Dynamic toughness evaluation and early warning method and system for cardiovascular and metabolic diseases

Abstract

The invention provides a dynamic toughness evaluation and early warning method and system for cardiovascular and metabolic diseases. The method comprises the following steps: collecting continuous cardiovascular-metabolism time sequence data, and extracting phase delay parameters to construct a lipid transport rhythm out-of-synchronization characteristic spectrum; quantifying the topological connection strength of the gene cluster based on the three-dimensional genome interaction strength matrix, and generating a genetic prediction model; a vascular endothelial metabolism buffer attenuation trajectory is calculated through simulation, and a critical environment exposure parameter is determined by matching a genetic instability threshold value; and fusing multi-source data to construct a dynamic toughness model, calculating a phase space shrinkage rate of a vascular metabolism steady-state boundary, and triggering graded early warning. According to the technical scheme provided by the invention, ultra-early warning of cardiovascular metabolism risks is realized, and the individual intervention target spot recognition precision is improved.

Description

Technical Field

[0001] This application relates to the technical field of disease risk early warning, and particularly to a method and system for dynamic resilience assessment and early warning of cardiovascular and metabolic diseases. Background Art

[0002] With the increasing demand for analyzing the dynamic coupling mechanism of cardiovascular and metabolic diseases in precision medicine, there is an urgent need in clinical practice to construct a multi-modal assessment system that integrates lipoprotein oscillation rhythm monitoring, topological connection strength analysis of metabolic sensing pathways, and endothelial metabolic buffer capacity simulation, so as to break through the spatio-temporal limitations of traditional static models.

[0003] In existing solutions, mainstream risk assessment relies on static indicators such as blood pressure and cholesterol, and cannot capture the rhythm desynchronization caused by the phase delay of metabolic substrate supply; moreover, although new artificial intelligence models introduce machine learning algorithms, they lack a dynamic matching mechanism for the vascular shear stress gradient field and the genetic instability threshold, resulting in significant cross-scenario adaptation errors, thus causing poor early warning effects for cardiovascular and metabolic risks and low accuracy in identifying individualized intervention targets. Summary of the Invention

[0004] Embodiments of this application provide a method and system for dynamic resilience assessment and early warning of cardiovascular and metabolic diseases, so as to solve the problem of poor early warning effects for cardiovascular and metabolic risks in the prior art.

[0005] In a first aspect, embodiments of this application provide a method for dynamic resilience assessment and early warning of cardiovascular and metabolic diseases, including:

[0006] Extract the phase delay parameter between the cardiovascular elastic chamber and the metabolic substrate supply from the coupled data of cardiovascular and metabolic in the continuous time series of the obtained target object, so as to construct a multi-modal oscillation feature spectrum including lipid transport rhythm desynchronization indicators;

[0007] Based on genomic data, identify the topological connection strength of the vascular tone regulation gene cluster and the metabolic sensing pathway gene cluster, and combine the phase delay parameters in the multi-modal oscillation feature spectrum to quantify the influence weight of genetic variation on the coupling efficiency of the coupled data, so as to generate a genetic prediction model;

[0008] According to the local shear stress distribution of the blood vessels of the target object and the environmental oxidative load parameters, simulate and calculate the attenuation trajectory function of the vascular endothelial metabolic buffer capacity, and analyze the dynamic matching degree matrix between the attenuation trajectory function and the instability threshold in the genetic prediction model, so as to determine the critical environmental exposure parameter combination;

[0009] Integrate the lipid transport rhythm desynchronization index, the instability threshold, and the critical environmental exposure parameter combination to construct a dynamic resilience assessment model, calculate the phase space contraction rate of the vascular metabolic homeostasis boundary, and generate a hierarchical warning signal when the phase space contraction rate exceeds the vascular wall remodeling compensation ability.

[0010] Optionally, the simulation calculation of the decay trajectory function of the vascular endothelial metabolic buffer capacity according to the local shear stress distribution of the blood vessels and the environmental oxidation load parameters of the target object includes:

[0011] Based on the three-dimensional stress distribution map of the vascular wall of the target object, extract the local shear stress distribution of the target vascular bifurcation segment, construct a dynamic response model in combination with the monitoring data of endothelial cell metabolic flux, calculate the phase lag amount of lipid transport efficiency to shear stress fluctuations through frequency domain coupling analysis, and generate a metabolic delay characteristic map at the vascular bifurcation;

[0012] According to the spatio-temporal distribution of the environmental oxidation load parameters, establish an oxidative stress wave propagation equation to solve the concentration standing wave formation threshold of the metabolic buffer medium at the vascular bifurcation through the oxidative stress wave propagation equation, and the concentration standing wave formation threshold is used to calibrate the dynamic response boundary of the endothelial metabolic buffer capacity;

[0013] Input the metabolic delay characteristic map at the vascular bifurcation into the dynamic response model, combine the concentration standing wave formation threshold, and solve the decay trajectory function of the vascular endothelial metabolic buffer capacity through spatio-temporal convolution operation.

[0014] Optionally, analyze the dynamic matching degree matrix between the decay trajectory function and the instability threshold in the genetic prediction model to determine the critical environmental exposure parameter combination, including:

[0015] Synchronously obtain the evolution curve of the instability threshold corresponding to the vascular tension regulation gene cluster in the genetic prediction model;

[0016] Calculate the buffer capacity decay rate based on the time derivative of the decay trajectory function, extract the curvature extreme points of the instability threshold evolution curve, and establish a dynamic matching degree matrix between the buffer capacity decay rate and the curvature extreme points;

[0017] Based on the dynamic matching degree matrix, when the matching degree of the buffer capacity decay rate at the coordinate point of the vascular bifurcation exceeds the curvature tolerance range of the corresponding gene cluster, mark it as a high-risk area of metabolic reserve depletion, and associate the spatio-temporal distribution parameters of the environmental oxidation load at the coordinate point of the vascular bifurcation;

[0018] Based on the matching degree data in the dynamic matching degree matrix, simulate the standing wave amplification effect of the coordinate points in the high-risk area of metabolic reserve depletion through the oxidative stress wave propagation equation to calculate the critical environmental exposure parameter combination that causes a cliff-like decline in the metabolic buffer capacity. The critical environmental exposure parameter combination includes the oxidative load intensity threshold, exposure duration, and spatial action radius.

[0019] Optionally, calculate the buffer capacity attenuation rate based on the time derivative of the attenuation trajectory function, and extract the curvature extreme points of the instability threshold evolution curve to establish a dynamic matching degree matrix between the buffer capacity attenuation rate and the curvature extreme points, including:

[0020] Perform time-domain differential processing on the attenuation trajectory function, and use the central difference method to calculate the metabolic buffer capacity attenuation rate at each spatial coordinate point within a preset time window. The width of the preset time window is one-fourth of the characteristic period parameter of the metabolic oscillation of the blood vessel wall;

[0021] For the instability threshold evolution curve output by the genetic prediction model, calculate the curvature parameter of the instability threshold evolution curve, and use the sliding window extreme value detection algorithm to identify the set of curvature extreme points. The set of curvature extreme points satisfies the condition that the first derivative of the curvature parameter is zero and the second derivative is negative;

[0022] Construct a spatio-temporal matching tensor, couple the metabolic buffer capacity attenuation rate with the nearest neighbor curvature extreme point in the set of curvature extreme points according to the time alignment criterion, and generate a dynamic matching degree matrix. The dimensions of the dynamic matching degree matrix include the number of spatial grids, the number of time nodes, and the number of gene clusters.

[0023] Optionally, it further includes:

[0024] Perform normalization processing on the dynamic matching degree matrix, calculate the historical matching degree mean and standard deviation of each spatial point, and form a standardized dynamic matching degree matrix distribution map. The standardized dynamic matching degree matrix distribution map contains normalized matching degrees;

[0025] Calculate the instability risk weight factor through the curvature tolerance range specific to the gene cluster. The instability risk weight factor is used to reflect the instability threshold critical values of different gene clusters;

[0026] Perform a convolution operation on the normalized matching degree and the instability risk weight factor to generate a comprehensive matching degree index. The comprehensive matching degree index is used to associate the critical environmental exposure parameter combination.

[0027] Optionally, a dynamic resilience assessment model is constructed by integrating the lipid transport rhythm desynchronization index, the instability threshold, and the critical environmental exposure parameter combination, and the phase space contraction rate of the vascular metabolic homeostasis boundary is calculated. When the phase space contraction rate exceeds the vascular wall remodeling compensation ability, a hierarchical warning signal is generated, including:

[0028] Construct a dynamic resilience assessment model, which is determined based on the instability parameter mapped by the lipid transport rhythm desynchronization index, the dynamic constraint boundary curvature parameter corresponding to the instability threshold, and the non-linear dissipation rate parameter derived from the critical environmental exposure parameter combination, and the absorption threshold of the vascular wall remodeling compensation ability to the gradient field perturbation is quantified through Lyapunov exponent analysis;

[0029] Apply the dynamic resilience assessment model to the assessment of the vascular wall remodeling compensation ability, and calculate the phase space contraction rate of the vascular metabolic homeostasis boundary, which is used to characterize the absorption ability of the vascular wall to the metabolic oscillation energy perturbation;

[0030] When the non-linear dissipation rate breaks through the dynamic constraint boundary curvature and the phase space contraction rate exceeds the absorption threshold, a hierarchical warning signal corresponding to the plaque instability tendency is generated according to the boundary break azimuth angle and the dissipative hot spot spatial coordinates.

[0031] Optionally, before generating the hierarchical warning signal corresponding to the plaque instability tendency according to the boundary break azimuth angle and the dissipative hot spot spatial coordinates when the non-linear dissipation rate breaks through the dynamic constraint boundary curvature and the phase space contraction rate exceeds the absorption threshold, it further includes:

[0032] Map the lipid transport rhythm desynchronization index to the vascular wall cell energy metabolism state space to generate a multi-dimensional gradient field distribution of the lipid transport rhythm instability degree;

[0033] Based on the instability threshold in the genetic prediction model, construct a dynamic constraint boundary of the coupling degree between vascular tension and metabolism, and the curvature characteristics of the dynamic constraint boundary are adjusted in real time with the critical environmental exposure parameter combination;

[0034] Establish a coupling equation between the critical environmental exposure parameter combination and the multi-dimensional gradient field distribution, and calculate the non-linear dissipation rate of the metabolic oscillation energy at the vascular bifurcation.

[0035] Optionally, the construction of the dynamic resilience assessment model, which is determined according to the lipid transport rhythm instability degree, the dynamic constraint boundary curvature, and the non-linear dissipation rate of the metabolic oscillation energy, includes:

[0036] Map the lipid transport rhythm instability degree to the energy metabolism state space of vascular wall cells to generate a spatial distribution function of the lipid transport rhythm instability degree, and the spatial distribution function is used to characterize the degree of metabolic imbalance of vascular walls in different regions;

[0037] Construct a dynamic constraint boundary of the coupling degree between vascular tension and metabolism based on the instability threshold in the genetic prediction model, and the curvature characteristics of the dynamic constraint boundary are adjusted in real time according to the critical environmental exposure parameter combination to generate a curvature distribution function of the dynamic constraint boundary;

[0038] Establish a coupling equation between the critical environmental exposure parameter combination and the spatial distribution function of the lipid transport rhythm instability degree, calculate the nonlinear dissipation rate of metabolic oscillation energy at the vascular bifurcation, and generate a spatio-temporal distribution function of the nonlinear dissipation rate;

[0039] Integrate the spatial distribution function of the lipid transport rhythm instability degree, the curvature distribution function of the dynamic constraint boundary, and the spatio-temporal distribution function of the nonlinear dissipation rate to construct a dynamic resilience evaluation model, and the dynamic resilience evaluation model is used to evaluate the vascular wall remodeling and compensation ability in different regions.

[0040] Optionally, the method for identifying the topological connection strength between the vascular tension regulation gene cluster and the metabolic sensing pathway gene cluster based on genomics data, and combining the phase delay parameter in the multimodal oscillation feature spectrum to quantify the influence weight of genetic variation on the coupling efficiency of the coupling data to generate a genetic prediction model includes:

[0041] Extract the co-expression network of the vascular tension regulation gene cluster and the metabolic sensing pathway gene cluster based on genomics data, and calculate the topological connection strength between gene clusters, and the topological connection strength is used to characterize the functional synergy of gene clusters in regulating the coupling efficiency of cardiovascular and metabolism;

[0042] Map the phase delay parameter in the multimodal oscillation feature spectrum to the gene cluster co-expression network to generate a phase delay weighted gene cluster network, and the phase delay weighted gene cluster network is used to characterize the correlation between the functional synergy between gene clusters and the coupling efficiency of the coupling data;

[0043] Identify single nucleotide polymorphism sites in the vascular tension regulation gene cluster and the metabolic sensing pathway gene cluster based on genetic variation data, and calculate the regulatory effect value of each polymorphism site on the topological connection strength between gene clusters, and the regulatory effect value is used to quantify the influence of genetic variation on the functional synergy of gene clusters;

[0044] Integrate the regulatory effect value with the phase delay weighted gene cluster network, and calculate the influence weight of genetic variation on the coupling efficiency of the coupling data, and the influence weight is used to characterize the contribution degree of genetic variation to the coupling efficiency by regulating the functional synergy of gene clusters;

[0045] Construct a genetic prediction model based on the influence weight, where the genetic prediction model is used to predict the change trend of the coupling efficiency of the coupling data of the target object under a specific genetic variation background.

