Data fusion processing method and system of intelligent sensor based on MEMS

Abstract

The invention relates to a data fusion processing method and system for an intelligent sensor based on MEMS, and the method comprises the following steps: carrying out the non-stationary signal decomposition of a multi-modal physiological parameter time sequence data stream, and obtaining a key vital sign feature sequence; performing phase coupling degree calculation on the key vital sign feature sequence to obtain an inter-organ function correlation intensity matrix; performing high-dimensional feature space projection on the critical patient based on the inter-organ function association intensity matrix to obtain a pathological state feature map of the patient; performing nonlinear kinetic analysis on the pathological state characteristic spectrum of the patient to obtain a disease progress dynamic trajectory; and performing clinical decision support reasoning based on the disease progress dynamic trajectory to obtain personalized treatment suggestions, thereby solving the technical problem that the existing analysis method is often limited to observation of a single physiological parameter or simple statistical analysis and lacks the ability to understand the disease mechanism from the overall perspective.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent sensors, and in particular to a data fusion processing method and system for an intelligent sensor based on MEMS. Background Art

[0002] In modern medical environments, real-time monitoring and accurate assessment of the physiological status of critically ill patients are crucial. However, traditional monitoring methods based on a single sensor or a few sensors are difficult to fully and accurately capture the complex physiological information of patients. With the development of microelectromechanical systems (MEMS) technology, the application of smart sensors has provided a new approach to solving this problem. By deploying a variety of MEMS sensors in the intensive care unit, continuous monitoring of multiple vital sign parameters of patients can be achieved, but how to effectively fuse these multimodal data and extract valuable medical information from them has become an urgent problem to be solved.

[0003] In addition, in clinical practice, doctors are faced with a highly complex dynamic system - the human body. The interactions between different organs and their functional correlations not only affect the progression of the disease, but also determine the effectiveness of treatment strategies. Existing analysis methods are often limited to the observation of a single physiological parameter or simple statistical analysis, and lack the ability to understand the disease mechanism from a holistic perspective. Therefore, developing a method that can reflect the strength of functional correlations between organs is of great significance for a deep understanding of the pathological process and the formulation of personalized treatment plans. This demand has promoted the research and development of MEMS-based intelligent sensor data fusion processing methods.

[0004] Finally, although there have been many studies on data fusion and signal processing technology, there are still many challenges in applying them to clinical decision support. For example, how to ensure the authenticity and reliability of the extracted vital sign feature sequence, how to identify patterns closely related to disease progression from high-dimensional feature space, etc. The existence of these problems not only limits the widespread clinical application of existing technologies, but also highlights the importance of further exploring data fusion processing methods based on MEMS smart sensors. By overcoming these challenges, the quality and efficiency of critically ill patient management can be significantly improved, thereby improving patient treatment outcomes. Summary of the invention

[0005] The main purpose of the present invention is to provide a data fusion processing method and system based on MEMS intelligent sensors, which solves the technical problem that existing analysis methods are often limited to the observation of a single physiological parameter or simple statistical analysis and lack the ability to understand the disease mechanism from a holistic perspective.

[0006] To achieve the above object, the present invention provides a data fusion processing method of a MEMS-based intelligent sensor, comprising the following steps: Perform multi-channel synchronous sampling and fusion processing on the physiological signals of critically ill patients collected by MEMS sensors to obtain multi-modal physiological parameter time series data stream; Performing non-stationary signal decomposition on the multimodal physiological parameter time series data stream to obtain a key vital sign feature sequence; Calculating the phase coupling degree of the key vital sign characteristic sequence to obtain an inter-organ functional association strength matrix; Performing high-dimensional feature space projection on the critically ill patient based on the inter-organ functional association strength matrix to obtain a feature map of the patient's pathological state; Performing nonlinear dynamic analysis on the characteristic graph of the patient's pathological state to obtain a dynamic trajectory of disease progression; Clinical decision support reasoning is performed based on the dynamic trajectory of disease progression to obtain personalized treatment recommendations.

[0007] Furthermore, the non-stationary signal decomposition is performed on the multimodal physiological parameter time series data stream to obtain a key vital sign feature sequence, including: Adaptively performing biorthogonal filtering separation on the multimodal physiological parameter time series data stream to obtain a nonlinear physiological fluctuation component, and performing multi-level harmonic analysis on the nonlinear physiological fluctuation component through an adaptive oscillation identification mechanism to obtain a physiological system phase change feature set; Based on the multi-scale covariance structure method, a statistical significance analysis is performed on the phase change feature set of the physiological system to obtain a key physiological coupling network, and a topological stability assessment is performed on the key physiological coupling network to obtain multi-organ function linkage data; Phase synchronization measurement and extraction are performed on the multi-organ function linkage data to obtain a key vital sign feature sequence; wherein the key vital sign feature sequence includes the cardiovascular system regulation ability, respiratory compensation reserve index, circulatory system homeostasis maintenance parameters and multi-system collaborative function characteristics.

[0008] Furthermore, the phase coupling degree is calculated based on the key vital sign feature sequence to obtain the inter-organ functional association strength matrix, including: Performing bispectral coherence analysis on the key vital sign characteristic sequence to obtain a nonlinear phase synchronization characteristic spectrum, and performing time-varying causal relationship analysis on the nonlinear phase synchronization characteristic spectrum based on wavelet bidirectional transformation to obtain a functional network connection strength map; Performing directional information transfer analysis on the functional network connection strength map by using a transfer entropy calculation method to obtain a multi-organ interaction matrix, and performing resonance frequency band screening on the multi-organ interaction matrix to obtain a collaborative working mode of key physiological systems; The phase locking value of the collaborative working mode of the key physiological systems is calculated to obtain the organ function synchronization degree data, and a graph theory network characteristic analysis is performed based on the organ function synchronization degree data to obtain the organ function association strength matrix; wherein the organ function association strength matrix includes the cardiopulmonary function collaborative efficiency coefficient, cerebrovascular autoregulation capacity parameters, renal blood perfusion status and multi-system metabolic balance network characteristics.

[0009] Furthermore, the high-dimensional feature space projection is performed based on the inter-organ functional association strength matrix to obtain the patient's pathological state feature map, including: Performing a tensor decomposition operation on the inter-organ functional association intensity matrix to obtain a multi-dimensional physiological system interaction feature space, performing topological structure extraction on the multi-dimensional physiological system interaction feature space to obtain a disease state topological skeleton diagram, and performing multi-scale persistence calculation on the disease state topological skeleton diagram to obtain a set of key pathological state branch points; Performing nonlinear boundary mapping on the key pathological state branch point set by using kernel surface reconstruction technology to obtain an organ function degradation partition map, and performing spectral clustering segmentation processing on the organ function degradation partition map to obtain a pathological state subspace structure; Performing geometric depth feature extraction on the pathological state subspace structure to obtain a disease progression path network, and performing Ricci curvature calculation based on the disease progression path network to obtain a pathological state transformation risk surface; Based on differential geometry mapping, a curvature flow evolution analysis is performed on the pathological state transformation risk surface to obtain a disease state manifold graph, and a characteristic vector field is constructed based on the disease state manifold graph to obtain a patient pathological state characteristic map, wherein the patient pathological state characteristic map includes a multi-organ dysfunction pattern, a critical disease development stage marker, a vital sign instability risk index, and an organ function recovery potential assessment feature.

[0010] Furthermore, the nonlinear dynamic analysis of the characteristic map of the patient's pathological state to obtain a dynamic trajectory of disease progression includes: Performing multi-scale complexity calculation on the patient's pathological state characteristic map to obtain a disease evolution complexity characteristic sequence, and performing recursive quantitative analysis on the disease evolution complexity characteristic sequence to obtain a state transition probability matrix; Extracting the dominant dynamical mode of the state transition probability matrix by singular value decomposition to obtain a disease state attractor structure, and performing bifurcation theory analysis on the disease state attractor structure to obtain a set of clinical state transition critical points; Performing reachability analysis on the set of critical points of clinical state transition to obtain a disease state transition network diagram, and performing minimum action path calculation based on the disease state transition network diagram to obtain key regulatory nodes for disease progression; Based on stochastic differential equations, a dynamic system evolution simulation is performed on the key regulatory nodes of the disease progression to obtain a time-varying disease state manifold, and a vector field integral calculation is performed based on the time-varying disease state manifold to obtain a dynamic trajectory of disease progression.

[0011] Furthermore, the vector field integral calculation is performed based on the time-varying disease state manifold to obtain a dynamic trajectory of disease progression, including: Performing Stokes theorem transformation on the time-varying disease state manifold to obtain a disease state boundary flux distribution map, and performing tangential field decomposition on the disease state boundary flux distribution map to obtain a pathological state migration velocity vector field; The geometric characteristics of the pathological state migration velocity vector field are analyzed by Riemann curvature tensor to obtain a set of disease progression path geodesics, and a manifold parallel transmission calculation is performed based on the set of disease progression path geodesics to obtain a minimum action path for clinical state conversion; The Hamilton-Jacobi equation is solved for the minimum action path of the clinical state transition to obtain the optimal control surface of the disease progression time, and the Poincaré section is constructed based on the optimal control surface of the disease progression time to obtain the dynamic trajectory of the disease progression.

