Clinical diagnosis and treatment path generation method and system for tracking chest pain patient

Abstract

The invention provides a clinical diagnosis and treatment path generation method and system for tracking a chest pain patient. Wherein a dynamic spatio-temporal data atlas is constructed by synchronously collecting respiratory rhythm phase difference, coronary artery calcification integral and hypersensitive troponin curve slope, and risk degree transition signals are generated by coupling analysis of ST segment elevation amplitude asymmetric growth, left ventricular ejection fraction attenuation gradient and B-type natriuretic peptide release rate. In the acute stage, the constraint relation between a vascular recanalization time window and thrombolysis taboo is dynamically bound, in the subacute stage, a phase synchronization rule for enhancing CT scanning and anticoagulant drug dosage is established through a multidisciplinary interface, intravascular ultrasonic plaque morphological mutation characteristics and extracorporeal circulation parameters are fused, the blood supply reconstruction time sequence is dynamically adjusted based on a myocardial oxygen consumption balance equation, and the thrombolysis time sequence is determined. And path self-optimization is realized through space-time superposition of an interventional therapy delay parameter and a drug metabolism curve. According to the technical scheme provided by the invention, chest pain diagnosis and treatment path dynamic optimization and multi-modal parameter collaborative decision-making are realized, and the risk layering precision and the treatment timeliness are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of diagnosis and treatment pathway generation, and in particular, to a method and system for generating a clinical diagnosis and treatment pathway for tracking chest pain patients. Background Art

[0002] With the increasing burden of cardiovascular diseases and the escalating demand for precision medicine, the chest pain center diagnosis and treatment system faces the dual challenges of multimodal data fusion and dynamic decision optimization.

[0003] In high-risk chest pain scenarios such as acute coronary syndrome and aortic dissection, it is necessary to build an intelligent diagnosis and treatment pathway generation system with the ability to coordinate and self-optimize spatiotemporal parameters; it is necessary to achieve multi-dimensional spatiotemporal correlation modeling of respiratory rhythm phase difference, coronary calcification integral and high-sensitivity troponin curve to break through the limitations of traditional single time point detection; it is necessary to establish a dynamic coupling analysis mechanism of asymmetric growth of ST segment elevation and B-type natriuretic peptide release rate to improve the sensitivity of risk stratification; it is necessary to construct a spatial constraint model of vascular recanalization time window and thrombolytic contraindications to achieve spatiotemporal adaptability optimization of treatment plans.

[0004] Among the existing technical solutions, the 0 / 1-hour clinical decision pathway based on high-sensitivity troponin (hs-cTn) accelerates chest pain assessment through a dynamic threshold algorithm; multimodal imaging integration technology is used to integrate coronary CTA, intravascular ultrasound and extracorporeal circulation parameters to construct a three-dimensional diagnosis and treatment model; and an intelligent body orchestration system is used to optimize tuberculosis infection risk assessment and surgical pathway planning through deep learning.

[0005] However, the existing technical solutions have the following technical defects: static data modeling cannot capture the dynamic correlation between respiratory phase difference and troponin curve, resulting in more than 20% missed diagnosis of early ACS; single-dimensional ST segment analysis ignores the spatiotemporal coupling effect of the left ventricular ejection fraction attenuation gradient, resulting in more than 30% misjudgment of risk, and the accuracy of risk stratification and timeliness of treatment are not high; traditional thrombolysis time window calculation does not integrate the characteristics of plaque morphological mutations, resulting in 15% of vascular recanalization timing deviating from the optimal solution. Summary of the invention

[0006] The embodiments of the present application provide a method and system for generating a clinical diagnosis and treatment pathway for tracking chest pain patients, so as to solve the problems of low risk stratification accuracy and low timeliness of treatment in the prior art.

[0007] In a first aspect, an embodiment of the present application provides a method for generating a clinical diagnosis and treatment pathway for tracking chest pain patients, comprising: By synchronously collecting the respiratory rhythm phase difference, coronary artery calcification score and high-sensitivity troponin curve slope within a preset time after the onset of chest pain, a spatiotemporal data map with dynamic priority marking is established, and incremental weight enhancement is implemented on the change rate of key indicators in the spatiotemporal data map to generate a clinical decision baseline framework; Based on the spatiotemporal data atlas, the spatiotemporal correlation pattern between the myocardial ischemic area and the abnormal electrocardiogram lead is identified, and when the asymmetric increase of the ST segment elevation amplitude is continuously detected, the coupling analysis linked with the left ventricular ejection fraction attenuation gradient and the B-type natriuretic peptide release rate is activated to generate a risk transition signal driving the diagnosis and treatment pathway; According to the intensity distribution of the risk transition signal driving the diagnosis and treatment pathway, the blood vessels are dynamically bound in the acute phase of the intensity distribution, and the time-space constraint relationship between the recanalization time window and the thrombolytic contraindications is constructed to construct an executable pathway topology structure. At the same time, in the subacute phase of the intensity distribution, a dynamic phase synchronization rule between the enhanced CT scan time node and the anticoagulant drug dosage curve is established through a multidisciplinary parameter negotiation interface; During the implementation of the executable path topology structure, the plaque morphological mutation characteristics of intravascular ultrasound and the circulatory auxiliary parameters of the extracorporeal life support device are integrated in real time, and based on the plaque rupture risk threshold and the myocardial oxygen consumption balance equation, the priority queue of the treatment plan is reconstructed and the timing dependency of the revascularization surgery is dynamically adjusted; The interventional treatment delay parameters and the dual antiplatelet drug metabolism curve are spatiotemporally superimposed according to the timing dependency to generate a causal association map, and the catheterization room activation delay and drug onset verification results in the causal association map are reversely mapped to the weight reinforcement model of the clinical decision baseline framework to drive the self-optimization update of the path topology structure and construct a clinical diagnosis and treatment pathway generation strategy.

[0008] Optionally, based on the spatiotemporal data atlas, the spatiotemporal correlation pattern between the myocardial ischemic area and the abnormal electrocardiogram lead is identified, and when the asymmetric increase of the ST segment elevation amplitude is continuously detected, the coupling analysis linked with the left ventricular ejection fraction attenuation gradient and the B-type natriuretic peptide release rate is activated to generate a risk transition signal driving the diagnosis and treatment pathway, including: Performing three-dimensional spatiotemporal positioning of the myocardial ischemic area in the spatiotemporal data atlas, extracting abnormal fluctuation phase characteristics of each lead channel, and establishing a dynamic propagation relationship model by aligning the multimodal signals in the abnormal fluctuation phase characteristics in time series; A dynamic sliding monitoring window is constructed for the dynamic propagation relationship model, the ST segment elevation amplitude is waveform decomposed, the peak characteristics, slope change rate and spatial lead distribution heterogeneity parameters are extracted, and when the asymmetric growth index is detected to exceed the dynamic adjustment threshold in three consecutive windows, the cardiac function compensation reserve analysis channel is activated; The spatiotemporal variation trajectory of the left ventricular ejection fraction attenuation gradient and the fluctuation characteristics of the B-type natriuretic peptide release rate in the cardiac function compensation reserve analysis channel are synchronously obtained, and a dynamic weight model of the ejection fraction change rate and the B-type natriuretic peptide release rate is established through a multi-source data coupling engine of electrocardiography, ultrasound, and biomarkers to calculate a composite quantitative index; The asymmetric growth index and the composite quantitative index are subjected to spatiotemporal superposition analysis. When it is detected that the spatiotemporal distribution of the two in the coronary artery blood supply area presents a critical coupling state, a directional risk transition vector is generated by inputting three-dimensional characteristic parameters of acute exacerbation probability, compensation failure time window and targeted intervention sensitivity based on the dynamic matching rule of vascular lesion classification; The three-dimensional feature parameters are subjected to multi-level cross-validation. When the probability of acute exacerbation in the multi-level cross-validation process exceeds the standard deviation range of the preset baseline value and the compensation failure time window overlaps with the current diagnosis and treatment stage, the target coordinates and path switching time constraints are preferentially intervened to generate a risk transition signal for driving the switching of the diagnosis and treatment path.

[0009] Optionally, according to the intensity distribution of the risk transition signal driving the diagnosis and treatment pathway, the time-space constraint relationship between the blood vessels, the recanalization time window and the thrombolytic contraindications is dynamically bound in the acute phase of the intensity distribution to construct an executable pathway topology structure, and at the same time, in the subacute phase of the intensity distribution, a dynamic phase synchronization rule between the enhanced CT scan time node and the anticoagulant drug dosage curve is established through a multidisciplinary parameter negotiation interface, including: Extracting the evolution characteristics of thrombolytic contraindications and the nonlinear growth curve of vascular occlusion rate based on the intensity distribution of the transition trigger signal, constructing a two-dimensional constraint matrix, mapping the gradient change of reperfusion injury probability through the time axis of the two-dimensional constraint matrix, and associating the anatomical topological relationship of coronary artery branches through the spatial axis of the two-dimensional constraint matrix; According to the gradient change characteristics in the two-dimensional constraint matrix, a dynamic matching rule between the CT angiography time window and the cardiac ultrasound examination frequency is established in the acute phase, and the priority sorting of the imaging examination nodes is driven by the real-time attenuation gradient of the hemodynamic parameters of the dynamic matching rule to generate a dynamic sequence chain of imaging examinations; The time distribution characteristics of the dynamic sequence chain of imaging examinations are injected into the thrombolysis contraindication matrix, the slope of the change of vascular occlusion rate in the thrombolysis contraindication matrix is ​​dynamically coupled with the myocardial survival threshold, and the catheterization room preparation stage, anticoagulant drug loading time window and balloon dilation operation sequence are introduced to generate a parallel execution framework; In the subacute phase, the operation sequence in the parallel execution framework is spatiotemporally encoded with the blood flow reserve parameters of the enhanced CT scan, and the dynamic phase synchronization rules of the enhanced CT scan time node and the anticoagulant drug dosage curve are established by inverse matching the anticoagulant drug metabolism rate with the scanning contrast agent clearance curve.

[0010] Optionally, the asymmetric growth index and the composite quantitative index are subjected to a spatiotemporal superposition analysis. When it is detected that the spatiotemporal distribution of the two in the coronary artery blood supply area presents a critical coupling state, based on the dynamic matching rule of vascular lesion classification, the three-dimensional characteristic parameters of acute exacerbation probability, compensation failure time window and targeted intervention sensitivity are input to generate a directional risk transition vector, including: A spatiotemporal convolution kernel group is introduced, and the spatiotemporal convolution kernel group parameters are calibrated through dynamic calibration of the branch vessel anatomical diameter, real-time pressure gradient and blood flow reserve fraction in the coronary artery blood supply area, and multi-scale feature extraction is performed on the asymmetric growth index and the composite quantitative index to generate a vascular topology weighted spatiotemporal superposition feature tensor; A dynamic threshold is obtained by calculating the sliding mean of the vascular endothelial shear stress waveform and the plaque morphology stability index, and the vascular topology weight spatiotemporal superposition feature tensor is activated layer by layer through the dynamic threshold adjustment. When the feature activation intensity of at least two adjacent vascular segments exceeds the critical threshold of the corresponding branch vascular lesion classification, the spatiotemporal coupling state mark is triggered; The covariance matrix of lesion calcification density gradient, fibrous cap thickness attenuation rate and microcirculatory resistance index in the vascular lesion classification parameter library was extracted, and a dynamic matching rule engine was established. Logistic regression was used to calculate the probability of acute exacerbation, and the compensation failure time window was predicted by the Kaplan-Meier modified model. The sensitivity of targeted intervention was evaluated based on the random forest classifier. The probability of acute exacerbation, the compensation failure time window and the targeted intervention sensitivity were three-dimensionally normalized and encoded to generate a directional risk transition vector.