[0046] In a second aspect, an embodiment of the present application provides a dynamic resilience assessment and early warning system for cardiovascular and metabolic diseases, including:

[0047] An extraction module, configured to extract the phase delay parameter between the cardiovascular elastic chamber and the metabolic substrate supply from the coupling data of the cardiovascular and metabolism in the continuous time series of the obtained target object, so as to construct a multi-modal oscillation feature spectrum including the lipid transport rhythm desynchronization index;

[0048] An identification module, configured to identify the topological connection strength between the vascular tone regulation gene cluster and the metabolic sensing pathway gene cluster based on genomic data, and combine the phase delay parameter in the multi-modal oscillation feature spectrum to quantify the influence weight of genetic variation on the coupling efficiency of the coupling data, so as to generate a genetic prediction model;

[0049] A calculation module, configured to simulate and calculate the attenuation trajectory function of the vascular endothelial metabolic buffer capacity according to the local shear force distribution of the blood vessels of the target object and the environmental oxidation load parameter, and analyze the dynamic matching degree matrix between the attenuation trajectory function and the instability threshold in the genetic prediction model, so as to determine the critical environmental exposure parameter combination;

[0050] A construction module, configured to fuse the lipid transport rhythm desynchronization index, the instability threshold, and the critical environmental exposure parameter combination to construct a dynamic resilience assessment model, so as to calculate the phase space shrinkage rate of the vascular metabolic steady-state boundary, and generate a hierarchical early warning signal when the phase space shrinkage rate exceeds the vascular wall remodeling compensation ability.

[0051] In the embodiments of the present application, phase delay parameters between the cardiovascular elastic chamber and the metabolic substrate supply are extracted from the cardiovascular and metabolic coupling data in the continuous time series of the obtained target object, and a multi-modal oscillation feature spectrum including lipid transport rhythm desynchronization indexes is constructed; the topological connection strength between the vascular tone regulation gene cluster and the metabolic sensing pathway gene cluster is identified based on genomic data, and the influence weight of genetic variation on the coupling efficiency of the coupling data is quantified by combining the phase delay parameters in the multi-modal oscillation feature spectrum to generate a genetic prediction model; according to the local shear force distribution of the blood vessels and the environmental oxidative load parameters of the target object, the attenuation trajectory function of the vascular endothelial metabolic buffer capacity is simulated and calculated, and the dynamic matching degree matrix between the attenuation trajectory function and the instability threshold in the genetic prediction model is analyzed to determine the critical environmental exposure parameter combination; the lipid transport rhythm desynchronization index, the instability threshold, and the critical environmental exposure parameter combination are integrated to construct a dynamic resilience assessment model, and the phase space contraction rate of the vascular metabolic steady-state boundary is calculated. When the phase space contraction rate exceeds the vascular wall remodeling compensation ability, a hierarchical early warning signal is generated.

[0052] The technical solution of the present application has the following beneficial effects:

[0053] Integrating dynamic physiological parameters and genetic topological networks, breaking through the limitations of traditional static risk assessment, and improving the cross-scale prediction accuracy; simulating through shear force gradient field parameters to quantify the attenuation trajectory of the vascular wall remodeling compensation ability; combining the metabolic oscillation energy dissipation rate and oxidative load parameters to accurately identify high-risk environmental exposure combinations; providing a quantitative basis for formulating targeted intervention strategies through a hierarchical early warning mechanism and reducing the incidence of major cardiovascular events.

[0054] Furthermore, by integrating the local shear force distribution of the blood vessels and the environmental oxidative load parameters of the target individual, a blood flow-metabolism coupling simulation model is used to calculate the attenuation trajectory function of the vascular endothelial metabolic buffer capacity; combined with the instability threshold of the genetic prediction model, the matching degree between the metabolic buffer attenuation rate and the genetic instability boundary is analyzed through a dynamic Bayesian network, and finally the critical environmental exposure parameter combination that triggers the failure of vascular compensation is determined. This method breaks through the limitations of traditional static risk assessment. Through shear force gradient field simulation and dynamic stability boundary analysis, it realizes the real-time quantitative monitoring of the vascular metabolic compensation ability, accurately identifies the environmental exposure critical point leading to plaque instability, and provides a spatio-temporal dynamic early warning window for individualized intervention.

[0055] These aspects or other aspects of the present application will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0057] Figure 1 The flowchart of a method for dynamic resilience assessment and early warning of cardiovascular and metabolic diseases provided by the present application is shown;

[0058] Figure 2 The structural schematic diagram of a system for dynamic resilience assessment and early warning of cardiovascular and metabolic diseases provided by the present application is shown. Detailed implementation manners

[0059] In order to enable those skilled in the art to better understand the solutions of the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application.

[0060] In some processes described in the specification, claims and the above drawings of the present application, multiple operations that appear in a specific order are included. However, it should be clearly understood that these operations can be executed not in the order in which they appear herein or in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes can include more or fewer operations, and these operations can be executed in sequence or in parallel. It should be noted that the descriptions such as "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are of different types.

[0061] The following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0062] Figure 1 The flowchart of a method for dynamic resilience assessment and early warning of cardiovascular and metabolic diseases provided by the embodiments of the present application is as Figure 1 shown, and the method includes:

[0063] 101. Extract the phase delay parameter between the cardiovascular elastic chamber and the metabolic substrate supply from the cardiovascular and metabolic coupling data in the continuous time series of the obtained target object, so as to construct a multi-modal oscillation feature spectrum including the lipid transport rhythm desynchronization index;

[0064] In this step, the cardiovascular and metabolic coupling data includes continuous time series data such as the blood pressure, heart rate, blood lipids, blood glucose level, liver and kidney function test results, and inflammatory markers of the target object, which are used to reflect the dynamic interaction between the cardiovascular system and the metabolic system.

[0065] The cardiovascular elastic chamber refers to the part in the heart and blood vessel system that can perform elastic regulation according to hemodynamic changes, such as the elastic chamber of the arterial wall.

[0066] The metabolic substrate supply refers to the supply situation of substrates (such as glucose, lipids, etc.) required in the metabolic process in the blood.

[0067] The phase delay parameter is used to describe the time delay relationship between the cardiovascular elastic chamber and the metabolic substrate supply, reflecting the coordination between the two in dynamic regulation.

[0068] The lipid transport rhythm desynchronization index is used to quantify the degree of desynchronization between the lipid transport efficiency in the blood vessel wall and the metabolic demand.

[0069] The multi-modal oscillation feature spectrum is a spectrogram containing various oscillation features (such as frequency, amplitude, phase delay, etc.), which is used to describe the dynamic coupling characteristics of the cardiovascular and metabolic systems.

[0070] The lipid transport rhythm desynchronization index is a biomarker or parameter used to quantify the degree of rhythmic disorder in the lipid metabolism process. It reflects the dysregulated state of lipid transport (such as the synthesis, secretion, transportation, and clearance of lipoproteins) in the time dimension, and is usually used to evaluate the coordination of the cardiovascular and metabolic systems.

[0071] In the embodiments of the present application, first, extract the continuous time series of cardiovascular and metabolic coupling data from the health examination data of the target object, including blood pressure, heart rate, blood lipids, blood glucose, liver and kidney function test results, and inflammatory markers, etc.

[0072] Secondly, use Fourier transform or wavelet transform to convert the time-domain data (i.e., cardiovascular and metabolic coupling data) into frequency-domain data to analyze the frequency characteristics between the cardiovascular elastic chamber and the metabolic substrate supply, and obtain the phase delay parameter by calculating the phase difference between the cardiovascular elastic chamber and the metabolic substrate supply in the frequency domain. The specific methods include cross-spectrum analysis or calculation of the Phase Locking Value (PLV).

[0073] Next, based on blood lipid data (such as triglycerides, low-density lipoprotein, etc.), calculate the transport efficiency of lipids in the blood vessel wall. By comparing the time difference between lipid transport efficiency and metabolic demand, calculate the desynchronization index of lipid transport rhythm. The specific methods include calculating the correlation coefficient or phase difference between the two.

[0074] Finally, integrate features such as the phase delay parameter and the desynchronization index of lipid transport rhythm to generate a multi-modal oscillation feature spectrum. Use spectral analysis methods (such as short-time Fourier transform or continuous wavelet transform) to generate the multi-modal oscillation feature spectrum, which reflects the dynamic coupling characteristics of the cardiovascular and metabolic systems.

[0075] 102. Identify the topological connection strength between the vascular tone regulation gene cluster and the metabolic sensing pathway gene cluster based on genomics data, and combine the phase delay parameter in the multi-modal oscillation feature spectrum to quantify the influence weight of genetic variation on the coupling efficiency of the coupling data, so as to generate a genetic prediction model;

[0076] In this step, the genomics data includes all the genetic information of an individual and can be used to identify the roles of specific gene clusters. In this application, the genomics data specifically includes the single nucleotide polymorphism sites and their regulatory effect values of the vascular tone regulation gene cluster and the metabolic sensing pathway gene cluster of the target object.

[0077] The vascular tone regulation gene cluster involves genes related to controlling vascular tone, while the metabolic sensing pathway gene cluster refers to genes related to the mechanism by which cells sense and respond to metabolic demands.

[0078] The topological connection strength refers to the tightness of the gene interaction network and is used to quantify the influence of genetic variation on the coupling efficiency between the cardiovascular and metabolic coupling data.

[0079] The genetic prediction model is a mathematical framework that predicts an individual's risk of developing cardiovascular and metabolic diseases by combining genomic data and other physiological parameters. Genetic variation refers to the regulatory effect of single nucleotide polymorphism sites in the gene cluster on gene function. The influence weight of the coupling efficiency is used to quantify the contribution degree of genetic variation to the dynamic coupling efficiency between the cardiovascular and metabolic systems.

[0080] In the embodiment of this application, first, extract the single nucleotide polymorphism sites (SNPs) of the vascular tone regulation gene cluster and the metabolic sensing pathway gene cluster from the genomics data of the target object, and identify the vascular tone regulation gene cluster and the metabolic sensing pathway gene cluster through gene co-expression network analysis.

[0081] Secondly, based on gene expression data, construct a co-expression network of the vascular tone regulation gene cluster and the metabolic sensing pathway gene cluster, and use graph theory methods (such as node degree, betweenness centrality, etc.) to calculate the topological connection strength between gene clusters, where the topological connection strength reflects their functional synergy. Then optimize the co-expression network through modular analysis or community detection algorithms, and extract the most representative gene cluster connections.

[0082] Next, based on SNPs data, calculate the effect value of each polymorphism site on the function of the gene cluster, and combine the phase delay parameters in the multi-modal oscillation feature spectrum to calculate the influence weight of genetic variation on the cardiovascular-metabolic coupling efficiency. Specific methods include multiple linear regression or Bayesian network analysis. And standardize the influence weight to ensure its comparability between different gene clusters.

[0083] Finally, based on the topological connection strength and influence weight, construct a genetic prediction model. Specific methods include machine learning algorithms such as random forest, gradient boosting, or neural network. Use the training set data to train the model, optimize the model parameters to ensure its prediction accuracy, and verify the model through cross-validation or an independent validation set to evaluate its prediction performance.

[0084] 103. According to the local shear stress distribution of blood vessels and environmental oxidation load parameters of the target object, simulate and calculate the decay trajectory function of the metabolic buffering capacity of vascular endothelial cells, and analyze the dynamic matching degree matrix between the decay trajectory function and the instability threshold in the genetic prediction model to determine the critical environmental exposure parameter combination;

[0085] In this step, the local shear stress distribution of blood vessels is the time-varying shear stress spatial gradient parameter of the blood vessel bifurcation segment extracted from the three-dimensional stress distribution map of the blood vessel wall, which refers to the force distribution exerted by blood flow on the blood vessel wall and is one of the important factors affecting the function of vascular endothelial cells.

[0086] The environmental oxidation load parameters involve the exposure levels of free radicals and other oxidative stress sources in the external environment. These factors act together on the metabolic buffering capacity of vascular endothelial cells. In this application, the environmental oxidation load parameters include the intensity, duration, and spatial action radius of oxidative stress waves, which are used to describe the impact of environmental oxidation load on the metabolic buffering capacity of vascular endothelial cells.

[0087] The decay trajectory function is used to describe the function of the metabolic buffering capacity of vascular endothelial cells changing with time.

[0088] The instability threshold is the key point at which the system changes from a stable state to an unstable state and is used to predict the occurrence and development of diseases.

[0089] The critical environmental exposure parameter combination refers to the set of external conditions that can cause system instability, and they act together with internal biological factors to affect disease development.

[0090] The dynamic matching degree matrix is used to quantify the matching degree between the attenuation trajectory function and the instability threshold in the genetic prediction model.

[0091] In the embodiments of the present application, first, based on the three-dimensional stress distribution map of the blood vessel wall of the target object, the time-varying shear force spatial gradient parameters of the blood vessel bifurcation segment are extracted, and the shear force spatial gradient parameters of the blood vessel bifurcation segment are calculated by the finite element analysis method.

[0092] Secondly, according to the environmental oxidation load parameters (such as the intensity, duration, spatial action radius, etc. of the oxidative stress wave), an oxidative stress wave propagation equation is established, and the oxidative stress wave propagation equation is solved by a numerical simulation method (such as the finite difference method or the finite element method) to obtain the concentration standing wave formation threshold of the metabolic buffer medium.

[0093] Then, the shear force distribution is combined with the oxidative stress wave propagation equation to construct a blood flow-metabolism dynamic response model, and the attenuation trajectory function of the metabolic buffer capacity of the vascular endothelium is solved by spatio-temporal convolution operation. The specific methods include convolutional neural network (CNN) or recurrent neural network (RNN).

[0094] Finally, the instability threshold evolution curve corresponding to the vascular tension regulation gene cluster is extracted from the genetic prediction model, the attenuation trajectory function is dynamically matched with the instability threshold evolution curve, and the matching degree matrix is calculated. The specific methods include dynamic time warping (DTW) or Euclidean distance calculation, and the matching degree matrix is optimized to ensure its comparability at different spatial coordinate points.

[0095] 104. Integrate the lipid transport rhythm desynchronization index, the instability threshold, and the critical environmental exposure parameter combination to construct a dynamic resilience assessment model to calculate the phase space contraction rate of the vascular metabolic homeostasis boundary, and generate a hierarchical warning signal when the phase space contraction rate exceeds the vascular wall remodeling compensation ability.

[0096] In this step, the dynamic resilience assessment model is used to evaluate the absorption ability of the blood vessel wall to the energy perturbation of metabolic oscillation, and it is a model reflecting the vascular wall remodeling compensation ability.

[0097] The phase space contraction rate is used to quantify the contraction degree of the vascular metabolic homeostasis boundary and reflects the absorption threshold of the blood vessel wall to the energy perturbation of metabolic oscillation.