[0012] Furthermore, the clinical decision support reasoning based on the dynamic trajectory of disease progression to obtain personalized treatment recommendations includes: Performing trajectory segmentation processing on the dynamic trajectory of disease progression to obtain a sequence of key pathological stage transition points, and performing multidimensional critical state analysis on the sequence of key pathological stage transition points to obtain a set of treatment intervention time windows; Based on the Bayesian causal network, the inter-organ action mechanism of the treatment intervention time window set is inferred to obtain a multi-level pathological causal chain structure, and the key node sensitivity analysis of the multi-level pathological causal chain structure is performed to obtain a treatment target priority matrix; The treatment resource allocation calculation is performed on the treatment target priority matrix through multi-objective constraint optimization to obtain a multidimensional pharmacological kinetic parameter space, and a nonlinear response surface is constructed on the multidimensional pharmacological kinetic parameter space to obtain a treatment plan-physiological response mapping relationship diagram; Performing a Pareto optimal solution analysis on the treatment plan-physiological response mapping relationship diagram to obtain a multi-objective balanced treatment strategy set, and performing a clinical risk-benefit quantitative assessment based on the multi-objective balanced treatment strategy set to obtain a safety boundary of the individualized intervention plan; Based on the temporal Bayesian decision network, dynamic treatment path planning is performed on the safety boundary of the individualized intervention plan to obtain a staged treatment target sequence, and treatment plan combination optimization calculation is performed based on the staged treatment target sequence to obtain personalized treatment recommendations.

[0013] The present invention also provides a data fusion processing system based on a MEMS intelligent sensor, comprising: The sampling module is used to perform multi-channel synchronous sampling and fusion processing on the physiological signals of critically ill patients collected by MEMS sensors to obtain a multi-modal physiological parameter time series data stream; A decomposition module, used for performing non-stationary signal decomposition on the multimodal physiological parameter time series data stream to obtain a key vital sign feature sequence; A calculation module, used to calculate the phase coupling degree of the key vital sign characteristic sequence to obtain an inter-organ functional association strength matrix; A projection module, used for performing high-dimensional feature space projection on the critically ill patient based on the inter-organ functional association strength matrix to obtain a feature map of the patient's pathological state; An analysis module, used for performing nonlinear dynamic analysis on the characteristic map of the patient's pathological state to obtain a dynamic trajectory of disease progression; The reasoning module is used to perform clinical decision support reasoning based on the dynamic trajectory of disease progression to obtain personalized treatment recommendations.

[0014] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0015] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned methods are implemented.

[0016] The data fusion processing method of a MEMS-based intelligent sensor provided by the present invention comprises the following steps: multi-channel synchronous sampling and fusion processing of the physiological signals of critically ill patients collected by MEMS sensors to obtain a multimodal physiological parameter time series data stream; non-stationary signal decomposition of the multimodal physiological parameter time series data stream to obtain a key vital sign feature sequence; phase coupling degree calculation of the key vital sign feature sequence to obtain an inter-organ functional association strength matrix; high-dimensional feature space projection of the critically ill patients based on the inter-organ functional association strength matrix to obtain a patient pathological state feature map; nonlinear dynamic analysis of the patient pathological state feature map to obtain a dynamic trajectory of disease progression; clinical decision support reasoning based on the dynamic trajectory of disease progression to obtain personalized treatment suggestions, solves the technical problem that the existing analysis methods are often limited to the observation of a single physiological parameter or simple statistical analysis, and lack the ability to understand the disease mechanism from an overall perspective, and realizes the nonlinear dynamic analysis of the patient pathological state feature map, which can track the dynamic trajectory of disease progression. This method not only helps to predict the development trend of the disease, but also can adjust the treatment strategy in time to cope with possible changes, thereby improving the treatment effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the steps of a data fusion processing method based on a MEMS intelligent sensor in one embodiment of the present invention; Figure 2 It is a structural block diagram of a data fusion processing system based on a MEMS intelligent sensor in one embodiment of the present invention; Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0018] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0020] like Figure 1 As shown, Figure 1 It is a schematic diagram of the steps of a data fusion processing method of a MEMS-based intelligent sensor in one embodiment of the present invention; In one embodiment of the present invention, a data fusion processing method for a MEMS-based intelligent sensor is provided, comprising the following steps: Step S1, performing multi-channel synchronous sampling and fusion processing on the physiological signals of critically ill patients collected by MEMS sensors to obtain a multi-modal physiological parameter time series data stream.

[0021] Specifically, in the data fusion processing method based on MEMS smart sensors, multi-channel synchronous sampling and fusion processing of the physiological signals of critically ill patients is a crucial first step. This process first relies on multiple MEMS sensors working simultaneously, which can capture different types of physiological signals with high precision, such as electrocardiogram, respiratory rate and blood oxygen saturation. Through multi-channel synchronous sampling, it is ensured that all collected data are not only synchronized in time, but also reflect the patient's multiple physiological states at the same time, thus providing a solid foundation for subsequent data analysis. Then, these raw data streams from different sensors are fused and processed, and advanced algorithms are used to integrate them into a multimodal physiological parameter time series data stream. This step not only needs to consider the time synchronization of data, but also needs to solve the compatibility and consistency between different types of data. For example, in an intensive care environment, a patient with severe heart disease may need to continuously monitor his heart activity, respiratory status and oxygen content in the blood. Assuming that three different MEMS sensors are used to measure the above three physiological parameters respectively, in actual operation, these three sensors will synchronously collect data at preset time intervals (such as once per second). The system then uses specific data fusion algorithms, such as Kalman filtering or wavelet transform, to process the raw data. In this way, not only can the noise interference caused by individual differences in sensors or environmental factors be eliminated, but the originally isolated signals can also be converted into a unified time-series data stream containing multiple information. In this way, the medical team can fully understand the patient's real-time health status on a single platform, and make more accurate diagnosis and treatment decisions based on this, significantly improving the management efficiency and quality of critically ill patients. This process fully demonstrates the key role of multi-channel synchronous sampling and fusion processing steps in improving the performance of medical monitoring systems.

[0022] Step S2, performing non-stationary signal decomposition on the multimodal physiological parameter time series data stream to obtain a key vital sign feature sequence.

[0023] Specifically, in the data fusion processing method based on MEMS smart sensors, non-stationary signal decomposition of multimodal physiological parameter time series data stream is one of the key steps, aiming to extract clinically significant key vital sign feature sequences from complex physiological data. This process first requires identifying and separating those signal components that change over time rather than being constant, because these components often contain important information about the patient's health status. Specifically, by applying advanced signal processing techniques such as empirical mode decomposition (EMD) or wavelet transform, the fluctuation components in different frequency ranges can be extracted from the original data stream, thereby revealing the physiological dynamic changes hidden behind it. These decomposed signal components can better reflect the trend of changes in the patient's vital signs and provide a more accurate basis for subsequent analysis. For example, in an intensive care environment, suppose we are monitoring a patient with severe respiratory failure, whose multimodal physiological parameter time series data stream includes multiple signals such as electrocardiogram, respiratory rate, and blood oxygen saturation. These signals exhibit significant non-stationary characteristics due to the influence of the disease, that is, they are not constant, but change over time. In order to extract useful information from these complex and changeable signals, we can use wavelet transform technology to decompose the original data stream into sub-signals at multiple scales. Each sub-signal represents a fluctuation component in a different frequency range, some of which may be closely related to the patient's breathing pattern or heart activity. In this way, we can obtain a series of key vital sign feature sequences, such as respiratory fluctuation characteristics in a specific frequency band or the changing trend of heart rate variability. These feature sequences not only help to more accurately assess the patient's current health status, but also provide important clues for predicting the progression of the disease. Therefore, by performing non-stationary signal decomposition on the multimodal physiological parameter time series data stream, the medical team can obtain more detailed and in-depth patient physiological information, and then formulate a more personalized and effective treatment plan. This process fully demonstrates the important role of non-stationary signal decomposition in improving the management of critically ill patients.

[0024] Step S3, calculating the phase coupling degree of the key vital sign feature sequence to obtain an inter-organ functional association strength matrix.

[0025] Specifically, in the data fusion processing method based on MEMS smart sensors, it is a crucial step to calculate the phase coupling of key vital sign feature sequences to obtain the functional association strength matrix between organs. This process first needs to start with the key vital sign feature sequences extracted from the previous step, which contain the time dynamic change information of different physiological parameters. By applying the phase coupling analysis technology, the synchronization and interaction between different physiological signals can be quantified, thereby revealing the functional association between organs. Specifically, the phase coupling calculation usually involves converting each feature sequence into the frequency domain or time-frequency domain, and then evaluating the phase relationship between them by methods such as cross-spectral density or phase difference distribution. This analysis can help identify which physiological signals have significant phase synchronization phenomena, and then infer the functional association strength between the corresponding organs. For example, in an intensive care environment, suppose we are monitoring a patient with severe heart disease and respiratory failure. After the non-stationary signal decomposition of the patient's multimodal physiological parameter time series data stream, key vital sign feature sequences including heart rate variability, respiratory rate fluctuations, and blood oxygen saturation changes are obtained. In order to further understand the interaction between these physiological signals, we can use the phase coupling calculation method. First, these feature sequences are converted to the frequency domain, and the cross-spectral density and phase difference distribution between them are calculated. Then, by analyzing these results, we can find that there is a significant phase synchronization phenomenon between heart rate variability and respiratory rate fluctuations, which indicates that there is a close functional connection between the heart and the lungs. In addition, the phase relationship between blood oxygen saturation changes and other physiological parameters can be observed, which can infer the coordinated work of multiple organ systems throughout the body. Finally, by integrating all these phase coupling results, we can construct an inter-organ functional association strength matrix, which not only reflects the interaction strength between each organ system, but also provides clinicians with in-depth insights into the overall health status of the patient. Based on this matrix, the medical team can more accurately assess the condition and formulate personalized treatment plans to improve the management effect and treatment success rate of critically ill patients. This process demonstrates the powerful ability of phase coupling calculation in revealing the functional association between organs.

