Dynamic self-adaptive pre-hospital stroke intelligent early warning and grading response method

Abstract

The invention discloses a dynamic self-adaptive pre-hospital stroke intelligent early warning and grading response method and system, and belongs to the technical field of medical information processing. In the ambulance transfer process, the system does not depend on fixed path points for monitoring any more, but dynamically and intelligently decides the optimal opportunity of the second CT scanning according to the patient state risk index and the road condition information which are calculated in real time. By quantifying the intervention efficiency coefficient of the medical intervention measure on the way, the initial bleeding rate is accurately corrected, so that the dynamic bleeding rate which better fits the actual condition of the patient is calculated. And finally, the system generates a multi-dimensional prediction report containing the optimal, most probable and worst scenes based on the rate, and sends the multi-dimensional prediction report to a target hospital in advance with a clear risk level. The problems of monitoring rigidity and rough prediction in the prior art are solved, precise and prospective pre-hospital early warning is achieved, the pertinence and efficiency of hospital end preparation are greatly improved, and precious treatment time is seized for stroke patients.

Description

Technical Field

[0001] This invention relates to the field of medical information processing technology, and in particular to a method and system for dynamic monitoring, intelligent prediction and graded early warning of stroke patients during ambulance transport. Background Technology

[0002] In pre-hospital emergency care for stroke patients, time is of the essence. Existing technologies include equipping ambulances with mobile CT scanners and performing two scans at the start and a fixed midpoint of the transport route to estimate the bleeding rate and predict the amount of bleeding upon arrival at the hospital. However, this approach has significant limitations: firstly, fixed scanning points cannot adapt to the dynamic changes in the patient's condition and the complex and ever-changing real-time road conditions, and the timing of monitoring may not be optimal; secondly, the evaluation of the effectiveness of interventions implemented by onboard medical personnel is relatively crude, usually only qualitative, making it difficult to quantify their actual impact on the bleeding trend, resulting in insufficient predictive accuracy; and thirdly, the information provided to the hospital is relatively limited, failing to support precise preparation of multiple contingency plans. Therefore, there is an urgent need for a pre-hospital emergency care solution that can dynamically adapt, provide precise quantification, and offer richer decision support information. Summary of the Invention

[0003] The purpose of this invention is to overcome the shortcomings of the prior art and provide a dynamic and adaptive intelligent early warning and graded response method and system for pre-hospital stroke. It can intelligently decide the timing of monitoring based on the patient's real-time status and external environment, quantitatively evaluate the intervention effect, and provide multi-scenario prediction, thereby giving hospitals more preparation time and improving the pertinence of preparation work.

[0004] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a dynamically adaptive intelligent early warning and graded response method for pre-hospital stroke, comprising the following steps: S1. Obtain the patient's first CT scan data and vital signs data at the transfer point to establish a baseline of the patient's condition; S2. During the transfer process, receive continuous vital sign data of the patient and environmental data of the ambulance in real time; S3. Based on the continuous vital signs data, calculate the patient's status risk index; S4. Based on the state risk index and the environmental data, a preset decision-making algorithm is used to dynamically make a decision and trigger a secondary scan command. S5. In response to the secondary scan command, acquire the patient's secondary CT scan data; S6. Calculate the initial bleeding rate based on the first and second CT scan data, and calculate the dynamic bleeding rate by combining the intervention efficacy coefficients corresponding to the medical interventions implemented during the two scans. S7. Based on the dynamic bleeding rate, generate a structured report containing at least two predicted scenarios and their corresponding risk levels; S8. Send the structured report to the target hospital.

[0005] Furthermore, the environmental data includes real-time traffic conditions and geographical location information; dynamic decision-making and triggering of secondary scanning instructions means that the execution location of the secondary scan is not a preset fixed midpoint of the transit path, but is determined by the decision-making algorithm based on the real-time calculated state risk index and traffic efficiency.

[0006] Furthermore, the logic of the decision algorithm includes: when the state risk index exceeds a first threshold, instructing a secondary scan to be performed at the nearest feasible location; when the state risk index is lower than the first threshold and the road condition traffic efficiency is lower than a second threshold, instructing a secondary scan to be performed at a predetermined location after the road condition has improved.

[0007] Furthermore, the intervention efficacy coefficient is a numerical coefficient obtained by matching the type and dosage parameters of the implemented medical intervention measures with the monitored trends of vital sign changes and a pre-stored historical data model.