[0011] Optionally, during the implementation of the executable path topology structure, the plaque morphological mutation characteristics of intravascular ultrasound and the circulatory auxiliary parameters of the extracorporeal life support device are integrated in real time, and based on the plaque rupture risk threshold and the myocardial oxygen consumption balance equation, the priority queue of the treatment plan is reconstructed and the timing dependency of the revascularization surgery is dynamically adjusted, including: The characteristic parameters of plaque morphological mutation were constructed through intravascular ultrasound image sequences, and the thickness gradient of plaque fiber cap, calcification density distribution and lipid core volume ratio were extracted using a multi-scale convolutional neural network. The plaque morphology-hemodynamic coupling characteristic vector was generated by combining the arterial pressure waveform and ventricular assist flow parameters collected in real time by extracorporeal life support equipment. The plaque morphology-hemodynamic coupling feature vector is input into a plaque rupture risk assessment model based on a random forest classifier, and the coronary artery perfusion pressure and ventricular wall tension product parameters in the myocardial oxygen consumption balance equation are simultaneously calculated. When the plaque rupture risk score exceeds the dynamic threshold and the oxygen consumption balance index deviates from the preset range, the revascularization surgery priority calculation channel is activated; A weighted correlation matrix of plaque rupture risk gradient and myocardial oxygen consumption imbalance degree is established in the revascularization surgery priority calculation channel, the weighted correlation matrix is ​​dynamically sorted using a sliding time window algorithm, and a time window and a start time priority queue are generated by combining the catheterization room resource occupancy status and the anticoagulant drug metabolic half-life parameters; According to the spatiotemporal constraint relationship between thrombolysis and interventional operations in the time window and the priority queue of the start time, a surgical timing dependency relationship is established, and the myocardial salvage index change curve under different timing combinations in the surgical timing dependency relationship is predicted by a recurrent neural network, and the revascularization scheme corresponding to the maximum slope drop point is selected as the optimal path.

[0012] Optionally, the step of inputting the plaque morphology-hemodynamic coupling feature vector into a plaque rupture risk assessment model based on a random forest classifier, synchronously calculating the coronary artery perfusion pressure and ventricular wall tension product parameter in the myocardial oxygen consumption balance equation, and activating a revascularization surgery priority calculation channel when the plaque rupture risk score exceeds a dynamic threshold and the oxygen consumption balance index deviates from a preset range, comprises: Dynamic Bayesian optimization was performed on the hyperparameters of the random forest classifier. The feature importance ranking was constructed based on the covariance matrix of the plaque fiber cap thickness gradient and the phase difference of the arterial pressure waveform. The interaction terms of calcification density distribution and ventricular assist flow parameters were selected as key input features to generate a dynamic threshold curve for plaque rupture risk score. Based on the dynamic threshold curve of the plaque rupture risk score, the product parameter of the coronary artery perfusion pressure and the ventricular wall tension is synchronously calculated, the fluctuation amplitude and the baseline offset of the product parameter are extracted by a sliding time window algorithm, and a two-dimensional deviation index is established in combination with the dynamic threshold curve of the plaque rupture risk score. When the two-dimensional deviation index exceeds the preset warning line for three consecutive times, a revascularization surgery priority calculation channel activation instruction is triggered; In the priority calculation channel of the revascularization surgery priority calculation channel activation instruction, a spatiotemporal correlation matrix of the plaque rupture risk gradient and the degree of myocardial oxygen consumption imbalance is constructed, and a dynamic weighted algorithm is used to fuse the catheter room resource occupancy state parameters and the anticoagulant drug metabolic half-life attenuation curve to generate a dynamic decision map; The interventional surgery start time in the dynamic decision map is input into the recurrent neural network for timing conflict detection, the optimal intervention path is screened through the myocardial salvage index prediction model, and the plaque morphology mutation characteristic parameters and circulation auxiliary parameters during the path execution process are fed back to the rupture risk assessment model for incremental learning and updating.

[0013] Optionally, the interventional treatment delay parameter and the dual antiplatelet drug metabolism curve are temporally and spatially superimposed according to the temporal dependency relationship to generate a causal association map, and the catheterization room activation delay and drug onset verification results in the causal association map are reversely mapped to the weight reinforcement model of the clinical decision baseline framework to drive the self-optimization update of the path topology structure and construct a clinical diagnosis and treatment path generation strategy, including: Time series alignment was used to fuse the interventional treatment delay parameters and dual antiplatelet drug metabolism curves. The phase difference parameters of drug concentration attenuation gradient and catheterization room preparation time were extracted through the sliding time window in the time series alignment process to generate a spatiotemporal superposition feature matrix. Constructing a causal association map based on a Bayesian network, taking the delay parameters and the slope of the drug metabolism curve in the spatiotemporal superposition feature matrix as map nodes, and identifying the causal relationship map between the coronary blood flow recovery rate and the platelet inhibition rate through dynamic directed edge weights; Inputting the catheterization room activation delay parameter and the drug onset verification result in the causal association map into the random forest regression model, calculating the dynamic adjustment coefficient of the weight enhancement model in the clinical decision baseline framework, and updating the association weight of the coronary artery calcification score and the slope of the high-sensitivity troponin curve through the gradient descent model; A deep reinforcement learning framework was used to construct a path topology self-optimization model, and the association weights were dynamically coupled with real-time intravascular ultrasound plaque morphology parameters to generate a clinical diagnosis and treatment pathway generation strategy.

[0014] In a second aspect, an embodiment of the present application provides a clinical diagnosis and treatment pathway generation system for tracking chest pain patients, comprising: An acquisition module is used to establish a spatiotemporal data map with dynamic priority markings by synchronously acquiring respiratory rhythm phase difference, coronary artery calcification score and high-sensitivity troponin curve slope within a preset time after the onset of chest pain, and to implement incremental weight enhancement on the change rate of key indicators in the spatiotemporal data map to generate a clinical decision baseline framework; An identification module is used to identify the spatiotemporal correlation pattern between the myocardial ischemic area and the abnormal electrocardiogram lead based on the spatiotemporal data map, and when the asymmetric increase of the ST segment elevation amplitude is continuously detected, activate the coupling analysis linked with the left ventricular ejection fraction attenuation gradient and the B-type natriuretic peptide release rate to generate a risk transition signal driving the diagnosis and treatment path; A construction module is used to dynamically bind blood vessels, the time-space constraint relationship between the recanalization time window and the contraindications of thrombolysis in the acute phase of the intensity distribution according to the intensity distribution of the risk transition signal driving the diagnosis and treatment pathway, and to construct an executable pathway topology structure. At the same time, in the subacute phase of the intensity distribution, a dynamic phase synchronization rule between the enhanced CT scanning time node and the anticoagulant drug dosage curve is established through a multidisciplinary parameter negotiation interface; A fusion module, used for real-time fusion of plaque morphological mutation characteristics of intravascular ultrasound and circulatory auxiliary parameters of extracorporeal life support equipment during the implementation of the executable path topology structure, and reconstructing the priority queue of treatment plans and dynamically adjusting the timing dependency of revascularization surgery based on the plaque rupture risk threshold and the myocardial oxygen consumption balance equation; A mapping module is used to perform spatiotemporal superposition of interventional treatment delay parameters and dual antiplatelet drug metabolism curves according to the timing dependency to generate a causal association map, and reversely map the catheterization room activation delay and drug onset verification results in the causal association map to the weighted reinforcement model of the clinical decision baseline framework, drive the self-optimization update of the path topology structure, and construct a clinical diagnosis and treatment path generation strategy.

[0015] In a third aspect, an embodiment of the present application provides a computing device, comprising 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 a method for generating a clinical diagnosis and treatment pathway for tracking chest pain patients as described in the first aspect.

[0016] 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 a method for generating a clinical diagnosis and treatment pathway for tracking chest pain patients as described in the first aspect.

[0017] In an embodiment of the present application, by synchronously collecting the respiratory rhythm phase difference, coronary artery calcification score and high-sensitivity troponin curve slope within a preset time after the onset of chest pain, a spatiotemporal data map with dynamic priority marking is established, and the change rate of key indicators in the spatiotemporal data map is incrementally weighted to generate a clinical decision baseline framework; based on the spatiotemporal data map, the spatiotemporal correlation pattern between the myocardial ischemic area and the abnormal electrocardiogram lead is identified, and when the asymmetric increase in the ST segment elevation amplitude is continuously detected, the coupling analysis linked to the left ventricular ejection fraction attenuation gradient and the B-type natriuretic peptide release rate is activated to generate a hazard transition signal driving the diagnosis and treatment pathway; according to the intensity distribution of the hazard transition signal driving the diagnosis and treatment pathway, the blood vessels are dynamically bound in the acute phase of the intensity distribution, and the time-space constraint relationship between the recanalization time window and the thrombolytic contraindications is constructed to construct an executable path topology. structure, and at the same time, in the subacute period of the intensity distribution, a dynamic phase synchronization rule between the enhanced CT scan time node and the anticoagulant drug dosage curve is established through a multidisciplinary parameter negotiation interface; during the implementation of the executable path topology structure, the plaque morphology mutation characteristics of intravascular ultrasound and the circulatory auxiliary parameters of the extracorporeal life support device are fused in real time, and based on the plaque rupture risk threshold and the myocardial oxygen consumption balance equation, the treatment plan priority queue is reconstructed and the timing dependency of the revascularization surgery is dynamically adjusted; the interventional treatment delay parameter and the dual antiplatelet drug metabolism curve are superimposed in time and space according to the timing dependency to generate a causal association map, and the catheter room activation delay and drug onset verification results in the causal association map are reversely mapped to the weight reinforcement model of the clinical decision baseline framework, driving the path topology structure to self-optimize and update, and construct a clinical diagnosis and treatment path generation strategy.

[0018] The technical solution of this application has the following beneficial effects: Through the spatiotemporal correlation modeling of the respiratory rhythm phase difference and the slope of the high-sensitivity troponin curve, the limitations of traditional single-time point detection are broken through and the sensitivity of early recognition of ACS is improved; based on the coupling analysis of the asymmetric growth characteristics of ST-segment elevation and the release rate of B-type natriuretic peptide, a dynamic mapping relationship between myocardial ischemia areas and electrocardiogram abnormalities is established to enhance the warning capability of risk transition; spatial constraint modeling of vascular recanalization time window and thrombolytic contraindications is used to achieve spatiotemporal adaptability optimization of acute treatment plans; integrating the intravascular ultrasound plaque morphological mutation characteristics and extracorporeal circulation parameters, a dynamic adjustment mechanism for the timing of revascularization reconstruction is constructed to reduce the risk of plaque rupture; through the reverse mapping of the causal association map, closed-loop optimization of the diagnosis and treatment path is achieved to form a personalized clinical decision-making iterative upgrade system.

[0019] Furthermore, the myocardial ischemic area is located in three-dimensional space and time and the abnormal fluctuation phase characteristics of the leads are extracted to establish a dynamic propagation model for time series alignment of multimodal signals; the ST segment elevation amplitude is waveform decomposed using a dynamic sliding monitoring window, and when three consecutive windows detect that the asymmetric growth index exceeds the threshold, the cardiac function compensatory reserve analysis channel is activated; through the ECG-ultrasound-biomarker multi-source data coupling engine, the spatiotemporal variation trajectories of the left ventricular ejection fraction attenuation gradient and the B-type natriuretic peptide release rate are synchronously integrated, and a dynamic weight model is constructed to generate a composite quantitative index; finally, through spatiotemporal superposition analysis and multi-level cross-validation, a directional risk transition vector is generated under the critical coupling state of the coronary artery blood supply area, and a hazard transition signal is generated based on the probability of acute exacerbation, the compensation failure time window and the intervention sensitivity parameters. This method achieves accurate spatiotemporal correlation modeling of myocardial ischemia areas and electrocardiogram abnormalities, and improves the early warning sensitivity of acute coronary syndrome through dynamic monitoring of asymmetric ST segment growth and linkage analysis of cardiac function compensatory reserve; combined with the dynamic weight model of ejection fraction attenuation gradient and B-type natriuretic peptide release rate, the spatiotemporal resolution of hazard transition signals reaches submillimeter level, reducing the misjudgment rate compared with traditional single-dimensional ST segment analysis methods; through the path switching constraints established by the multi-level cross-validation mechanism, the time window for identifying acute exacerbation events can be shortened, significantly improving the timeliness of treatment for high-risk patients.

[0020] 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

[0021] 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.

[0022] Figure 1 A flowchart of a method for generating a clinical diagnosis and treatment pathway for tracking chest pain patients provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a clinical diagnosis and treatment pathway generation system for tracking chest pain patients provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0024] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0025] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0026] Figure 1 A flowchart of a method for generating a clinical diagnosis and treatment pathway for tracking chest pain patients is provided in an embodiment of the present application. Figure 1 As shown, the method includes: 101. By synchronously collecting the respiratory rhythm phase difference, coronary artery calcification score and high-sensitivity troponin curve slope within a preset time after the onset of chest pain, a spatiotemporal data map with dynamic priority marking is established, and incremental weight enhancement is implemented on the change rate of key indicators in the spatiotemporal data map to generate a clinical decision baseline framework; In this step, the spatiotemporal data map is a comprehensive data structure. It constructs a dynamic physiological change model with time and space dimensions by synchronously collecting key indicators such as respiratory rhythm phase difference, coronary artery calcium score and high-sensitivity troponin curve slope within a preset time after the onset of chest pain. This map not only describes the changing trend of these physiological parameters, but also reveals the relationship between them, providing a rich information basis for clinical decision-making. Incremental weight enhancement refers to the process of dynamically adjusting the change rate of key indicators in the spatiotemporal data map. By giving higher weights to important data, these data will receive more attention in subsequent analysis and decision-making; this process helps to improve the accuracy of diagnosis and the effectiveness of treatment plans. The clinical decision baseline framework is a preliminary diagnosis and treatment pathway framework generated based on the above data and weight adjustment. It provides a systematic evaluation standard to help doctors develop personalized treatment plans based on the specific conditions of patients; this framework takes into account the influence of multiple factors and adapts to different clinical needs through continuous updating and optimization.