[0026] Step S4, performing high-dimensional feature space projection on the critically ill patient based on the inter-organ functional association strength matrix to obtain a feature map of the patient's pathological state.

[0027] Specifically, in the data fusion processing method based on MEMS smart sensors, it is a crucial step to project the high-dimensional feature space of critically ill patients based on the inter-organ functional association strength matrix to obtain the patient's pathological state feature map. This process first relies on the inter-organ functional association strength matrix obtained in the previous step, which contains the interaction strength information between different physiological signals. By mapping these complex interaction relationships into a high-dimensional feature space, the patient's pathological state and its dynamic changes can be more intuitively displayed. Specifically, this process usually involves applying dimensionality reduction techniques such as principal component analysis (PCA) or t-distributed random neighbor embedding (t-SNE) to convert the original high-dimensional data into low-dimensional visualization charts, making it easier for doctors to identify patterns and features related to disease progression. For example, in an intensive care environment, suppose we are monitoring a patient with severe heart disease and respiratory failure. After calculating the phase coupling degree, we obtain a detailed inter-organ functional association strength matrix, which contains the interaction strength between key vital sign features such as heart rate variability, respiratory rate fluctuations, and blood oxygen saturation changes. In order to further understand these complex relationships and transform them into actionable information, we map this matrix into a high-dimensional feature space. Using principal component analysis (PCA), we can compress multi-dimensional data into two-dimensional or three-dimensional space to generate a characteristic map of the patient's pathological state. In this process, each point represents the patient's overall health status at a certain moment, and the distance between the points reflects the degree of change in health status between different time points. For example, if the patient's pathological state map shows a clear clustering trend over a period of time, this may indicate that the condition is relatively stable; on the contrary, if the points in the map are scattered, it may indicate that the condition is worsening or new complications are emerging. In addition, by observing the distribution of different areas in the map, doctors can also discover potential pathological patterns, such as signs of dysfunction of certain specific organs, and then formulate more accurate treatment plans. This method of high-dimensional feature space projection not only improves the understanding of the patient's pathological state, but also provides strong support for clinical decision-making, improving the management efficiency and treatment effect of critically ill patients. The whole process shows how to extract valuable information from complex physiological data and transform it into intuitive visualization charts to better guide medical practice.

[0028] Step S5, performing nonlinear dynamic analysis on the characteristic map of the patient's pathological state to obtain a dynamic trajectory of disease progression.

[0029] Specifically, in the data fusion processing method based on MEMS smart sensors, it is a crucial step to perform nonlinear dynamic analysis on the patient's pathological state feature map to obtain the dynamic trajectory of disease progression. This process first relies on the patient's pathological state feature map generated in the previous step, which converts complex physiological data into intuitive visualization charts through high-dimensional feature space projection technology. In order to further understand the patient's pathological state and its changing trend over time, it is necessary to apply nonlinear dynamic analysis methods to reveal the intrinsic relationship and dynamic change pattern between these features. Specifically, this method usually includes calculating nonlinear dynamic indicators such as Lyapunov exponents and fractal dimensions to capture the complexity and instability in the system. For example, in an intensive care environment, suppose we are monitoring a patient with severe heart disease and respiratory failure. After high-dimensional feature space projection, we obtain a detailed patient pathological state feature map, in which each point represents the patient's overall health status at a certain moment. In order to extract dynamic information related to disease progression from these data, we can use nonlinear dynamic analysis methods. First, the degree of chaos of the system is evaluated by calculating the Lyapunov exponent, which can help us understand the complexity and unpredictability of the disease. Then, fractal dimension analysis can reveal the self-similarity and complexity of different regions in the pathological state map, thereby identifying potential pathological patterns. In addition, phase space reconstruction technology can be applied to map time series data into phase space and observe the changes in its trajectory. Through these analytical methods, we can construct a dynamic trajectory of disease progression, which not only reflects the changing trend of the patient's condition over time, but also helps doctors predict the future development of the disease. For example, if the trajectory shows obvious fluctuations or accelerated changes, it may indicate worsening of the disease or the emergence of new complications; on the contrary, if the trajectory tends to be stable, it indicates that the disease is relatively stable. This nonlinear dynamic analysis method not only improves the understanding of disease progression, but also provides strong support for clinical decision-making, enabling medical teams to adjust treatment plans more timely and accurately, and improve the management efficiency and treatment effect of critically ill patients. The whole process shows how to extract valuable dynamic information from complex pathological state feature maps and transform it into key clues to guide clinical practice.

[0030] Step S6, performing clinical decision support reasoning based on the dynamic trajectory of disease progression to obtain personalized treatment recommendations.

[0031] Specifically, in the data fusion processing method based on MEMS smart sensors, clinical decision support reasoning based on the dynamic trajectory of disease progression to obtain personalized treatment recommendations is the final and crucial step. This process first relies on the dynamic trajectory of disease progression generated in the previous step, which reveals the changing trends and complex patterns of the patient's condition over time through nonlinear dynamic analysis. In order to transform this complex dynamic information into actionable treatment recommendations, it is necessary to apply advanced clinical decision support systems (CDSS), combined with medical knowledge bases and machine learning algorithms, to comprehensively evaluate the patient's pathological state and its changing trends. Specifically, this method usually includes identifying key time points and turning points, predicting potential risk factors, and simulating the effects of different treatment options. For example, in an intensive care environment, suppose we are monitoring a patient with severe heart disease and respiratory failure. After nonlinear dynamic analysis, we obtain a detailed dynamic trajectory of disease progression, which not only shows the fluctuations of the patient's condition, but also reveals significant changes at certain specific time points. In order to extract personalized treatment recommendations from this dynamic information, we can use a clinical decision support system (CDSS). First, the system identifies early warning signs of worsening conditions based on key turning points in the trajectory, and proposes preliminary intervention measures based on relevant guidelines and best practices in the medical knowledge base. Next, the machine learning algorithm is trained on historical case data to simulate the effects of different treatment options, thereby recommending the most appropriate treatment for the current patient. For example, if the trajectory shows that the patient's heart rate variability has decreased significantly over a period of time, while respiratory rate fluctuations have increased, this may indicate further deterioration of heart and lung function. In this case, the CDSS may recommend adjusting drug doses or introducing new treatments, such as mechanical ventilation support. In addition, the system can continuously update its recommendations based on the patient's real-time physiological data to ensure that the treatment plan is always consistent with the patient's latest condition. This clinical decision support reasoning based on the dynamic trajectory of disease progression not only improves the accuracy and effectiveness of treatment, but also provides medical teams with powerful tools to help them develop more personalized and timely treatment strategies, thereby significantly improving the treatment outcomes and quality of life of critically ill patients. The entire process shows how to extract valuable clinical information from complex dynamic trajectories and transform them into specific treatment recommendations to better guide medical practice.

[0032] In a specific embodiment, the non-stationary signal decomposition of the multimodal physiological parameter time series data stream to obtain a key vital sign feature sequence includes: Adaptively performing biorthogonal filtering separation on the multimodal physiological parameter time series data stream to obtain a nonlinear physiological fluctuation component, and performing multi-level harmonic analysis on the nonlinear physiological fluctuation component through an adaptive oscillation identification mechanism to obtain a physiological system phase change feature set; Based on the multi-scale covariance structure method, a statistical significance analysis is performed on the phase change feature set of the physiological system to obtain a key physiological coupling network, and a topological stability assessment is performed on the key physiological coupling network to obtain multi-organ function linkage data; Phase synchronization measurement and extraction are performed on the multi-organ function linkage data to obtain a key vital sign feature sequence; wherein the key vital sign feature sequence includes the cardiovascular system regulation ability, respiratory compensation reserve index, circulatory system homeostasis maintenance parameters and multi-system collaborative function characteristics.