[0098] The hierarchical warning signal refers to a warning signal generated according to the comparison result between the phase space contraction rate and the vascular wall remodeling compensation ability, and is used to prompt the high risk of metabolic reserve depletion.

[0099] In the embodiments of the present application, first, an index of desynchronization of lipid transport rhythm, an instability threshold, and critical environmental exposure parameters are combined and fused to construct a dynamic resilience assessment model, and a suitable machine learning algorithm (such as a support vector machine, a random forest, or a deep learning model) is selected to construct the dynamic resilience assessment model.

[0100] Secondly, based on the Lyapunov exponent, the phase space contraction rate of the vascular metabolic homeostasis boundary is calculated through the dynamic resilience assessment model. The specific methods include calculating the maximum Lyapunov exponent or phase space reconstruction.

[0101] Finally, the phase space contraction rate is compared with the vascular wall remodeling compensation ability to determine whether it exceeds the absorption threshold. When the phase space contraction rate exceeds the absorption threshold, a graded warning signal is generated to indicate the high risk of metabolic reserve depletion.

[0102] The following is a specific example for steps 101-104:

[0103] For example, for a 55-year-old male patient, cardiovascular and metabolic coupling data such as his blood pressure (125 / 85 mmHg), heart rate (72 bpm), fasting blood glucose (6.1 mmol / L), LDL-C (3.4 mmol / L), and hs-CRP (2.8 mg / L) are obtained through continuous monitoring (step 101). The phase difference (delay of 1.2 seconds) between the aortic elasticity and blood glucose fluctuations is analyzed using wavelet transform, and a multimodal oscillation characteristic spectrum is generated by combining the phase desynchronization index (0.45) of LDL transport efficiency and energy demand. Genome detection shows that the topological connection strength between the NOS3 gene cluster (rs1799983-TT) and the PPARγ cluster (rs1801282-CC) is 0.68, and it is calculated through a Bayesian network that this mutation reduces the coupling efficiency by 23%, and a genetic prediction model is constructed (step 102). Based on the shear stress distribution (peak value of 4.5 Pa) simulated by CFD at the carotid bifurcation and PM2.5 exposure data (annual average of 45 μg / m 3 ), the trajectory function of the attenuation of the endothelial buffering capacity is simulated, and after matching with the instability threshold of the genetic model, the critical exposure combination is determined to be PM2.5 > 50 μg / m 3 for 6 months (step 103). The dynamic resilience assessment model constructed by fusing the above parameters shows that its phase space contraction rate reaches 0.78 (threshold of 0.65), triggering a level-three warning signal, and after clinical intervention, the contraction rate drops to 0.52 (step 104).

[0104] Optionally, in addition to using the above-mentioned cardiovascular and metabolic coupling data to generate a dynamic resilience assessment and early warning for cardiovascular and metabolic diseases, the collected cardiovascular and metabolic coupling data can also be used for risk prediction of cardiovascular and metabolic diseases. Specifically, this optional solution uses a random forest classifier combined with recursive feature elimination and cross-validation algorithms to screen out a preliminary feature set with relatively high importance scores from the cardiovascular and metabolic coupling data; then identifies and eliminates features with multicollinearity through a correlation heatmap, and applies principal component analysis for dimensionality reduction to form a target feature set; then uses the target feature set to train a machine learning model, and optimizes the model performance through hyperparameter tuning, performance verification, and sensitivity analysis; finally, inputs the health-related variables of a new individual into the trained model to output the risk probability of suffering from cardiovascular and metabolic diseases. This method realizes the accurate prediction of disease risks through multi-step feature screening and model optimization.

[0105] In order to further improve the accuracy of the dynamic resilience assessment and early warning for cardiovascular and metabolic diseases, in some embodiments, in step 103, according to the local shear stress distribution of the blood vessels of the target object and the environmental oxidation load parameters, the attenuation trajectory function of the vascular endothelial metabolic buffer capacity is simulated and calculated, and the dynamic matching degree matrix between the attenuation trajectory function and the instability threshold in the genetic prediction model is analyzed to determine the critical environmental exposure parameter combination, including:

[0106] 1031. Based on the three-dimensional stress distribution map of the blood vessel wall, extract the local shear stress distribution of the bifurcated segment of the target blood vessel, combine the monitoring data of the endothelial cell metabolic flux to construct a dynamic response model, calculate the phase lag amount of the lipid transport efficiency to the shear stress fluctuation through frequency domain coupling analysis, and generate a metabolic delay feature map at the blood vessel bifurcation;

[0107] In step 1031, the three-dimensional stress distribution map of the blood vessel wall is an image describing the stress conditions of the blood vessel at different positions, including shear stress, pressure, and tension, etc. The local shear stress distribution refers to the spatial variation of the frictional force generated by blood flow on the blood vessel wall within a specific region (such as the blood vessel bifurcation). The dynamic response model is used to simulate and predict the interaction between hemodynamics and endothelial cell metabolic activities.

[0108] In the embodiments of the present application, usually, the three-dimensional stress distribution map of the blood vessel wall is obtained by combining medical imaging techniques (such as MRI or CT scans) with computational fluid dynamics (CFD) simulations. Specifically, first, the blood vessel structure is reconstructed using high-resolution image data, and then CFD software is applied for numerical simulations, considering factors such as blood flow characteristics, blood vessel wall elasticity, and boundary conditions, and finally, a three-dimensional stress distribution map of the blood vessel wall containing stress distribution information is generated.

[0109] Specifically, the process of generating the two-dimensional stress distribution map of the blood vessel wall includes: 1) Medical imaging data preprocessing: Obtain the DICOM format image data of the blood vessels of the target object by MRI or CT scanning, extract the contour of the blood vessel cavity through threshold segmentation (such as the Otsu algorithm), and perform three-dimensional reconstruction using the Marching Cubes algorithm. 2) CFD simulation parameter setting: Set the blood as a non-Newtonian fluid (Carreau-Yasuda model) and the blood vessel wall as an anisotropic hyperelastic material (Mooney-Rivlin model) in ANSYS Fluent. The boundary conditions include the inlet flow velocity waveform (based on ultrasonic Doppler measurement) and the outlet pressure boundary (Windkessel model). 3) Stress distribution output: Calculate the steady-state and transient hemodynamic parameters, output the spatio-temporal distribution data of the wall shear stress and pressure, and store it in the VTK format for subsequent analysis.

[0110] Secondly, use image processing algorithms to extract data of the bifurcated segment of the target blood vessel from the above three-dimensional stress distribution map of the blood vessel wall, especially focusing on the changes of the shear stress over time and space. This step requires accurate identification of the maximum value, minimum value and change trend of the shear stress.

[0111] Then, combine the extracted local shear stress distribution of the blood vessel with the endothelial cell metabolic flux data obtained from experimental measurements (such as glucose uptake rate, ATP production rate), and establish a dynamic response model using the method of systems biology, which can reflect how the shear stress affects the metabolism of endothelial cells. The modeling method can be implemented using a conventional scheme, and this application will not expand on this.

[0112] Specifically, the process of constructing the dynamic response model includes: 1) Endothelial metabolic flux data integration: Real-time monitor the glucose uptake rate (unit: μmol / (min·10∧6 cells )) and ATP production rate (unit: nmol / (min·mg protein )) of endothelial cells through a microelectrode array, and align them with the shear stress data according to the spatial coordinates. 2) System dynamics equation: Establish a coupling equation between the shear stress (τ) and the metabolic flux (M):

[0113]

[0114] where k1 is the shear stress response coefficient (calibrated through in vitro blood vessel perfusion experiments), and k2 is the metabolic decay rate (determined through the cell oxygen consumption rate).

[0115] Finally, for the study of lipid transport efficiency, the shear stress fluctuations and lipid concentration signals are first transformed into the frequency domain using the Fast Fourier Transform (FFT) method. Then, the phase lag amount is determined by comparing the phase differences of the two at different frequencies, and a metabolic delay characteristic map at the vascular bifurcation is generated. Among them, shear stress fluctuations refer to the changes in the shear stress intensity acting on the vascular endothelium over time. It can be short-term fluctuations caused by factors such as periodic changes in heart rate, respiratory movements, and body position changes, or long-term trend changes due to long-term living habits and disease progression.

[0116] Specifically, the frequency domain The combined analysis and phase lag calculation process includes: 1) Signal preprocessing: detrending and windowing the shear stress fluctuation signal (sampling frequency 100 Hz) and lipid concentration signal (obtained by dynamic imaging of fluorescently labeled lipoproteins) with a Hanning window. 2) Cross-spectrum analysis: calculating the cross-power spectral density (CPSD) of the two signals, and the phase difference where P τ and P lipid are the auto-power spectra of shear stress and lipid concentration respectively. 3) Characteristic map generation: Select 10×10 grid points at the vascular bifurcation, draw a heat map of the phase lag amount (mean value in the 0.5 - 5 Hz frequency band) at each point, and generate a metabolic delay characteristic map.

[0117] 1032. According to the spatio-temporal distribution of environmental oxidation load parameters, establish an oxidative stress wave propagation equation to solve the concentration standing wave formation threshold of the metabolic buffer medium at the vascular bifurcation through the oxidative stress wave propagation equation, and the concentration standing wave formation threshold is used to calibrate the dynamic response boundary of the endothelial metabolic buffer capacity;

[0118] Step 1032 mainly involves establishing an oxidative stress wave propagation equation according to the spatio-temporal distribution of environmental oxidation load parameters, and solving the concentration standing wave formation threshold of the metabolic buffer medium at the vascular bifurcation through the oxidative stress wave propagation equation. This standing wave formation threshold is used to calibrate the dynamic response boundary of the endothelial metabolic buffer capacity, that is, to determine under what conditions the vascular endothelial cells will lose their normal metabolic buffer function.

[0119] In the embodiments of the present application, first, spatio-temporal distribution data of reactive oxygen species (ROS) in the environment need to be obtained through experiments or sensor monitoring. These data include, but are not limited to, the concentrations of ROS at different time points and different positions.

[0120] Secondly, based on the collected data, a mathematical modeling method is used to establish equations that describe how ROS spreads in the body. This typically involves partial differential equations (PDEs), taking into account factors such as the generation rate, diffusion coefficient, and scavenging rate of ROS. The model also needs to consider the impact of blood flow on the spread of ROS, and fluid dynamics simulations can be combined to more accurately predict the distribution of ROS within blood vessels.

[0121] Specifically, the oxidative stress wave equation can be an extended reaction-diffusion-convection equation:

[0122]

[0123] where C max is the maximum ROS tolerance concentration (determined through cell viability experiments), V max and K m are the SOD enzyme kinetic parameters (calibrated through the Lineweaver–Burk double-reciprocal plot method).

[0124] Next, numerical methods (such as the finite difference method or the finite element method) are used to solve the above equations to determine under which conditions ROS concentration standing waves will form at blood vessel bifurcations. Here, a "standing wave" refers to a state where the ROS concentration remains relatively stable within a specific region, indicating that this region has reached a state of equilibrium, but this equilibrium is often unhealthy and marks the beginning of endothelial cells losing their normal functions.

[0125] Specifically, the numerical solution and stability analysis process includes: 1) Spatial discretization: An unstructured tetrahedral mesh (minimum mesh size 0.1 mm) is used, and it is refined to 0.02 mm at blood vessel bifurcations, with a total number of meshes approximately 2×10^6. 2) Time marching strategy: The Crank–Nicolson implicit scheme is used to ensure numerical stability, with a time step Δt = 0.01 s. 3) Bifurcation point determination: The maximum Lyapunov exponent of the Jacobian matrix is calculated through the Arnoldi iteration method, and when the exponent changes from negative to positive, the system is determined to be unstable.

[0126] Finally, based on the obtained standing wave formation threshold, the relationship between it and the metabolic buffering capacity of endothelial cells is further analyzed to determine at what value of the ROS concentration endothelial cell dysfunction will occur. This process can be verified through a combination of biological experiments and computer simulations.

[0127] Specifically, the experimental verification method includes: 1) In vitro verification platform: Reconstruct the vascular bifurcation geometry in a PDMS microfluidic chip, and use a fluorescence probe (DCFH-DA) to monitor the ROS concentration distribution in real time. The root mean square error (RMSE < 15%) is compared with the simulation results. 2) Clinical relevance analysis: Perform coronary OCT examinations on 50 patients with coronary heart disease, and find that the spatial coincidence rate between the plaque rupture location and the standing wave region predicted by simulation (C ≥ 0.8C max ) reaches 82%.

[0128] 1033. Input the metabolic delay characteristic map at the vascular bifurcation into the dynamic response model, combine the concentration standing wave formation threshold, and solve the decay trajectory function of the vascular endothelial metabolic buffer capacity through spatio-temporal convolution operation, and simultaneously obtain the instability threshold evolution curve corresponding to the vascular tension regulation gene cluster in the genetic prediction model;

[0129] Step 1033 aims to input the metabolic delay characteristic map at the vascular bifurcation into the dynamic response model, combine the concentration standing wave formation threshold, and solve the decay trajectory function of the vascular endothelial metabolic buffer capacity through spatio-temporal convolution operation. At the same time, this step also simultaneously obtains the instability threshold evolution curve corresponding to the vascular tension regulation gene cluster in the genetic prediction model, providing a basis for subsequent analysis.

[0130] First, it is necessary to integrate the metabolic delay characteristic map at the vascular bifurcation obtained from step 1031 with the concentration standing wave formation threshold determined in step 1032. This step involves normalizing the data from different sources to ensure that they can be compared and analyzed within the same framework.

[0131] Use deep learning technology to construct a spatio-temporal convolutional network (STCN) to simulate the complex interaction between blood flow and metabolism. STCN can capture local patterns in space and dynamic changes in time, and is particularly suitable for processing multi-dimensional data such as shear stress fluctuations and ROS concentration changes.

[0132] Specifically, the STCN network architecture includes:

[0133] Input layer: Four-dimensional tensor (spatial x×y×z grid, time series length T = 1000 frames).

[0134] The convolution module includes: Spatial convolution: 3×3×3 three-dimensional convolution kernel, 64 channels, ReLU activation. Temporal convolution: One-dimensional causal convolution, kernel length 5, 128 channels.

