A method for real-time monitoring of dynamic evolution of traditional Chinese medicine syndromes of cardiovascular and cerebrovascular diseases

Abstract

The present application relates to the technical field of traditional Chinese medicine intelligent diagnosis and medical dynamic monitoring, in particular to a real-time monitoring method for dynamic evolution of traditional Chinese medicine syndromes of cardiovascular and cerebrovascular diseases. Firstly, the patient is classified into heart system, brain system and heart-brain comorbidity, the collection module is started and stopped according to the classification, and the collection frequency is set to complete specific collection of multi-modal data. Then, invalid data and redundant features are removed, four-examination data preprocessing is completed, and then the corresponding syndrome evolution chain model is matched to identify the critical turning points of syndrome evolution, and the compliance of critical warning features is verified item by item. Finally, the weight of syndrome elements is adjusted adaptively according to the determination result, and the dynamic results of syndromes and critical warning information are output in stages. This method realizes real-time monitoring of traditional Chinese medicine syndromes, the determination standard is quantified and unified, the critical risk of the disease can be accurately predicted, the monitoring needs of single disease and comorbidity are considered, the efficiency of traditional Chinese medicine syndrome differentiation and the safety of diagnosis and treatment are effectively improved, and it is suitable for clinical normalization intelligent monitoring of cardiovascular and cerebrovascular diseases.

Description

Technical Field

[0001] This invention relates to the field of intelligent diagnosis and dynamic medical monitoring technology in traditional Chinese medicine, and more specifically, to a method for real-time monitoring of the dynamic evolution of TCM syndromes in cardiovascular and cerebrovascular diseases. Background Technology

[0002] The incidence of cardiovascular and cerebrovascular diseases continues to rise, and traditional Chinese medicine (TCM) syndrome differentiation and treatment are widely used in the diagnosis and treatment of these diseases. However, traditional TCM syndrome differentiation relies heavily on static assessments performed by physicians during face-to-face consultations, making it difficult to track the dynamic progression of patient syndromes in real time, resulting in significant lag in diagnosis and treatment. Current clinical monitoring methods largely focus on Western physiological indicators, failing to incorporate TCM's four diagnostic methods for targeted data collection. The uniform data collection model lacks disease differentiation, easily generating a large amount of redundant and invalid data. Furthermore, there is a lack of a standardized TCM syndrome evolution assessment system, making it impossible to identify critical points of syndrome deterioration based on changes in the patient's condition. Critical risk warnings rely on physician experience, leading to strong subjectivity and inconsistent assessment standards. In addition, conventional syndrome differentiation methods use fixed weights for diagnostic elements, failing to adapt to the needs of patients with different disease stages and severity levels. For patients with comorbid cardiovascular and cerebrovascular diseases, there is a lack of dual-dimensional simultaneous monitoring and assessment methods, making it difficult to meet the actual clinical needs for dynamic, digital, and precise real-time monitoring of TCM syndromes in cardiovascular and cerebrovascular diseases. Summary of the Invention

[0003] In view of this, the present invention addresses the shortcomings of the prior art by proposing a method for real-time monitoring of the dynamic evolution of TCM syndromes in cardiovascular and cerebrovascular diseases, aiming to solve at least one of the problems mentioned in the background art.

[0004] This invention provides a method for real-time monitoring of the dynamic evolution of TCM syndromes in cardiovascular and cerebrovascular diseases, comprising the following steps: determining whether a patient has a heart disease, a brain disease, or a comorbid heart and brain disease by disease classification; starting and stopping the corresponding acquisition module according to the classification results and setting the acquisition frequency to complete the specific acquisition of multimodal monitoring data; By eliminating unqualified data through data validity, core features are screened and redundant features are eliminated according to disease type, thus completing the data preprocessing and feature screening for the four diagnostic methods. Match the specific syndrome evolution chain model of the corresponding disease, identify the critical turning point through feature combination verification logic, the critical turning point is the critical node for the evolution of syndrome into critical condition, and judge whether all critical warning features meet the criteria one by one. Based on the determination of whether the turning point has been triggered, the proportion of dialectical elements is adjusted through weight adaptive logic, and dynamic results of syndromes and critical warning information are generated according to the hierarchical output logic.

[0005] In some embodiments, when determining whether a patient has a cardiovascular disease, a neurological disease, or a cardiovascular-cerebrovascular comorbidity through disease classification, starting and stopping the corresponding acquisition module according to the classification result and setting the acquisition frequency to complete the specific acquisition of multimodal monitoring data, the process includes: The system detects the patient's disease diagnosis results. When coronary heart disease or arrhythmia is diagnosed, it is determined to be a cardiac disease and the ECG and pulse acquisition modules are activated. When cerebral infarction or hypertensive encephalopathy is diagnosed, it is determined to be a brain disease and the brain oxygen, gait, and tongue infrared acquisition modules are activated. When both cardiovascular and neurological diseases are diagnosed simultaneously, it is determined to be a comorbid cardiovascular disease, and the full acquisition module is activated simultaneously, with acquisition bandwidth allocated according to disease priority.

[0006] In some embodiments, the process of preprocessing and feature selection of diagnostic data by removing unqualified data through data validity, screening core features by disease type, removing redundant features, and completing the four diagnostic methods data preprocessing and feature selection includes: The signal-to-noise ratio of the collected data is detected. If the signal-to-noise ratio is lower than the preset signal-to-noise ratio threshold, the invalid monitoring data is directly discarded. When the signal-to-noise ratio meets the standard, further detection of feature attributes is performed. If the feature is a non-core redundant feature, the redundant feature is removed. When the core features are specific to a disease, the core features are retained and the effective features are collected.