[0033] Specifically, in the data fusion processing method based on MEMS smart sensors, the process of performing non-stationary signal decomposition on the multimodal physiological parameter time series data stream to obtain the key vital sign feature sequence is extremely complex and delicate. This process requires not only the application of advanced signal processing technology, but also the combination of multi-scale data analysis and statistical significance analysis to fully reveal the patient's pathological state and its dynamic changes. First, the multimodal physiological parameter time series data stream is adaptively separated by dual orthogonal filtering, which is the first step of the whole process. Through this method, nonlinear physiological fluctuation components can be separated from the original data stream. These components contain complex fluctuation patterns exhibited by patients under different physiological states. For example, in an intensive care environment, a patient with severe heart disease and respiratory failure will have complex fluctuations in multiple physiological parameters such as electrocardiogram, respiratory rate, and blood oxygen saturation. Through adaptive dual orthogonal filtering separation, these fluctuation components can be extracted from the mixed signal, and further time-frequency joint analysis can be performed to generate a dynamic spectrum feature map. This map not only includes the cardiac electrophysiological activity pattern, but also covers important information such as vascular resistance change characteristics, pulmonary ventilation function parameters, and body temperature regulation loop signals. This information provides rich basic data for subsequent analysis. Next, the dynamic spectrum feature map is subjected to multi-level harmonic analysis through an adaptive oscillation recognition mechanism, which is the key link of the second step. This mechanism can identify the multi-level harmonic components in the dynamic spectrum feature map and extract parameter resonance boundary sequences from it. These boundary sequences reflect the resonance characteristics between different physiological signals, laying the foundation for further understanding the interaction between organs. For example, in the case of the above patient, through multi-level harmonic analysis, a specific resonance relationship between cardiac electrophysiological activity and respiratory frequency can be found, which helps to reveal the changing trend of the strength of cardiopulmonary coupling. Subsequently, the parameter resonance boundary sequence is subjected to non-stationary endpoint detection to obtain the physiological system phase change feature set. This detection method can capture the transition points of the physiological system in different states, thereby helping to identify potential pathological changes. The statistical significance analysis of the physiological system phase change feature set based on the multi-scale covariance structure is the core content of the third step. In this way, the correlation and synchronization between different physiological signals can be evaluated, and then the key physiological coupling network can be constructed. For example, in the case of the aforementioned patient, by performing multi-scale covariance analysis on characteristics such as heart rate variability, respiratory rate fluctuations, and changes in blood oxygen saturation, the complex relationship between the cardiopulmonary system, the feedback efficiency of the neural-circulatory system, and the endocrine-metabolic axis regulation parameters can be revealed. Next, the topological stability of the key physiological coupling network is evaluated to obtain multi-organ functional linkage data. These data include not only the strength of cardiopulmonary coupling, but also important contents such as the feedback efficiency of the neural-circulatory system, the regulation parameters of the endocrine-metabolic axis, and the characteristics of information transmission between organs.These linkage data provide strong support for a comprehensive understanding of the patient's pathological state and its progression. Finally, the phase synchronization measurement calculation of the multi-organ function linkage data is performed to obtain the functional system integration matrix, and the nonlinear principal component extraction of the functional system integration matrix is ​​performed to obtain the key vital sign feature sequence. This process quantifies the synchronization and coordination between different physiological systems through phase synchronization measurement calculation. For example, in the case of the aforementioned patient, by calculating the phase synchronization of the cardiovascular system, respiratory system and other important physiological systems, an integration matrix can be obtained, which reflects the collaborative work between the systems. Then, the most representative feature sequences are extracted from the integration matrix using the nonlinear principal component extraction method. These feature sequences include the cardiovascular system regulation ability, respiratory compensation reserve index, circulatory system homeostasis maintenance parameters, and multi-system collaborative functional characteristics. These key vital sign feature sequences not only provide doctors with a comprehensive patient health status assessment tool, but also provide a scientific basis for formulating personalized treatment plans. In order to better understand the practical application of this complex process, we can continue to use the previous case of critically ill patients. Assuming that the patient is experiencing an exacerbation of acute heart failure, through the detailed analysis of the above steps, the medical team can not only monitor the patient's cardiac electrophysiological activity pattern, respiratory rate fluctuations, and blood oxygen saturation changes in real time, but also deeply understand the interaction between these signals. For example, through the dynamic spectrum feature map, it is found that there is a significant resonance phenomenon between cardiac electrophysiological activity and respiratory rate, suggesting that the strength of cardiopulmonary coupling may be affected. Then, through multi-level harmonic analysis and non-stationary endpoint detection, it is identified that the patient's physiological system has undergone a significant phase change at a certain moment, which may be an early warning sign of worsening of the disease. Further, through the analysis of multi-organ function linkage data, it is found that the feedback efficiency of the neural-circulatory system is reduced and the regulation parameters of the endocrine-metabolic axis are abnormal. This information provides an important reference for adjusting the treatment strategy. Finally, through phase synchronization metric calculation and nonlinear principal component extraction, a series of key vital sign feature sequences are obtained. These sequences not only reflect the patient's current health status, but also provide strong support for predicting future disease development. The whole process shows how to extract valuable information from complex physiological data and transform it into key clues to guide clinical practice, thereby improving the management efficiency and treatment effect of critically ill patients.

[0034] In a specific embodiment, the phase coupling degree is calculated based on the key vital sign feature sequence to obtain the inter-organ functional association strength matrix, including: Performing bispectral coherence analysis on the key vital sign characteristic sequence to obtain a nonlinear phase synchronization characteristic spectrum, and performing time-varying causal relationship analysis on the nonlinear phase synchronization characteristic spectrum based on wavelet bidirectional transformation to obtain a functional network connection strength map; Performing directional information transfer analysis on the functional network connection strength map by using a transfer entropy calculation method to obtain a multi-organ interaction matrix, and performing resonance frequency band screening on the multi-organ interaction matrix to obtain a collaborative working mode of key physiological systems; The phase locking value of the collaborative working mode of the key physiological systems is calculated to obtain the organ function synchronization degree data, and a graph theory network characteristic analysis is performed based on the organ function synchronization degree data to obtain the organ function association strength matrix; wherein the organ function association strength matrix includes the cardiopulmonary function collaborative efficiency coefficient, cerebrovascular autoregulation capacity parameters, renal blood perfusion status and multi-system metabolic balance network characteristics.

[0035] Specifically, the process of calculating the phase coupling degree based on the key vital sign feature sequence and obtaining the inter-organ functional association strength matrix is ​​an important step to deeply understand the complex interactions between multiple organ systems. This process can not only reveal the synchronization and coordination of different physiological systems through a series of advanced signal processing and data analysis techniques, but also provide strong support for personalized medicine. First, the bispectral coherence analysis of the key vital sign feature sequence is performed, which is the first step of the whole process. In this way, nonlinear phase synchronization feature spectra can be extracted from complex physiological signals. These feature spectra contain the intrinsic connections and interaction patterns between various physiological systems. For example, in a patient with severe cardiopulmonary disease, the nonlinear phase synchronization characteristics between cardiac electrical activity and respiratory rate are particularly important. Further, by performing high-order cross-frequency decomposition on the nonlinear phase synchronization feature spectrum, multi-organ signal coupling metrics can be obtained. These metrics reflect the coupling strength of different organ signals in a specific frequency range, which is of great significance for evaluating the functional association between organs. For example, in the example of the aforementioned patient, through high-order cross-frequency decomposition, it was found that cardiac electrical activity and respiratory rate were significantly coupled in certain high-frequency bands, which suggests a close interaction between the cardiopulmonary system. Next, the time-varying causal relationship analysis of the multi-organ signal coupling metric is performed based on wavelet bidirectional transformation, which is the key link of the second step. This method can capture the dynamic causal relationship between different physiological signals and generate an inter-organ information flow vector field. This vector field not only shows how information is transmitted between different organs, but also reveals the directionality and intensity of information transmission. For example, in the case of the above-mentioned patient, through wavelet bidirectional transformation, it was found that cardiac electrical activity has a significant effect on respiratory rate, and changes in respiratory rate feedback regulate cardiac function. Then, by calculating the topological complexity of the inter-organ information flow vector field, a functional network connection strength map can be obtained. This chart includes important information such as the bidirectional regulation intensity of the cardiovascular-respiratory system, the information transmission efficiency of the brain-kidney axis, the liver-pancreas metabolic synergy index, and the circulatory-endocrine system coupling marker. These data provide valuable clues for a comprehensive understanding of the patient's pathological state. Subsequently, the functional network connection strength map is analyzed for directional information transfer by the transfer entropy calculation method, which is the core content of the third step. Transfer entropy is an effective tool to quantify the direction and intensity of information flow. Through this method, a multi-organ interaction matrix can be obtained. For example, in the case of the patient mentioned above, through the transfer entropy calculation, it was found that the information transmission intensity from the heart to the kidney was significantly higher than the feedback from the kidney to the heart, which may imply some potential pathological mechanism. Then, by screening the resonance frequency band of the multi-organ interaction matrix, the collaborative working mode of the key physiological system can be obtained.These patterns include important contents such as the synchronization characteristics of heart-lung gas exchange, parameters of brain-heart bidirectional regulation pathways, kidney-vascular pressure feedback loops, and liver-pancreas metabolic regulation networks. These collaborative working patterns not only reveal the interaction between different physiological systems, but also provide a scientific basis for the development of personalized treatment plans. Finally, the phase locking value of the collaborative working mode of the key physiological systems is calculated, which is the last link in the whole process. In this way, the data on the degree of synchronization of organ functions can be obtained. For example, in the case of the aforementioned patient, through the calculation of the phase locking value, it was found that the heart and lungs showed a high degree of synchronization in the gas exchange process, while the bidirectional regulation between the heart and the brain showed a certain degree of disorder. Then, based on the data on the degree of synchronization of organ functions, the graph network characteristics were analyzed, and finally the functional association strength matrix between organs was obtained. This matrix includes important information such as the coefficient of cardiopulmonary function synergy efficiency, parameters of cerebrovascular autoregulation capacity, renal blood perfusion status, and characteristics of multi-system metabolic balance networks. These data not only provide doctors with a comprehensive patient health status assessment tool, but also provide strong support for adjusting treatment strategies. In order to better understand the practical application of this complex process, we can continue to use the previous case of critically ill patients. Assuming that the patient is experiencing an exacerbation of acute heart failure, through the detailed analysis of the above steps, the medical team can not only monitor the patient's cardiac electrophysiological activity pattern, respiratory rate fluctuations, and blood oxygen saturation changes in real time, but also deeply understand the interaction between these signals. For example, through bispectral coherence analysis, it was found that there was a significant nonlinear phase synchronization feature between cardiac electrical activity and respiratory rate, indicating a close interaction between the cardiopulmonary system. Further, through high-order cross-frequency decomposition, it was identified that the patient's heart and lungs had significant coupling strength in certain specific frequency ranges, which may be an early warning sign of worsening of the disease. Then, based on wavelet bidirectional transformation, the causal effect of cardiac electrical activity on respiratory rate was analyzed, and it was found that abnormal cardiac function did affect the stability of the respiratory system. Through transfer entropy calculation, it was revealed that the intensity of information transmission from the heart to other organs (such as the kidneys) increased significantly, indicating that abnormal cardiac function has spread to other organ systems. Finally, through the calculation of phase locking values ​​of the collaborative working mode of key physiological systems and the analysis of graph theory network characteristics, a detailed inter-organ functional association strength matrix was obtained. This matrix not only reflects the current pathological state of the patient, but also provides an important reference for predicting future disease progression and adjusting treatment strategies. The whole process demonstrates how to extract valuable information from complex physiological data and transform it into key clues to guide clinical practice, thereby improving the management efficiency and treatment effects of critically ill patients.