[0135] Output layer: Fully connected layer mapped to the scalar value of the metabolic buffer capacity, and the loss function uses the Huber loss (δ = 1.0).

[0136] Using the trained STCN model, the integrated dataset is input to solve the variation law of vascular endothelial metabolic buffer capacity over time and space, that is, the decay trajectory function. This function describes how the endothelial cell metabolic buffer capacity gradually weakens under specific conditions, such as different shear stress distributions or ROS concentration levels.

[0137] Specifically, the training and validation include:

[0138] Dataset: Synthetic data (1000 groups of CFD + oxidative stress simulation results) and clinical data (follow-up data of 30 patients) are divided into training set / test set at a ratio of 7:3.

[0139] Hyperparameter optimization: Bayesian optimization is used to determine the learning rate (final value 2e-4) and batch size (32).

[0140] Performance metric: The prediction error MAE of the test set is 12.3% (95% CI: 10.1 - 14.5%).

[0141] When calculating the decay trajectory function, the influence of genetic factors also needs to be considered. Using the pre-established genetic prediction model, according to the individual's gene information (especially the gene cluster related to vascular tone regulation), the evolution curve of the instability threshold caused by the change of these gene expression levels over time is obtained synchronously.

[0142] Specifically, the process of synchronously obtaining genetic data includes: 1) Gene expression time series: The expression levels of vascular tone-related genes (such as eNOS, ACE) are detected every 6 hours by qPCR to construct the expression level-time curve. 2) Calculation of instability threshold: When the standard deviation of gene expression level exceeds 3 times the baseline, it is determined as the instability threshold point.

[0143] 1034. Calculate the buffer capacity decay rate based on the time derivative of the decay trajectory function, extract the curvature extreme points of the instability threshold evolution curve, and establish a dynamic matching degree matrix between the buffer capacity decay rate and the curvature extreme points;

[0144] Step 1034 involves calculating the time derivative of the vascular endothelial metabolic buffer capacity decay trajectory function obtained in the previous steps to determine the buffer capacity decay rate. At the same time, extract the curvature extreme points of the instability threshold evolution curve in the genetic prediction model, and establish a dynamic matching degree matrix between these decay rates and the curvature extreme points. This matrix is used to evaluate the change trend of vascular health status under different combinations of environmental exposure parameters.

[0145] In the embodiment of the present application, first, the decay trajectory function obtained from step 1033 needs to be differentiated, that is, calculate its first derivative with respect to time. This can be achieved by numerical differentiation methods, such as using the finite difference method to approximate the instantaneous change rate at each time point.

[0146] Specifically, the numerical differentiation method is implemented through the following central difference formula:

[0147]

[0148] where Δt = 0.1 s, corresponding to 1 / 4 of the characteristic period of the metabolic oscillation of the blood vessel wall (about 0.4 s).

[0149] Among them, the curvature extreme value detection algorithm is obtained through the following curvature calculation formula:

[0150]

[0151] where s is the instability threshold curve.

[0152] Extreme value determination: The sliding window width is 10 points (corresponding to 0.5 s), and local maximum points are detected (satisfying and ).

[0153] For the instability threshold evolution curve in the genetic prediction model, extreme points are found by analyzing its second derivative (i.e., curvature). These extreme points mark the positions where the curve shape changes significantly, which may indicate important turning points in gene expression levels or functional states.

[0154] Combining the buffer capacity decay rate calculated above with the curvature extreme points forms a two-dimensional matrix. In this matrix, the rows represent different time points or spatial positions, and the columns correspond to various environmental exposure parameters (such as oxidation load intensity, duration, and scope of action). By comparing the matching degrees under various parameter combinations, it can be identified which conditions are most likely to lead to the deterioration of blood vessel health.

[0155] Specifically, the process of constructing the dynamic matching degree matrix includes: 1) Spatiotemporal alignment: Align the decay rate matrix R(x, y, t) with the curvature extreme point sequence K(t) along the time axis, and the missing data are filled by cubic spline interpolation.

[0156] 2) Matching degree calculation:

[0157]

[0158] where σ = 0.1, which is optimized and determined by the grid search method.

[0159] For example, in the smoker cohort, the area with a matching degree > 0.8 coincides with 91% of the plaque progression area shown by CT angiography (p < 0.001).

[0160] Finally, by statistically analyzing the data in the dynamic matching degree matrix, key environmental exposure factors and their critical values are identified, providing a scientific basis for prevention and treatment.

[0161] 1035. Based on the dynamic matching degree matrix, when the matching degree of the buffer capacity attenuation rate at the coordinate point of the vascular bifurcation exceeds the curvature tolerance range of the corresponding gene cluster, it is marked as a high-risk area of metabolic reserve depletion, and the spatio-temporal distribution parameters of the environmental oxidative load at the coordinate point of the vascular bifurcation are associated;

[0162] The goal of step 1035 is to determine which regions are regarded as high-risk areas of metabolic reserve depletion according to the dynamic matching degree matrix of the buffer capacity attenuation rate and the instability threshold evolution curve calculated in the previous step. Specifically, when the matching degree of the buffer capacity attenuation rate at the coordinate point of the vascular bifurcation exceeds the curvature tolerance range of the corresponding gene cluster, this coordinate point will be marked as a high-risk area, and its spatio-temporal distribution parameters of the environmental oxidative load will be associated.

[0163] First, it is necessary to clarify the curvature tolerance range corresponding to each gene cluster. This is usually set based on large-scale population data or experimental studies, reflecting the acceptable fluctuation range of gene expression level changes under normal physiological conditions. Exceeding this range may mean that cell functions begin to show abnormalities.

[0164] Using the dynamic matching degree matrix constructed in step 1034, compare the matching degree of the buffer capacity attenuation rate at each coordinate point (i.e., the vascular bifurcation segment at a specific position and time) with the instability threshold of the gene cluster. If the matching degree exceeds the preset curvature tolerance range, it is considered that there is a high risk of metabolic reserve depletion at this point.

[0165] Specifically, the setting of the curvature tolerance range includes: 1) Population baseline data: Based on the gene expression fluctuation data of 1000 healthy people, calculate the 95% confidence interval of the curvature parameters of each gene cluster as the tolerance range. 2) Dynamic adjustment mechanism: When the environmental PM2.5 concentration > 35 μg / m 3 ³, the tolerance range shrinks by 20% (according to the hazard ratio HR = 1.32 in the cohort study).

[0166] Mark all coordinate points that exceed the curvature tolerance range to form a high-risk area map. This step can be achieved with the help of geographic information system (GIS) software to visually display the risk levels of different parts.

[0167] Specifically, the visualization of high-risk areas includes: 1) 3D rendering: Mapping the areas with exceeded matching degree to the 3D vascular model, and using a red gradient to represent the risk level (RGB: 255*(M - 0.8) / 0.2, 0, 0). 2) Spatiotemporal heat map: Generating a time-slice animation in ParaView to show the migration pattern of high-risk areas with the extension of exposure time.

[0168] Finally, link these high-risk areas with the spatiotemporal distribution parameters of the specific environmental oxidative load, and analyze which external factors (such as air pollution, smoking, etc.) may be the main reasons for the depletion of metabolic reserve in these areas. This process helps to identify potential risk factors and formulate targeted intervention measures.

[0169] Specifically, the extraction of spatiotemporal distribution parameters of environmental oxidative load includes: 1) Oxidative load intensity: Inverting the PM2.5 exposure concentration through Gaussian process regression, with a spatial resolution of 100m×100m. 2) Exposure duration: Based on the individual location trajectories recorded by wearable sensors, calculate the cumulative exposure time of the coordinate points in high-risk areas (error ±5 minutes).

[0170] 1036. According to the matching degree data in the dynamic matching degree matrix, simulate the standing wave amplification effect of the coordinate points in the high-risk area of metabolic reserve depletion through the oxidative stress wave propagation equation, and calculate the critical environmental exposure parameter combination that leads to a cliff-like decline in metabolic buffer capacity. The critical environmental exposure parameter combination includes the oxidative load intensity threshold, exposure duration, and spatial action radius.

[0171] The goal of step 1036 is to simulate the standing wave amplification effect of the coordinate points in the high-risk area of metabolic reserve depletion through the oxidative stress wave propagation equation, and calculate the critical environmental exposure parameter combination that leads to a cliff-like decline in metabolic buffer capacity. These parameters include, but are not limited to, the oxidative load intensity threshold, exposure duration, and spatial action radius. This step aims to identify the key environmental factors and their action mechanisms that are most likely to cause a sharp deterioration of vascular health.

[0172] First, based on the data obtained in the previous steps (such as the high-risk areas determined in step 1035), set the initial conditions and boundary conditions of the oxidative stress wave propagation equation. This includes specifying information such as the ROS concentration distribution at the initial moment and the ROS flux on the boundary.

[0173] Use numerical methods such as the finite difference method or the finite element method to solve the oxidative stress wave propagation equation. Consider the effects of factors such as oxidative load intensity, exposure time, and spatial action radius in the model. In particular, simulate how ROS propagates in the body and forms a standing wave amplification effect under different environmental exposure conditions.

[0174] By changing the input parameters (such as increasing the oxidation load intensity or prolonging the exposure time), observe the system response, especially paying attention to those critical turning points that lead to a sudden decrease in the metabolic buffer capacity. These turning points usually mark the critical point of transition from a relatively stable physiological state to an acute injury state.

[0175] According to the simulation results, determine the specific combination of environmental exposure parameters that can trigger a cliff-like drop in the metabolic buffer capacity. This step requires multiple iterative simulations, adjusting the parameters until the exact critical value is found. The final output results will include important indicators such as the oxidation load intensity threshold, exposure duration, and spatial action radius.

[0176] Specifically, the process of determining the critical environmental exposure parameters is through: 1) Orthogonal experimental design: Using the L9(3∧4) orthogonal table, conduct combined simulations on the oxidation load intensity (30 / 45 / 60 μg / m 3 ), duration (3 / 6 / 9 months), and spatial radius (1 / 2 / 3 km).

[0177] 2) Response surface analysis: Construct a second-order polynomial model:

[0178] ΔC = β0 + β1X1 + β2X2 + β3X3 + β 12 X1X2 + ∈

[0179] where ΔC is the buffer capacity decline rate, and X1 is the standardized exposure parameter.

[0180] Among them, the determination of the cliff-like drop includes: 1) Mutation detection: Use the CUSUM control chart to monitor the time series of the buffer capacity, and trigger an alarm when the cumulative deviation exceeds the threshold (3σ). 2) Critical parameter extraction: Determine the minimum exposure combination that causes ΔC > 50% through dichotomy search (such as PM2.5 = 52 μg / m 3 for 5.2 months).

[0181] In order to further improve the dynamic resilience assessment and early warning accuracy of cardiovascular and metabolic diseases, in some embodiments, calculate the buffer capacity decay rate based on the time derivative of the attenuation trajectory function described in step 1034, and extract the curvature extreme points of the instability threshold evolution curve, and establish a dynamic matching degree matrix between the buffer capacity decay rate and the curvature extreme points, including:

[0182] 201. Perform time-domain differential processing on the attenuation trajectory function, and use the central difference method to calculate the metabolic buffer capacity decay rate at each spatial coordinate point within a preset time window, and the width of the preset time window is one-fourth of the characteristic period parameter of the vascular wall metabolic oscillation;

[0183] Among them, the attenuation trajectory function describes the trend of the metabolic buffer capacity of vascular endothelium changing with time and space, and is used to evaluate the change of local metabolic function. The central difference method is a numerical differentiation method that estimates the derivative by calculating the difference between adjacent points, and is used here to calculate the attenuation rate of the metabolic buffer capacity. The width of the preset time window is one-fourth of the characteristic period parameter of the metabolic oscillation of the vascular wall, ensuring that the calculation result has a high time resolution. The attenuation rate of the metabolic buffer capacity is used to quantify the change rate of the metabolic buffer capacity of vascular endothelium with time, reflecting the dynamic change of local metabolic function.

[0184] In the embodiment of the present application, first, obtain the attenuation trajectory function from step 1033, and this function describes the trend of the metabolic buffer capacity of vascular endothelium changing with time and space.

[0185] Secondly, perform time-domain differential processing on the attenuation trajectory function, and use the central difference method to calculate the attenuation rate of the metabolic buffer capacity at each spatial coordinate point within the preset time window. The specific formula is:

[0186]

[0187] Among them, Γ(s, t) is the attenuation trajectory function, and Δτ is the width of the preset time window.

[0188] Then, the width of the preset time window is one-fourth of the characteristic period parameter of the metabolic oscillation of the vascular wall, ensuring that the calculation result has a high time resolution.

[0189] Finally, calculate the attenuation rate of the metabolic buffer capacity at each spatial coordinate point through the central difference method, and generate a spatio-temporal distribution map of the attenuation rate.

[0190] 202. For the instability threshold evolution curve output by the genetic prediction model, calculate the curvature parameter of the instability threshold evolution curve, and use the sliding window extreme value detection algorithm to identify the set of curvature extreme points. The set of curvature extreme points satisfies the condition that the first derivative of the curvature parameter is zero and the second derivative is negative;

[0191] Among them, the instability threshold evolution curve shows the trend of the instability threshold corresponding to the vascular tension regulation gene cluster changing with time, helping to understand the impact of genetic variation on cardiovascular health. The curvature parameter describes the degree of bending of the instability threshold evolution curve. Through the sliding window extreme value detection algorithm, the set of curvature extreme points can be identified, and these points mark important transitions in the system state. Sliding window extreme value detection algorithm: An algorithm for identifying the extreme points of a curve, which detects the changes in the first derivative and the second derivative of the curvature parameter through a sliding window. Set of curvature extreme points: The set of points that satisfy the condition that the first derivative of the curvature parameter is zero and the second derivative is negative, marking important transitions in the system state.

[0192] In the embodiments of the present application, first, obtain the instability threshold evolution curve from the genetic prediction model, and this curve describes the change trend of the instability threshold corresponding to the vascular tension regulation gene cluster over time.