[0007] In some embodiments, the specific syndrome evolution chain model matching the corresponding disease identifies critical turning points through feature combination verification logic. These critical turning points are the critical nodes in the evolution of syndromes into critical conditions. When judging whether all critical warning features are met, the process includes: When the disease classification results are for cardiovascular diseases, the syndrome evolution chain is matched with Qi stagnation in the heart vessels syndrome, cold coagulation in the heart vessels syndrome, blood stasis in the heart vessels syndrome, phlegm obstruction in the heart vessels syndrome, phlegm and blood stasis intermingling in the heart vessels syndrome, Qi deficiency and blood stasis syndrome, Qi and Yin deficiency syndrome, heart Yang deficiency syndrome, and heart Yang collapse syndrome. When it is a brain disease, it is matched with the syndrome evolution chain of blood stasis in the brain collaterals, qi stagnation and blood stasis, phlegm and blood stasis, wind and phlegm obstructing the collaterals, qi deficiency and blood stasis, liver yang hyperactivity, yang hyperactivity transforming into wind, yin deficiency and wind stirring, and internal closure and external collapse. When there is a comorbidity of heart and brain, the syndrome chains of the two diseases are loaded simultaneously and the syndrome transfer judgment is performed separately.

[0008] In some embodiments, the specific syndrome evolution chain model matching the corresponding disease identifies critical turning points through feature combination verification logic. These critical turning points are the critical nodes in the evolution of syndromes into critical conditions. When judging whether all critical warning features are met, the model further includes: The detection of critical turning points in cardiovascular diseases is based on the following characteristics: when the decrease in heart rate exceeds a preset heart rate threshold, the decrease in blood pressure exceeds a preset blood pressure threshold, and the pulse becomes extremely weak, the condition is simultaneously identified as a critical turning point in cardiovascular diseases. If only one or two of the three characteristics meet the criteria, an early warning sign is marked and the data collection frequency is increased; If none of the three characteristics meet the criteria, then routine symptom monitoring will continue and no turning point will be triggered.

[0009] In some embodiments, the specific syndrome evolution chain model matching the corresponding disease identifies critical turning points through feature combination verification logic. These critical turning points are the critical nodes in the evolution of syndromes into critical conditions. When judging whether all critical warning features are met, the model further includes: The system continuously monitors the characteristics of critical turning points in brain diseases for 72 hours. When the fluctuation of blood pressure exceeds the preset blood pressure threshold, the facial thermogram asymmetry exceeds the preset thermogram threshold, and the gait rhythm disorder meets the criteria at the same time, it is judged as a critical turning point in brain diseases. If any of the three features is abnormal, a trend warning is issued and the sampling frequency is increased. If none of the three features are abnormal, then regular monitoring will continue and no inflection point will be triggered.

[0010] In some embodiments, when adjusting the proportion of dialectical elements through weighted adaptive logic based on the determination result of whether a turning point is triggered, and generating dynamic results of syndromes and critical warning information according to hierarchical output logic, the following steps are included: The test determines whether the critical turning point meets the corresponding judgment rules. When a critical turning point is determined, the diagnostic weight of the core characteristics of the corresponding disease is increased. When a turning point is not identified but there are early warning signs, the weight of the core features is increased to strengthen monitoring. When there is no warning and the turning point has not been determined, the basic dialectical weights are maintained and the dialectical process is carried out normally.

[0011] In some embodiments, the specific syndrome evolution chain model matching the corresponding disease, identifying critical turning points through feature combination verification logic, wherein the critical turning point is the critical node for the evolution of syndrome into critical condition, and when judging whether all critical warning features are met item by item, further includes: Parallel detection of critical turning points in the cardiac and cerebral systems of comorbid cardiovascular disease; when a critical turning point in the cardiac system is identified, it is determined to be a critical turning point in comorbid cardiovascular disease. When a critical turning point in the cerebral system is identified, it is determined to be a critical turning point in cardiac-cerebral comorbidity. If no turning point is identified for either of the two diseases, then routine comorbidity diagnosis and continuous monitoring should be performed.

[0012] In some embodiments, the specific syndrome evolution chain model matching the corresponding disease, identifying critical turning points through feature combination verification logic, wherein the critical turning point is the critical node for the evolution of syndrome into critical condition, and when judging whether all critical warning features are met item by item, further includes: Detect the probability of the current syndrome attribution. When the probability of attribution is higher than a preset probability threshold, the current syndrome is directly locked. When the probability of attribution is between a low preset probability threshold and a high preset probability threshold, it is marked as a syndrome transition period and the collection frequency is increased. When the probability of attribution is lower than the low preset probability threshold, the feature is deemed insufficient and monitoring data is re-collected.

[0013] In some embodiments, when adjusting the proportion of dialectical elements according to the determination result of whether a turning point is triggered, and generating dynamic results of syndromes and critical warning information according to hierarchical output logic, the method further includes: The system detects whether a critical turning point has been identified. If a critical turning point is identified, a Level 1 critical warning is issued. If the characteristics do not return to normal within the preset monitoring time after the warning, the warning level will be upgraded and intervention prompts will be strengthened. If the characteristics are determined to return to normal within the preset monitoring time after the warning, the warning will be lifted and regular monitoring will resume.

[0014] Compared with existing technologies, the advantages of this invention are as follows: Data purification is achieved through signal-to-noise ratio verification and feature screening, effectively eliminating interfering data, simplifying computational data volume, and improving system operating efficiency. Syndrome assessment is completed based on a dedicated syndrome evolution chain, and critical turning points are accurately identified by combining quantitative thresholds, achieving objective early warning of critical conditions in Traditional Chinese Medicine (TCM) and significantly reducing the probability of missed or incorrect diagnoses. This solution can simultaneously complete dual-dimensional syndrome monitoring of cardiovascular and cerebrovascular comorbidities, adapting to complex clinical scenarios. It dynamically adjusts the syndrome differentiation ratio using a weighted adaptive mechanism, conforming to the syndrome evolution pattern and significantly improving the accuracy of syndrome differentiation. Simultaneously, a hierarchical early warning closed-loop management system is established, which can flexibly adjust the monitoring frequency and early warning level according to the patient's condition. This not only allows for early prediction of disease deterioration trends and sufficient time for clinical intervention but also avoids ineffective monitoring and resource waste. The overall level of intelligence is high, aligning with TCM diagnostic and treatment concepts, and its clinical practicality and promotional value are extremely high.