[0036] In a specific embodiment, the high-dimensional feature space projection is performed based on the inter-organ functional association strength matrix to obtain the patient's pathological state feature map, including: Performing a tensor decomposition operation on the inter-organ functional association intensity matrix to obtain a multi-dimensional physiological system interaction feature space, performing topological structure extraction on the multi-dimensional physiological system interaction feature space to obtain a disease state topological skeleton diagram, and performing multi-scale persistence calculation on the disease state topological skeleton diagram to obtain a set of key pathological state branch points; Performing nonlinear boundary mapping on the key pathological state branch point set by using kernel surface reconstruction technology to obtain an organ function degradation partition map, and performing spectral clustering segmentation processing on the organ function degradation partition map to obtain a pathological state subspace structure; Performing geometric depth feature extraction on the pathological state subspace structure to obtain a disease progression path network, and performing Ricci curvature calculation based on the disease progression path network to obtain a pathological state transformation risk surface; Based on differential geometry mapping, a curvature flow evolution analysis is performed on the pathological state transformation risk surface to obtain a disease state manifold graph, and a characteristic vector field is constructed based on the disease state manifold graph to obtain a patient pathological state characteristic map, wherein the patient pathological state characteristic map includes a multi-organ dysfunction pattern, a critical disease development stage marker, a vital sign instability risk index, and an organ function recovery potential assessment feature.

[0037] Specifically, the process of projecting a high-dimensional feature space based on the inter-organ functional association strength matrix to obtain the patient's pathological state feature map is a key step in deeply understanding and quantifying the interactions between complex physiological systems. This process can not only reveal the coordinated disorder patterns of different physiological systems through a series of advanced data processing and analysis techniques, but also provide strong support for personalized medicine. First, the inter-organ functional association strength matrix is ​​subjected to a tensor decomposition operation, which is the first step of the whole process. In this way, multidimensional physiological system interaction feature spaces can be extracted from complex multidimensional data. These feature spaces contain the intrinsic connections and interaction patterns between various physiological systems. For example, in a patient with severe cardiopulmonary disease, the interaction characteristics between cardiac electrical activity and vital signs such as respiratory rate and blood oxygen saturation are particularly important. Further, the topological structure of the multidimensional physiological system interaction feature space is extracted based on homotopy persistence analysis, and a disease state topological skeleton diagram can be obtained. This skeleton diagram not only shows the connection relationship between different physiological systems, but also reveals the stability of these relationships. For example, in the example of the aforementioned patient, the coupling between cardiac electrical activity and respiratory rate was found to have a high persistence through homotopy persistence analysis, indicating a close interaction between the cardiopulmonary system. Then, by performing multi-scale persistence calculation on the disease state topological skeleton graph, a set of key pathological state branch points can be obtained. These branch points reflect the important connection points and potential risk areas between physiological systems at different scales. Then, the nonlinear boundary mapping of the key pathological state branch point set is performed by the kernel surface reconstruction technology, which is the core link of the second step. This method can capture the nonlinear dynamic changes between different physiological systems and generate an organ function degradation partition map. This partition map not only shows the degree and range of functional degradation of different organs, but also reveals the nonlinear characteristics of the degradation process. For example, in the case of the above-mentioned patient, through the kernel surface reconstruction technology, it was found that there was a significant nonlinear boundary between cardiac function degradation and respiratory rate fluctuation, which may imply some potential pathological mechanism. Then, by performing spectral clustering segmentation processing on the organ function degradation partition map, the pathological state subspace structure can be obtained. These subspace structures provide more detailed pathological information and help identify different pathological states and their evolution paths. For example, in the example of the above-mentioned patient, through spectral clustering segmentation processing, the close connection between cardiac function degradation and abnormal renal blood perfusion was found, which provides important clues for further formulating treatment plans. Next, the geometric deep feature extraction of the pathological state subspace structure is performed, which is the key content of the third step. In this way, disease progression pathway networks can be extracted from complex pathological state subspaces. These networks not only show the transition paths between different pathological states, but also reveal the stability and risks of these paths.For example, in the case of the aforementioned patient, through the extraction of geometric deep features, it was found that there was a relatively stable progression path between cardiac function degeneration and renal failure, suggesting that urgent intervention was needed to prevent the disease from worsening. Then, based on the disease progression path network, Ricci curvature calculation was performed to obtain the pathological state conversion risk surface. This surface not only reflects the difficulty and risk of conversion between different pathological states, but also provides an important reference for evaluating the treatment effect. Subsequently, the pathological state conversion risk surface was subjected to curvature flow evolution analysis based on differential geometry mapping, which is the core content of the fourth step. This method can capture the dynamic changes between different pathological states and generate a disease state manifold map. This manifold map not only shows the trend of pathological state changes over time, but also reveals the geometric characteristics of these changes. For example, in the case of the aforementioned patient, through the curvature flow evolution analysis, it was found that there was a significant dynamic correlation between cardiac function degeneration and decreased cerebrovascular autoregulation ability, suggesting that the functional states of multiple systems need to be considered comprehensively to adjust the treatment strategy. Then, the characteristic vector field is constructed based on the disease state manifold map, and finally the patient's pathological state characteristic map is obtained. This atlas not only includes important contents such as multi-organ dysfunction coordination patterns, critical disease development stage markers, vital sign instability risk index, and organ function recovery potential assessment characteristics, but also provides doctors with a comprehensive patient health status assessment tool. In order to better understand the practical application of this complex process, we can continue to use the previous case of critically ill patients. Assuming that the patient is experiencing the exacerbation of acute heart failure, through the detailed analysis of the above steps, the medical team can not only monitor the patient's cardiac electrophysiological activity pattern, respiratory rate fluctuations, and blood oxygen saturation changes in real time, but also deeply understand the interaction between these signals. For example, through tensor decomposition operations, the multidimensional physiological system interaction feature space is extracted from the inter-organ functional association intensity matrix, revealing the complex interaction pattern between cardiac electrical activity and vital signs such as respiratory rate and blood oxygen saturation. Furthermore, based on homotopy persistence analysis, the disease state topological skeleton diagram is obtained, showing the close coupling relationship between cardiac electrical activity and respiratory rate, and through multi-scale persistence calculation, a set of key pathological state branch points is identified, which reflect the early warning signs of disease deterioration. Then, through the kernel surface reconstruction technology, the set of key pathological state branch points was mapped into an organ function degradation partition map, revealing the nonlinear boundary between cardiac function degradation and abnormal renal blood perfusion. Then, by performing spectral clustering segmentation on the organ function degradation partition map, the pathological state subspace structure was obtained, and the pathological information was further refined. For example, through geometric deep feature extraction, a stable progression path between cardiac function degradation and renal failure was found, suggesting the need for urgent intervention measures. Then, based on the Ricci curvature calculation, the pathological state conversion risk surface was obtained, reflecting the difficulty and risk of conversion between different pathological states.Finally, through differential geometry mapping, curvature flow evolution analysis was performed to generate a disease state manifold map, and based on this, a characteristic vector field was constructed to obtain the patient's pathological state characteristic map. This map not only shows the patient's multi-organ dysfunction coordination pattern, but also provides important information such as critical disease development stage markers, vital sign instability risk index, and organ function recovery potential assessment characteristics, providing a scientific basis for adjusting treatment strategies. The whole process shows how to extract valuable information from complex physiological data and transform it into key clues to guide clinical practice, thereby improving the management efficiency and treatment effect of critically ill patients.

[0038] In a specific embodiment, the nonlinear dynamic analysis of the characteristic map of the patient's pathological state to obtain a dynamic trajectory of disease progression includes: Performing multi-scale complexity calculation on the patient's pathological state characteristic map to obtain a disease evolution complexity characteristic sequence, and performing recursive quantitative analysis on the disease evolution complexity characteristic sequence to obtain a state transition probability matrix; The dominant dynamics mode of the state transition probability matrix is ​​extracted by singular value decomposition to obtain a disease state attractor structure, and the disease state attractor structure is analyzed by bifurcation theory to obtain a set of clinical state transition critical points, wherein the set of clinical state transition critical points includes precursors of cardiovascular function collapse, respiratory system compensation limit parameters, markers of multi-organ dysfunction and irreversible points of metabolic disorders; Performing reachability analysis on the set of critical points of clinical state transition to obtain a disease state transition network diagram, and performing minimum action path calculation based on the disease state transition network diagram to obtain key regulatory nodes for disease progression; Based on stochastic differential equations, a dynamic system evolution simulation is performed on the key regulatory nodes of the disease progression to obtain a time-varying disease state manifold, and a vector field integral calculation is performed based on the time-varying disease state manifold to obtain a dynamic trajectory of disease progression; wherein, the dynamic trajectory of disease progression includes a temporal pattern of multi-organ function degradation, a diffusion path of physiological system disorders, a clinical state deterioration rate map, and an inter-organ functional linkage collapse sequence.