[0027] In an embodiment of the present application, first, the system synchronously collects a variety of physiological data within a preset time after the onset of chest pain; second, these data are integrated into a spatiotemporal data map; third, incremental weight enhancement is implemented on the change rate of key indicators in the map to ensure that important data receive more attention; finally, a clinical decision baseline framework is generated to provide a reference for subsequent diagnosis and treatment.

[0028] Suppose a patient is admitted to the hospital due to acute chest pain. The system synchronously collects the patient's respiratory rhythm phase difference, coronary artery calcification score and high-sensitivity troponin curve slope within the first hour after the onset of chest pain; secondly, the system integrates these data into a spatiotemporal data map; thirdly, the system incrementally weights the change rate of key indicators in the map and identifies that the change in the slope of the high-sensitivity troponin curve is the most significant; finally, a preliminary clinical decision baseline framework is generated to guide doctors for further examination and treatment.

[0029] 102. Based on the spatiotemporal data atlas, identify the spatiotemporal correlation pattern between the myocardial ischemic area and the abnormal electrocardiogram lead, and when the asymmetric increase of the ST segment elevation amplitude is continuously detected, activate the coupling analysis linked with the left ventricular ejection fraction attenuation gradient and the B-type natriuretic peptide release rate to generate a risk transition signal that drives the diagnosis and treatment pathway; In this step, the ST segment is a part of the electrocardiogram located between the QRS complex and the T wave. It represents the time period between the depolarization of the ventricular myocytes and the beginning of repolarization. Abnormalities of the ST segment (such as elevation or depression) are usually associated with heart diseases such as myocardial ischemia or myocardial infarction.

[0030] B-type Natriuretic Peptide (BNP). It is a hormone secreted by the heart, mainly used to regulate fluid balance and blood pressure. Elevated BNP levels are usually associated with heart diseases such as heart failure and are a commonly used biomarker for heart failure in clinical practice.

[0031] Myocardial ischemic areas refer to parts of the heart that lack oxygen due to insufficient blood supply, which is usually reflected by abnormal electrocardiogram leads; identifying these areas is crucial for early detection and intervention of acute cardiovascular events. Spatiotemporal association patterns describe the complex relationship between myocardial ischemic areas and abnormal electrocardiogram leads, including temporal and spatial connections; the identification of this pattern helps to locate the problem more accurately and take targeted measures. Coupling analysis combines the left ventricular ejection fraction attenuation gradient and the B-type natriuretic peptide release rate to comprehensively evaluate changes in cardiac functional status; this method can provide more comprehensive information than a single indicator, thereby supporting more effective clinical decision-making. The risk transition signal is a warning signal triggered when an asymmetric increase in the amplitude of ST segment elevation is detected, indicating the need for emergency intervention; the generation of this signal is based on multi-dimensional data analysis to ensure timely response to potential cardiovascular risks.

[0032] In the embodiment of the present application, first, based on the spatiotemporal data map, the system identifies the spatiotemporal correlation pattern between the myocardial ischemic area and the abnormal electrocardiogram lead; secondly, when the asymmetric growth of ST segment elevation is continuously detected, the coupling analysis is activated; thirdly, the left ventricular ejection fraction attenuation gradient and the B-type natriuretic peptide release rate are combined to evaluate the cardiac function state; finally, a risk transition signal that drives the diagnosis and treatment pathway is generated to prompt the doctor to take emergency measures.

[0033] For example, continuing with the above example, assuming that the patient's electrocardiogram shows abnormalities in multiple leads, the system identifies the spatiotemporal correlation pattern between the myocardial ischemic area and these leads; secondly, the system detects the asymmetric increase in the amplitude of the ST segment elevation; thirdly, the system activates the coupling analysis, combined with the left ventricular ejection fraction attenuation gradient and the B-type natriuretic peptide release rate, and finds that the heart function has significantly decreased; finally, a danger transition signal is generated, prompting the doctor to take emergency intervention measures immediately.

[0034] 103. According to the intensity distribution of the risk transition signal driving the diagnosis and treatment pathway, dynamically bind the blood vessels in the acute phase of the intensity distribution, and construct an executable pathway topology structure by the time-space constraint relationship between the recanalization time window and the thrombolytic contraindications. At the same time, in the subacute phase of the intensity distribution, establish a dynamic phase synchronization rule between the enhanced CT scan time node and the anticoagulant drug dosage curve through a multidisciplinary parameter negotiation interface; In this step, the acute phase of intensity distribution refers to the stage when the patient's condition deteriorates rapidly, during which rapid action is needed to prevent further deterioration. Data analysis at this stage is crucial to guide immediate treatment. The revascularization time window is the optimal time window from the onset of symptoms to the revascularization surgery. Missing this time period may significantly reduce the treatment effect. The time-space constraint relationship of thrombolytic contraindications takes into account the patient's specific conditions and determines whether thrombolytic therapy is suitable. This involves a comprehensive evaluation of multiple factors to ensure the safety and effectiveness of the treatment. The multidisciplinary parameter negotiation interface jointly determines the best treatment plan through the collaboration of experts from different departments. This method can integrate multiple opinions and improve the quality of decision-making. Enhanced CT scan time node selects the right time for enhanced CT scanning to obtain more accurate imaging information, thereby guiding subsequent treatment. Timely imaging examinations are indispensable for accurate diagnosis. Anticoagulant drug dosage curve adjusts the dosage of anticoagulants according to the patient's real-time condition to maintain the stability of blood circulation, which requires precise monitoring and timely adjustment to avoid the risk of bleeding or thrombosis.

[0035] In the embodiments of the present application, first, the time-space constraint relationship between the vascular recanalization time window and the contraindications to thrombolysis is dynamically bound in the acute phase; second, an executable path topology is constructed; third, in the subacute phase, the dynamic phase synchronization rules between the enhanced CT scan time nodes and the anticoagulant drug dosage curve are determined through the multidisciplinary parameter negotiation interface; finally, all treatment measures are ensured to be coordinated and consistent to improve the treatment effect.

[0036] For example, continuing with the above example, assuming that the patient enters the acute phase, the system dynamically binds the time-space constraint relationship between the vascular recanalization time window and the contraindications to thrombolysis; secondly, the system constructs an executable path topology structure; thirdly, in the subacute phase, the dynamic phase synchronization rules between the enhanced CT scan time nodes and the anticoagulant drug dosage curve are determined through the multidisciplinary parameter negotiation interface; finally, all treatment measures are coordinated and consistent to improve the treatment effect.

[0037] 104. During the implementation of the executable path topology structure, the plaque morphological mutation characteristics of intravascular ultrasound and the circulatory auxiliary parameters of the extracorporeal life support device are integrated in real time, and based on the plaque rupture risk threshold and the myocardial oxygen consumption balance equation, the priority queue of the treatment plan is reconstructed and the timing dependency of the revascularization surgery is dynamically adjusted; In this step, the plaque morphological mutation feature refers to the change in plaque morphology detected by intravascular ultrasound, which may indicate an increased risk of plaque rupture. Monitoring these changes is of great significance for preventing acute cardiovascular events. The circulatory assistance parameters of extracorporeal life support devices include relevant parameters when using ECMO and other devices, which are used to maintain blood circulation. Especially in the case of severe cardiopulmonary insufficiency, the optimization and adjustment of these parameters are crucial to improving patient survival. The safety limit set by the plaque rupture risk threshold, exceeding which the plaque is considered to be at risk of rupture, requires immediate measures. The setting of this threshold is based on a large number of clinical studies and experience summaries. The myocardial oxygen consumption balance equation is used to calculate the balance between myocardial oxygen consumption and oxygen supply to ensure that the myocardium is adequately supplied with oxygen, which is critical for maintaining normal heart function. The treatment priority queue arranges the most reasonable treatment sequence according to the weight of each indicator to maximize the treatment effect, which requires comprehensive consideration of the patient's specific situation and the effects of various treatment methods. The timing dependency of revascularization surgery refers to the time sequence and dependency between different treatment steps, ensuring that each step is performed at the right time to achieve the best treatment effect, which requires meticulous time management and coordination.

[0038] In the embodiments of the present application, firstly, the system integrates the plaque morphological mutation characteristics of intravascular ultrasound and the circulatory assistance parameters of the extracorporeal life support device in real time; secondly, based on the plaque rupture risk threshold and the myocardial oxygen consumption balance equation, the priority queue of the treatment plan is reconstructed; thirdly, the timing dependency of the revascularization surgery is dynamically adjusted to ensure that each treatment step is performed at the best time; finally, an optimized treatment plan is generated to guide doctors to implement effective revascularization surgery and improve the treatment effect and survival rate of patients.

[0039] For example, continuing with the above example, assuming that the patient has severe coronary artery stenosis in the acute phase, the system integrates the plaque morphology mutation characteristics detected by intravascular ultrasound and the circulatory assistance parameters of the ECMO device in real time; secondly, the system reconstructs the treatment priority queue based on the plaque rupture risk threshold and the myocardial oxygen consumption balance equation; thirdly, it dynamically adjusts the timing dependency of the revascularization surgery to ensure that PCI (percutaneous coronary intervention) is performed at the best time; finally, it generates an optimized treatment plan to guide doctors to successfully perform the revascularization surgery, significantly improving the patient's treatment effect and survival rate.

[0040] 105. The interventional treatment delay parameters and the dual antiplatelet drug metabolism curve are temporally and spatially superimposed according to the timing dependency to generate a causal association map, and the catheterization room activation delay and drug onset verification results in the causal association map are reversely mapped to the weight reinforcement model of the clinical decision baseline framework to drive the self-optimization update of the path topology structure and construct a clinical diagnosis and treatment path generation strategy.

[0041] In this step, the interventional treatment delay parameter refers to the time interval between the decision to perform interventional treatment and the actual start of treatment. This time interval has an important impact on the treatment effect. A longer delay may lead to worsening of the condition, so this time period needs to be shortened as much as possible. The dual antiplatelet drug metabolism curve describes the metabolic process and effect of patients after taking dual antiplatelet drugs, helping doctors to evaluate the drug onset time and sustained effect, which is crucial to ensure the effectiveness and safety of the drug. Spatiotemporal superposition refers to the integration and analysis of the interventional treatment delay parameter and the dual antiplatelet drug metabolism curve in the time and space dimensions to generate a causal association map. This superposition helps to fully understand the various factors in the treatment process and their interrelationships. The causal association map is a data structure used to show the causal relationship between the interventional treatment delay and the drug onset verification results. It can help doctors better understand and predict the treatment effect and make more accurate decisions. The catheterization room activation delay refers to the time interval between the decision to perform interventional treatment and the actual readiness of the catheterization room. This delay directly affects the timeliness and effectiveness of treatment. The weight reinforcement model that is reversely mapped to the clinical decision baseline framework can further optimize the treatment path. The drug efficacy verification results are the actual verification results of the dual antiplatelet drug metabolism curve, which are used to confirm whether the drug has achieved the expected effect within the expected time. These results are fed back into the clinical decision baseline framework to drive the self-optimization update of the pathway topology structure.

[0042] In the embodiment of the present application, first, the system performs spatiotemporal superposition of the interventional treatment delay parameters and the dual antiplatelet drug metabolism curve based on the timing dependency; secondly, a causal association map is generated to show the causal relationship between the interventional treatment delay and the drug efficacy verification results; thirdly, the catheterization room activation delay and the drug efficacy verification results in the causal association map are reversely mapped to the weighted reinforcement model of the clinical decision baseline framework; finally, based on these feedback information, the path topology structure is driven to self-optimize and update, and a clinical diagnosis and treatment path generation strategy is constructed to ensure that each treatment step can be performed at the best time to improve the overall treatment effect.