[0015] The above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure.

[0016] Other features and aspects of the present invention will become clearer from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0017] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 A flowchart of a method for real-time monitoring of the dynamic evolution of TCM syndromes in cardiovascular and cerebrovascular diseases provided in an embodiment of the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0020] In the description of this application, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0021] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0022] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0023] See Figure 1As shown in the embodiment of this application, a method for real-time monitoring of the dynamic evolution of TCM syndromes in cardiovascular and cerebrovascular diseases includes the following steps: The patient is identified as having a heart disease, a brain disease, or a comorbid heart and brain disease by disease classification. The corresponding acquisition module is started and stopped according to the classification results and the acquisition frequency is set to complete the specific acquisition of multimodal monitoring data. By eliminating unqualified data through data validity, core features are screened and redundant features are eliminated according to disease type, thus completing the data preprocessing and feature screening for the four diagnostic methods. Match the specific syndrome evolution chain model of the corresponding disease, identify the critical turning point through feature combination verification logic, the critical turning point is the critical node for the evolution of syndrome into critical condition, and judge whether all critical warning features meet the criteria one by one. Based on the determination of whether the turning point has been triggered, the proportion of dialectical elements is adjusted through weight adaptive logic, and dynamic results of syndromes and critical warning information are generated according to the hierarchical output logic.

[0024] It should be understood that, based on the core theory of TCM syndrome differentiation for cardiovascular and cerebrovascular diseases, patients are precisely divided into three categories: cardiovascular diseases, cerebrovascular diseases, and cardiovascular-cerebrovascular comorbidities. This abandons the traditional uniform data collection model, and instead differentiates the start and stop of data collection modules and matches the collection frequency according to the differences in disease types, achieving specificity and targeting in data collection. For the original four diagnostic methods and physiological monitoring data collected, data purification is completed through signal-to-noise ratio verification and redundant feature removal, selecting the core syndrome differentiation features specific to each disease type, and eliminating invalid and interfering data to ensure the accuracy of the input data. Relying on a pre-constructed TCM syndrome evolution chain model specific to each disease type, combined with multi-dimensional feature combination verification logic, the critical critical turning point of syndrome transformation into critical condition is accurately identified, and the status of critical warning features is verified item by item. Finally, based on whether the turning point is triggered and whether there are warning precursors, the weighted adaptive algorithm dynamically adjusts the ratio of TCM syndrome differentiation elements, breaking away from the limitations of fixed syndrome differentiation weights, and outputting real-time syndrome differentiation results and graded critical warning information in a tiered manner. To eliminate ambiguity in the technical solutions, this method uses globally unified core monitoring parameters. All disease severity assessments adopt a continuous 72-hour dynamic monitoring mode and unifies the application scenarios of various preset thresholds, providing a standardized basis for subsequent accurate assessments.

[0025] Example Description: After the monitoring system is activated for a newly diagnosed cardiovascular and cerebrovascular disease patient, the device first automatically reads the patient's confirmed medical record to complete the disease classification, activates the corresponding data collection device and sets the collection frequency; after continuously collecting multimodal pulse, electrocardiogram, tongue appearance, cerebral oxygenation, gait and other data for 72 hours, the system automatically verifies the validity of the data and completes feature screening; it calls the matching syndrome evolution chain model, compares the feature data in real time, and determines whether the critical turning point conditions have been reached; finally, it dynamically adjusts the syndrome differentiation weights based on the judgment results and outputs the patient's current TCM syndrome classification and the corresponding risk warning level. The technical solutions offered by this approach yielded significant benefits: First, they enabled dynamic, real-time, and intelligent TCM diagnosis of cardiovascular and cerebrovascular diseases, breaking the limitations of traditional TCM's single-session, static diagnosis and accurately capturing the gradual and fluctuating evolution of syndromes. Second, through disease-specific data collection and feature screening, they significantly reduced the amount of invalid data processing, improved system efficiency, and prevented redundant data from interfering with diagnosis results. Third, relying on standardized syndrome evolution chains and turning point judgment logic, they achieved objective and quantitative early warning of critical conditions in TCM, solving the problems of traditional diagnosis relying on physician experience, strong subjectivity, and high rates of missed and misdiagnosed cases. Fourth, through a weighted adaptive adjustment mechanism, they adapted to the diagnosis needs of patients with different disease stages and severity levels, significantly improving the accuracy of diagnosis. Fifth, they established a globally unified 72-hour monitoring standard, standardizing the monitoring system for the cardiovascular, cerebrovascular, and comorbid diseases, eliminating the defects of inconsistent technical judgment criteria, and making monitoring results more comparable and clinically relevant.

[0026] In some specific embodiments, when determining whether a patient has a cardiovascular disease, a neurological disease, or a cardiovascular-cerebrovascular comorbidity through disease classification, starting and stopping the corresponding acquisition module according to the classification result and setting the acquisition frequency to complete the specific acquisition of multimodal monitoring data, the process includes: The system detects the patient's disease diagnosis results. When coronary heart disease or arrhythmia is diagnosed, it is determined to be a cardiac disease and the ECG and pulse acquisition modules are activated. When cerebral infarction or hypertensive encephalopathy is diagnosed, it is determined to be a brain disease and the brain oxygen, gait, and tongue infrared acquisition modules are activated. When both cardiovascular and neurological diseases are diagnosed simultaneously, it is determined to be a comorbid cardiovascular disease, and the full acquisition module is activated simultaneously, with acquisition bandwidth allocated according to disease priority.