[0039] Specifically, the process of performing nonlinear dynamic analysis on the patient's pathological state characteristic map to obtain the dynamic trajectory of disease progression is a key step in deeply exploring and understanding the dynamic changes of complex physiological systems. This process, through a series of advanced data processing and mathematical modeling techniques, can not only reveal the conversion rules between different pathological states, but also provide strong support for the formulation of personalized treatment plans. First, the multi-scale complexity calculation of the patient's pathological state characteristic map is performed, which is the first step of the whole process. This method aims to extract disease evolution complexity characteristic sequences from complex pathological state data, which contain multiple scale characteristics of the disease changing over time. For example, in a patient with severe cardiopulmonary disease, the temporal evolution pattern between cardiac electrical activity and vital signs such as respiratory rate and blood oxygen saturation is particularly critical. Further, by recursively quantitatively analyzing the disease evolution complexity characteristic sequence, a state transition probability matrix can be obtained. This matrix not only shows the possibility of conversion between different pathological states, but also reveals the probability distribution of these conversions. For example, in the example of the aforementioned patient, the coupling between cardiac electrical activity and respiratory rate was found to have a high conversion probability through recursive quantitative analysis, indicating a close interaction between the cardiopulmonary system. Then, the dominant dynamic mode of the state transition probability matrix is ​​extracted by singular value decomposition, which is the core link of the second step. This method can capture the main transition modes between different pathological states and generate a disease state attractor structure. This attractor structure not only shows the intrinsic connection between different pathological states, but also reveals the stability of these connections. For example, in the case of the above-mentioned patient, a significant attractor structure between cardiac function degeneration and respiratory rate fluctuation was found through singular value decomposition, which may imply some potential pathological mechanism. Then, by performing bifurcation theory analysis on the disease state attractor structure, a set of clinical state transition critical points can be obtained. These critical points reflect the risk areas where pathological states undergo major changes under different conditions. For example, in the case of the above-mentioned patient, through bifurcation theory analysis, important critical points such as precursors of cardiovascular function collapse, respiratory system compensation limit parameters, markers of multi-organ dysfunction, and irreversible points of metabolic disorders were identified, providing a basis for timely intervention. Next, the reachability analysis of the set of clinical state transition critical points is performed, which is the key content of the third step. In this way, a disease state transition network diagram can be constructed starting from different critical points. This network diagram not only shows the transition paths between different pathological states, but also reveals the possibilities and risks of these paths. For example, in the case of the aforementioned patient, through accessibility analysis, a close connection between heart function degeneration and renal failure was found, which provided important clues for further formulating treatment plans. Then, based on the disease state transition network diagram, the minimum action path calculation was performed to obtain the key regulatory nodes for disease progression.These nodes are not only the key turning points in the development of the disease, but also provide targets for the formulation of effective intervention measures. Subsequently, the dynamic system evolution simulation of the key regulatory nodes of the disease progression is carried out based on stochastic differential equations, which is the core content of the fourth step. This method can capture the dynamic changes between different pathological states and generate a time-varying disease state manifold. This manifold not only shows the changing trend of the pathological state over time, but also reveals the geometric characteristics of these changes. For example, in the case of the above-mentioned patient, the dynamic association between cardiac function degeneration and renal failure was simulated by stochastic differential equations, and it was found that the mutual influence between the two showed obvious nonlinear characteristics. Then, the vector field integral calculation was performed based on the time-varying disease state manifold, and the dynamic trajectory of disease progression was finally obtained. This trajectory not only includes important contents such as the temporal pattern of multi-organ function degeneration, the diffusion path of physiological system disorders, the atlas of clinical state deterioration rate, and the sequence of functional linkage collapse between organs, but also provides doctors with a comprehensive patient health status assessment tool. In order to better understand the practical application of this complex process, we can continue to use the previous case of critically ill patients. Assuming that the patient is experiencing an exacerbation of acute heart failure, through the detailed analysis of the above steps, the medical team can not only monitor the patient's cardiac electrophysiological activity pattern, respiratory rate fluctuations, and blood oxygen saturation changes in real time, but also deeply understand the interaction between these signals. For example, through multi-scale complexity calculation, the disease evolution complexity feature sequence is extracted from the patient's pathological state feature map, revealing the complex interaction pattern between cardiac electrical activity and vital signs such as respiratory rate and blood oxygen saturation. Further, by recursively quantitatively analyzing the disease evolution complexity feature sequence, the state transition probability matrix is ​​obtained, showing the close coupling relationship between cardiac electrical activity and respiratory rate, and the disease state attractor structure is identified through singular value decomposition. Then, by performing bifurcation theory analysis on the disease state attractor structure, important critical points such as precursors of cardiovascular function collapse, respiratory system compensation limit parameters, multi-organ function dyssynergism markers, and irreversible points of metabolic disorders are identified. Then, by performing reachability analysis on these critical points, a disease state transition network diagram is constructed to further refine the pathological information. For example, through the calculation of the minimum action path, a stable progression path between cardiac function deterioration and renal failure was discovered, suggesting the need for urgent intervention measures. Then, based on the stochastic differential equation, a dynamic system evolution simulation was performed to generate a time-varying disease state manifold, and based on this, a vector field integral calculation was performed to obtain the dynamic trajectory of disease progression. This trajectory not only shows the temporal pattern of multi-organ functional deterioration in patients, but also provides important information such as the diffusion path of physiological system disorders, the rate map of clinical state deterioration, and the sequence of functional linkage collapse between organs, providing a scientific basis for adjusting treatment strategies.The whole process demonstrates how to extract valuable information from complex physiological data and transform it into key clues to guide clinical practice, thereby improving the management efficiency and treatment effects of critically ill patients.

[0040] In a specific embodiment, the vector field integral calculation is performed based on the time-varying disease state manifold to obtain the dynamic trajectory of disease progression, including: Performing Stokes theorem transformation on the time-varying disease state manifold to obtain a disease state boundary flux distribution map, and performing tangential field decomposition on the disease state boundary flux distribution map to obtain a pathological state migration velocity vector field; The geometric characteristics of the pathological state migration velocity vector field are analyzed by Riemann curvature tensor to obtain a set of disease progression path geodesics, and a manifold parallel transmission calculation is performed based on the set of disease progression path geodesics to obtain a minimum action path for clinical state conversion; The Hamilton-Jacobi equation is solved for the minimum action path of the clinical state transition to obtain the optimal control surface of the disease progression time, and the Poincaré section is constructed based on the optimal control surface of the disease progression time to obtain the dynamic trajectory of the disease progression.

[0041] Specifically, the process of performing vector field integral calculation based on the time-varying disease state manifold to obtain the dynamic trajectory of disease progression is a key step to deeply understand and quantify the dynamic changes of complex physiological systems. This process can not only reveal the conversion rules between different pathological states through a series of advanced mathematical and geometric analysis techniques, but also provide strong support for the formulation of personalized treatment plans. First, the time-varying disease state manifold is transformed by Stokes theorem, which is the first step of the whole process. Stokes theorem is an important mathematical tool that can transform complex high-dimensional manifolds into flux distribution maps on the boundary. By applying Stokes theorem transformation to the time-varying disease state manifold, a disease state boundary flux distribution map can be obtained. This distribution map not only shows the changes of the disease state at different time points, but also reveals the boundary characteristics of these changes. For example, in a patient with severe cardiopulmonary disease, the dynamic change pattern between cardiac electrical activity and vital signs such as respiratory rate and blood oxygen saturation is particularly important. Further, by performing tangential field decomposition on the disease state boundary flux distribution map, the pathological state migration velocity vector field can be obtained. This vector field not only shows the migration direction and speed between different pathological states, but also reveals the dynamic characteristics of these migrations. For example, in the case of the patient mentioned above, through the decomposition of the tangential field, it was found that there was a significant difference in migration speed between the degeneration of cardiac function and the fluctuation of respiratory rate, suggesting that attention should be paid to the synchronous changes of the heart and respiratory system. Next, the geometric characteristics of the pathological state migration velocity vector field are analyzed by the Riemann curvature tensor, which is the core link of the second step. The Riemann curvature tensor is a mathematical tool for describing the geometric characteristics of manifolds. Through this method, a set of disease progression path geodesics can be extracted from the pathological state migration velocity vector field. These geodesics not only show the shortest path between different pathological states, but also reveal the geometric characteristics of these paths. For example, in the case of the patient mentioned above, through the Riemann curvature tensor analysis, a significant geodesic between cardiac function degeneration and renal failure was found, which may imply some potential pathological mechanism. Then, based on the set of disease progression path geodesics, manifold parallel transmission calculations were performed to obtain the minimum action path of clinical state conversion. These paths not only show the most effective conversion paths between different pathological states, but also provide an important reference for evaluating the treatment effect. Then, the Hamilton-Jacobi equation is solved for the minimum action path of the clinical state transition, which is the key content of the third step. The Hamilton-Jacobi equation is a classic equation used to describe the optimal control problem of dynamic systems. Through this method, the optimal control surface of disease progression time can be extracted from the minimum action path. This surface not only shows the optimal transition time between different pathological states, but also reveals the time dependence of these transitions.For example, in the case of the patient mentioned above, by solving the Hamilton-Jacobi equation, it was found that the optimal conversion time between cardiac function deterioration and renal failure has obvious nonlinear characteristics, suggesting that the functional status of multiple systems needs to be considered comprehensively to adjust the treatment strategy. Then, based on the optimal control surface of the disease progression time, the Poincaré section is constructed, and finally the dynamic trajectory of disease progression is obtained. This trajectory not only includes important contents such as the time series pattern of multi-organ functional deterioration, the diffusion path of physiological system disorder, the clinical state deterioration rate map, and the functional linkage collapse sequence between organs, but also provides doctors with a comprehensive patient health status assessment tool. In order to better understand the practical application of this complex process, we can continue to use the previous case of critically ill patients. Assuming that this patient is experiencing the exacerbation period of acute heart failure, through the detailed analysis of the above steps, the medical team can not only monitor the patient's cardiac electrophysiological activity pattern, respiratory rate fluctuations, and blood oxygen saturation changes in real time, but also deeply understand the interaction between these signals. For example, through the Stokes theorem transformation, the disease state boundary flux distribution map is extracted from the time-varying disease state manifold, revealing the dynamic change pattern between cardiac electrical activity and vital signs such as respiratory rate and blood oxygen saturation. Furthermore, by performing tangential field decomposition on the disease state boundary flux distribution map, the pathological state migration velocity vector field was obtained, showing the close coupling relationship between cardiac electrical activity and respiratory rate, and the set of geodesic lines of the disease progression path was identified through Riemann curvature tensor analysis. Then, by performing manifold parallel transmission calculation on these geodesic lines, the minimum action path of clinical state transition was obtained, which provided a target for further formulating treatment plans. Then, by solving the Hamilton-Jacobi equation for the minimum action path, the optimal control surface of disease progression time was obtained, revealing the optimal conversion time between different pathological states. Finally, based on the optimal control surface of disease progression time, Poincaré sections were constructed to generate a dynamic trajectory of disease progression. This trajectory not only shows the temporal pattern of multi-organ functional degradation of patients, but also provides important information such as the diffusion path of physiological system disorders, the rate map of clinical state deterioration, and the sequence of functional linkage collapse between organs, providing a scientific basis for adjusting treatment strategies. Throughout the process, Stokes theorem transformation helps us extract the flow distribution map on the boundary from complex high-dimensional data, thereby revealing the dynamic change pattern of the disease; tangential field decomposition further refines the speed and direction of pathological state migration, providing detailed dynamic characteristics. The application of Riemann curvature tensor enables us to capture the geometric characteristics of the disease progression path, and manifold parallel transport calculation helps us find the most effective clinical state transition path.The solution of Hamilton-Jacobi equation provides us with the optimal control surface, which reveals the transition time between different pathological states, while the construction of Poincaré cross section finally generates the dynamic trajectory of disease progression, providing a comprehensive patient health status assessment tool. The whole process shows how to extract valuable information from complex physiological data and transform it into key clues to guide clinical practice, thereby improving the management efficiency and treatment effect of critically ill patients.