[0193] Secondly, calculate the curvature parameter of the instability threshold evolution curve, and the specific formula is:

[0194]

[0195] where K(t) is the curvature parameter, κ(t) is the instability threshold evolution curve; dκ / dt is the first derivative of the instability threshold evolution curve, representing the change rate of the instability threshold over time; d 2 κ / dt 2 is the second derivative of the instability threshold evolution curve, representing the change rate of the change rate of the instability threshold; (1+(dκ / dt) 2 ) 3 / 2 is the normalization factor, which is used to adjust the scale of the curvature parameter so that it can accurately reflect the degree of curvature of the curve.

[0196] Next, use the sliding window extreme value detection algorithm to identify the set of curvature extreme points. The specific steps include:

[0197] Calculate the first derivative and the second derivative of the curvature parameter.

[0198] Detect the points that satisfy the first derivative being zero and the second derivative being negative, and mark them as curvature extreme points.

[0199] Finally, store the detected set of curvature extreme points for subsequent construction of the dynamic matching degree matrix.

[0200] 203. Construct a spatio-temporal matching tensor, couple the metabolic buffer capacity decay rate with the nearest neighbor curvature extreme points in the set of curvature extreme points according to the time alignment criterion, and generate a dynamic matching degree matrix.

[0201] Among them, the spatio-temporal matching tensor: a multi-dimensional data structure used to integrate the information of the metabolic buffer capacity decay rate and the curvature extreme points. The dynamic matching degree matrix: used to quantify the dynamic matching relationship between the metabolic buffer capacity decay rate and the curvature extreme points, and its dimensions include the number of spatial grids, the number of time nodes, and the number of gene clusters. The time alignment criterion: align the metabolic buffer capacity decay rate with the curvature extreme points in time to ensure that their time dimensions are consistent.

[0202] In the embodiments of the present application, first, couple the metabolic buffer capacity decay rate with the curvature extreme points according to the time alignment criterion to construct a spatio-temporal matching tensor. The specific steps include:

[0203] Align the spatio-temporal distribution map of the metabolic buffer capacity decay rate with the set of curvature extreme points in time.

[0204] Construct a multi-dimensional tensor, whose dimensions include the number of spatial grids, the number of time nodes, and the number of gene clusters.

[0205] Secondly, generate a dynamic matching degree matrix through a spatio-temporal matching tensor. The specific formula is:

[0206]

[0207] where β(s, t) is the attenuation rate of the metabolic buffer capacity, and κ(t p ) is the extreme value point of the nearest neighbor curvature.

[0208] Finally, optimize the dynamic matching degree matrix to ensure its comparability at different spatial coordinate points.

[0209] The following is a specific example for steps 201-203:

[0210] Taking a 50-year-old female target object as an example, first extract the cardiovascular and metabolic coupling data of continuous time series from her health examination data to construct an attenuation trajectory function. Calculate the attenuation rate of her metabolic buffer capacity through the central difference method, and it is found that the metabolic buffer capacity of her vascular endothelium shows a significant attenuation trend within a specific time window. Then, obtain the evolution curve of the instability threshold from the genetic prediction model, calculate its curvature parameter, and identify the set of curvature extreme value points through the sliding window extreme value detection algorithm. Finally, construct a spatio-temporal matching tensor, align the attenuation rate of the metabolic buffer capacity with the curvature extreme value points in time, and generate a dynamic matching degree matrix. By analyzing the dynamic matching degree matrix, it is found that there is a significant matching relationship between the attenuation rate of her metabolic buffer capacity and the curvature extreme value points at specific spatial coordinate points, indicating the risk of instability in her cardiovascular system.

[0211] This method can more accurately quantify the dynamic resilience of the cardiovascular system by calculating the attenuation rate of the metabolic buffer capacity and identifying the extreme value points of the curvature of the evolution curve of the instability threshold, constructing a dynamic matching degree matrix. By integrating the information of the attenuation rate of the metabolic buffer capacity and the curvature extreme value points through a spatio-temporal matching tensor to generate a dynamic matching degree matrix, it provides a more reliable basis for the early warning of cardiovascular and metabolic diseases. This method can effectively improve the accuracy of dynamic resilience assessment and early warning, and provide scientific support for clinical intervention and personalized treatment.

[0212] Furthermore, after step 1034, the method further includes:

[0213] 301. Normalize the dynamic matching degree matrix, calculate the historical matching degree mean and standard deviation of each spatial point, and form a standardized distribution map of the dynamic matching degree matrix;

[0214] Among them, the standardized dynamic matching degree matrix distribution map provides a unified reference framework by normalizing the historical matching degree mean and standard deviation of each spatial point. The standardized dynamic matching degree matrix distribution map contains normalized matching degrees. Normalization processing: converting the values in the dynamic matching degree matrix into a standardized range (such as 0 to 1) to facilitate comparison between different spatial points. Historical matching degree mean and standard deviation: representing the average matching degree and the fluctuation range in historical data for each spatial point respectively, and used for normalization processing.

[0215] Obtain the dynamic matching degree matrix from step 1034. This matrix describes the dynamic matching relationship between the metabolic buffer capacity decay rate and the curvature extreme point. Calculate the historical matching degree mean and standard deviation of each spatial point. The mean represents the average level of the matching degree, and the standard deviation represents the fluctuation range of the matching degree. Perform normalization processing on the dynamic matching degree matrix by subtracting the mean from the matching degree of each spatial point and dividing by the standard deviation to obtain the normalized matching degree. Visualize the normalized matching degree matrix to generate a standardized dynamic matching degree matrix distribution map for subsequent analysis.

[0216] 302. Calculate the instability risk weight factor through the curvature tolerance range specific to the gene cluster. The instability risk weight factor is used to reflect the instability threshold critical value of different gene clusters.

[0217] Among them, the instability risk weight factor reflects the instability threshold critical value of different gene clusters and is used to quantify the potential risks of different gene clusters. Curvature tolerance range specific to the gene cluster: the fluctuation range of the instability threshold critical value corresponding to different gene clusters, used to quantify the stability of the gene cluster. Instability threshold critical value: the critical value at which the gene cluster transitions from a stable state to an unstable state, reflecting the stability of the gene cluster.

[0218] Obtain the curvature tolerance range of different gene clusters from the genetic prediction model. This range reflects the fluctuation range of the instability threshold critical value of the gene cluster. Calculate the instability risk weight factor through the curvature tolerance range. The specific method is to compare the curvature parameter of the gene cluster with the instability threshold critical value, calculate its deviation degree, and convert it into a weight factor through an exponential function. Optimize the instability risk weight factor to ensure its comparability between different gene clusters.

[0219] 303. Perform a convolution operation on the normalized matching degree and the instability risk weight factor to generate a comprehensive matching degree index. The comprehensive matching degree index is used to associate critical environmental exposure parameter combinations.

[0220] Among them, the comprehensive matching degree index combines the normalized matching degree and the instability risk weight factor through convolution operation to generate a comprehensive evaluation index, which is used to quantify the comprehensive relationship between the decay rate of metabolic buffer capacity, the curvature extreme point and the instability risk of the gene cluster, and correlates with environmental exposure parameters. Normalized matching degree: The value in the dynamically normalized matching degree matrix after normalization, which is used to quantify the matching relationship between the decay rate of metabolic buffer capacity and the curvature extreme point. Convolution operation: A mathematical operation used to combine the normalized matching degree and the instability risk weight factor to generate the comprehensive matching degree index.

[0221] Perform convolution operation on the normalized matching degree and the instability risk weight factor to generate the comprehensive matching degree index. The specific method is to multiply the normalized matching degree and the instability risk weight factor element by element and sum the results to obtain the comprehensive matching degree index. Optimize the comprehensive matching degree index to ensure its comparability at different spatial coordinate points.

[0222] For example, taking a 55-year-old male target object as an example, first obtain the historical matching degree mean and standard deviation of each spatial point from the dynamically normalized matching degree matrix, perform normalization processing to generate a normalized dynamically normalized matching degree matrix distribution map. Then, calculate the instability risk weight factor through the curvature tolerance range specific to the gene cluster and find that the instability risk of its vascular tone regulation gene cluster is relatively high. Finally, perform convolution operation on the normalized matching degree and the instability risk weight factor to generate the comprehensive matching degree index, and find that there is a significant matching relationship between the decay rate of its metabolic buffer capacity and the curvature extreme point at specific spatial coordinate points, indicating the presence of instability risk in its cardiovascular system. By correlating with environmental exposure parameters, further confirm that the environmental oxidation load intensity in the high-risk area is relatively high.

[0223] This method performs normalization processing on the dynamically normalized matching degree matrix, calculates the historical matching degree mean and standard deviation of each spatial point, and generates a normalized dynamically normalized matching degree matrix distribution map. Calculate the instability risk weight factor through the curvature tolerance range specific to the gene cluster to quantify the potential risks of different gene clusters. Finally, perform convolution operation on the normalized matching degree and the instability risk weight factor to generate the comprehensive matching degree index, which is used to correlate with environmental exposure parameters. This method can more accurately evaluate the dynamic resilience of the cardiovascular system and provide a scientific basis for early warning and intervention.

[0224] In order to further improve the accuracy of dynamic resilience assessment and early warning of cardiovascular and metabolic diseases, in some embodiments, fuse the desynchronization index, instability threshold and critical environmental exposure parameter combination described in step 104 to construct a dynamic resilience assessment model, calculate the phase space contraction rate of the vascular metabolic homeostasis boundary, and generate a hierarchical early warning signal when the phase space contraction rate exceeds the vascular wall remodeling compensation ability, including:

[0225] 1041. Map the lipid transport rhythm desynchronization index to the energy metabolism state space of vascular wall cells to generate a multi-dimensional gradient field distribution of the lipid transport rhythm instability degree;

[0226] Step 1041 involves mapping the desynchronization index (especially the desynchronization index of the lipid transport rhythm) in the multi-modal oscillation feature spectrum to the energy metabolism state space of vascular wall cells. This step aims to generate a multi-dimensional gradient field distribution describing the lipid transport rhythm instability degree, which helps to understand the instability degree of the lipid transport process at different positions.

[0227] First, extract the desynchronization index data regarding the lipid transport rhythm from the previous steps. These data usually come from physiological signal analysis, such as electrocardiogram, hemodynamic monitoring, etc.

[0228] Second, construct a mathematical model to represent the energy metabolism state space of vascular wall cells, where each dimension represents different metabolic parameters (such as ATP level, redox state, etc.).

[0229] Finally, map the desynchronization index into the defined energy metabolism state space, and use interpolation techniques or other mathematical methods to create a multi-dimensional gradient field distribution map. This map shows the stability differences of the lipid transport rhythm in different regions.

[0230] For example, the researchers first collected the lipid transport rhythm data of the patients and determined the desynchronization index through frequency domain analysis. Then, they constructed an energy metabolism state space model including ATP concentration, NADH / NAD+ ratio, etc. By mapping the desynchronization index into this model, they successfully generated a three-dimensional gradient field distribution map showing the lipid transport rhythm instability degree. The results showed that in some specific regions, especially near the vascular bifurcation points, the lipid transport rhythm showed significant instability, suggesting that these regions may be high-risk areas for atherosclerosis.

[0231] 1042. Based on the instability threshold in the genetic prediction model, construct a dynamic constraint boundary for the coupling degree between vascular tension and metabolism, and the curvature characteristics of the dynamic constraint boundary are adjusted in real time according to the combination of critical environmental exposure parameters;

[0232] The goal of step 1042 is to construct a dynamic constraint boundary between vascular tension and metabolism coupling degree based on the instability threshold in the genetic prediction model, and this boundary can adjust its curvature characteristics in real time according to the change of the combination of critical environmental exposure parameters. This dynamic constraint boundary reflects the ability range of vascular wall cells to maintain normal physiological functions under the influence of different external conditions.

[0233] Extract the changes in the expression levels of gene clusters related to vascular tone regulation and their corresponding instability thresholds from the genetic prediction model. These thresholds mark the key points at which significant changes occur in gene expression or functional states.

[0234] Based on the instability thresholds and the known mechanisms of vascular tone and metabolic coupling, establish a mathematical model to describe the relationship between the two. This typically involves a system of non-linear kinetic equations that incorporate the effects of factors such as vascular smooth muscle contraction and nitric oxide released by endothelial cells on vascular tone, as well as the support of energy metabolism for these processes.

[0235] Combine environmental exposure parameters (such as the intensity, duration, and spatial action radius of oxidative load), and adjust the curvature of the above dynamic constraint boundaries through numerical simulation methods. When environmental conditions change, for example, increasing the level of oxidative stress, the boundary may become steeper or new inflection points may appear, reflecting a weakened ability of the system to respond to external pressure.

[0236] Validate the model using experimental data to ensure that it can accurately reflect the actual situation. If deviations are found, return to adjust the model parameters or improve the assumptions until the model prediction results match the experimental observations.

[0237] For example, the researchers first determined the instability thresholds of several key genes (such as the gene encoding nitric oxide synthase), which are crucial for maintaining normal vascular tone. Then, they used this information to construct a mathematical model that incorporates the interaction between vascular tone regulation and metabolic support. The model not only considers the equilibrium in the basal physiological state but also simulates the response of the vascular system under different environmental exposure conditions (such as long-term exposure to high concentrations of air pollutants). Through numerical simulation, it was observed that as the level of oxidative stress increased, the curvature of the dynamic constraint boundary gradually became larger, indicating that the ability of the vascular wall to maintain normal tone is challenged in a high oxidative load environment. In addition, the study also found that under certain specific conditions, even if the intensity of oxidative load did not reach the preset instability threshold, due to the cumulative effect over time, obvious morphological changes would occur in the boundary, suggesting that chronic low-dose exposure may also lead to health problems. Based on these findings, the research team proposed a series of preventive measures, including reducing pollution exposure and strengthening antioxidant protection, aiming to reduce the risk of cardiovascular diseases.

[0238] 1043. Establish the coupling equation between the critical environmental exposure parameter combination and the multi-dimensional gradient field distribution, and calculate the non-linear dissipation rate of metabolic oscillation energy at the vascular bifurcation;

[0239] Step 1043 aims to establish a coupling equation between the critical environmental exposure parameter combinations and the multi-dimensional gradient field distribution (describing the instability degree of lipid transport rhythm), and calculate the non-linear dissipation rate of metabolic oscillation energy at the vascular bifurcation through this equation. This process helps to understand how external environmental factors affect the energy metabolism state of vascular endothelial cells, especially their stability in the face of adverse conditions such as oxidative stress.