[0027] It should be understood that the system automatically connects to the hospital's electronic medical records, reads the patient's disease diagnosis results, and achieves automatic classification. Among them, cardiovascular diseases specifically refer to two core cardiovascular diseases: coronary heart disease and arrhythmia. The core pathogenesis of these diseases is concentrated in the obstruction of the heart vessels, deficiency of heart qi, and depletion of heart yang. The core signs are reflected in the pulse and changes in electrocardiogram rhythm. Therefore, the electrocardiogram acquisition module and pulse acquisition module are specifically used to focus on the core data of cardiovascular syndrome differentiation. Brain diseases specifically refer to two core cerebrovascular diseases: cerebral infarction and hypertensive encephalopathy. The core pathogenesis of these diseases is liver yang hyperactivity, wind-phlegm obstruction of collaterals, and qi deficiency and blood stasis. The core signs are reflected in brain oxygen supply, limb gait, and the distribution of qi and blood cold and heat on the face. Therefore, the brain oxygen acquisition module, gait acquisition module, and tongue infrared acquisition module are specifically used. Cardiovascular and cerebrovascular comorbidities refer to complex symptoms in which patients are diagnosed with both cardiovascular and cerebrovascular diseases at the same time. The pathogenesis is complex, the syndrome evolves faster, and the risk of critical illness is higher. Therefore, all acquisition modules are used simultaneously. To address previous technical deficiencies, this solution clarifies the priority rules for acquisition bandwidth in cardiovascular and cerebrovascular disease comorbidities: critical cardiovascular diseases have a higher priority than cerebrovascular diseases. By default, the system allocates 80% of the acquisition bandwidth to the acquisition module corresponding to the critical disease, and the remaining 20% ​​of the bandwidth is used to ensure routine monitoring of the other disease. If both diseases have early warning signs, the bandwidth is evenly distributed and the overall acquisition frequency is increased, thus completely closing the technical feature of "allocating acquisition bandwidth based on disease priority".

[0028] Exemplary Explanation: When a patient is diagnosed with simple coronary heart disease, the system classifies it as a cardiac disease, only activating the ECG and pulse acquisition modules while disabling irrelevant modules such as brain oxygenation and gait monitoring, and collecting data at a routine frequency of once every 5 minutes; when a patient is diagnosed with cerebral infarction, it is classified as a cerebrovascular disease, and the brain oxygenation, gait, and tongue infrared modules are activated for monitoring; when a patient is simultaneously diagnosed with hypertensive encephalopathy and arrhythmia, it is classified as a comorbid cardiovascular disease, activating all acquisition modules, prioritizing the bandwidth for ECG and pulse data acquisition, while also considering the monitoring of related brain data. The corresponding technical effects include: First, achieving precise matching of data collection resources, avoiding idle operation of irrelevant modules, significantly reducing equipment energy consumption and system computing load, and extending equipment lifespan; Second, targeted collection of core diagnostic data for specific diseases, avoiding invalid data collection from the source, and laying a precise data foundation for subsequent feature screening and diagnostic analysis; Third, completing the closed-loop logic of comorbidity bandwidth allocation, solving the problem of existing technical features being suspended and unable to be implemented, making comorbidity monitoring more targeted; Fourth, aligning with the differences in the pathogenesis of cardiovascular and cerebrovascular diseases in traditional Chinese medicine, realizing the precise diagnosis and treatment logic of "collecting data according to the disease and differentiating syndromes based on data", significantly improving the matching degree of subsequent syndrome evolution monitoring; Fifth, the differentiated collection mode effectively reduces redundant interference from multimodal data, improving the overall response speed and operational stability of the monitoring system.

[0029] In some specific embodiments, the process of preprocessing and feature selection of the four diagnostic methods (inspection, diagnosis, and treatment) by removing unqualified data through data validity, screening core features by disease type, removing redundant features, and completing the preprocessing and feature selection of the four diagnostic methods includes: The signal-to-noise ratio of the collected data is detected. If the signal-to-noise ratio is lower than the preset signal-to-noise ratio threshold, the invalid monitoring data is directly discarded. When the signal-to-noise ratio meets the standard, further detection of feature attributes is performed. If the feature is a non-core redundant feature, the redundant feature is removed. When the core features are specific to a disease, the core features are retained and the effective features are collected.

[0030] It should be understood that the first step, data signal-to-noise ratio (SNR) detection, involves noise analysis of the real-time collected pulse, ECG, cerebral oxygenation, infrared thermography, and gait data. When the SNR is <30dB, the data is considered severely affected by environmental interference, equipment fluctuations, and patient positioning, and is automatically discarded by the system, not included in subsequent calculations. When the SNR is ≥30dB, the data signal is considered valid, and the system proceeds to the second step, feature screening. Based on the patient's disease classification, the system retrieves the corresponding disease's feature library and classifies the feature attributes of the valid data. Redundant features that are not core or related to the TCM diagnosis of the disease, such as irrelevant gait details in cardiac monitoring and weak ECG fluctuations in cerebral monitoring, are automatically discarded. Core diagnostic features specific to the disease, such as pulse rate, pulse strength, and ECG rhythm in the cardiac system, and cerebral oxygen saturation, gait rhythm, and tongue temperature difference in the cerebral system, are all accurately collected, classified, and stored to form a structured core feature dataset.

[0031] Example explanation: If the signal-to-noise ratio of pulse data collected from patients with coronary heart disease is 22dB due to the patient's limb movement, which is lower than the preset threshold of 30dB, the system will directly discard the data and re-collect it; if the signal-to-noise ratio of the pulse data is 38dB, the data is valid, the system will remove redundant features such as small fluctuations in pulse amplitude, retain the core diagnostic features of the heart system such as pulse velocity, pulse rhythm, and pulse strength, and complete the collection. The technical benefits of this step are significant: First, by quantifying the signal-to-noise ratio threshold, objective judgment of data validity is achieved, eliminating the subjectivity of manual screening and ensuring standardized and unified data preprocessing. Second, the dual-layer purification mechanism filters out environmental, equipment, and human interference to the greatest extent, greatly improving the authenticity and reliability of monitoring data. Third, redundant features of various diseases are specifically eliminated, significantly simplifying data calculation dimensions, reducing system computing power consumption, and improving the response speed of real-time monitoring. Fourth, core diagnostic features are accurately collected, ensuring that subsequent syndrome evolution analysis and critical turning point determination are based on effective core data, improving the accuracy of diagnosis and the precision of early warning from the source. Fifth, the standardized preprocessing process is adapted to multimodal data types, achieving unified and standardized processing of monitoring data from different dimensions, and solving the technical challenge of difficult integration and analysis of mixed multi-source data.