[0042] In a specific embodiment, the clinical decision support reasoning based on the dynamic trajectory of disease progression to obtain personalized treatment recommendations includes: Performing trajectory segmentation processing on the dynamic trajectory of disease progression to obtain a sequence of key pathological stage transition points, and performing multidimensional critical state analysis on the sequence of key pathological stage transition points to obtain a set of treatment intervention time windows; Based on the Bayesian causal network, the inter-organ action mechanism of the treatment intervention time window set is inferred to obtain a multi-level pathological causal chain structure, and the key node sensitivity analysis of the multi-level pathological causal chain structure is performed to obtain a treatment target priority matrix; The treatment resource allocation calculation is performed on the treatment target priority matrix through multi-objective constraint optimization to obtain a multidimensional pharmacological kinetic parameter space, and a nonlinear response surface is constructed on the multidimensional pharmacological kinetic parameter space to obtain a treatment plan-physiological response mapping relationship diagram; Performing a Pareto optimal solution analysis on the treatment plan-physiological response mapping relationship diagram to obtain a multi-objective balanced treatment strategy set, and performing a clinical risk-benefit quantitative assessment based on the multi-objective balanced treatment strategy set to obtain a safety boundary of the individualized intervention plan; Based on the temporal Bayesian decision network, dynamic treatment path planning is performed on the safety boundary of the individualized intervention plan to obtain a staged treatment target sequence, and treatment plan combination optimization calculation is performed based on the staged treatment target sequence to obtain personalized treatment recommendations.

[0043] Specifically, the process of clinical decision support reasoning based on the dynamic trajectory of disease progression to obtain personalized treatment recommendations is a complex and multi-level analysis process, which aims to develop the most optimized treatment strategy for patients by deeply understanding the changes in the patient's pathological state and the physiological mechanisms behind it. This process requires not only the support of advanced mathematical and statistical methods, but also a deep understanding of biological, medical and pharmacological knowledge. First, the dynamic trajectory of disease progression is segmented, which is the first step of the whole process. The purpose of trajectory segmentation is to identify a sequence of key pathological stage transition points, which mark the key moments when the disease transitions from one stage to another. For example, in a patient with chronic kidney disease and cardiovascular disease, a change in the correlation between worsening renal function and decreased heart pumping capacity may be observed at a certain time point, which is one of the key pathological stage transition points we need to pay attention to. Then, multidimensional critical state analysis of these key pathological stage transition point sequences can reveal the pathological state characteristics at each transition point and further determine the best time for intervention, that is, the set of treatment intervention time windows. This analysis helps doctors understand when to take action most effectively. For example, in the above case, it is found that the best time to start intensive treatment is before the heart's pumping capacity decreases significantly. Next, the inter-organ mechanism of action is inferred for the set of treatment intervention time windows based on the Bayesian causal network, which is the core of the second step. Bayesian causal network is a powerful tool that can help us understand the causal relationship between different variables. In this way, a multi-level pathological causal chain structure can be inferred from the set of treatment intervention time windows, revealing the complex interaction pattern between different organs. For example, in the example of the patient mentioned above, the potential causal relationship between cardiac function degeneration and renal failure was found through Bayesian causal network analysis, suggesting that the conditions of these two systems should be considered simultaneously during treatment. Then, the key node sensitivity analysis of these multi-level pathological causal chain structures can be performed to obtain the treatment target priority matrix, so as to clarify which parts or processes should be the main targets of treatment. For example, in this case, it was found that improving the metabolic efficiency of cardiomyocytes is crucial to slowing the progression of the disease, so it is used as the primary treatment target. Subsequently, the treatment resource allocation calculation of the treatment target priority matrix is ​​performed through multi-objective constraint optimization, which is an important part of the third step. Multi-objective constrained optimization is a method for solving resource allocation problems in complex systems. Through this method, the optimal drug dose and treatment regimen combination can be calculated from the therapeutic target priority matrix to generate a multidimensional pharmacokinetics parameter space. This parameter space not only shows the effects of different drugs and treatments, but also reveals the interactions between them. For example, in the above case, through multi-objective constrained optimization, the optimal drug combination that can effectively improve heart function and protect kidney function was found.Next, a nonlinear response surface is constructed for this multidimensional pharmacokinetics parameter space, and a treatment regimen-physiological response mapping relationship diagram can be obtained, which shows the expected physiological response under different treatment regimens. This mapping relationship diagram provides intuitive guidance for doctors to help them choose the treatment regimen that best suits the patient. Then, the treatment regimen-physiological response mapping relationship diagram is subjected to Pareto optimal solution analysis, which is a key step in the fourth step. Pareto optimal solution analysis is a method for evaluating the trade-off relationship between multiple options. Through this method, a set of treatment strategies that can achieve the best balance between multiple goals can be screened from the treatment regimen-physiological response mapping relationship diagram, that is, a multi-objective balanced treatment strategy set. For example, in the case of the aforementioned patient, a set of treatment regimens that can significantly improve the heart's pumping capacity without causing additional burden on the kidneys was found through Pareto optimal solution analysis. Next, based on this multi-objective balanced treatment strategy set, a clinical risk-benefit quantitative assessment is performed to obtain the safety boundary of the individualized intervention plan, and the risks and benefits of each treatment strategy are clarified. For example, in this case, it was found that although some high-intensity treatment regimens can quickly improve heart function, they may increase the risk of kidney damage in the long run, so they need to be selected with caution. Finally, the dynamic treatment path planning of the safety boundary of the individualized intervention plan is carried out based on the temporal Bayesian decision network, which is the core task of the fifth step. The temporal Bayesian decision network is a powerful tool for decision analysis combined with the time dimension. Through this method, a phased treatment target sequence can be planned from the safety boundary of the individualized intervention plan, and specific treatment targets can be set for each stage. For example, in the case of the above patient, a comprehensive treatment plan including short-term stabilization of cardiac function, medium-term recovery of partial renal function, and long-term maintenance of both was formulated through the temporal Bayesian decision network. Then, based on this phased treatment target sequence, the treatment plan combination optimization calculation is performed, and finally personalized treatment recommendations are obtained. This recommendation not only takes into account the patient's current pathological state, but also predicts possible changes in the future, ensuring the flexibility and adaptability of the treatment plan. In summary, through a detailed analysis of the dynamic trajectory of disease progression, combined with advanced technologies such as Bayesian causal networks, multi-objective constraint optimization, Pareto optimal solution analysis, and temporal Bayesian decision networks, we can tailor a set of scientific and reasonable personalized treatment recommendations for each patient. These technologies work together to not only improve the effectiveness and safety of treatment, but also provide strong support for clinical decision-making. For example, in the case of a patient with chronic kidney disease and cardiovascular disease, through the implementation of the above series of steps, the medical team can not only accurately locate the treatment target, but also adjust the drug dosage and treatment plan according to the patient's specific situation, and ultimately achieve the best treatment effect. Throughout the process, various advanced analytical methods complement each other, making personalized treatment possible, greatly improving the management efficiency and treatment quality of critically ill patients.

[0044] The above describes the data fusion processing method of the MEMS-based smart sensor in the embodiment of the present invention. The following describes the data fusion processing system of the MEMS-based smart sensor in the embodiment of the present invention. Figure 2 In one embodiment of the present invention, a data fusion processing system based on a MEMS intelligent sensor includes: The sampling module 21 is used to perform multi-channel synchronous sampling on the physiological signals of critically ill patients collected by the MEMS sensor to obtain a multi-modal physiological parameter time series data stream; A decomposition module 22, used for performing non-stationary signal decomposition on the multimodal physiological parameter time series data stream to obtain a key vital sign feature sequence; A calculation module 23 is used to calculate the phase coupling degree of the key vital sign characteristic sequence to obtain an inter-organ functional association strength matrix; A projection module 24 is used to perform high-dimensional feature space projection on the critically ill patient based on the inter-organ functional association strength matrix to obtain a feature map of the patient's pathological state; An analysis module 25 is used to perform nonlinear dynamic analysis on the characteristic spectrum of the patient's pathological state to obtain a dynamic trajectory of disease progression; The reasoning module 26 is used to perform clinical decision support reasoning based on the dynamic trajectory of disease progression to obtain personalized treatment recommendations.