[0240] First, a mathematical model capable of describing the relationship between critical environmental exposure parameters (such as oxidative load intensity, exposure time, and spatial action radius) and the multi-dimensional gradient field distribution needs to be constructed. This model should take into account the influence mechanisms of different environmental factors on the instability degree of lipid transport rhythm.

[0241] Secondly, the data obtained from the previous steps are integrated, including but not limited to: the specific values of the critical environmental exposure parameter combinations; the multi-dimensional gradient field distribution maps describing the instability degree of lipid transport rhythm; the changes in the dynamic constraint boundary curvature.

[0242] Using the above coupling equation and the integrated dataset, the non-linear dissipation rate of metabolic oscillation energy at a specific location (such as the vascular bifurcation) is calculated through numerical simulation methods. This usually involves solving complex differential equations to capture the dynamic characteristics of energy dissipation over time.

[0243] A detailed analysis of the calculated non-linear dissipation rate is carried out to identify the conditions under which significant energy loss or system instability will occur. This information is of great significance for evaluating vascular health status and predicting potential risks.

[0244] 1044. Construct a dynamic resilience assessment model, which is determined based on the instability parameters mapped by the lipid transport rhythm desynchronization index, the dynamic constraint boundary curvature parameters corresponding to the instability threshold, and the non-linear dissipation rate parameters derived from the critical environmental exposure parameter combinations, and is used to evaluate the vascular wall remodeling compensation ability of different regions, and quantify the absorption threshold of the vascular wall remodeling compensation ability to gradient field perturbations through Lyapunov exponent analysis;

[0245] The goal of step 1044 is to construct a dynamic resilience assessment model for the cardiovascular-metabolic system. This model is based on the instability degree of lipid transport rhythm, the dynamic constraint boundary curvature, and the non-linear dissipation rate of metabolic oscillation energy, and is used to evaluate the vascular wall remodeling compensation ability of different regions, and quantify the absorption threshold of the vascular wall to gradient field perturbations through Lyapunov exponent analysis. This step is crucial for predicting and preventing the development of cardiovascular diseases.

[0246] First, it is necessary to integrate the data obtained from the previous steps, including information such as the multi-dimensional gradient field distribution of the lipid transport rhythm instability degree, the curvature characteristics of the dynamic constraint boundary, and the non-linear dissipation rate of the metabolic oscillation energy. Ensure that all data are compared and analyzed on the same spatio-temporal scale.

[0247] Based on the above data, use the method of systems biology to establish a mathematical model to describe the dynamic behavior of the cardiovascular-metabolic system. The model should include:

[0248] The lipid transport rhythm instability degree as an input variable;

[0249] The curvature of the dynamic constraint boundary reflects the stability and adaptability of the system;

[0250] The non-linear dissipation rate of the metabolic oscillation energy represents the response of the system to external perturbations.

[0251] Use the Lyapunov Exponent to quantify the stability of the system. The Lyapunov Exponent can be used to evaluate whether the system can return to its original state when faced with small perturbations, or whether it will deviate from its original trajectory and enter an unstable state. Calculate the Lyapunov Exponents in different regions to determine its ability to absorb perturbations.

[0252] Verify and optimize the model to ensure that it accurately reflects the actual situation. If deviations are found, adjust the parameters or improve the assumptions until the model prediction results match the experimental observations.

[0253] 1045. When the non-linear dissipation rate breaks through the curvature of the dynamic constraint boundary and the phase space contraction rate exceeds the absorption threshold, generate a graded warning signal corresponding to the instability tendency of the patch according to the boundary breakthrough azimuth angle and the spatial coordinates of the dissipation hot spot.

[0254] The goal of step 1045 is to generate a graded warning signal when the non-linear dissipation rate breaks through the curvature of the dynamic constraint boundary and the phase space contraction rate exceeds the absorption threshold. Specifically, according to the boundary breakthrough azimuth angle and the spatial coordinates of the dissipation hot spot, generate a graded warning signal corresponding to the instability tendency of the patch. This step aims to provide a mechanism to identify and warn potential cardiovascular risk areas so that intervention measures can be taken in a timely manner.

[0255] First, monitor the non-linear dissipation rate of the metabolic oscillation energy in real time and compare it with the curvature of the dynamic constraint boundary. When the non-linear dissipation rate increases significantly and breaks through the curvature of the dynamic constraint boundary, it indicates that the system has entered an unstable state.

[0256] Secondly, the phase space contraction rate is calculated through Lyapunov exponent analysis to quantify the system's ability to absorb perturbations. If the phase space contraction rate exceeds a pre-set absorption threshold, it means that the system cannot effectively cope with the current external or internal pressure and there is a high risk of instability.

[0257] Next, determine the specific location (i.e., azimuth angle) where the non-linear dissipation rate breaks through the dynamic constraint boundary and the spatial coordinates of the dissipation hotspots within this region. This information helps to precisely locate high-risk areas, facilitating subsequent medical evaluation and treatment planning.

[0258] According to the above analysis results, a graded warning signal is generated according to a pre-set standard. The grading standard can be divided into three levels: low, medium, and high according to the risk level, and each level corresponds to different intervention measure suggestions. For example, low risk may only require lifestyle adjustments, while high risk requires immediate medical intervention or even surgical treatment.

[0259] Finally, the warning signal is fed back to the medical team, and the model parameters and warning standards are continuously optimized according to the actual effects to ensure the accuracy and effectiveness of the system.

[0260] In a simulation experiment, the research team found that there was a significant increase in the non-linear dissipation rate at the bifurcation of a certain patient's blood vessels, and the phase space contraction rate exceeded the set absorption threshold. Further analysis showed that this area was located at the bifurcation of the right carotid artery and had obvious dissipation hotspots. Based on this, the system automatically generated a warning signal at the "high risk" level and recommended that the patient immediately undergo further examinations and possible treatments.

[0261] This example demonstrates how to use advanced computational models and technical means to achieve early warning and precise management of cardiovascular diseases. By integrating multi-source data and applying complex mathematical analysis methods, the accuracy of disease prediction can be greatly improved, providing strong support for personalized medicine.

[0262] In order to further improve the dynamic resilience assessment and warning accuracy of cardiovascular and metabolic diseases, in some embodiments, in step 1044, the constructed dynamic resilience assessment model is determined based on the instability parameter mapped by the lipid transport rhythm desynchronization index, the dynamic constraint boundary curvature parameter corresponding to the instability threshold, and the non-linear dissipation rate parameter derived from the combination of the critical environmental exposure parameters, and includes:

[0263] 401. Map the lipid transport rhythm instability degree to the energy metabolism state space of vascular wall cells to generate the spatial distribution function of the lipid transport rhythm instability degree;

[0264] Vascular wall cell energy metabolism state space: A multi-dimensional space used to describe the energy distribution of vascular wall cells in different metabolic states. Spatial distribution function: Used to characterize the degree of metabolic imbalance in different regions of the vascular wall, reflecting the spatial distribution of the instability degree of lipid transport rhythm.

[0265] First, obtain the instability degree of lipid transport rhythm from step 101, which reflects the degree of desynchronization between lipid transport efficiency and metabolic demand. Secondly, map the instability degree of lipid transport rhythm to the vascular wall cell energy metabolism state space. The specific method is to convert the discrete instability degree data of lipid transport rhythm into a continuous spatial distribution function through an interpolation algorithm (such as bilinear interpolation or cubic spline interpolation). Finally, describe the degree of metabolic imbalance in different regions of the vascular wall through the spatial distribution function, and generate a spatial distribution map of the instability degree of lipid transport rhythm.

[0266] 402. Construct a dynamic constraint boundary for the coupling degree between vascular tension and metabolism based on the instability threshold in the genetic prediction model, and generate a curvature distribution function of the dynamic constraint boundary;

[0267] Among them, the dynamic constraint boundary is used to describe the dynamic change range of the coupling degree between vascular tension and metabolism, reflecting the stability boundary of the system under different environmental exposure parameters. Its curvature characteristics are adjusted in real time with the combination of critical environmental exposure parameters to generate a curvature distribution function of the dynamic constraint boundary. Curvature distribution function: Used to describe the degree of bending of the dynamic constraint boundary, reflecting the geometric characteristics of the boundary at different spatial coordinate points.

[0268] First, obtain the instability threshold from the genetic prediction model, which reflects the stability boundary of the gene cluster. Secondly, construct a dynamic constraint boundary for the coupling degree between vascular tension and metabolism based on the instability threshold. The specific method is to convert the instability threshold data into a continuous dynamic constraint boundary through an interpolation algorithm (such as bilinear interpolation or cubic spline interpolation). Then, calculate the curvature parameters of the dynamic constraint boundary. The specific method is to calculate the first derivative and second derivative of the boundary through numerical differentiation, and then calculate the curvature parameters. Finally, describe the degree of bending of the dynamic constraint boundary through the curvature distribution function, generate a curvature distribution map, visualize the generated curvature distribution function, and verify its accuracy through experimental data or clinical data.

[0269] 403. Establish a coupling equation between the combination of critical environmental exposure parameters and the spatial distribution function of the instability degree of lipid transport rhythm, calculate the non-linear dissipation rate of metabolic oscillation energy at the vascular bifurcation, and generate a spatio-temporal distribution function of the non-linear dissipation rate;

[0270] Critical environmental exposure parameter combination: including the oxidation load intensity threshold, exposure duration, and spatial action radius, used to describe the impact of environmental oxidation load on the metabolic buffering capacity of vascular endothelium. Coupling equation: used to describe the dynamic relationship between the critical environmental exposure parameter combination and the spatial distribution function of lipid transport rhythm instability. Nonlinear dissipation rate: used to quantify the dissipation rate of metabolic oscillation energy at blood vessel bifurcations, reflecting the dynamic changes of local metabolic function.

[0271] First, obtain the critical environmental exposure parameter combination from step 103, including the oxidation load intensity threshold, exposure duration, and spatial action radius. Secondly, establish a coupling equation between the critical environmental exposure parameter combination and the spatial distribution function of lipid transport rhythm instability. The specific method is to describe the dynamic relationship between the two through multiple regression analysis or partial differential equations. Calculate the nonlinear dissipation rate of metabolic oscillation energy at blood vessel bifurcations through the coupling equation. The specific method is to solve the coupling equation through numerical simulation (such as finite element analysis or finite difference method). Finally, describe the changes of the nonlinear dissipation rate in time and space through a spatio-temporal distribution function, and generate a spatio-temporal distribution map of the nonlinear dissipation rate.

[0272] 404. Integrate the spatial distribution function of lipid transport rhythm instability, the dynamic constraint boundary curvature distribution function, and the spatio-temporal distribution function of the nonlinear dissipation rate to construct a dynamic resilience assessment model.

[0273] Dynamic resilience assessment model: used to evaluate the absorption capacity of the blood vessel wall against metabolic oscillation energy perturbations, and a model reflecting the vascular wall remodeling compensation ability. Vascular wall remodeling compensation ability: used to describe the self-repair ability of the vascular wall under metabolic oscillation energy perturbations, reflecting the stability of local metabolic function.

[0274] First, integrate the spatial distribution function of lipid transport rhythm instability, the dynamic constraint boundary curvature distribution function, and the spatio-temporal distribution function of the nonlinear dissipation rate to generate the input data of the dynamic resilience assessment model. Select a suitable machine learning algorithm (such as random forest, support vector machine, or deep learning model) to construct the dynamic resilience assessment model. Use the training set data to train the model, optimize the model parameters, and ensure its prediction accuracy. Validate the model through cross-validation or an independent validation set to evaluate its prediction performance. Secondly, apply the dynamic resilience assessment model to evaluate the vascular wall remodeling compensation ability in different regions, generate the evaluation results, visualize the evaluation results, and verify its accuracy through experimental data or clinical data.

[0275] For example, taking a 60-year-old female target subject as an example, first, map the instability degree of her lipid transport rhythm to the energy metabolism state space of vascular wall cells to generate the spatial distribution function of the instability degree of lipid transport rhythm. Next, based on the instability threshold in the genetic prediction model, construct the dynamic constraint boundary of the coupling degree between vascular tension and metabolism to generate the curvature distribution function of the dynamic constraint boundary. Then, establish the coupling equation between the critical environmental exposure parameter combination and the spatial distribution function of the instability degree of lipid transport rhythm, calculate the nonlinear dissipation rate of metabolic oscillation energy at the vascular bifurcation, and generate the spatio-temporal distribution function of the nonlinear dissipation rate. Finally, integrate the spatial distribution function of the instability degree of lipid transport rhythm, the curvature distribution function of the dynamic constraint boundary, and the spatio-temporal distribution function of the nonlinear dissipation rate to construct a dynamic resilience assessment model and evaluate her vascular wall remodeling compensation ability. Through analysis, it is found that there are significant metabolic imbalances and instability risks in specific regions of her vascular wall, indicating that intervention measures need to be taken.

[0276] This method maps the instability degree of lipid transport rhythm to the energy metabolism state space of vascular wall cells to generate the spatial distribution function, and combines the curvature distribution function of the dynamic constraint boundary and the spatio-temporal distribution function of the nonlinear dissipation rate to construct a dynamic resilience assessment model. This model can comprehensively evaluate the vascular wall remodeling compensation ability in different regions, providing a scientific basis for the early warning and intervention of cardiovascular and metabolic diseases. By integrating multi-source data, this method significantly improves the accuracy and reliability of dynamic resilience assessment, providing strong support for clinical practice and personalized treatment.

[0277] In order to further improve the accuracy of dynamic resilience assessment and early warning of cardiovascular and metabolic diseases, in some embodiments, the step of identifying the topological connection strength between the vascular tension regulation gene cluster and the metabolic sensing pathway gene cluster based on genomics data in step 102, and quantifying the influence weight of genetic variation on the coupling efficiency of the coupling data by combining the phase delay parameter in the multi-modal oscillation feature spectrum to generate a genetic prediction model includes:

[0278] 1021. Extract the co-expression network of the vascular tension regulation gene cluster and the metabolic sensing pathway gene cluster from the genomics data of the target subject, and calculate the topological connection strength between the gene clusters;

[0279] Among them, the topological connection strength is used to characterize the functional synergy of the gene cluster in regulating the coupling efficiency of cardiovascular and metabolism, and reflects the role of the gene cluster in regulating the coupling efficiency of cardiovascular and metabolism. Co-expression network: A network structure that describes the correlation of expression levels between gene clusters, used to reflect the functional synergy of gene clusters.