[0032] In some specific embodiments, the specific syndrome evolution chain model matching the corresponding disease identifies critical turning points through feature combination verification logic. These critical turning points are the critical nodes in the evolution of syndromes into critical conditions. When determining whether all critical warning features are met, the process includes: When the disease classification results are for cardiovascular diseases, the syndrome evolution chain is matched with Qi stagnation in the heart vessels syndrome, cold coagulation in the heart vessels syndrome, blood stasis in the heart vessels syndrome, phlegm obstruction in the heart vessels syndrome, phlegm and blood stasis intermingling in the heart vessels syndrome, Qi deficiency and blood stasis syndrome, Qi and Yin deficiency syndrome, heart Yang deficiency syndrome, and heart Yang collapse syndrome. When it is a brain disease, it is matched with the syndrome evolution chain of blood stasis in the brain collaterals, qi stagnation and blood stasis, phlegm and blood stasis, wind and phlegm obstructing the collaterals, qi deficiency and blood stasis, liver yang hyperactivity, yang hyperactivity transforming into wind, yin deficiency and wind stirring, and internal closure and external collapse. When there is a comorbidity of heart and brain, the syndrome chains of the two diseases are loaded simultaneously and the syndrome transfer judgment is performed separately.

[0033] It should be understood that for cardiovascular diseases (coronary heart disease, arrhythmia), a multi-level progressive syndrome evolution chain is matched, namely, Qi stagnation in the heart vessels syndrome, cold coagulation in the heart vessels syndrome, blood stasis in the heart vessels syndrome, phlegm obstruction in the heart vessels syndrome, phlegm and blood stasis intermingling in the heart vessels syndrome, Qi deficiency and blood stasis syndrome, Qi and Yin deficiency syndrome, heart Yang deficiency syndrome, and heart Yang collapse syndrome, following the critical progression pattern of cardiovascular diseases: "excess of pathogenic factors - mixed deficiency and excess - deficiency - Yang collapse"; for cerebrovascular diseases (cerebral infarction, hypertensive encephalopathy), a multi-level progressive syndrome evolution chain is matched, namely, blood stasis obstructing the brain collaterals. The system identifies syndromes such as Qi stagnation and blood stasis syndrome, phlegm and blood stasis syndrome, wind-phlegm obstruction syndrome, Qi deficiency and blood stasis syndrome, liver yang hyperactivity syndrome, yang hyperactivity transforming into wind syndrome, yin deficiency and wind stirring syndrome, and internal closure and external collapse syndrome. These syndromes align with the progressive deterioration pathogenesis of cerebrovascular diseases, characterized by "excessive pathogenic factors - mixed deficiency and excess - wind stirring - closure and collapse." For comorbid cardiovascular and cerebrovascular diseases, the system employs a dual-model parallel computing mechanism, simultaneously loading two sets of syndrome evolution chains for the cardiovascular and cerebrovascular systems. These chains independently determine the transfer of syndromes in the cardiovascular and cerebrovascular systems, ensuring that the two models operate independently and synchronously, comprehensively covering the complex pathogenesis of comorbid diseases. All syndrome evolution chains are adapted to a 72-hour continuous monitoring timeline, enabling full-process tracking of the dynamic transmission of syndromes.

[0034] Exemplary explanation: For patients with arrhythmia, the system continuously monitors the evolution trend of patients from mild blood stasis to qi and yin deficiency and heart yang collapse for 72 hours based on the syndrome evolution chain of the heart system; for patients with cerebral infarction, the system monitors the dynamic changes of liver yang, phlegm stasis and wind syndrome based on the syndrome chain of the brain system; for patients with hypertension and coronary heart disease, the two models run simultaneously to track the bidirectional syndrome transmission of the heart and brain. The corresponding technical effects are as follows: First, the evolution model is constructed strictly based on the classical TCM syndrome differentiation theory, ensuring the TCM professionalism and theoretical basis of intelligent monitoring and avoiding intelligent monitoring from deviating from the core pathogenesis of TCM. Second, exclusive syndrome chains are matched for different diseases, achieving accurate adaptation of the syndrome differentiation model and solving the problem that general models cannot adapt to the differentiated pathogenesis of heart and brain diseases. Third, the parallel mechanism of dual models for comorbidities accurately covers complex clinical comorbidity scenarios, making up for the technical shortcomings of traditional single syndrome differentiation models in dealing with complex diseases. Fourth, the multi-level progressive syndrome chain can accurately capture the dynamic evolution process of mild, moderate, severe, and critical symptoms, achieving early identification and early warning of syndrome changes. Fifth, the standardized and structured operation of the model greatly improves the objectivity and repeatability of TCM syndrome dynamic judgment, getting rid of the limitations of traditional individual physician syndrome differentiation experience differences.

[0035] In some specific embodiments, the specific syndrome evolution chain model matching the corresponding disease identifies critical turning points through feature combination verification logic. These critical turning points are the critical nodes in the evolution of syndromes into critical conditions. When judging whether all critical warning features are met, the model further includes: The detection of critical turning points in cardiovascular diseases is based on the following characteristics: when the decrease in heart rate exceeds a preset heart rate threshold, the decrease in blood pressure exceeds a preset blood pressure threshold, and the pulse becomes extremely weak, the condition is simultaneously identified as a critical turning point in cardiovascular diseases. If only one or two of the three characteristics meet the criteria, an early warning sign is marked and the data collection frequency is increased; If none of the three characteristics meet the criteria, then routine symptom monitoring will continue and no turning point will be triggered.