[0045] In this embodiment, for the specific implementation of each unit in the above system embodiment, please refer to the above method embodiment, which will not be repeated here.

[0046] Reference Figure 3 The present invention also provides a computer device in an embodiment, wherein the internal structure of the computer device can be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0047] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0048] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0049] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided by the present invention and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

[0050] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0051] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A data fusion processing method based on MEMS intelligent sensor, characterized in that: The following steps are involved: Perform multi-channel synchronous sampling and fusion processing on the physiological signals of critically ill patients collected by MEMS sensors to obtain multi-modal physiological parameter time series data stream; Performing non-stationary signal decomposition on the multimodal physiological parameter time series data stream to obtain a key vital sign feature sequence; Calculating the phase coupling degree of the key vital sign characteristic sequence to obtain an inter-organ functional association strength matrix; Performing high-dimensional feature space projection on the critically ill patient based on the inter-organ functional association strength matrix to obtain a feature map of the patient's pathological state; Performing nonlinear dynamic analysis on the characteristic graph of the patient's pathological state to obtain a dynamic trajectory of disease progression; Clinical decision support reasoning is performed based on the dynamic trajectory of disease progression to obtain personalized treatment recommendations.

2. The data fusion processing method based on MEMS intelligent sensor according to claim 1 is characterized in that: The non-stationary signal decomposition of the multimodal physiological parameter time series data stream to obtain a key vital sign feature sequence includes: Adaptively performing biorthogonal filtering separation on the multimodal physiological parameter time series data stream to obtain a nonlinear physiological fluctuation component, and performing multi-level harmonic analysis on the nonlinear physiological fluctuation component through an adaptive oscillation identification mechanism to obtain a physiological system phase change feature set; Based on the multi-scale covariance structure method, a statistical significance analysis is performed on the phase change feature set of the physiological system to obtain a key physiological coupling network, and a topological stability assessment is performed on the key physiological coupling network to obtain multi-organ function linkage data; Phase synchronization measurement and extraction are performed on the multi-organ function linkage data to obtain a key vital sign feature sequence; wherein the key vital sign feature sequence includes the cardiovascular system regulation ability, respiratory compensation reserve index, circulatory system homeostasis maintenance parameters and multi-system collaborative function characteristics.

3. The data fusion processing method based on MEMS intelligent sensor according to claim 1 is characterized in that: The phase coupling degree is calculated based on the key vital sign characteristic sequence to obtain the inter-organ functional association strength matrix, including: Performing bispectral coherence analysis on the key vital sign feature sequence to obtain a nonlinear phase synchronization feature spectrum, and performing time-varying causal relationship analysis on the nonlinear phase synchronization feature spectrum based on wavelet bidirectional transformation to obtain a functional network connection strength map; Performing directional information transfer analysis on the functional network connection strength map by using a transfer entropy calculation method to obtain a multi-organ interaction matrix, and performing resonance frequency band screening on the multi-organ interaction matrix to obtain a collaborative working mode of key physiological systems; The phase locking value of the collaborative working mode of the key physiological systems is calculated to obtain the organ function synchronization degree data, and a graph theory network characteristic analysis is performed based on the organ function synchronization degree data to obtain the organ function association strength matrix; wherein the organ function association strength matrix includes the cardiopulmonary function collaborative efficiency coefficient, cerebrovascular autoregulation capacity parameters, renal blood perfusion status and multi-system metabolic balance network characteristics.

4. The data fusion processing method based on MEMS intelligent sensor according to claim 1 is characterized in that: The high-dimensional feature space projection is performed based on the inter-organ functional association strength matrix to obtain the patient's pathological state feature map, including: Performing a tensor decomposition operation on the inter-organ functional association intensity matrix to obtain a multi-dimensional physiological system interaction feature space, performing topological structure extraction on the multi-dimensional physiological system interaction feature space to obtain a disease state topological skeleton diagram, and performing multi-scale persistence calculation on the disease state topological skeleton diagram to obtain a set of key pathological state branch points; Performing nonlinear boundary mapping on the key pathological state branch point set by using kernel surface reconstruction technology to obtain an organ function degradation partition map, and performing spectral clustering segmentation processing on the organ function degradation partition map to obtain a pathological state subspace structure; Performing geometric depth feature extraction on the pathological state subspace structure to obtain a disease progression path network, and performing Ricci curvature calculation based on the disease progression path network to obtain a pathological state transformation risk surface; Based on differential geometry mapping, a curvature flow evolution analysis is performed on the pathological state transformation risk surface to obtain a disease state manifold graph, and a characteristic vector field is constructed based on the disease state manifold graph to obtain a patient pathological state characteristic map, wherein the patient pathological state characteristic map includes a multi-organ dysfunction pattern, a critical disease development stage marker, a vital sign instability risk index, and an organ function recovery potential assessment feature.

5. The data fusion processing method based on MEMS intelligent sensor according to claim 1 is characterized in that: The nonlinear dynamic analysis of the characteristic map of the patient's pathological state to obtain a dynamic trajectory of disease progression includes: Performing multi-scale complexity calculation on the patient's pathological state characteristic map to obtain a disease evolution complexity characteristic sequence, and performing recursive quantitative analysis on the disease evolution complexity characteristic sequence to obtain a state transition probability matrix; Extracting the dominant dynamical mode of the state transition probability matrix by singular value decomposition to obtain a disease state attractor structure, and performing bifurcation theory analysis on the disease state attractor structure to obtain a set of clinical state transition critical points; Performing reachability analysis on the set of critical points of clinical state transition to obtain a disease state transition network diagram, and performing minimum action path calculation based on the disease state transition network diagram to obtain key regulatory nodes for disease progression; Based on stochastic differential equations, a dynamic system evolution simulation is performed on the key regulatory nodes of the disease progression to obtain a time-varying disease state manifold, and a vector field integral calculation is performed based on the time-varying disease state manifold to obtain a dynamic trajectory of disease progression.

6. The data fusion processing method based on MEMS intelligent sensor according to claim 5 is characterized in that: The step of performing vector field integral calculation based on the time-varying disease state manifold to obtain a dynamic trajectory of disease progression includes: Performing Stokes theorem transformation on the time-varying disease state manifold to obtain a disease state boundary flux distribution map, and performing tangential field decomposition on the disease state boundary flux distribution map to obtain a pathological state migration velocity vector field; The geometric characteristics of the pathological state migration velocity vector field are analyzed by Riemann curvature tensor to obtain a set of disease progression path geodesics, and a manifold parallel transmission calculation is performed based on the set of disease progression path geodesics to obtain a minimum action path for clinical state conversion; The Hamilton-Jacobi equation is solved for the minimum action path of the clinical state transition to obtain the optimal control surface of the disease progression time, and the Poincaré section is constructed based on the optimal control surface of the disease progression time to obtain the dynamic trajectory of the disease progression.

7. The data fusion processing method based on MEMS intelligent sensor according to claim 1 is characterized in that: The clinical decision support reasoning based on the dynamic trajectory of disease progression to obtain personalized treatment recommendations includes: Performing trajectory segmentation processing on the dynamic trajectory of disease progression to obtain a sequence of key pathological stage transition points, and performing multidimensional critical state analysis on the sequence of key pathological stage transition points to obtain a set of treatment intervention time windows; Based on the Bayesian causal network, the inter-organ action mechanism of the treatment intervention time window set is inferred to obtain a multi-level pathological causal chain structure, and the key node sensitivity analysis of the multi-level pathological causal chain structure is performed to obtain a treatment target priority matrix; The treatment resource allocation calculation is performed on the treatment target priority matrix through multi-objective constraint optimization to obtain a multidimensional pharmacological kinetic parameter space, and a nonlinear response surface is constructed on the multidimensional pharmacological kinetic parameter space to obtain a treatment plan-physiological response mapping relationship diagram; Performing a Pareto optimal solution analysis on the treatment plan-physiological response mapping relationship diagram to obtain a multi-objective balanced treatment strategy set, and performing a clinical risk-benefit quantitative assessment based on the multi-objective balanced treatment strategy set to obtain a safety boundary of the individualized intervention plan; Based on the temporal Bayesian decision network, dynamic treatment path planning is performed on the safety boundary of the individualized intervention plan to obtain a staged treatment target sequence, and treatment plan combination optimization calculation is performed based on the staged treatment target sequence to obtain personalized treatment recommendations.

8. A data fusion processing system based on MEMS intelligent sensor, characterized in that: include: The sampling module is used to perform multi-channel synchronous sampling and fusion processing on the physiological signals of critically ill patients collected by MEMS sensors to obtain a multi-modal physiological parameter time series data stream; A decomposition module, used for performing non-stationary signal decomposition on the multimodal physiological parameter time series data stream to obtain a key vital sign feature sequence; A calculation module, used to calculate the phase coupling degree of the key vital sign characteristic sequence to obtain an inter-organ functional association strength matrix; A projection module, used for performing high-dimensional feature space projection on the critically ill patient based on the inter-organ functional association strength matrix to obtain a feature map of the patient's pathological state; An analysis module, used for performing nonlinear dynamic analysis on the characteristic map of the patient's pathological state to obtain a dynamic trajectory of disease progression; The reasoning module is used to perform clinical decision support reasoning based on the dynamic trajectory of disease progression to obtain personalized treatment recommendations.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images