[0043] For example, continuing with the above example, assuming that after the patient decides to undergo PCI, the system records the interventional treatment delay parameters and performs spatiotemporal superposition based on the dual antiplatelet drug metabolism curve; secondly, the system generates a causal association map, showing the causal relationship between the interventional treatment delay and the drug efficacy verification results; thirdly, the system reversely maps the catheterization room activation delay and the drug efficacy verification results in the causal association map to the weighted reinforcement model of the clinical decision baseline framework; finally, based on this feedback information, the system drives the path topology structure to self-optimize and update, ensuring that the catheterization room is ready in the shortest time, and confirming that the drug has achieved the expected effect within the expected time, ultimately improving the overall treatment effect and patient survival rate.

[0044] In summary, steps 101 to 105 cover the entire process from synchronously collecting key physiological data, establishing spatiotemporal data maps, identifying spatiotemporal correlation patterns between myocardial ischemic areas and abnormal ECG leads, generating risk transition signals that drive diagnostic and treatment pathways, and constructing executable pathway topology structures, to real-time fusion of intravascular ultrasound data and extracorporeal life support equipment parameters and causal analysis. It aims to provide a systematic evaluation and treatment framework to meet the needs of personalized medicine, ensure that patients can receive the most suitable treatment at the best time, and improve diagnostic accuracy, treatment efficacy, and survival rate. Through these steps, the system can not only dynamically adjust the priority queue of treatment options, but also optimize the time-space relationship between interventional treatment delays and drug metabolism curves, thereby achieving precision medicine and efficient clinical decision support.

[0045] In order to further improve the recognition accuracy of the spatiotemporal correlation pattern between the myocardial ischemic area and the abnormal electrocardiogram lead, in some embodiments, step 102 identifies the spatiotemporal correlation pattern between the myocardial ischemic area and the abnormal electrocardiogram lead based on the spatiotemporal data map, and when the asymmetric increase of the ST segment elevation amplitude is continuously detected, the coupling analysis linked to the left ventricular ejection fraction attenuation gradient and the B-type natriuretic peptide release rate is activated to generate a risk transition signal driving the diagnosis and treatment path, including: extracting the evolution characteristics of thrombolytic contraindications and the nonlinear growth curve of vascular occlusion rate based on the intensity distribution of the transition trigger signal, constructing a two-dimensional constraint matrix, mapping the gradient change of the probability of reperfusion injury through the time axis of the two-dimensional constraint matrix, and associating the anatomical topological relationship of the coronary artery branches through the spatial axis of the two-dimensional constraint matrix; according to the gradient change characteristics in the two-dimensional constraint matrix, In the acute phase, a dynamic matching rule between the CT angiography time window and the frequency of cardiac ultrasound examination is established, and the priority sorting of the imaging examination nodes is driven by the real-time attenuation gradient of the hemodynamic parameters of the dynamic matching rule to generate an imaging examination dynamic sequence chain; the time distribution characteristics of the imaging examination dynamic sequence chain are injected into the thrombolysis contraindication matrix, the vascular occlusion rate change slope in the thrombolysis contraindication matrix is ​​dynamically coupled with the myocardial survival threshold, the catheter room preparation stage, the anticoagulant loading time window and the balloon dilation operation sequence are introduced to generate a parallel execution framework; in the subacute phase, the operation sequence in the parallel execution framework is spatiotemporally encoded with the blood flow reserve parameters of the enhanced CT scan, and the dynamic phase synchronization rule between the enhanced CT scan time node and the anticoagulant dosage curve is established through the reverse matching of the anticoagulant metabolism rate and the scanning contrast agent clearance curve.

[0046] In this embodiment, three-dimensional spatiotemporal positioning is a method for capturing the specific location of the myocardial ischemic area and its changing trend over time through precise spatial and temporal positioning, ensuring that the lesion area can be accurately identified. This positioning method helps to more accurately identify and treat heart problems. Abnormal fluctuation phase characteristics refer to the time point and phase characteristics of abnormal fluctuations that appear in each lead channel. By extracting these characteristics, we can better understand the abnormal conditions in the electrocardiogram, which are usually manifested as waveform changes or irregular fluctuations in a specific time period. These characteristics provide an important basis for subsequent analysis. The dynamic propagation relationship model is to align multimodal signals through time series, establish a dynamic propagation relationship model, and describe the propagation path and law of abnormal fluctuations between different leads; this model can help identify potential myocardial ischemic areas and their diffusion trends, and provide a comprehensive risk assessment. The dynamic sliding monitoring window is a mechanism for real-time monitoring of the ST segment elevation amplitude. By setting a dynamic adjustment threshold to identify abnormal growth trends, this method can improve the early warning capability of events such as acute myocardial infarction and ensure timely intervention measures. The cardiac function compensation reserve analysis channel synchronously obtains the spatiotemporal variation trajectory of the left ventricular ejection fraction attenuation gradient and the fluctuation characteristics of the B-type natriuretic peptide release rate to evaluate the cardiac function status and its compensatory capacity. This channel provides comprehensive cardiac function assessment information to help doctors formulate the best treatment plan. The composite quantitative index is a comprehensive indicator calculated by the multi-source data coupling engine of ECG, ultrasound and biomarkers, reflecting the cardiac function status and risk level. This index combines multiple parameters to provide a more comprehensive risk assessment and guide clinical decision-making. The directional risk transition vector is based on the dynamic matching rules of vascular lesion classification, inputs the three-dimensional characteristic parameters of acute exacerbation probability, compensation failure time window and targeted intervention sensitivity, and generates a directional risk transition vector to guide clinical decision-making. This vector helps doctors determine the best treatment time and plan. Multi-level cross-validation ensures the reliability and accuracy of the test results through a multi-level data verification process. This process can effectively reduce false positive and false negative results and improve the quality of diagnosis.

[0047] In the embodiment of the present application, firstly, the myocardial ischemic area in the spatiotemporal data map is three-dimensionally located in space-time and time, and the abnormal fluctuation phase characteristics of each lead channel are extracted; secondly, the dynamic propagation relationship model is established by aligning the abnormal fluctuation phase characteristics in time series; thirdly, a dynamic sliding monitoring window is constructed, the ST segment elevation amplitude is waveform decomposed, and the peak characteristics, slope change rate and spatial lead distribution heterogeneity parameters are extracted; when the asymmetric growth index is detected to break through the dynamic adjustment threshold in three consecutive windows, the cardiac function compensatory reserve analysis channel is activated; the spatiotemporal change trajectory of the left ventricular ejection fraction attenuation gradient and the fluctuation characteristics of the B-type natriuretic peptide release rate are synchronously obtained, and the electrocardiogram is used to analyze the fluctuation characteristics of the left ventricular ejection fraction attenuation gradient. The ultrasound-biomarker multi-source data coupling engine establishes a dynamic weight model for the ejection fraction change rate and the B-type natriuretic peptide release rate, and calculates the composite quantitative index; the asymmetric growth index and the composite quantitative index are subjected to spatiotemporal superposition analysis. When the spatiotemporal distribution of the two in the coronary artery blood supply area presents a critical coupling state, the three-dimensional characteristic parameters of acute exacerbation probability, compensation failure time window and targeted intervention sensitivity are input based on the dynamic matching rules of vascular lesion classification to generate a directional risk transition vector; finally, the three-dimensional characteristic parameters are subjected to multi-level cross-validation, and the target coordinates and path switching time constraints are prioritized for intervention to generate a risk transition signal for driving the switching of diagnosis and treatment paths.

[0048] Here is a specific example: Assuming that a patient has chest pain symptoms, the system first performs three-dimensional spatiotemporal positioning of the myocardial ischemic area and extracts the abnormal fluctuation phase characteristics of each lead channel; secondly, the system establishes a dynamic propagation relationship model by aligning the time series of the abnormal fluctuation phase characteristics; thirdly, the system constructs a dynamic sliding monitoring window, performs waveform decomposition of the ST segment elevation amplitude, and extracts the peak characteristics, slope change rate and spatial lead distribution heterogeneity parameters; when the asymmetric growth index is detected to exceed the dynamic adjustment threshold in three consecutive windows, the cardiac function compensatory reserve analysis channel is activated; the spatiotemporal change trajectory of the left ventricular ejection fraction attenuation gradient and the fluctuation characteristics of the B-type natriuretic peptide release rate are simultaneously obtained, and the ejection fraction is established through the multi-source data coupling engine of electrocardiography, ultrasound and biomarkers. The dynamic weight model of the change rate and B-type natriuretic peptide release rate was used to calculate the composite quantitative index; the asymmetric growth index and the composite quantitative index were subjected to a spatiotemporal superposition analysis. When the spatiotemporal distribution of the two in the coronary artery blood supply area showed a critical coupling state, the three-dimensional characteristic parameters of acute exacerbation probability, compensation failure time window and targeted intervention sensitivity were input based on the dynamic matching rules of vascular lesion classification to generate a directional risk transition vector; finally, the system performed multi-level cross-validation on the three-dimensional characteristic parameters. When the probability of acute exacerbation in the multi-level cross-validation process exceeded the standard deviation range of the preset baseline value and the compensation failure time window overlapped with the current diagnosis and treatment stage, a risk transition signal was generated to drive the switching of diagnosis and treatment pathways, guiding doctors to take emergency measures and successfully avoiding the deterioration of the disease.

[0049] In order to further improve the intensity distribution processing accuracy of the hazard transition signal driving the diagnosis and treatment pathway, in certain embodiments, step 103 dynamically binds the time-space constraint relationship between the vascular recanalization time window and the thrombolytic contraindications in the acute phase of the intensity distribution according to the intensity distribution of the hazard transition signal driving the diagnosis and treatment pathway, and constructs an executable path topology structure. At the same time, in the subacute phase of the intensity distribution, a dynamic phase synchronization rule between the enhanced CT scan time node and the anticoagulant drug dosage curve is established through a multidisciplinary parameter negotiation interface, including: extracting the evolution characteristics of the thrombolytic contraindications and the nonlinear growth curve of the vascular occlusion rate based on the intensity distribution of the transition trigger signal, constructing a two-dimensional constraint matrix, mapping the reperfusion injury probability gradient change through the time axis of the two-dimensional constraint matrix, and associating the anatomical topological relationship of the coronary artery branches through the spatial axis of the two-dimensional constraint matrix; according to the two-dimensional constraint matrix The gradient change characteristics in the array are used to establish a dynamic matching rule between the CT angiography time window and the frequency of cardiac ultrasound examination in the acute phase, and the priority sorting of the image examination nodes is driven by the real-time attenuation gradient of the hemodynamic parameters of the dynamic matching rule to generate a dynamic sequence chain of image examination; the time distribution characteristics of the dynamic sequence chain of image examination are injected into the thrombolysis contraindication matrix, the slope of the vascular occlusion rate change in the thrombolysis contraindication matrix is ​​dynamically coupled with the myocardial survival threshold, the catheterization room preparation stage, the anticoagulant loading time window and the balloon dilatation operation sequence are introduced to generate a parallel execution framework; in the subacute phase, the operation sequence in the parallel execution framework is spatiotemporally encoded with the blood flow reserve parameters of the enhanced CT scan, and the dynamic phase synchronization rule between the enhanced CT scan time node and the anticoagulant dosage curve is established through the inverse matching of the anticoagulant metabolism rate and the scanning contrast agent clearance curve.

[0050] In this embodiment, the two-dimensional constraint matrix is ​​a data structure that combines the time axis and the space axis, and is used to extract the evolution characteristics of thrombolytic contraindications and the nonlinear growth curve of vascular occlusion rate. The matrix maps the gradient change of the probability of reperfusion injury through the time axis, and associates the anatomical topological relationship of the coronary artery branches through the space axis, providing a comprehensive data framework for analysis and decision-making. The dynamic matching rule is a method for establishing the time window of CT angiography and the frequency of cardiac ultrasound examination in the acute phase. The rule drives the priority sorting of the imaging examination nodes through the real-time attenuation gradient of the hemodynamic parameters to generate a dynamic sequence chain of imaging examinations. The dynamic sequence chain of imaging examinations is a time distribution feature sequence generated based on the dynamic matching rule. The time nodes of the imaging examination are sorted according to the priority to form an orderly inspection process. The sequence chain not only considers the timing of the imaging examination, but also combines the real-time hemodynamic parameters of the patient. The parallel execution framework is an operation sequence framework generated in the subacute phase, which combines the catheter room preparation stage, the anticoagulant loading time window and the balloon dilatation operation sequence. The framework performs spatiotemporal encoding by enhancing the blood flow reserve parameters of CT scans to ensure efficient coordination between various treatment steps. The dynamic phase synchronization rule is a method to establish the enhanced CT scanning time node and the anticoagulant dosage curve by inversely matching the anticoagulant metabolism rate with the scanning contrast agent clearance curve. This rule ensures that during the subacute period, the use of enhanced CT scanning and anticoagulant drugs can be coordinated with each other to improve the overall treatment effect.