[0036] It should be understood that the system continuously collects core cardiac monitoring data in real time for 72 hours, and verifies three critical characteristics in parallel: when the magnitude of heart rate decrease, the magnitude of blood pressure decrease, and the characteristic of a weak pulse all meet the standards at the same time, it accurately determines that the patient has reached the critical turning point of cardiac disease, indicating that the syndrome is about to evolve into a sudden collapse of heart yang and a syncope crisis; when only one or two of the three characteristics are abnormal and meet the standards, it is judged as a critical warning precursor, and the system automatically increases the data collection frequency from the usual once / 5 minutes to once / 1 minute to strengthen high-frequency monitoring and tracking; when all three characteristics are normal, the normal collection frequency and syndrome monitoring mode are maintained, and the critical turning point determination is not triggered.

[0037] Example: A patient with coronary heart disease has a baseline heart rate of 75 beats / min and a baseline systolic blood pressure of 125 mmHg. During a 72-hour monitoring period, the heart rate drops to 58 beats / min (a decrease of 22.7%, exceeding the threshold) and the systolic blood pressure drops to 105 mmHg (a decrease of 16%, exceeding the threshold). At the same time, the pulse data is identified as weak and almost imperceptible. If all three characteristics meet the criteria, the system determines that a critical turning point in cardiac disease has been triggered. If only the heart rate and blood pressure are abnormal, but the pulse is normal, then a warning precursor is marked and monitored at high frequency. The technical solutions offer significant advantages: First, they complete the 72-hour continuous monitoring standard for cardiovascular diseases, achieving full unification with the monitoring system for brain diseases and eliminating discrepancies in technical assessment criteria. Second, they clarify the thresholds for quantitative changes in heart rate and blood pressure, transforming the traditional, vague description of a critical condition in Traditional Chinese Medicine (TCM) as "weak pulse and sudden drop in blood pressure and heart rate" into quantifiable and machine-recognizable objective indicators, completely resolving the shortcomings of previous solutions that were vaguely defined and impractical. Third, they employ a multi-feature joint judgment mechanism, significantly improving the accuracy of identifying critical turning points and avoiding false or missed warnings caused by fluctuations in a single indicator. Fourth, they establish a tiered treatment logic, distinguishing between complete crises, warning precursors, and normal states, enabling stratified and precise intervention and avoiding over-monitoring and under-monitoring. Fifth, they frequently track warning signs, allowing early detection of the nascent stages of critical conditions, providing ample time for clinical rescue and TCM intervention, and significantly reducing the incidence and mortality rates of acute and critical cardiovascular diseases.

[0038] In some specific embodiments, the specific syndrome evolution chain model matching the corresponding disease identifies critical turning points through feature combination verification logic. These critical turning points are the critical nodes in the evolution of syndromes into critical conditions. When judging whether all critical warning features are met, the model further includes: The system continuously monitors the characteristics of critical turning points in brain diseases for 72 hours. When the fluctuation of blood pressure exceeds the preset blood pressure threshold, the facial thermogram asymmetry exceeds the preset thermogram threshold, and the gait rhythm disorder meets the criteria at the same time, it is judged as a critical turning point in brain diseases. If any of the three features is abnormal, a trend warning is issued and the sampling frequency is increased. If none of the three features are abnormal, then regular monitoring will continue and no inflection point will be triggered.

[0039] It should be understood that the system performs continuous 72-hour monitoring of patients with brain diseases, simultaneously verifying three critical condition indicators: when the blood pressure fluctuation range, facial thermogram asymmetry, and gait rhythm disorder all meet the standards, the patient is determined to have reached the critical turning point of brain disease, indicating that critical conditions such as yin deficiency and wind stirring, stroke hemiplegia, and coma are about to occur; when any one of the three characteristics is abnormal, it is marked as a disease trend warning, and the data collection frequency is automatically increased to continuously track changes in the condition; when there are no abnormal fluctuations in the three characteristics, the normal monitoring mode is maintained, and the critical turning point is not triggered.

[0040] Example description: A patient with hypertensive encephalopathy experiences repeated fluctuations in blood pressure within 72 hours, with a maximum fluctuation difference of 28 mmHg. The facial infrared thermometer shows a temperature difference of 2.1℃ between the left and right sides. At the same time, gait detection shows rhythm disorder. If all three indicators are within the normal range, the system determines that a critical turning point in the cerebral system has been triggered. If only the blood pressure fluctuation is abnormal, and the other indicators are normal, a trend warning is marked and high-frequency monitoring is initiated. The corresponding technical effects are as follows: First, by clearly defining the core thresholds of various brain systems, the abstract crisis phenomena of wind-heat and liver yang hyperactivity in traditional Chinese medicine are transformed into precise quantitative indicators, making the criteria for judging brain system critical conditions clear, practical, and reproducible. Second, 72-hour long-term continuous monitoring can effectively avoid misjudgments caused by instantaneous data fluctuations and accurately capture the trend of progressive deterioration of brain system diseases. Third, the single-item abnormal trend early warning mechanism can identify the insidious deterioration of the condition in advance, solving the clinical pain points of sudden onset and difficulty in prediction of traditional brain system diseases. Fourth, the multi-dimensional joint judgment mode covers the three brain system syndrome differentiation dimensions of qi and blood, cold and heat, and limb function, which fully conforms to the pathogenesis of brain system disease crises. Fifth, the graded monitoring strategy effectively balances monitoring accuracy and equipment energy consumption, ensuring accurate capture of critical risks while improving the long-term stability and practicality of the system.

[0041] In some specific embodiments, when adjusting the proportion of dialectical elements through weighted adaptive logic based on the determination result of whether a turning point is triggered, and generating dynamic results of syndromes and critical warning information according to hierarchical output logic, the following steps are included: The test determines whether the critical turning point meets the corresponding judgment rules. When a critical turning point is determined, the diagnostic weight of the core characteristics of the corresponding disease is increased. When a turning point is not identified but there are early warning signs, the weight of the core features is increased to strengthen monitoring. When there is no warning and the turning point has not been determined, the basic dialectical weights are maintained and the dialectical process is carried out normally.