[0280] In the embodiments of the present application, first, extract the expression data of the vascular tension regulation gene cluster and the metabolic sensing pathway gene cluster from the genomics data of the target subject.

[0281] Secondly, construct a co-expression network based on gene expression data. The specific method is to calculate the Pearson correlation coefficient or mutual information between gene clusters to generate a correlation matrix between gene clusters. The specific steps include:

[0282] Calculate the Pearson correlation coefficient between each pair of gene clusters to generate a correlation matrix.

[0283] Set a correlation threshold, retain significantly correlated gene cluster pairs, and construct a co-expression network.

[0284] Next, calculate the topological connection strength between gene clusters through graph theory methods (such as node degree, betweenness centrality, etc.) to reflect the functional cooperation of gene clusters. The specific steps include:

[0285] Calculate the node degree of each gene cluster to reflect the number of its connections with other gene clusters.

[0286] Calculate the betweenness centrality of each gene cluster to reflect its importance in the network.

[0287] Finally, optimize the co-expression network through modularity analysis or community detection algorithms, and extract the most representative gene cluster connections. The specific steps include:

[0288] Use the modularity analysis algorithm to divide the co-expression network into multiple modules, and extract the core gene cluster connections within the modules.

[0289] Identify the community structure in the network through the community detection algorithm, and extract the key connections between communities.

[0290] It should be noted that the preprocessing of gene expression data includes: 1) Data source: Extract the FPKM values of the vascular tone regulation gene clusters (such as NOS3, EDN1) and the metabolic sensing pathway gene clusters (such as PPARGC1A, SLC2A4) from RNA-seq data, and perform log2(FPKM + 1) transformation to stabilize the variance. 2) Batch effect correction: Use the ComBat algorithm to eliminate the influence of different sequencing batches, and use PCA visualization to verify the correction effect (the first 3 principal components explain the variance > 85%).

[0291] Among them, the process of generating the correlation matrix includes: 1) Correlation coefficient calculation: Use the WGCNAR package to calculate the weighted correlation coefficient between gene clusters (weight β = 6, satisfying the scale-free network topology property), and set the significance threshold to p < 0.01 (corrected by Benjamini-Hochberg FDR). 2) Supplementary mutual information analysis: For non-linear relationships, use the ARACNe algorithm to calculate mutual information, retain gene cluster pairs with M1 > 0.3, and take the union with the Pearson results.

[0292] Among them, the process of quantifying topological parameters includes: 1) Node degree calculation: Define the node degree ki = Σ j≠i A ij , where A ij is an adjacency matrix element (A ij = 1 indicates significant correlation).

[0293] 2) Betweenness centrality: Calculate the number of times the shortest path passes based on the Brandes fast algorithm. The formula is:

[0294]

[0295] where σ st is the total number of shortest paths from s to t, and σ st (v) is the number of paths passing through v.

[0296] Among them, the network optimization and module extraction process includes: 1) Modularity analysis: Use the Louvain algorithm for community detection, with a resolution parameter γ = 1.0 and an intra-module connection density threshold > 0.8. 2) Core connection screening: For each module, extract the top 10% of the edges with the highest connection degree within the module as core connections to form a refined co-expression network.

[0297] For example, in 100 hypertensive patients, the topological connection strength between the NOS3 gene cluster and the PPARγ cluster is 0.72 ± 0.15, which is significantly higher than that in the healthy control group (0.41 ± 0.11, p < 0.001.

[0298] 1022. Map the phase delay parameter in the multi-modal oscillation feature spectrum to the gene cluster co-expression network to generate a phase delay weighted gene cluster network;

[0299] Among them, the phase delay weighted gene cluster network is used to characterize the correlation between the functional synergy between gene clusters and the coupling efficiency of the coupling data. Phase delay parameter: Used to describe the time delay relationship between the cardiovascular elastic chamber and the supply of metabolic substrates, reflecting their synergy in dynamic regulation.

[0300] First, extract the phase delay parameter from the multi-modal oscillation feature spectrum, which reflects the dynamic coupling characteristics between the cardiovascular and metabolic systems.

[0301] Secondly, map the phase delay parameter to the gene cluster co-expression network to generate a phase delay weighted gene cluster network. The specific method is to add the phase delay parameter as a weight to the edges of the co-expression network through a weighting algorithm. The specific steps include:

[0302] Match the phase delay parameter with the edges in the co-expression network to generate weighted edges.

[0303] Normalize the weighted edges to ensure their comparability between different gene clusters.

[0304] Finally, optimize the phase-delay weighted gene cluster network to ensure its comparability among different gene clusters. The specific steps include:

[0305] Use graph optimization algorithms (such as the minimum spanning tree algorithm) to optimize the network structure and extract the most representative weighted connections.

[0306] Identify the community structure in the network through community detection algorithms and extract the key weighted connections between communities.

[0307] It should be noted that the phase-delay parameter mapping process includes: 1) Data alignment: Synchronize the time axis of the phase-delay parameters (time resolution 10 ms) of the multimodal oscillation feature spectrum with the gene expression data (time resolution 6 hours) through cubic spline interpolation. 2) Edge weight assignment: For the edge e ij in the co-expression network, its weight is updated as follows:

[0308] w′ ij = w ij ·exp(-Δφ ij / τ)

[0309] where Δφ ij is the mean phase delay of the corresponding gene cluster, and τ = 0.5 is the decay constant (optimized and determined through grid search).

[0310] Among them, the normalization process includes: Normalize the edge weights using the softmax function:

[0311]

[0312] Ensure that the sum of all weights is 1 to avoid the influence of scale differences on subsequent analysis.

[0313] Among them, the network structure optimization process includes: 1) Minimum spanning tree construction: Use the Kruskal algorithm to retain the edges with weights greater than 0.05, generate a connected sub-network, and remove isolated nodes. 2) Key connection identification: Based on edge betweenness centrality (calculate the number of times the shortest path between all node pairs passes through the edge), extract the top 5% of the high-betweenness edges as functional hubs.

[0314] 1023. Identify single nucleotide polymorphism sites in the gene clusters regulating vascular tone and the gene clusters in the metabolic sensing pathway based on genetic variation data, and calculate the regulatory effect value of each polymorphism site on the topological connection strength between gene clusters;

[0315] Among them, the regulatory effect value is used to quantify the impact of genetic variation on the functional synergy of gene clusters. Genetic variation data: Include single nucleotide polymorphism sites (SNPs) in the gene clusters regulating vascular tone and the gene clusters in the metabolic sensing pathway of the target object.

[0316] In the embodiments of the present application, first, single nucleotide polymorphism sites in the vasotonic regulatory gene cluster and the metabolic sensing pathway gene cluster are identified from the genomic data of the target object.

[0317] Secondly, the regulatory effect value of each polymorphism site on the topological connection strength between gene clusters is calculated by multiple regression analysis or Bayesian network analysis. The specific steps include:

[0318] Construct a multiple regression model, using SNPs data as the independent variable and topological connection strength as the dependent variable, and calculate the regulatory effect value of each SNPs.

[0319] Use Bayesian network analysis to identify the causal relationship between SNPs and topological connection strength, and calculate the regulatory effect value.

[0320] Finally, optimize the regulatory effect value to ensure its comparability between different gene clusters. The specific steps include:

[0321] Normalize the regulatory effect value so that its mean is 0 and the standard deviation is 1.

[0322] Screen out the SNPs with significant regulatory effects through significance tests (such as t-test or F-test).

[0323] Specifically, the process of SNPs screening and annotation includes: 1) Quality control criteria: Retain SNPs with MAF>5% and Hardy-Weinberg equilibrium p>0.001, and perform functional annotation using ANNOVAR, and preferentially select missense mutations and regulatory region SNPs (such as eQTL). 2) Linkage disequilibrium processing: Cluster SNPs with r 2 <0.2 as the threshold, and select representative tagSNPs for each cluster. Among them, the construction of the multiple regression model is achieved through the following formula:

[0324]

[0325] Where Y is the topological connection strength, X_i is the SNP genotype (additive coding 0 / 1 / 2), and β_i is the regulatory effect value.

[0326] Furthermore, perform multiple test correction: Adopt Bonferroni correction, and the significance threshold α = 0.05 / p (p is the total number of SNPs).

[0327] Among them, the Bayesian network analysis process includes: 1) Network structure learning: Use the HC algorithm (scoring function BIC) of the bnlearn package, and limit the maximum number of parent nodes = 3 to avoid overfitting. 2) Effect value calculation: Estimate the posterior probability through Markov chain Monte Carlo (MCMC) sampling, and the effect value is defined as the conditional probability difference:

[0328] ΔP = P(Y > Q 75 |X = 1) - P(Y > Q 75 |X = 0)

[0329] where Q 75 is the 75th percentile of the connection strength.

[0330] 1024. Integrate the regulatory effect value with the phase-delay weighted gene cluster network, and calculate the influence weight of genetic variation on the coupling efficiency of the coupling data;

[0331] wherein, the influence weight is used to characterize the contribution degree of genetic variation to the coupling efficiency by regulating the functional synergy of gene clusters.

[0332] In the embodiments of the present application, first, obtain the regulatory effect value from step 1023, which reflects the regulatory effect of the single nucleotide polymorphism site on the topological connection strength between gene clusters. Obtain the phase-delay weighted gene cluster network from step 1022, which reflects the correlation between the functional synergy between gene clusters and the coupling efficiency.

[0333] Secondly, integrate the regulatory effect value with the phase-delay weighted gene cluster network, and calculate the influence weight of genetic variation on the coupling efficiency. The specific method is to add the regulatory effect value as a weight to the phase-delay weighted gene cluster network through a weighted algorithm. The specific steps include:

[0334] Match the regulatory effect value with the edges in the phase-delay weighted gene cluster network to generate weighted edges.

[0335] Normalize the weighted edges to ensure their comparability between different gene clusters.

[0336] Finally, optimize the influence weight to ensure its comparability between different gene clusters. The specific steps include:

[0337] Use a graph optimization algorithm (such as the minimum spanning tree algorithm) to optimize the network structure and extract the most representative weighted connections.

[0338] Identify the community structure in the network through a community detection algorithm and extract the key weighted connections between communities.

[0339] It should be noted that the weight fusion algorithm includes: 1) Linear weighting: Update the final weight of each edge:

[0340]

[0341] where γ = 0.5 is a regulatory factor (determined by leave-one-out cross-validation), and β_{ij}∧{SNP} is the mean value of the SNP effect values of the gene clusters connected at both ends.

[0342] Among them, the normalization process includes: Z - score standardization, and for the influence weights,

[0343]

[0344] where μ and σ are respectively the mean and standard deviation of the weights of the entire network, and the edges with |z| > 2.58 are retained (p < 0.01).

[0345] Among them, the optimization of network robustness includes: 1) Random forest feature selection: Use a random forest (ntree = 500) to calculate the importance scores of edge weights, and remove redundant connections with scores < 0.01. 2) Small - world property optimization: Adjust the network through the simulated annealing algorithm to make it satisfy the small - world coefficient σ > 1 (the clustering coefficient C is > 1 compared with the random network, and the characteristic path length L is close to the random network).

[0346] 1025. Construct a genetic prediction model based on the influence weights.

[0347] Among them, the genetic prediction model is used to predict the change trend of the coupling efficiency of the coupling data of the target object under a specific genetic variation background.

[0348] In the embodiments of the present application, first, obtain the influence weights from step 1024, and this weight reflects the contribution degree of genetic variation to the coupling efficiency. Select a suitable machine - learning algorithm (such as random forest, support vector machine, or deep - learning model) to construct a genetic prediction model.

[0349] Secondly, use the training set data to train the model, optimize the model parameters, and ensure its prediction accuracy. The specific steps include:

[0350] Use the influence weights as input features and the coupling efficiency as the output label to train the machine - learning model.

[0351] Use the cross - validation method to optimize the model parameters and ensure its generalization ability.

[0352] Then, verify the model through cross - validation or an independent validation set, and evaluate its prediction performance. The specific steps include:

[0353] Use the validation set data to evaluate the prediction accuracy of the model, and calculate indicators such as accuracy, recall rate, and F1 - score.

[0354] Evaluate the discrimination ability of the model through the ROC curve and AUC value.

[0355] Finally, apply the genetic prediction model to the prediction of the coupling efficiency of the target object to generate a prediction result. The specific steps include:

[0356] Input the genetic variation data and influence weights of the target object to generate the coupling efficiency prediction results.

[0357] Visualize the prediction results to generate a prediction report.

[0358] It should be noted that the model architecture design includes:

[0359] Input features: Include 128-dimensional features such as influence weights, SNP effect values, topological connection strengths, etc.

[0360] Model selection: Adopt the XGBoost gradient boosting tree, and the parameter settings are max_depth = 5, learning_rate = 0.1, n_estimators = 200.

[0361] Among them, the training strategy includes: 1) Data division: Divide the training set, validation set, and test set according to 7:2:1, and use stratified sampling to keep the case-control ratio consistent. 2) Regularization: The L2 regularization coefficient λ = 1.0, and the early stopping method (patience = 10 rounds) is used to prevent overfitting.

[0362] Among them, the performance evaluation includes: 1) Main indicators: The AUC of the test set = 0.91 (95% CI: 0.88 - 0.94), the sensitivity is 82%, and the specificity is 89%. 2) Calibration curve: The Brier score = 0.11, and the Hosmer-Lemeshow test p = 0.23, indicating that the predicted probability and the observed frequency match well.