[0051] In the embodiment of the present application, firstly, the evolution characteristics of thrombolytic contraindications and the nonlinear growth curve of vascular occlusion rate are extracted based on the intensity distribution of the transition trigger signal to construct a two-dimensional constraint matrix; secondly, the anatomical topological relationship of the coronary artery branches associated with the gradient change of the probability of reperfusion injury and the spatial axis is mapped through the time axis of the matrix; thirdly, according to the gradient change characteristics in the two-dimensional constraint matrix, a dynamic matching rule between the CT angiography time window and the frequency of cardiac ultrasound examination is established in the acute phase, and the priority sorting of the imaging examination nodes is driven by the real-time attenuation gradient of the hemodynamic parameters to generate a dynamic sequence chain of imaging examinations; then, the time distribution characteristics of the dynamic sequence chain of imaging examinations are injected into the thrombolytic contraindication matrix, the slope of the vascular occlusion rate change is dynamically coupled with the myocardial survival threshold, the catheter room preparation stage, the anticoagulant loading time window and the balloon dilatation operation sequence are introduced to generate a parallel execution framework; finally, in the subacute phase, the operation sequence in the parallel execution framework is spatiotemporally encoded with the blood flow reserve parameters of the enhanced CT scan, and the dynamic phase synchronization rule between the enhanced CT scan time node and the anticoagulant dosage curve is established through the inverse matching of the anticoagulant metabolism rate and the scanning contrast agent clearance curve.

[0052] Here is a specific example: Assuming that a patient is rushed to the hospital due to sudden severe chest pain at night, the system first extracts the evolution characteristics of thrombolytic contraindications and the nonlinear growth curve of vascular occlusion rate based on the intensity distribution of the transition trigger signal, and constructs a two-dimensional constraint matrix; secondly, the system maps the anatomical topological relationship of the coronary artery branches to the gradient change of the probability of reperfusion injury and the spatial axis through the time axis of the matrix; thirdly, according to the gradient change characteristics in the two-dimensional constraint matrix, a dynamic matching rule between the CT angiography time window and the frequency of cardiac ultrasound examination is established in the acute phase, and the priority sorting of the imaging examination nodes is driven by the real-time attenuation gradient of the hemodynamic parameters to generate a dynamic sequence chain of imaging examinations; then, the system The time distribution characteristics of the dynamic sequence chain of imaging examinations were injected into the thrombolysis contraindication matrix, the slope of the vascular occlusion rate change was dynamically coupled with the myocardial survival threshold, the catheterization room preparation stage, the anticoagulant loading time window and the balloon dilation operation sequence were introduced to generate a parallel execution framework; finally, in the subacute period, the system spatiotemporally encoded the operation sequence in the parallel execution framework with the blood flow reserve parameters of the enhanced CT scan, and established a dynamic phase synchronization rule between the enhanced CT scan time node and the anticoagulant dosage curve through the inverse matching of the anticoagulant metabolic rate and the scanning contrast agent clearance curve, which ensured the efficient coordination of each treatment step and significantly improved the treatment effect and survival rate of patients.

[0053] In order to further improve the accuracy of spatiotemporal superposition analysis of the asymmetric growth index and the composite quantitative index, in some embodiments, step 102 performs spatiotemporal superposition analysis on the asymmetric growth index and the composite quantitative index. When it is detected that the spatiotemporal distribution of the two in the coronary artery blood supply area is in a critical coupling state, based on the dynamic matching rules of vascular lesion classification, the three-dimensional characteristic parameters of acute exacerbation probability, compensation failure time window and targeted intervention sensitivity are input to generate a directional risk transition vector, including: introducing a spatiotemporal convolution kernel group, calibrating the spatiotemporal convolution kernel group parameters through dynamic calibration of the branch vessel anatomical diameter, real-time pressure gradient and blood flow reserve fraction in the coronary artery blood supply area, performing multi-scale feature extraction on the asymmetric growth index and the composite quantitative index, and generating a vascular topology weighted spatiotemporal superposition feature tensor; and generating a directional risk transition vector through endothelial shear stress. The dynamic threshold is calculated by the sliding mean of the force waveform and the plaque morphology stability index. The dynamic threshold is adjusted to activate the spatiotemporal superposition feature tensor of the vascular topology weight layer by layer. When it is detected that the feature activation intensity of at least two adjacent vascular segments exceeds the critical threshold of the corresponding branch vascular lesion classification, the spatiotemporal coupling state mark is triggered; the covariance matrix of the lesion calcification density gradient, the fibrous cap thickness attenuation rate and the microcirculation resistance index in the vascular lesion classification parameter library is extracted, and a dynamic matching rule engine is established. Logistic regression is used to calculate the probability of acute exacerbation, and the compensation failure time window is predicted by the Kaplan-Meier modified model. The sensitivity of targeted intervention is evaluated according to the random forest classifier. The probability of acute exacerbation, the compensation failure time window and the targeted intervention sensitivity are three-dimensionally normalized and encoded to generate a directional risk transition vector.

[0054] In this embodiment, the spatiotemporal convolution kernel group is a method for dynamically calibrating the anatomical diameter, real-time pressure gradient and blood flow reserve fraction of the branch vessels in the coronary artery blood supply area, which is used to calibrate the spatiotemporal convolution kernel group parameters, and generate the spatiotemporal superposition feature tensor of the vascular topology weight by performing multi-scale feature extraction on the asymmetric growth index and the composite quantization index, so as to ensure that the key information at different time and space scales can be captured, and improve the accuracy of feature extraction and the ability to understand complex data structures. Dynamic threshold adjustment is a mechanism obtained by calculating the sliding mean of the vascular endothelial shear stress waveform and the plaque morphology stability index, which is used to activate the spatiotemporal superposition feature tensor of the vascular topology weight layer by layer. When the feature activation intensity of at least two adjacent vascular segments exceeds the critical threshold of the corresponding branch vessel lesion classification, the spatiotemporal coupling state mark is triggered to ensure that the potential risk areas are accurately identified at different time points and locations, and intervention measures are taken in time to improve the accuracy of diagnosis and treatment effect. The dynamic matching rule engine is built based on logistic regression, Kaplan-Meier modified model and random forest classifier, and is used to evaluate the probability of acute exacerbation, compensation failure time window and sensitivity of targeted intervention. By extracting the covariance matrix of lesion calcification density gradient, fibrous cap thickness attenuation rate and microcirculatory resistance index in the vascular lesion classification parameter library, a directional risk transition vector is generated to guide clinical decision-making, provide comprehensive risk assessment, and help doctors formulate the best treatment plan to ensure that each step is carried out at the best time. The directional risk transition vector is a comprehensive indicator generated by three-dimensional normalized encoding of the probability of acute exacerbation, compensation failure time window and sensitivity of targeted intervention. The vector is generated based on the dynamic matching rules of vascular lesion classification, guiding clinical decision-making, helping doctors determine the best treatment time and plan, ensuring that patients can receive the most suitable treatment in the shortest time, and improving the overall treatment effect and survival rate.

[0055] In the embodiment of the present application, firstly, a spatiotemporal convolution kernel group is introduced, and the spatiotemporal convolution kernel group parameters are calibrated by dynamically calibrating the anatomical diameter of the branch vessels, the real-time pressure gradient and the blood flow reserve fraction in the coronary artery blood supply area, and multi-scale feature extraction is performed on the asymmetric growth index and the composite quantization index to generate a vascular topology weighted spatiotemporal superposition feature tensor; secondly, a dynamic threshold is obtained by calculating the sliding mean of the vascular endothelial shear stress waveform and the plaque morphology stability index, and the vascular topology weighted spatiotemporal superposition feature tensor is activated layer by layer through the dynamic threshold adjustment, and the feature activation intensity of at least two adjacent vascular segments is detected to exceed When it reaches the critical threshold of branch vascular lesion classification, the spatiotemporal coupling state marker is triggered; secondly, the covariance matrix of lesion calcification density gradient, fibrous cap thickness attenuation rate and microcirculatory resistance index in the vascular lesion classification parameter library is extracted, and a dynamic matching rule engine is established. Logistic regression is used to calculate the probability of acute exacerbation, and the compensation failure time window is predicted by the Kaplan-Meier modified model, and the sensitivity of targeted intervention is evaluated based on the random forest classifier; finally, the probability of acute exacerbation, the compensation failure time window and the sensitivity of targeted intervention are three-dimensionally normalized and encoded to generate a directional risk transition vector to guide clinical decision-making.

[0056] Here is a specific example: Assuming that a patient is sent to the hospital for treatment due to sudden chest pain, the system first introduces the spatiotemporal convolution kernel group, calibrates the spatiotemporal convolution kernel group parameters through dynamic calibration of the branch vessel anatomical diameter, real-time pressure gradient and blood flow reserve fraction in the coronary artery blood supply area, extracts multi-scale features of the asymmetric growth index and the composite quantization index, and generates a vascular topology weighted spatiotemporal superposition feature tensor; secondly, the system obtains a dynamic threshold through the sliding mean calculation of the vascular endothelial shear stress waveform and the plaque morphology stability index, and activates the vascular topology weighted spatiotemporal superposition feature tensor layer by layer through the dynamic threshold adjustment, and detects that the feature activation intensity of at least two adjacent vascular segments exceeds their corresponding The critical threshold of branch vessel lesion classification triggered the spatiotemporal coupling state marker; secondly, the system extracted the covariance matrix of lesion calcification density gradient, fibrous cap thickness attenuation rate and microcirculatory resistance index in the vascular lesion classification parameter library, established a dynamic matching rule engine, calculated the probability of acute exacerbation by logistic regression, predicted the compensation failure time window by the Kaplan-Meier modified model, and evaluated the sensitivity of targeted intervention based on the random forest classifier; finally, the system performed three-dimensional normalized encoding on the probability of acute exacerbation, the compensation failure time window and the sensitivity of targeted intervention, generated a directional risk transition vector, guided the doctors to take emergency measures and successfully avoided the deterioration of the disease.

[0057] In order to further improve the accuracy of the timing dependency of the revascularization surgery by real-time fusion of plaque morphological mutation characteristics of intravascular ultrasound and circulatory assistance parameters of extracorporeal life support equipment, and reconstruct the priority queue of treatment plans and dynamically adjust the timing dependency of revascularization surgery based on the plaque rupture risk threshold and the myocardial oxygen consumption balance equation, in some embodiments, the executable path topology structure described in step 104 is implemented, including: constructing plaque morphological mutation characteristic parameters through intravascular ultrasound image sequences, extracting plaque fiber cap thickness gradient, calcification density distribution and lipid core volume ratio by using a multi-scale convolutional neural network, and generating a plaque morphology-hemodynamic coupling feature vector by combining the arterial pressure waveform and ventricular assist flow parameters collected in real time by the extracorporeal life support equipment; inputting the plaque morphology-hemodynamic coupling feature vector into a plaque rupture risk assessment model based on a random forest classifier, and synchronously calculating myocardial consumption. The product parameters of coronary artery perfusion pressure and ventricular wall tension in the oxygen balance equation, when the plaque rupture risk score exceeds the dynamic threshold and the oxygen consumption balance index deviates from the preset range, activate the revascularization surgery priority calculation channel; establish a weighted association matrix of plaque rupture risk gradient and myocardial oxygen consumption imbalance degree in the revascularization surgery priority calculation channel, use a sliding time window algorithm to dynamically sort the weighted association matrix, and combine the catheter room resource occupancy status and anticoagulant drug metabolic half-life parameters to generate a time window and start-time priority queue; according to the time and space constraint relationship between thrombolysis and interventional operations in the time window and start-time priority queue, establish a surgical timing dependency, predict the myocardial salvage index change curve under different timing combinations in the surgical timing dependency through a recurrent neural network, and select the revascularization scheme corresponding to the maximum slope drop point as the optimal path.