[0042] It should be understood that the system receives the aforementioned turning point determination results in real time and performs weight adjustments in three scenarios: First, when the critical turning point for a corresponding disease is detected, the system automatically increases the weight ratio of all core diagnostic features for that disease (the critical weight ratio is increased to over 85%), prioritizing the adoption of critical-related core features and focusing on the diagnosis of critical conditions; Second, when no critical turning point is triggered, but there are warning signs of abnormalities in one or two of the aforementioned indicators, the weight of core features is automatically increased to over 60%, strengthening the monitoring and diagnostic acceptance of abnormal indicators and focusing on tracking the trend of disease progression; Third, when there are no warning signs and no turning point is triggered, the system maintains the preset basic diagnostic weight (basic weight of core features 40%-50%) and performs routine standardized diagnosis. The weight adjustment process is fully automated and real-time, continuously iterating and optimizing with the dynamic changes in 72-hour monitoring data.

[0043] Example explanation: For patients with coronary heart disease, the basic diagnostic weights are maintained, and the core data of pulse and electrocardiogram are used in a balanced manner; when patients show signs of decreased heart rate, the weights of electrocardiogram and pulse characteristics are increased to strengthen the diagnosis of heart deficiency and blood stasis syndromes; when a critical turning point in the cardiac system is triggered, the weights of crisis-related characteristics are significantly increased, and the critical syndrome of sudden collapse of heart yang is given priority. The technical benefits of this step are as follows: First, by dynamically adjusting the weights adaptively, the diagnostic system is precisely matched to the severity of the patient's condition, breaking the rigidity of traditional fixed-weight diagnostic methods. Second, the tiered weight control mode differentiates the diagnostic focus for mild cases, prodromal stages, and critical stages, significantly improving the accuracy of diagnosis at different disease stages. Third, real-time dynamic weight iteration perfectly matches the core principle of TCM syndromes—"dynamic transmission and gradual progression"—and closely reflects real clinical changes. Fourth, the weights of core features are specifically strengthened while the interference of secondary features is weakened, further improving the relevance and accuracy of syndrome assessment. Fifth, automated weight adjustment requires no manual intervention, enhancing the intelligence and automation of the entire monitoring system and reducing the operational burden on clinicians.

[0044] In some specific embodiments, the specific syndrome evolution chain model matching the corresponding disease, which identifies critical turning points through feature combination verification logic, wherein the critical turning point is the critical node for the evolution of syndrome into critical condition, and when judging whether all critical warning features are met item by item, further includes: Parallel detection of critical turning points in the cardiac and cerebral systems of comorbid cardiovascular disease; when a critical turning point in the cardiac system is identified, it is determined to be a critical turning point in comorbid cardiovascular disease. When a critical turning point in the cerebral system is identified, it is determined to be a critical turning point in cardiac-cerebral comorbidity. If no turning point is identified for either of the two diseases, then routine comorbidity diagnosis and continuous monitoring should be performed.

[0045] It should be understood that the system continuously collects core monitoring data from the cardiac and neurological systems for 72 hours, performing two judgments in parallel: if the cardiac channel detection meets the standards and triggers a critical turning point in the cardiac system, regardless of whether the neurological indicators are abnormal, it directly determines that the overall cardiac-neurotic comorbidity has triggered a critical turning point; if the neurological channel detection meets the standards and triggers a critical turning point in the neurological system, regardless of the status of the cardiac indicators, it also determines that the comorbidity has triggered a critical turning point; if neither the cardiac nor neurological channel meets the standards and there are no abnormal indicators, the patient is determined to be in a stable comorbidity state, and routine syndrome differentiation and continuous tracking monitoring of the comorbidity are performed. Simultaneously, combined with the aforementioned bandwidth priority rules, the system automatically optimizes the allocation of collection resources under comorbidity warning conditions, prioritizing the data collection accuracy for the corresponding disease in the crisis.

[0046] Example description: For patients with comorbid coronary heart disease and cerebral infarction, the system simultaneously verifies cardiac heart rate, blood pressure, pulse indicators and cerebral blood pressure, thermogram, gait indicators. If any one of the diseases reaches the critical condition standard, the comorbidity is determined to enter the critical condition warning state; when both diseases are stable, the changes in symptoms are continuously and routinely monitored. The corresponding technical effects are as follows: First, the dual-channel parallel verification mechanism fully adapts to the characteristics of high incidence, complex pathogenesis, and superimposed risks in clinical cardiocerebrovascular comorbidities, making up for the coverage blind spots of a single monitoring system; second, the logic of triggering comorbidity warnings by single-disease crisis aligns with the holistic concept of "one organ in danger, the whole body in danger" in traditional Chinese medicine, avoiding missed diagnoses due to neglecting single organ crises; third, the optimized linkage bandwidth resources enable precise key monitoring in critical states of comorbidity, improving the efficiency of crisis capture; fourth, the unified comorbidity judgment criteria standardize and regulate the critical warning of complex diseases, solving the problem of the lack of unified quantitative standards for clinical comorbidity differentiation; and fifth, the continuous tracking routine monitoring logic enables dynamic management during the stable period of comorbidity, and early prediction of potential syndrome evolution risks.

[0047] In some specific embodiments, the specific syndrome evolution chain model matching the corresponding disease, which identifies critical turning points through feature combination verification logic, wherein the critical turning point is the critical node for the evolution of syndrome into critical condition, and when judging whether all critical warning features are met item by item, further includes: Detect the probability of the current syndrome attribution. When the probability of attribution is higher than a preset probability threshold, the current syndrome is directly locked. When the probability of attribution is between a low preset probability threshold and a high preset probability threshold, it is marked as a syndrome transition period and the collection frequency is increased. When the probability of attribution is lower than the low preset probability threshold, the feature is deemed insufficient and monitoring data is re-collected.