[0363] This method extracts the gene cluster co-expression network in genomics data, calculates the topological connection strength, and combines the phase delay parameters in the multi-modal oscillation feature spectrum to generate a phase delay weighted gene cluster network. By identifying single nucleotide polymorphism sites and calculating the regulatory effect values, it quantifies the impact of genetic variations on the functional synergy of gene clusters. Finally, based on the influence weights, a genetic prediction model is constructed to predict the change trend of the coupling efficiency of the target object under a specific genetic variation background. This method can comprehensively evaluate the impact of genetic variations on the coupling efficiency of the cardiovascular and metabolic systems, providing a scientific basis for early warning and intervention. By integrating multi-source data, this method significantly improves the accuracy and reliability of genetic prediction, providing strong support for clinical practice and personalized treatment.

[0364] Figure 2 This is a schematic structural diagram of a dynamic resilience assessment and early warning system for cardiovascular and metabolic diseases provided by an embodiment of the present application, as Figure 2 shown, the device includes:

[0365] An extraction module 21, configured to extract a phase delay parameter between a cardiovascular elastic chamber and a metabolic substrate supply from the coupled data of cardiovascular and metabolism in the continuous time series of the acquired target object, and construct a multi-modal oscillation feature spectrum including an index of lipid transport rhythm desynchronization;

[0366] An identification module 22, configured to identify the topological connection strength between a vascular tone regulation gene cluster and a metabolic sensing pathway gene cluster based on genomic data, and combine the phase delay parameter in the multi-modal oscillation feature spectrum to quantify the influence weight of genetic variation on the coupling efficiency of the coupled data, and generate a genetic prediction model;

[0367] A calculation module 23, configured to simulate and calculate an attenuation trajectory function of the vascular endothelial metabolic buffering capacity according to the vascular local shear force distribution and the environmental oxidation load parameter of the target object, analyze a dynamic matching degree matrix between the attenuation trajectory function and an instability threshold in the genetic prediction model, and determine a critical environmental exposure parameter combination;

[0368] A construction module 24, configured to fuse the lipid transport rhythm desynchronization index, the instability threshold, and the critical environmental exposure parameter combination, construct a dynamic resilience evaluation model, calculate a phase space shrinkage rate of the vascular metabolic steady-state boundary, and generate a hierarchical warning signal when the phase space shrinkage rate exceeds the vascular wall remodeling compensation ability.

[0369] Figure 2 The dynamic resilience evaluation and warning system for cardiovascular and metabolic diseases can execute Figure 1 The dynamic resilience evaluation and warning method for cardiovascular and metabolic diseases described in the embodiments shown, and its implementation principle and technical effects will not be elaborated. For the dynamic resilience evaluation and warning system for cardiovascular and metabolic diseases in the above embodiments, the specific manners of operations performed by each module and unit have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0370] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for dynamic resilience assessment and early warning of cardiovascular and metabolic diseases, characterized in that, Comprising: Extracting the phase delay parameter between the cardiovascular elastic chamber and the metabolic substrate supply from the coupled data of cardiovascular and metabolism within the continuous time series of the obtained target object, so as to construct a multi-modal oscillation feature spectrum including the lipid transport rhythm desynchronization index; Identifying the topological connection strength between the vascular tone regulation gene cluster and the metabolic sensing pathway gene cluster based on genomic data, and combining the phase delay parameter in the multi-modal oscillation feature spectrum to quantify the influence weight of genetic variation on the coupling efficiency of the coupled data, so as to generate a genetic prediction model; According to the vascular local shear force distribution and environmental oxidation load parameters of the target object, simulating and calculating the attenuation trajectory function of the vascular endothelial metabolic buffer capacity, and analyzing the dynamic matching degree matrix between the attenuation trajectory function and the instability threshold in the genetic prediction model to determine the critical environmental exposure parameter combination; Fusing the lipid transport rhythm desynchronization index, the instability threshold and the critical environmental exposure parameter combination to construct a dynamic resilience assessment model, so as to calculate the phase space contraction rate of the vascular metabolic homeostasis boundary, and generating a hierarchical warning signal when the phase space contraction rate exceeds the vascular wall remodeling compensation ability.

2. The method according to claim 1, wherein The simulating and calculating the attenuation trajectory function of the vascular endothelial metabolic buffer capacity according to the vascular local shear force distribution and environmental oxidation load parameters of the target object includes: Based on the three-dimensional stress distribution map of the vascular wall of the target object, extracting the vascular local shear force distribution of the target vascular bifurcation segment, constructing a dynamic response model in combination with the monitoring data of endothelial cell metabolic flux, and calculating the phase lag amount of lipid transport efficiency to shear force fluctuation through frequency domain coupling analysis to generate a metabolic delay feature map at the vascular bifurcation; According to the spatio-temporal distribution of the environmental oxidation load parameters, establishing an oxidative stress wave propagation equation to solve the concentration standing wave formation threshold of the metabolic buffer medium at the vascular bifurcation through the oxidative stress wave propagation equation, and the concentration standing wave formation threshold is used to calibrate the dynamic response boundary of the endothelial metabolic buffer capacity; Inputting the metabolic delay feature map at the vascular bifurcation into the dynamic response model, and combining the concentration standing wave formation threshold to solve the attenuation trajectory function of the vascular endothelial metabolic buffer capacity through spatio-temporal convolution operation.

3. The method according to claim 2, characterized in that Analyzing the dynamic matching degree matrix between the attenuation trajectory function and the instability threshold in the genetic prediction model to determine the critical environmental exposure parameter combination includes: Synchronously obtaining the instability threshold evolution curve corresponding to the vascular tone regulation gene cluster in the genetic prediction model; Calculating the buffer capacity attenuation rate based on the time derivative of the attenuation trajectory function, and extracting the curvature extreme point of the instability threshold evolution curve to establish a dynamic matching degree matrix between the buffer capacity attenuation rate and the curvature extreme point; Based on the dynamic matching degree matrix, when the matching degree of the buffer capacity attenuation rate at the coordinate point of the vascular bifurcation exceeds the curvature tolerance range of the corresponding gene cluster, it is marked as a high-risk area of metabolic reserve depletion, and the spatio-temporal distribution parameters of the environmental oxidation load at the coordinate point of the vascular bifurcation are associated; According to the matching degree data in the dynamic matching degree matrix, simulate the standing wave amplification effect of the coordinate points in the high-risk area of metabolic reserve depletion through the oxidative stress wave propagation equation, so as to calculate the critical environmental exposure parameter combination that causes a cliff-like decline in the metabolic buffer capacity. The critical environmental exposure parameter combination includes the oxidative load intensity threshold, the exposure duration, and the spatial action radius.

4. The method according to claim 3, wherein Calculating the buffer capacity attenuation rate based on the time derivative of the attenuation trajectory function, and extracting the curvature extreme points of the instability threshold evolution curve to establish a dynamic matching degree matrix between the buffer capacity attenuation rate and the curvature extreme points, including: Perform time-domain differential processing on the attenuation trajectory function, and use the central difference method to calculate the metabolic buffer capacity attenuation rate of each spatial coordinate point within a preset time window. The width of the preset time window is one-fourth of the characteristic period parameter of the vascular wall metabolic oscillation. For the instability threshold evolution curve output by the genetic prediction model, calculate the curvature parameter of the instability threshold evolution curve, and use the sliding window extreme value detection algorithm to identify the set of curvature extreme points. The set of curvature extreme points satisfies the condition that the first derivative of the curvature parameter is zero and the second derivative is negative. Construct a spatio-temporal matching tensor, couple the metabolic buffer capacity attenuation rate with the nearest neighbor curvature extreme points in the set of curvature extreme points according to the time alignment criterion, and generate a dynamic matching degree matrix. The dimensions of the dynamic matching degree matrix include the number of spatial grids, the number of time nodes, and the number of gene clusters.

5. The method according to claim 4, wherein It also includes: Perform normalization processing on the dynamic matching degree matrix, calculate the historical matching degree mean and standard deviation of each spatial point, and form a standardized dynamic matching degree matrix distribution map, which contains the normalized matching degree. Calculate the instability risk weight factor through the curvature tolerance range specific to the gene cluster. The instability risk weight factor is used to reflect the instability threshold critical values of different gene clusters. Perform convolution operation on the normalized matching degree and the instability risk weight factor to generate a comprehensive matching degree index, which is used to associate the critical environmental exposure parameter combination.

6. The method according to claim 1, wherein Fusing the lipid transport rhythm desynchronization index, the instability threshold, and the critical environmental exposure parameter combination to construct a dynamic resilience assessment model to calculate the phase space contraction rate of the vascular metabolic steady-state boundary, and generate a hierarchical warning signal when the phase space contraction rate exceeds the vascular wall remodeling compensation ability, including: Construct a dynamic resilience assessment model, which is determined based on the instability degree parameter mapped by the lipid transport rhythm desynchronization index, the dynamic constraint boundary curvature parameter corresponding to the instability threshold, and the non-linear dissipation rate parameter derived from the critical environmental exposure parameter combination, and quantify the absorption threshold of the vascular wall remodeling compensation ability to the gradient field perturbation through Lyapunov exponent analysis. Apply the dynamic resilience assessment model to the assessment of the vascular wall remodeling compensation ability, and calculate the phase space contraction rate of the vascular metabolic steady-state boundary. The phase space contraction rate is used to characterize the absorption ability of the vascular wall to the metabolic oscillation energy perturbation. When the non-linear dissipation rate breaks through the curvature of the dynamic constraint boundary and the phase space contraction rate exceeds the absorption threshold, a hierarchical warning signal corresponding to the instability tendency of the patch is generated according to the boundary breakthrough azimuth angle and the spatial coordinates of the dissipation hot spot.

7. The method according to claim 6, characterized in that Before generating the hierarchical warning signal corresponding to the instability tendency of the patch according to the boundary breakthrough azimuth angle and the spatial coordinates of the dissipation hot spot when the non-linear dissipation rate breaks through the curvature of the dynamic constraint boundary and the phase space contraction rate exceeds the absorption threshold, it further includes: Mapping the lipid transport rhythm desynchronization index to the energy metabolism state space of vascular wall cells to generate a multi-dimensional gradient field distribution of the lipid transport rhythm instability degree; Based on the instability threshold in the genetic prediction model, a dynamic constraint boundary of the coupling degree between vascular tension and metabolism is constructed, and the curvature characteristics of the dynamic constraint boundary are adjusted in real time according to the critical environmental exposure parameter combination; An coupling equation between the critical environmental exposure parameter combination and the multi-dimensional gradient field distribution is established, and the non-linear dissipation rate of the metabolic oscillation energy at the vascular bifurcation is calculated.

8. The method according to claim 6, wherein The construction of the dynamic resilience assessment model, which is determined based on the instability degree parameters mapped by the lipid transport rhythm desynchronization index, the curvature parameters of the dynamic constraint boundary corresponding to the instability threshold, and the non-linear dissipation rate parameters derived from the critical environmental exposure parameter combination, includes: Mapping the lipid transport rhythm instability degree to the energy metabolism state space of vascular wall cells to generate a spatial distribution function of the lipid transport rhythm instability degree; Based on the instability threshold in the genetic prediction model, a dynamic constraint boundary of the coupling degree between vascular tension and metabolism is constructed to generate a curvature distribution function of the dynamic constraint boundary; An coupling equation between the critical environmental exposure parameter combination and the spatial distribution function of the lipid transport rhythm instability degree is established, the non-linear dissipation rate of the metabolic oscillation energy at the vascular bifurcation is calculated, and a spatio-temporal distribution function of the non-linear dissipation rate is generated; Integrating the spatial distribution function of the lipid transport rhythm instability degree, the curvature distribution function of the dynamic constraint boundary, and the spatio-temporal distribution function of the non-linear dissipation rate to construct a dynamic resilience assessment model, which is used to evaluate the vascular wall remodeling compensation ability in different regions.

9. The method according to claim 1, wherein Based on genomics data, identifying the topological connection strength between the vascular tension regulation gene cluster and the metabolic sensing pathway gene cluster, and combining the phase delay parameter in the multi-modal oscillation feature spectrum to quantify the influence weight of genetic variation on the coupling efficiency of the coupling data to generate a genetic prediction model, includes: Extracting the co-expression network of the vascular tension regulation gene cluster and the metabolic sensing pathway gene cluster based on genomics data to calculate the topological connection strength between gene clusters; Mapping the phase delay parameter in the multi-modal oscillation feature spectrum to the gene cluster co-expression network to generate a phase delay weighted gene cluster network; Identifying single nucleotide polymorphism sites in the vascular tension regulation gene cluster and the metabolic sensing pathway gene cluster based on genetic variation data, and calculating the regulatory effect value of each polymorphism site on the topological connection strength between gene clusters; Integrate the regulatory effect value with the phase delay weighted gene cluster network, and calculate the influence weight of genetic variation on the coupling efficiency of the coupling data; Construct a genetic prediction model based on the influence weight, and the genetic prediction model is used to predict the change trend of the coupling efficiency of the coupling data of the target object under a specific genetic variation background.

10. A dynamic resilience assessment and early warning system for cardiovascular and metabolic diseases, characterized in that, It includes: An extraction module, configured to extract the phase delay parameter between the cardiovascular elastic chamber and the metabolic substrate supply from the coupling data of cardiovascular and metabolism in the continuous time series of the obtained target object, so as to construct a multi-modal oscillation feature spectrum including the lipid transport rhythm desynchronization index; An identification module, configured to identify the topological connection strength between the vascular tone regulation gene cluster and the metabolic sensing pathway gene cluster based on genomic data, and combine the phase delay parameter in the multi-modal oscillation feature spectrum to quantify the influence weight of genetic variation on the coupling efficiency of the coupling data, so as to generate a genetic prediction model; A calculation module, configured to simulate and calculate the attenuation trajectory function of the vascular endothelial metabolic buffer capacity according to the local shear force distribution of the blood vessels of the target object and the environmental oxidation load parameter, and analyze the dynamic matching degree matrix between the attenuation trajectory function and the instability threshold in the genetic prediction model, so as to determine the critical environmental exposure parameter combination; A construction module, configured to fuse the lipid transport rhythm desynchronization index, the instability threshold and the critical environmental exposure parameter combination, construct a dynamic resilience assessment model, so as to calculate the phase space contraction rate of the vascular metabolic steady-state boundary, and generate a hierarchical warning signal when the phase space contraction rate exceeds the vascular wall remodeling compensation ability.

Images