[0058] In this embodiment, the characteristic parameters of plaque morphology mutation are a data set constructed through intravascular ultrasound image sequences, and a multi-scale convolutional neural network is used to extract key features such as plaque fiber cap thickness gradient, calcification density distribution, and lipid core volume ratio; these features are combined with arterial pressure waveforms and ventricular assist flow parameters collected in real time by extracorporeal life support equipment to generate plaque morphology-hemodynamic coupling feature vectors, ensuring that the complex relationship between plaque morphology and hemodynamics can be captured, providing an important basis for subsequent analysis. The plaque rupture risk assessment model is a computational framework based on a random forest classifier, which is used to synchronously calculate the coronary artery perfusion pressure and ventricular wall tension product parameters in the myocardial oxygen consumption balance equation; when the plaque rupture risk score exceeds the dynamic threshold and the oxygen consumption balance index deviates from the preset range, the revascularization surgery priority calculation channel is activated to provide a comprehensive risk assessment and help doctors formulate the best treatment plan. The weighted association matrix is ​​a data structure established in the priority calculation channel of revascularization surgery. The sliding time window algorithm is used to dynamically sort the risk gradient of plaque rupture and the degree of myocardial oxygen consumption imbalance. The matrix combines the resource occupancy status of the catheter room and the metabolic half-life parameters of anticoagulant drugs to generate a time window and a start-time priority queue to ensure that each step is performed at the best time. The surgical sequence dependency is a sequential rule established based on the spatiotemporal constraint relationship between thrombolysis and interventional operations in the time window and start-time priority queue. The recurrent neural network is used to predict the change curve of the myocardial salvage index under different combinations, and the revascularization scheme corresponding to the maximum slope drop point is selected as the optimal path to ensure the best treatment effect in the shortest time.

[0059] In the embodiment of the present application, firstly, the characteristic parameters of plaque morphological mutation are constructed through intravascular ultrasound image sequence, and the plaque fiber cap thickness gradient, calcification density distribution and lipid core volume ratio are extracted by multi-scale convolutional neural network. The plaque morphology-hemodynamic coupling characteristic vector is generated by combining the arterial pressure waveform and ventricular assist flow parameters collected in real time by the extracorporeal life support equipment; secondly, the characteristic vector is input into the plaque rupture risk assessment model based on random forest classifier, and the coronary artery perfusion pressure and ventricular wall tension product parameters in the myocardial oxygen balance equation are calculated synchronously. When the plaque rupture risk score exceeds the dynamic threshold and the oxygen balance index deviates from the preset range, the activation The priority calculation channel for revascularization surgery; secondly, a weighted correlation matrix of plaque rupture risk gradient and myocardial oxygen consumption imbalance degree is established in the priority calculation channel for revascularization surgery, and the weighted correlation matrix is ​​dynamically sorted using a sliding time window algorithm. The time window and start-time priority queue are generated based on the catheterization room resource occupancy status and the metabolic half-life parameters of anticoagulant drugs. Finally, according to the spatiotemporal constraint relationship between thrombolysis and interventional operations in the time window and start-time priority queue, the surgical timing dependency is established, and the myocardial salvage index change curve under different combinations is predicted through a recurrent neural network, and the revascularization scheme corresponding to the maximum slope drop point is selected as the optimal path.

[0060] Here is a specific example: Assuming that the chest pain center of a large hospital receives a patient with severe chest pain at night, the plaque morphology mutation characteristic parameters are first constructed through the intravascular ultrasound image sequence, and the plaque fiber cap thickness gradient, calcification density distribution and lipid core volume ratio are extracted using a multi-scale convolutional neural network. Combined with the arterial pressure waveform and ventricular assist flow parameters collected in real time by the extracorporeal life support equipment, a plaque morphology-hemodynamic coupling characteristic vector is generated; secondly, the characteristic vector is input into the plaque rupture risk assessment model based on the random forest classifier, and the coronary artery perfusion pressure and ventricular wall tension product parameters in the myocardial oxygen balance equation are simultaneously calculated. When the plaque rupture risk score exceeds the dynamic threshold and the oxygen balance index deviates from the preset range, the activation Secondly, a weighted correlation matrix of plaque rupture risk gradient and myocardial oxygen consumption imbalance degree was established in the priority calculation channel for revascularization surgery, and the weighted correlation matrix was dynamically sorted by using a sliding time window algorithm. The time window and start-time priority queue were generated based on the catheterization room resource occupancy status and the metabolic half-life parameters of anticoagulant drugs. Finally, according to the spatiotemporal constraint relationship between thrombolysis and interventional operations in the time window and start-time priority queue, the surgical timing dependency was established, and the myocardial salvage index change curve under different combinations was predicted by a recurrent neural network. The revascularization scheme corresponding to the maximum slope drop point was selected as the optimal path, which significantly improved the treatment effect and survival rate of patients.

[0061] In order to further improve the accuracy of the plaque rupture risk assessment model and dynamically adjust the priority and timing dependency of revascularization surgery, in certain embodiments, step 104 inputs the plaque morphology-hemodynamic coupling feature vector into the plaque rupture risk assessment model based on the random forest classifier, and synchronously calculates the coronary artery perfusion pressure and ventricular wall tension product parameters in the myocardial oxygen consumption balance equation. When the plaque rupture risk score exceeds the dynamic threshold and the oxygen consumption balance index deviates from the preset range, the revascularization surgery priority calculation channel is activated, including: dynamically Bayesian tuning the hyperparameters of the random forest classifier, constructing a feature importance ranking based on the covariance matrix of the plaque fiber cap thickness gradient and the arterial pressure waveform phase difference, screening the interaction terms of the calcification density distribution and the ventricular assist flow parameters as key input features, and generating a plaque rupture risk score dynamic threshold curve; synchronously calculating the coronary artery perfusion pressure based on the plaque rupture risk score dynamic threshold curve. The product parameter of ventricular pressure and ventricular wall tension is extracted by a sliding time window algorithm, and the fluctuation amplitude and baseline offset of the product parameter are extracted. A two-dimensional deviation index is established in combination with the dynamic threshold curve of the plaque rupture risk score. When the two-dimensional deviation index exceeds the preset warning line for three consecutive times, the activation instruction of the revascularization surgery priority calculation channel is triggered; in the priority calculation channel of the revascularization surgery priority calculation channel activation instruction, a spatiotemporal correlation matrix of the plaque rupture risk gradient and the degree of myocardial oxygen consumption imbalance is constructed, and a dynamic weighted algorithm is used to fuse the catheter room resource occupancy state parameters and the anticoagulant drug metabolic half-life attenuation curve to generate a dynamic decision map; the interventional surgery start time in the dynamic decision map is input into a recurrent neural network for timing conflict detection, the optimal interventional path is screened by a myocardial salvage index prediction model, and the plaque morphology mutation characteristic parameters and circulatory auxiliary parameters during the path execution are fed back to the rupture risk assessment model for incremental learning and updating.

[0062] In this embodiment, the dynamic threshold curve of the plaque rupture risk score is a data structure generated by dynamically Bayesian tuning the hyperparameters of the random forest classifier. The feature importance ranking is constructed based on the covariance matrix of the plaque fiber cap thickness gradient and the phase difference of the arterial pressure waveform, and the interaction term of the calcification density distribution and the ventricular assist flow parameter is screened as the key input feature; the curve is used to generate the dynamic threshold of the plaque rupture risk score to ensure that potential risk areas can be accurately identified and intervention measures can be taken in time. The two-dimensional deviation index is based on the dynamic threshold curve of the plaque rupture risk score. The coronary artery perfusion pressure and ventricular wall tension product parameters are synchronously calculated, and the fluctuation amplitude and baseline offset of the product parameters are extracted by the sliding time window algorithm. The dynamic threshold curve of the plaque rupture risk score is combined to establish a data indicator; when the two-dimensional deviation index exceeds the preset warning line three times in a row, the activation instruction of the revascularization surgery priority calculation channel is triggered to ensure accurate identification of potential risk areas at different times and locations. The spatiotemporal association matrix is ​​a data structure constructed in the revascularization surgery priority calculation channel. It uses a dynamic weighted algorithm to fuse the catheter room resource occupancy state parameters and the anticoagulant drug metabolic half-life attenuation curve to generate a dynamic decision map. This matrix ensures that each step is performed at the best time and optimizes the diagnosis and treatment path. Recurrent neural network timing conflict detection is a detection method that inputs the interventional surgery start time in the dynamic decision map into the recurrent neural network. The optimal intervention path is selected through the myocardial salvage index prediction model, and the plaque morphology mutation characteristic parameters and circulation auxiliary parameters during the path execution process are fed back to the rupture risk assessment model for incremental learning and updating, ensuring that the system can continuously improve and optimize the treatment plan.

[0063] In the embodiment of the present application, firstly, the hyperparameters of the random forest classifier are dynamically Bayesian tuned, and the feature importance ranking is constructed based on the covariance matrix of the plaque fiber cap thickness gradient and the phase difference of the arterial pressure waveform, and the interaction terms of the calcification density distribution and the ventricular assist flow parameters are screened as key input features to generate a dynamic threshold curve for the plaque rupture risk score; secondly, based on the curve, the product parameters of the coronary artery perfusion pressure and the ventricular wall tension are synchronously calculated, and the fluctuation amplitude and baseline offset of the product parameters are extracted through the sliding time window algorithm. Combined with the dynamic threshold curve of the plaque rupture risk score, a two-dimensional deviation index is established. When the two-dimensional deviation index exceeds the preset warning level three times in a row, the two-dimensional deviation index is automatically generated. The activation instruction of the revascularization surgery priority calculation channel is triggered when the line is on; secondly, the spatiotemporal correlation matrix of the plaque rupture risk gradient and the degree of myocardial oxygen consumption imbalance is constructed in the revascularization surgery priority calculation channel, and the dynamic weighted algorithm is used to fuse the catheterization room resource occupancy state parameters and the anticoagulant drug metabolic half-life attenuation curve to generate a dynamic decision map; finally, the interventional surgery start time in the dynamic decision map is input into the recurrent neural network for timing conflict detection, the optimal interventional path is selected through the myocardial salvage index prediction model, and the plaque morphology mutation characteristic parameters and circulation auxiliary parameters during the path execution are fed back to the rupture risk assessment model for incremental learning and updating.

[0064] Here is a specific example: Assuming that a patient was rushed to the emergency center for treatment due to severe chest pain, we first performed dynamic Bayesian optimization on the hyperparameters of the random forest classifier, constructed a feature importance ranking based on the covariance matrix of the plaque fiber cap thickness gradient and the phase difference of the arterial pressure waveform, screened the interaction terms of the calcification density distribution and the ventricular assist flow parameters as key input features, and generated a dynamic threshold curve for the plaque rupture risk score. Secondly, based on this curve, we simultaneously calculated the product parameters of the coronary artery perfusion pressure and ventricular wall tension, extracted the fluctuation amplitude and baseline offset of the product parameters through the sliding time window algorithm, and established a two-dimensional deviation index in combination with the dynamic threshold curve of the plaque rupture risk score. When the two-dimensional deviation index exceeded the preset warning line three times in a row, , triggering the activation instruction of the revascularization surgery priority calculation channel; secondly, a spatiotemporal correlation matrix of plaque rupture risk gradient and myocardial oxygen consumption imbalance degree was constructed in the revascularization surgery priority calculation channel, and a dynamic weighted algorithm was used to fuse the catheterization room resource occupancy state parameters and the anticoagulant drug metabolic half-life attenuation curve to generate a dynamic decision map; finally, the interventional surgery start time in the dynamic decision map was input into the recurrent neural network for timing conflict detection, and the optimal interventional path was selected through the myocardial salvage index prediction model, and the plaque morphology mutation characteristic parameters and circulation auxiliary parameters during the path execution were fed back to the rupture risk assessment model for incremental learning and updating, which significantly improved the treatment effect and survival rate of patients.

[0065] In order to further improve the accuracy of spatiotemporal superposition analysis of interventional treatment delay parameters and dual antiplatelet drug metabolic curves, and generate a causal association map to optimize the clinical diagnosis and treatment pathway, in certain embodiments, step 105 describes spatiotemporal superposition of the interventional treatment delay parameters and the dual antiplatelet drug metabolic curve according to the temporal dependency relationship to generate a causal association map, and reversely map the catheter room activation delay and drug onset verification results in the causal association map to the weight reinforcement model of the clinical decision baseline framework, drive the self-optimization update of the path topology structure, and construct a clinical diagnosis and treatment pathway generation strategy, including: using time series alignment to fuse the interventional treatment delay parameters and the dual antiplatelet drug metabolic curve, extracting the drug concentration attenuation gradient and the catheter room preparation time through the sliding time window in the time series alignment process phase difference parameters to generate a spatiotemporal superposition feature matrix; a causal association map is constructed based on a Bayesian network, and the delay parameters and the slope of the drug metabolism curve in the spatiotemporal superposition feature matrix are used as map nodes, and the causal relationship map of coronary blood flow recovery rate and platelet inhibition rate is identified by dynamic directed edge weights; the catheter room activation delay parameters and the drug onset verification results in the causal association map are input into the random forest regression model, and the dynamic adjustment coefficient of the weight reinforcement model in the clinical decision baseline framework is calculated, and the association weight of the coronary artery calcification score and the slope of the high-sensitivity troponin curve is updated through the gradient descent model; a path topology structure self-optimization model is constructed using a deep reinforcement learning framework, and the association weight is dynamically coupled with the real-time intravascular ultrasound plaque morphology parameters to generate a clinical diagnosis and treatment pathway generation strategy.