[0008] Furthermore, the at least two predicted scenarios include a best-case scenario, a most likely scenario, and a worst-case scenario; the risk level is associated with different scenarios and is presented in the structured report with different color codes.

[0009] Furthermore, if a secondary scan cannot be performed as instructed, a coordination request is sent to the emergency dispatch system, which then coordinates another ambulance to complete the collection of the secondary scan data at a designated location.

[0010] In a second aspect, the present invention provides a dynamically adaptive pre-hospital stroke intelligent early warning and graded response system for implementing the method described in the first aspect, the system comprising: The baseline establishment module, configured at the transport origin, is used to acquire and process the initial CT scan data and vital sign data to establish a patient baseline. The real-time data stream receiving module is used to continuously receive the patient's vital signs data stream and the vehicle's environmental data stream during the transfer process; The status risk assessment module is used to calculate the patient's real-time risk index based on vital sign data stream; The dynamic scanning decision module is connected to the state risk assessment module and the real-time data stream receiving module, and is used to dynamically generate secondary scanning instructions based on the risk index and environmental data stream through a decision algorithm. The secondary scan execution and processing module is used to respond to the secondary scan command, control the CT equipment to perform the scan and process the secondary CT scan data; The intelligent prediction engine, connected to the baseline establishment module and the secondary scan execution and processing module, is used to calculate the initial average bleeding rate and, in combination with the intervention data from the real-time data stream receiving module, calculate the intervention efficacy coefficient and dynamic bleeding rate, thereby generating a multi-scenario prediction report. The report sending module is used to send the generated report to the target hospital.

[0011] Furthermore, the system also includes a vehicle-to-vehicle collaborative management module, which is configured to send a request to the dispatch center when there are equipment or environmental limitations in executing a secondary scan command, and coordinate nearby ambulances with CT scanning capabilities to perform the scanning task at a predetermined meeting point.

[0012] Beneficial effects of the present invention 1. Dynamic adaptive monitoring: By analyzing the patient's condition and road conditions in real time, it intelligently decides the best time for a second scan, breaking the rigid pattern of fixed path points and closely linking the monitoring behavior with the patient's actual safety, so that the captured disease trend is more representative.

[0013] 2. Significantly improved prediction accuracy: By introducing an "intervention efficacy coefficient" based on historical data model matching, the abstract clinical intervention effect is transformed into a calculable correction parameter, making the estimation and prediction of bleeding rate more accurate and closer to clinical reality.

[0014] 3. Rich Decision Support Dimensions: The multi-scenario prediction reports provided enable hospitals to understand potential risks from multiple dimensions, from best to worst, thereby enabling them to carry out graded and hierarchical resource allocation and contingency plan preparation, which greatly improves the efficiency and pertinence of pre-hospital and in-hospital coordination.

[0015] 4. Enhanced system robustness: The introduction of inter-vehicle collaboration mechanism improves the system's responsiveness and overall service reliability when single ambulance resources are limited. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the overall process of the dynamically adaptive pre-hospital stroke intelligent early warning and graded response method of the present invention. Figure 2 This is a schematic diagram of the dynamically adaptive pre-hospital stroke intelligent early warning and graded response system of the present invention. Detailed Implementation

[0017] like Figure 1 As shown, Figure 1 This is a schematic diagram of the overall process of the dynamically adaptive intelligent early warning and graded response method for pre-hospital stroke according to the present invention. The present invention provides a dynamically adaptive intelligent early warning and graded response method for pre-hospital stroke, comprising the following steps: S1. Obtain the patient's first CT scan data and vital signs data at the transfer point to establish a baseline of the patient's condition; S2. During the transfer process, receive continuous vital sign data of the patient and environmental data of the ambulance in real time; S3. Based on the continuous vital signs data, calculate the patient's status risk index; S4. Based on the state risk index and the environmental data, a preset decision-making algorithm is used to dynamically make a decision and trigger a secondary scan command. S5. In response to the secondary scan command, acquire the patient's secondary CT scan data; S6. Calculate the initial bleeding rate based on the first and second CT scan data, and calculate the dynamic bleeding rate by combining the intervention efficacy coefficients corresponding to the medical interventions implemented during the two scans. S7. Based on the dynamic bleeding rate, generate a structured report containing at least two predicted scenarios and their corresponding risk levels; S8. Send the structured report to the target hospital.

[0018] The environmental data includes real-time traffic conditions and geographic location information; dynamic decision-making and triggering of secondary scanning instructions means that the execution location of the secondary scan is not a preset fixed midpoint of the transfer path, but is determined by the decision algorithm based on the real-time calculated state risk index and traffic efficiency.

