emergency medical route intelligent generation and management system based on big data as described in claim 1, characterized in that, The emergency route generation module includes: The emergency route planning submodule is used to determine the time-sensitive threshold corresponding to emergency care and the surrounding medical resource points with emergency care conditions based on the patient's condition. It selects the medical resource point with the shortest distance from the surrounding medical resource points with emergency care conditions as the target medical resource and plans an emergency route to reach the target medical resource. The route optimization submodule is used to determine the route priority of emergency routes by using the global acute coronary event registration score (GRACE score) of the rule base and a machine learning model, and to use the emergency route with the highest priority as the emergency transport route. The "Skip Inefficient Steps" submodule is used for program optimization of target medical resources. For high-risk patients, based on the currently known condition, it guides them to skip inefficient routine waiting procedures during emergency visits.

6. The emergency medical route intelligent generation and management system based on big data as described in claim 1, characterized in that, The planning adjustment module includes: The tracking and early warning submodule is used to determine the core quality control indicators of emergency medical services. It evaluates whether the emergency medical transport route meets the requirements of the core quality control indicators based on real-time tracking. If the requirements are exceeded, an early warning is triggered and improvement suggestions are pushed. The emergency medical resources dynamic adjustment submodule is used to track the dynamics of target medical resources and road conditions in real time. If the target medical resources are occupied, a new available target medical resource is identified and the emergency medical transport route is redefined. If the road conditions indicate that the emergency medical transport route is congested, the route is dynamically adjusted according to the road conditions to obtain the adjusted emergency medical transport route.

7. The emergency medical route intelligent generation and management system based on big data as described in claim 4, characterized in that, The risk assessment module includes: The emergency transport tracking submodule is used to continuously acquire the patient's vital signs during emergency transport by connecting with the emergency equipment on the ambulance. The parameter change curve generation submodule is used to draw corresponding vital sign curves based on the patient's vital signs obtained from the emergency transport tracking submodule. The risk tracking submodule is used to assess whether the risk situation has changed based on the patient's vital signs curve. If so, the risk level is adjusted accordingly.

8. The emergency medical route intelligent generation and management system based on big data as described in claim 5, characterized in that, The emergency route planning submodule includes: The medical resource candidate area determination unit is used to obtain medical resource points in the patient's location through network connection, determine the time-sensitive threshold corresponding to emergency treatment based on the patient's condition, and select the area range where the transportation time is less than the patient's emergency treatment time-sensitive threshold as the candidate area for medical resource points in combination with the real-time traffic status obtained through the network. The initial medical resource selection unit is used to determine the necessary emergency conditions based on the patient's condition, eliminate medical resource points in the candidate area that do not meet the emergency conditions, and obtain medical resource points that meet the emergency conditions for the patient's condition. The reference time determination unit is used to obtain the average advance preparation time of similar cases in the past at medical resource points that meet the emergency conditions. It compares the required advance preparation time with the estimated time to reach the corresponding medical resource point and takes the longer time as the reference time. The target medical resource and emergency route determination unit is used to select the medical resource points in the candidate area that meet the emergency conditions with the shortest reference time as the target medical resource, and the shortest transportation route corresponding to the target medical resource as the emergency route.

9. The emergency medical route intelligent generation and management system based on big data as described in claim 1, characterized in that, It also includes a collaborative interaction module, which is used to establish real-time interactive communication between the emergency vehicle and the target medical resource provider, promptly share the real-time vital signs of the patient in the emergency vehicle with the target medical resource provider; and send collaborative requests to the target medical resource provider, urging the target medical resource provider to start relevant emergency preparations in advance according to the collaborative requests; and supports real-time video communication between the emergency vehicle and the target medical resource provider.

10. The emergency medical route intelligent generation and management system based on big data as described in claim 1, characterized in that, The planning adjustment module includes: The path weight generation submodule is used to model the local traffic network using graph neural networks, predict the travel delays at different time periods and different road nodes, and assign dynamic weights to emergency routes based on the travel delays. The training data acquisition submodule is used to collect historical traffic data, emergency records, and traffic police dispatch logs of local roads to build a multi-dimensional training set; The route evaluation submodule is used to combine the type and urgency of the emergency rescue mission to recommend a set of route candidates with predicted delay labels to dispatchers and the system. The emergency route correction submodule is used to perform weighted analysis on candidate routes in the route candidate set based on dynamic weights, and determine whether the emergency route needs to be adjusted based on the analysis results.

Images