[0066] In this embodiment, the spatiotemporal superposition feature matrix is ​​a data structure generated by aligning and fusing the interventional treatment delay parameter and the dual antiplatelet drug metabolism curve through time series, and the sliding time window is used to extract the phase difference parameter between the drug concentration attenuation gradient and the catheter room preparation time; the matrix can capture the complex relationship between drug metabolism and catheter room preparation time, providing an important basis for subsequent analysis. The causal association map is constructed based on the Bayesian network, and the delay parameters and the slope of the drug metabolism curve in the spatiotemporal superposition feature matrix are used as map nodes, and the causal relationship between the coronary blood flow recovery rate and the platelet inhibition rate is identified through dynamic directed edge weights; this map helps to identify the mutual influence between different factors and guide clinical decision-making. The dynamic adjustment coefficient is to calculate the dynamic adjustment coefficient of the weight reinforcement model in the clinical decision baseline framework through the random forest regression model, and update the association weight of the coronary artery calcification score and the slope of the high-sensitivity troponin curve through the gradient descent model; this method ensures that potential risk areas can be accurately identified at different times and locations and intervention measures can be taken in a timely manner. The pathway topology self-optimization model is constructed using a deep reinforcement learning framework, which dynamically couples the association weights with real-time intravascular ultrasound plaque morphology parameters to generate a clinical diagnosis and treatment pathway generation strategy. The model can achieve seamless connection between multiple treatment steps, ensuring that each step is performed at the best time, thereby improving the overall treatment effect.

[0067] In an embodiment of the present application, firstly, time series alignment is used to fuse the interventional treatment delay parameter and the dual antiplatelet drug metabolism curve, and the phase difference parameter between the drug concentration attenuation gradient and the catheter room preparation time is extracted through the sliding time window in the time series alignment process to generate a spatiotemporal superposition feature matrix; secondly, a causal association map is constructed based on a Bayesian network, and the delay parameters and the slope of the drug metabolism curve in the spatiotemporal superposition feature matrix are used as map nodes, and the causal relationship between the coronary blood flow recovery rate and the platelet inhibition rate is identified through dynamic directed edge weights; thirdly, the catheter room activation delay parameters and the drug onset verification results in the causal association map are input into a random forest regression model, and the dynamic adjustment coefficient of the weight reinforcement model in the clinical decision baseline framework is calculated, and the association weight between the coronary artery calcification score and the slope of the high-sensitivity troponin curve is updated through the gradient descent model; finally, a path topology structure self-optimization model is constructed using a deep reinforcement learning framework, and the association weights are dynamically coupled with real-time intravascular ultrasound plaque morphology parameters to generate a clinical diagnosis and treatment path generation strategy.

[0068] Here is a specific example: Assuming that a patient is admitted to the hospital due to persistent chest tightness and palpitations, the system first uses time series alignment to fuse the interventional treatment delay parameters and the dual antiplatelet drug metabolism curve, and extracts the phase difference parameters of the drug concentration attenuation gradient and the catheterization room preparation time through the sliding time window in the time series alignment process, and generates a spatiotemporal superposition feature matrix; secondly, the system constructs a causal association graph based on the Bayesian network, uses the delay parameters and the slope of the drug metabolism curve in the spatiotemporal superposition feature matrix as graph nodes, and identifies the causal relationship between the coronary blood flow recovery rate and the platelet inhibition rate through dynamic directed edge weights. ; Secondly, the system input the catheterization laboratory activation delay parameters and drug onset verification results in the causal association map into the random forest regression model, calculated the dynamic adjustment coefficient of the weight reinforcement model in the clinical decision baseline framework, and updated the association weights of the coronary artery calcification score and the slope of the high-sensitivity troponin curve through the gradient descent model; finally, the system used a deep reinforcement learning framework to construct a path topology structure self-optimization model, dynamically coupled the association weights with real-time intravascular ultrasound plaque morphology parameters, and generated a clinical diagnosis and treatment pathway generation strategy, which significantly improved the treatment effect and survival rate of patients.

[0069] Figure 2 A schematic diagram of a clinical diagnosis and treatment pathway generation system for tracking chest pain patients is provided in an embodiment of the present application. Figure 2 As shown, the device comprises: The acquisition module 21 is used to establish a spatiotemporal data map with dynamic priority marking by synchronously acquiring the respiratory rhythm phase difference, coronary artery calcification score and high-sensitivity troponin curve slope within a preset time after the onset of chest pain, and to perform incremental weight enhancement on the change rate of key indicators in the spatiotemporal data map to generate a clinical decision baseline framework; The identification module 22 is used to identify the spatiotemporal correlation pattern between the myocardial ischemic area and the abnormal electrocardiogram lead based on the spatiotemporal data map, and when the asymmetric increase of the ST segment elevation amplitude is continuously detected, activate the coupling analysis linked with the left ventricular ejection fraction attenuation gradient and the B-type natriuretic peptide release rate to generate a risk transition signal driving the diagnosis and treatment path; A construction module 23 is used to dynamically bind blood vessels, the time-space constraint relationship between the recanalization time window and the thrombolytic contraindications in the acute phase of the intensity distribution according to the intensity distribution of the risk transition signal driving the diagnosis and treatment pathway, and to construct an executable pathway topology structure. At the same time, in the subacute phase of the intensity distribution, a dynamic phase synchronization rule between the enhanced CT scan time node and the anticoagulant drug dosage curve is established through a multidisciplinary parameter negotiation interface; A fusion module 24 is used for, during the implementation of the executable path topology structure, real-time fusion of plaque morphological mutation characteristics of intravascular ultrasound and circulatory auxiliary parameters of extracorporeal life support equipment, and based on the plaque rupture risk threshold and myocardial oxygen consumption balance equation, reconstructing the priority queue of treatment plans and dynamically adjusting the timing dependency of revascularization surgery; The mapping module 25 is used to perform spatiotemporal superposition of the interventional treatment delay parameters and the dual antiplatelet drug metabolism curve according to the timing dependency to generate a causal association map, and reversely map the catheterization room activation delay and drug onset verification results in the causal association map to the weight reinforcement model of the clinical decision baseline framework, drive the self-optimization update of the path topology structure, and construct a clinical diagnosis and treatment path generation strategy.

[0070] Figure 2 The clinical diagnosis and treatment pathway generation system for tracking chest pain patients can be performed Figure 1 The implementation principle and technical effect of the method for generating a clinical diagnosis and treatment pathway for tracking chest pain patients described in the illustrated embodiment will not be repeated. The specific manner in which each module and unit performs operations in the above-mentioned embodiment of a clinical diagnosis and treatment pathway generation system for tracking chest pain patients has been described in detail in the embodiment of the method, and will not be elaborated here.

[0071] In one possible design, Figure 2 A clinical diagnosis and treatment pathway generation system for tracking chest pain patients in the illustrated embodiment can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0072] The processing component 32 is used to: establish a spatiotemporal data map with dynamic priority markings by synchronously collecting respiratory rhythm phase difference, coronary artery calcification score and high-sensitivity troponin curve slope within a preset time after the onset of chest pain, and implement incremental weight reinforcement on the change rate of key indicators in the spatiotemporal data map to generate a clinical decision baseline framework; based on the spatiotemporal data map, identify the spatiotemporal correlation pattern between the myocardial ischemic area and the abnormal electrocardiogram lead, and when the asymmetric increase of the ST segment elevation amplitude is continuously detected, activate the coupling analysis linked with the left ventricular ejection fraction attenuation gradient and the B-type natriuretic peptide release rate to generate a driving diagnosis and treatment path risk transition signal; according to the intensity distribution of the driving diagnosis and treatment path risk transition signal, dynamically bind the blood vessels in the acute phase of the intensity distribution, and construct an executable path topology based on the time-space constraint relationship between the recanalization time window and the thrombolytic contraindications. The structure of the flutter is established, and at the same time, in the subacute period of the intensity distribution, the dynamic phase synchronization rules of the enhanced CT scanning time node and the anticoagulant drug dosage curve are established through the multidisciplinary parameter negotiation interface; during the implementation of the executable path topology structure, the plaque morphological mutation characteristics of intravascular ultrasound and the circulatory auxiliary parameters of the extracorporeal life support equipment are integrated in real time, and based on the plaque rupture risk threshold and the myocardial oxygen consumption balance equation, the priority queue of the treatment plan is reconstructed and the timing dependency of the revascularization surgery is dynamically adjusted; the interventional treatment delay parameter and the dual antiplatelet drug metabolism curve are superimposed in time and space according to the timing dependency to generate a causal association map, and the catheter room activation delay and drug onset verification results in the causal association map are reversely mapped to the weight reinforcement model of the clinical decision baseline framework, driving the path topology structure to self-optimize and update, and construct a clinical diagnosis and treatment path generation strategy.

[0073] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. 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.

[0074] The storage component 31 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.

[0075] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0076] 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.

[0077] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0078] 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.

[0079] 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 illustrated embodiment is a method for generating a clinical diagnosis and treatment pathway for tracking chest pain patients.

[0080] 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.

[0081] 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.

[0082] 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.

[0083] 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 a clinical diagnosis and treatment pathway for tracking chest pain patients, characterized in that: include: By synchronously collecting the respiratory rhythm phase difference, coronary artery calcification score and high-sensitivity troponin curve slope within a preset time after the onset of chest pain, a spatiotemporal data map with dynamic priority marking is established, and incremental weight enhancement is implemented on the change rate of key indicators in the spatiotemporal data map to generate a clinical decision baseline framework; Based on the spatiotemporal data atlas, the spatiotemporal correlation pattern between the myocardial ischemic area and the abnormal electrocardiogram lead is identified, and when the asymmetric increase of the ST segment elevation amplitude is continuously detected, the coupling analysis linked with the left ventricular ejection fraction attenuation gradient and the B-type natriuretic peptide release rate is activated to generate a risk transition signal driving the diagnosis and treatment pathway; According to the intensity distribution of the risk transition signal driving the diagnosis and treatment pathway, the blood vessels are dynamically bound in the acute phase of the intensity distribution, and the time-space constraint relationship between the recanalization time window and the thrombolytic contraindications is constructed to construct an executable pathway topology structure. At the same time, in the subacute phase of the intensity distribution, a dynamic phase synchronization rule between the enhanced CT scan time node and the anticoagulant drug dosage curve is established through a multidisciplinary parameter negotiation interface; During the implementation of the executable path topology structure, the plaque morphological mutation characteristics of intravascular ultrasound and the circulatory auxiliary parameters of the extracorporeal life support device are integrated in real time, and based on the plaque rupture risk threshold and the myocardial oxygen consumption balance equation, the priority queue of the treatment plan is reconstructed and the timing dependency of the revascularization surgery is dynamically adjusted; The interventional treatment delay parameters and the dual antiplatelet drug metabolism curve are spatiotemporally superimposed according to the timing dependency to generate a causal association map, and the catheterization room activation delay and drug onset verification results in the causal association map are reversely mapped to the weight reinforcement model of the clinical decision baseline framework to drive the self-optimization update of the path topology structure and construct a clinical diagnosis and treatment pathway generation strategy.

2. The method according to claim 1, characterized in that Based on the spatiotemporal data map, the spatiotemporal correlation pattern between the myocardial ischemic area and the abnormal electrocardiogram lead is identified. When the asymmetric increase of the ST segment elevation amplitude is continuously detected, the coupling analysis linked with the left ventricular ejection fraction attenuation gradient and the B-type natriuretic peptide release rate is activated to generate a risk transition signal driving the diagnosis and treatment path, including: Performing three-dimensional spatiotemporal positioning of the myocardial ischemic area in the spatiotemporal data atlas, extracting abnormal fluctuation phase characteristics of each lead channel, and establishing a dynamic propagation relationship model by aligning the multimodal signals in the abnormal fluctuation phase characteristics in time series; A dynamic sliding monitoring window is constructed for the dynamic propagation relationship model, the ST segment elevation amplitude is waveform decomposed, the peak characteristics, slope change rate and spatial lead distribution heterogeneity parameters are extracted, and when the asymmetric growth index is detected to exceed the dynamic adjustment threshold in three consecutive windows, the cardiac function compensation reserve analysis channel is activated; The spatiotemporal variation trajectory of the left ventricular ejection fraction attenuation gradient and the fluctuation characteristics of the B-type natriuretic peptide release rate in the cardiac function compensation reserve analysis channel are synchronously obtained, and a dynamic weight model of the ejection fraction change rate and the B-type natriuretic peptide release rate is established through a multi-source data coupling engine of electrocardiography, ultrasound, and biomarkers to calculate a composite quantitative index; The asymmetric growth index and the composite quantitative index are subjected to spatiotemporal superposition analysis. When it is detected that the spatiotemporal distribution of the two in the coronary artery blood supply area presents a critical coupling state, a directional risk transition vector is generated by inputting three-dimensional characteristic parameters of acute exacerbation probability, compensation failure time window and targeted intervention sensitivity based on the dynamic matching rule of vascular lesion classification; The three-dimensional feature parameters are subjected to multi-level cross-validation. When the probability of acute exacerbation in the multi-level cross-validation process exceeds the standard deviation range of the preset baseline value and the compensation failure time window overlaps with the current diagnosis and treatment stage, the target coordinates and path switching time constraints are preferentially intervened to generate a risk transition signal for driving the switching of the diagnosis and treatment path.