[0019] The logic of the decision algorithm includes: when the state risk index exceeds a first threshold, instructing a secondary scan to be performed at the nearest feasible location; when the state risk index is lower than the first threshold and the road condition efficiency is lower than a second threshold, instructing a secondary scan to be performed at a predetermined location after the road condition has improved.

[0020] The intervention efficacy coefficient is a numerical coefficient obtained by matching the type and dosage parameters of the implemented medical intervention measures with the monitored trends of changes in vital signs and a pre-stored historical data model.

[0021] The at least two predicted scenarios include a best-case scenario, a most likely scenario, and a worst-case scenario; the risk level is associated with different scenarios and is presented in the structured report with different color codes.

[0022] If a secondary scan cannot be performed as instructed, a coordination request is sent to the emergency dispatch system, which then coordinates another ambulance to complete the collection of the secondary scan data at a designated location.

[0023] A preferred embodiment of the present invention will now be described in detail.

[0024] In step S1, after the ambulance arrives at the patient's location, an initial head CT scan is immediately performed, and a life monitor is connected; the system records the initial bleeding volume q1, as well as data such as blood pressure, heart rate, and blood oxygen saturation as a baseline.

[0025] In steps S2-S4, the ambulance heads towards the hospital. The system's central processing unit continuously receives vital signs and real-time traffic information. Assuming that 10 minutes after departure, the system calculates using an algorithm that the patient's risk index has rapidly increased due to a sudden rise in blood pressure, exceeding a preset threshold; simultaneously, GPS data shows that the road ahead is clear. At this point, the dynamic scan decision module immediately generates a secondary scan command, instructing the ambulance to perform a second CT scan at the next safe stop within a 3-minute drive. This embodies the core principle of "patient-state driven" technology.

[0026] In steps S5-S6, the second scan is completed, and the bleeding volume q2 is obtained. The system calculates the initial bleeding rate V. _initial =(q2 - q1) / Δt. Simultaneously, the system detected the use of a specific antihypertensive drug en route. Based on the drug's historical efficacy data and the patient's actual vital sign response, the intervention efficacy coefficient η = 1.15 was calculated for this administration. Subsequently, the dynamic bleeding rate V was calculated. _dynamic = V_ initial / η. Here, η>1 indicates that the drug is effective and has an unexpected inhibitory effect on the increase of bleeding.

[0027] In step S7, the intelligent prediction engine is based on V_ dynamic Considering the remaining travel time, the following calculations are performed: Most likely scenario (trend continues): Bleeding amount Q_ likely ; Best-case scenario (η increased to 1.3): Bleeding Q_ best ; Worst-case scenario (η decays to 0.8): Bleeding Q_ worst .

[0028] The report will automatically include Q_ likely Marked in orange (medium to high risk), along with numerical values ​​for two other scenarios.

[0029] In step S8, the report is transmitted via the 5G network to the emergency center's large screen at the target hospital. Based on this, the hospital immediately activates an orange alert, notifies the neurosurgery and interventional radiology teams to be on standby, and prepares sufficient Q... _worst Blood products and surgical resources that may be needed in this scenario.

[0030] like Figure 2 As shown, Figure 2 This is a schematic diagram of the dynamically adaptive pre-hospital stroke intelligent early warning and graded response system of the present invention. The system includes: The baseline establishment module, configured at the transport origin, is used to acquire and process the initial CT scan data and vital sign data to establish a patient baseline. The real-time data stream receiving module is used to continuously receive the patient's vital signs data stream and the vehicle's environmental data stream during the transfer process; The status risk assessment module is used to calculate the patient's real-time risk index based on vital sign data stream; The dynamic scanning decision module is connected to the state risk assessment module and the real-time data stream receiving module, and is used to dynamically generate secondary scanning instructions based on the risk index and environmental data stream through a decision algorithm. The secondary scan execution and processing module is used to respond to the secondary scan command, control the CT equipment to perform the scan and process the secondary CT scan data; The intelligent prediction engine, connected to the baseline establishment module and the secondary scan execution and processing module, is used to calculate the initial average bleeding rate and, in combination with the intervention data from the real-time data stream receiving module, calculate the intervention efficacy coefficient and dynamic bleeding rate, thereby generating a multi-scenario prediction report. The report sending module is used to send the generated report to the target hospital.

[0031] The system also includes a vehicle-to-vehicle coordination management module, which is configured to send a request to the dispatch center when there are equipment or environmental limitations in executing a secondary scan command, and coordinate nearby ambulances with CT scanning capabilities to perform the scanning task at a predetermined meeting point.