3. The method according to claim 1, characterized in that: According to the intensity distribution of the risk transition signal driving the diagnosis and treatment pathway, the blood vessels are dynamically bound in the acute phase of the intensity distribution, and the time-space constraint relationship between the recanalization time window and the thrombolytic contraindications is constructed to construct an executable path topology structure. At the same time, in the subacute phase of the intensity distribution, a dynamic phase synchronization rule between the enhanced CT scan time node and the anticoagulant drug dosage curve is established through a multidisciplinary parameter negotiation interface, including: Extracting the evolution characteristics of thrombolytic contraindications and the nonlinear growth curve of vascular occlusion rate based on the intensity distribution of the transition trigger signal, constructing a two-dimensional constraint matrix, mapping the gradient change of reperfusion injury probability through the time axis of the two-dimensional constraint matrix, and associating the anatomical topological relationship of coronary artery branches through the spatial axis of the two-dimensional constraint matrix; According to the gradient change characteristics in the two-dimensional constraint matrix, a dynamic matching rule between the CT angiography time window and the cardiac ultrasound examination frequency is established in the acute phase, and the priority sorting of the imaging examination nodes is driven by the real-time attenuation gradient of the hemodynamic parameters of the dynamic matching rule to generate a dynamic sequence chain of imaging examinations; The time distribution characteristics of the dynamic sequence chain of imaging examinations are injected into the thrombolysis contraindication matrix, the slope of the change of vascular occlusion rate in the thrombolysis contraindication matrix is ​​dynamically coupled with the myocardial survival threshold, and the catheterization room preparation stage, anticoagulant drug loading time window and balloon dilation operation sequence are introduced to generate a parallel execution framework; In the subacute phase, the operation sequence in the parallel execution framework is spatiotemporally encoded with the blood flow reserve parameters of the enhanced CT scan, and the dynamic phase synchronization rules of the enhanced CT scan time node and the anticoagulant drug dosage curve are established by inverse matching the anticoagulant drug metabolism rate with the scanning contrast agent clearance curve.

4. The method according to claim 2, characterized in that: The asymmetric growth index and the composite quantitative index are subjected to a spatiotemporal superposition analysis. When it is detected that the spatiotemporal distribution of the two in the coronary artery blood supply area presents a critical coupling state, based on the dynamic matching rule of vascular lesion classification, the three-dimensional characteristic parameters of acute exacerbation probability, compensation failure time window and targeted intervention sensitivity are input to generate a directional risk transition vector, including: A spatiotemporal convolution kernel group is introduced, and the spatiotemporal convolution kernel group parameters are calibrated through dynamic calibration of the branch vessel anatomical diameter, real-time pressure gradient and blood flow reserve fraction in the coronary artery blood supply area, and multi-scale feature extraction is performed on the asymmetric growth index and the composite quantitative index to generate a vascular topology weighted spatiotemporal superposition feature tensor; A dynamic threshold is obtained by calculating the sliding mean of the vascular endothelial shear stress waveform and the plaque morphology stability index, and the vascular topology weight spatiotemporal superposition feature tensor is activated layer by layer through the dynamic threshold adjustment. When the feature activation intensity of at least two adjacent vascular segments exceeds the critical threshold of the corresponding branch vascular lesion classification, the spatiotemporal coupling state mark is triggered; The covariance matrix of lesion calcification density gradient, fibrous cap thickness attenuation rate and microcirculatory resistance index in the vascular lesion classification parameter library was extracted, and a dynamic matching rule engine was established. Logistic regression was used to calculate the probability of acute exacerbation, and the compensation failure time window was predicted by the Kaplan-Meier modified model. The sensitivity of targeted intervention was evaluated based on the random forest classifier. The probability of acute exacerbation, the compensation failure time window and the targeted intervention sensitivity were three-dimensionally normalized and encoded to generate a directional risk transition vector.

5. The method according to claim 1, characterized in that During the implementation of the executable path topology structure, the plaque morphological mutation characteristics of intravascular ultrasound and the circulatory auxiliary parameters of the extracorporeal life support device are integrated in real time, and based on the plaque rupture risk threshold and the myocardial oxygen consumption balance equation, the priority queue of the treatment plan is reconstructed and the timing dependency of the revascularization surgery is dynamically adjusted, including: The characteristic parameters of plaque morphological mutation were constructed through intravascular ultrasound image sequences, and the thickness gradient of plaque fiber cap, calcification density distribution and lipid core volume ratio were extracted using a multi-scale convolutional neural network. The plaque morphology-hemodynamic coupling characteristic vector was generated by combining the arterial pressure waveform and ventricular assist flow parameters collected in real time by extracorporeal life support equipment. The plaque morphology-hemodynamic coupling feature vector is input into a plaque rupture risk assessment model based on a random forest classifier, and the coronary artery perfusion pressure and ventricular wall tension product parameters in the myocardial oxygen consumption balance equation are simultaneously calculated. When the plaque rupture risk score exceeds the dynamic threshold and the oxygen consumption balance index deviates from the preset range, the revascularization surgery priority calculation channel is activated; A weighted correlation matrix of plaque rupture risk gradient and myocardial oxygen consumption imbalance degree is established in the revascularization surgery priority calculation channel, the weighted correlation matrix is ​​dynamically sorted using a sliding time window algorithm, and a time window and a start time priority queue are generated by combining the catheterization room resource occupancy status and the anticoagulant drug metabolic half-life parameters; According to the spatiotemporal constraint relationship between thrombolysis and interventional operations in the time window and the priority queue of the start time, a surgical timing dependency relationship is established, and the myocardial salvage index change curve under different timing combinations in the surgical timing dependency relationship is predicted by a recurrent neural network, and the revascularization scheme corresponding to the maximum slope drop point is selected as the optimal path.

6. The method according to claim 5, characterized in that The plaque morphology-hemodynamic coupling feature vector is input into a plaque rupture risk assessment model based on a random forest classifier, and the coronary artery perfusion pressure and ventricular wall tension product parameters in the myocardial oxygen consumption balance equation are simultaneously calculated. When the plaque rupture risk score exceeds a dynamic threshold and the oxygen consumption balance index deviates from a preset range, a revascularization surgery priority calculation channel is activated, including: Dynamic Bayesian optimization was performed on the hyperparameters of the random forest classifier. The feature importance ranking was constructed based on the covariance matrix of the plaque fiber cap thickness gradient and the phase difference of the arterial pressure waveform. The interaction terms of calcification density distribution and ventricular assist flow parameters were selected as key input features to generate a dynamic threshold curve for plaque rupture risk score. Based on the dynamic threshold curve of the plaque rupture risk score, the product parameter of the coronary artery perfusion pressure and the ventricular wall tension is synchronously calculated, the fluctuation amplitude and the baseline offset of the product parameter are extracted by a sliding time window algorithm, and a two-dimensional deviation index is established in combination with the dynamic threshold curve of the plaque rupture risk score. When the two-dimensional deviation index exceeds the preset warning line for three consecutive times, a revascularization surgery priority calculation channel activation instruction is triggered; In the priority calculation channel of the revascularization surgery priority calculation channel activation instruction, a spatiotemporal correlation matrix of the plaque rupture risk gradient and the degree of myocardial oxygen consumption imbalance is constructed, and a dynamic weighted algorithm is used to fuse the catheter room resource occupancy state parameters and the anticoagulant drug metabolic half-life attenuation curve to generate a dynamic decision map; The interventional surgery start time in the dynamic decision map is input into the recurrent neural network for timing conflict detection, the optimal intervention path is screened through the myocardial salvage index prediction model, and the plaque morphology mutation characteristic parameters and circulation auxiliary parameters during the path execution process are fed back to the rupture risk assessment model for incremental learning and updating.

7. The method according to claim 1, characterized in that The interventional treatment delay parameter and the dual antiplatelet drug metabolism curve are temporally and spatially superimposed according to the temporal dependency relationship to generate a causal association map, and the catheterization room activation delay and drug onset verification results in the causal association map are reversely mapped to the weight reinforcement model of the clinical decision baseline framework to drive the self-optimization update of the path topology structure and construct a clinical diagnosis and treatment path generation strategy, including: Time series alignment was used to fuse the interventional treatment delay parameters and dual antiplatelet drug metabolism curves. The phase difference parameters of drug concentration attenuation gradient and catheterization room preparation time were extracted through the sliding time window in the time series alignment process to generate a spatiotemporal superposition feature matrix. Constructing a causal association map based on a Bayesian network, taking the delay parameters and the slope of the drug metabolism curve in the spatiotemporal superposition feature matrix as map nodes, and identifying the causal relationship map between the coronary blood flow recovery rate and the platelet inhibition rate through dynamic directed edge weights; Inputting the catheterization room activation delay parameter and the drug onset verification result in the causal association map into the random forest regression model, calculating the dynamic adjustment coefficient of the weight enhancement model in the clinical decision baseline framework, and updating the association weight of the coronary artery calcification score and the slope of the high-sensitivity troponin curve through the gradient descent model; A deep reinforcement learning framework was used to construct a path topology self-optimization model, and the association weights were dynamically coupled with real-time intravascular ultrasound plaque morphology parameters to generate a clinical diagnosis and treatment pathway generation strategy.

8. A clinical diagnosis and treatment pathway generation system for tracking chest pain patients, characterized in that: include: An acquisition module is used to establish a spatiotemporal data map with dynamic priority markings by synchronously acquiring respiratory rhythm phase difference, coronary artery calcification score and high-sensitivity troponin curve slope within a preset time after the onset of chest pain, and to implement incremental weight enhancement on the change rate of key indicators in the spatiotemporal data map to generate a clinical decision baseline framework; An identification module is used to identify the spatiotemporal correlation pattern between the myocardial ischemic area and the abnormal electrocardiogram lead based on the spatiotemporal data map, and when the asymmetric increase of the ST segment elevation amplitude is continuously detected, activate the coupling analysis linked with the left ventricular ejection fraction attenuation gradient and the B-type natriuretic peptide release rate to generate a risk transition signal driving the diagnosis and treatment path; A construction module is used to dynamically bind blood vessels, the time-space constraint relationship between the recanalization time window and the contraindications of thrombolysis in the acute phase of the intensity distribution according to the intensity distribution of the risk transition signal driving the diagnosis and treatment pathway, and to construct an executable pathway topology structure. At the same time, in the subacute phase of the intensity distribution, a dynamic phase synchronization rule between the enhanced CT scanning time node and the anticoagulant drug dosage curve is established through a multidisciplinary parameter negotiation interface; A fusion module, used for real-time fusion of plaque morphological mutation characteristics of intravascular ultrasound and circulatory auxiliary parameters of extracorporeal life support equipment during the implementation of the executable path topology structure, and reconstructing the priority queue of treatment plans and dynamically adjusting the timing dependency of revascularization surgery based on the plaque rupture risk threshold and the myocardial oxygen consumption balance equation; A mapping module is used to perform spatiotemporal superposition of interventional treatment delay parameters and dual antiplatelet drug metabolism curves according to the timing dependency to generate a causal association map, and reversely map the catheterization room activation delay and drug onset verification results in the causal association map to the weighted reinforcement model of the clinical decision baseline framework, drive the self-optimization update of the path topology structure, and construct a clinical diagnosis and treatment path generation strategy.

9. A computing device, 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 a clinical diagnosis and treatment pathway generation method for tracking chest pain patients as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a method for generating a clinical diagnosis and treatment pathway for tracking chest pain patients as described in any one of claims 1 to 7 is implemented.

Images