[0032] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Based on the technical essence of the present invention, any simple modifications, equivalent substitutions, and improvements made to the above embodiments within the spirit and principles of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A dynamically adaptive pre-hospital stroke intelligent early warning and grading response method, characterized in that, include: S1. Obtain the patient's first CT scan data at the transfer point to establish a baseline of the patient's condition; S2. During the transfer process, receive continuous vital sign data of the patient and environmental data of the ambulance in real time; S3. Based on the continuous vital signs data, calculate the patient's status risk index; S4. Based on the state risk index and the environmental data, a preset decision-making algorithm is used to dynamically make a decision and trigger a secondary scan command. S5. In response to the secondary scan command, acquire the patient's secondary CT scan data; S6. Calculate the initial bleeding rate based on the first and second CT scan data, and calculate the dynamic bleeding rate by combining the intervention efficacy coefficients corresponding to the medical interventions implemented during the two scans. S7. Based on the dynamic bleeding rate, generate a structured report containing at least two predicted scenarios and their corresponding risk levels; S8. Send the structured report to the target hospital.

2. The dynamic adaptive pre-hospital stroke intelligent early warning and grading response method according to claim 1, characterized in that, The environmental data includes real-time traffic conditions and geographic location information; dynamic decision-making and triggering of secondary scanning instructions means that the execution location of the secondary scan is not a preset fixed midpoint of the transfer path, but is determined by the decision algorithm based on the real-time calculated state risk index and traffic efficiency.

3. The dynamically adaptive pre-hospital stroke intelligent early warning and graded response method according to claim 2, characterized in that, The logic of the decision algorithm includes: when the state risk index exceeds a first threshold, instructing a secondary scan to be performed at the nearest feasible location; when the state risk index is lower than the first threshold and the road condition efficiency is lower than a second threshold, instructing a secondary scan to be performed at a predetermined location after the road condition has improved.

4. The dynamically adaptive pre-hospital stroke intelligent early warning and graded response method according to claim 1, characterized in that, The intervention efficacy coefficient is a numerical coefficient quantified by matching the type and dosage parameters of the implemented medical intervention with the monitored trends of vital signs changes, and then with a pre-stored historical data model.

5. The method for dynamic adaptive pre-hospital stroke intelligent early warning and graded response according to claim 1, characterized in that, The at least two predicted scenarios include a best-case scenario, a most likely scenario, and a worst-case scenario; the risk level is associated with different scenarios and is presented in the structured report with different color codes.

6. The method for dynamic adaptive pre-hospital stroke intelligent early warning and graded response according to claim 1, characterized in that, If a secondary scan cannot be performed as instructed, a coordination request is sent to the emergency dispatch system, which then coordinates another ambulance to complete the collection of the secondary scan data at a designated location.

7. A dynamically adaptive pre-hospital stroke intelligent early warning and graded response system for implementing the dynamically adaptive pre-hospital stroke intelligent early warning and graded response method according to any one of claims 1-6, characterized in that, include: The baseline establishment module, configured at the transport origin, is used to acquire and process the initial CT scan data and vital sign data to establish a patient baseline. The real-time data stream receiving module is used to continuously receive the patient's vital signs data stream and the vehicle's environmental data stream during the transfer process; The status risk assessment module is used to calculate the patient's real-time risk index based on vital sign data stream; The dynamic scanning decision module is connected to the state risk assessment module and the real-time data stream receiving module, and is used to dynamically generate secondary scanning instructions based on the risk index and environmental data stream through a decision algorithm. The secondary scan execution and processing module is used to respond to the secondary scan command, control the CT equipment to perform the scan and process the secondary CT scan data; The intelligent prediction engine, connected to the baseline establishment module and the secondary scan execution and processing module, is used to calculate the initial average bleeding rate and, in combination with the intervention data from the real-time data stream receiving module, calculate the intervention efficacy coefficient and dynamic bleeding rate, thereby generating a multi-scenario prediction report. The report sending module is used to send the generated report to the target hospital.

8. The dynamically adaptive pre-hospital stroke intelligent early warning and graded response system according to claim 7, characterized in that, It also includes a vehicle-to-vehicle coordination management module, which is configured to send a request to the dispatch center when there are equipment or environmental limitations in executing a secondary scan command, and coordinate nearby ambulances with CT scanning capabilities to perform the scanning task at a predetermined meeting point.

Images