[0048] It should be understood that the system calculates the current syndrome attribution probability in real time and implements control in three tiers: When the syndrome attribution probability is >85%, it is determined that the currently collected core features are sufficient and the syndrome matching degree is extremely high, directly locking the current syndrome diagnosis result and stably outputting a fixed syndrome type; when the syndrome attribution probability is between 60% and 85%, it is determined that the patient's syndrome is in a dynamic transformation stage and the syndrome type has not yet stabilized, marked as a syndrome transition period, and the system automatically increases the collection frequency, intensifies the monitoring of syndrome evolution details, and captures syndrome transformation nodes; when the syndrome attribution probability is <60%, it is determined that the current number of effective core features is insufficient, the data support is insufficient, and the credibility of the syndrome diagnosis result is low, and the system automatically triggers a new round of full-dimensional data collection and monitoring to supplement effective feature data and re-complete the syndrome assessment. The entire process is adapted to a 72-hour continuous monitoring time series, dynamically updating probability values ​​and judgment results.

[0049] Example explanation: After processing the monitoring data of cerebral infarction patients, the probability of Qi deficiency and blood stasis syndrome is 88%, which is higher than the high threshold. The system locks the current Qi deficiency and blood stasis syndrome type. When the probability is 72%, it is marked as the syndrome transition period and monitored at high frequency. When the probability is 55%, data re-collection is triggered to supplement monitoring indicators. The technical effects of this solution are as follows: First, it clarifies the calculation basis and quantification threshold of syndrome probability, completely solving the defects of the original technical solution, which was logically ambiguous and technically unclear, and providing clear data support for syndrome determination. Second, the three-level probability grading and control mechanism accurately distinguishes three clinical states: stable syndrome, syndrome transformation, and insufficient data, perfectly adapting to the intermediate process of dynamic evolution of TCM syndromes. Third, high-frequency monitoring during the transition period can accurately capture the critical node of syndrome transformation, solving the problem that traditional syndrome differentiation cannot identify hidden syndrome transformation. Fourth, the automatic re-collection mechanism for insufficient data ensures that all syndrome differentiation results are based on sufficient and effective core data, greatly improving the credibility and accuracy of syndrome differentiation results. Fifth, the probability quantification judgment realizes the upgrade of TCM syndrome judgment from qualitative to quantitative judgment, making the syndrome differentiation results more objective, more accurate, and more clinically valuable.

[0050] In some specific embodiments, when adjusting the proportion of dialectical elements through weighted adaptive logic based on the determination result of whether a turning point is triggered, and generating dynamic results of syndromes and critical warning information according to hierarchical output logic, the method further includes: The system detects whether a critical turning point has been identified. If a critical turning point is identified, a Level 1 critical warning is issued. If the characteristics do not return to normal within the preset monitoring time after the warning, the warning level will be upgraded and intervention prompts will be strengthened. If the characteristics are determined to return to normal within the preset monitoring time after the warning, the warning will be lifted and regular monitoring will resume.

[0051] It should be understood that the system first determines whether a critical turning point has been triggered. If it is, a Level 1 critical warning is directly output, along with simultaneous clinical intervention prompts. After a Level 1 warning is triggered, the system continuously monitors core critical characteristics for 30 minutes. If abnormal characteristics do not return to normal within 30 minutes and continue to exceed the threshold, the system automatically upgrades the warning level, strengthening the prompts for emergency intervention, clinical treatment, and continuous monitoring to increase clinical attention. If all critical warning characteristics return to the normal threshold range within 30 minutes and the patient's condition stabilizes, the system immediately lifts the critical warning and automatically switches back to the routine monitoring mode, continuing dynamic monitoring of symptoms. The warning level is linked to the aforementioned weighted adaptive mechanism throughout the process; upgrading the warning simultaneously increases the weight of critical characteristics in syndrome differentiation, and lifting the warning simultaneously restores the basic weight.

[0052] Example description: After a patient triggers a critical turning point in their cardiac condition, the system immediately sends a Level 1 critical warning; if the heart rate and blood pressure do not return to normal after 30 minutes of continuous monitoring, the system upgrades the warning and prompts for emergency clinical intervention; if all indicators return to normal within 30 minutes, the warning is lifted and routine monitoring resumes. The corresponding technical effects are as follows: First, it constructs a complete closed-loop system of "early warning triggering - continuous monitoring - level upgrade - early warning cancellation," solving the shortcomings of traditional monitoring and early warning systems that lack follow-up management and dynamic iteration. Second, it clarifies the 30-minute early warning monitoring duration threshold, making early warning level adjustments standardized and quantifiable, avoiding the subjectivity and lag of manual judgment. Third, the tiered early warning upgrade mechanism can accurately distinguish the progression of critical and acute illnesses, providing a basis for differentiated intervention in clinical practice and avoiding the problems of over-intervention for mild cases and untimely intervention for severe cases. Fourth, it deeply links early warning with syndrome differentiation weights and monitoring frequency, achieving dynamic matching of risk level, monitoring intensity, and syndrome differentiation accuracy, significantly improving the system's intelligent management level. Fifth, it establishes a normalized early warning cancellation mechanism, avoiding long-term ineffective early warnings, reducing clinical interference, and improving the practicality and adaptability of the monitoring system. Sixth, it provides full-process dynamic time-series management, perfectly adapting to the clinical characteristics of rapid changes in cardiovascular and cerebrovascular disease conditions and large risk fluctuations, effectively reducing the rate of missed diagnosis and delayed treatment of acute and critical illnesses, and greatly enhancing the clinical application value of intelligent monitoring of cardiovascular and cerebrovascular diseases in traditional Chinese medicine.

[0053] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for real-time monitoring of the dynamic evolution of TCM syndromes in cardiovascular and cerebrovascular diseases, characterized in that, Includes the following steps: The patient is identified as having a heart disease, a brain disease, or a comorbid heart and brain disease by disease classification. The corresponding acquisition module is started and stopped according to the classification results and the acquisition frequency is set to complete the specific acquisition of multimodal monitoring data. By eliminating unqualified data through data validity, core features are screened and redundant features are eliminated according to disease type, thus completing the data preprocessing and feature screening for the four diagnostic methods. Match the specific syndrome evolution chain model of the corresponding disease, identify the critical turning point through feature combination verification logic, the critical turning point is the critical node for the evolution of syndrome into critical condition, and judge whether all critical warning features meet the criteria one by one. Based on the determination of whether the turning point has been triggered, the proportion of dialectical elements is adjusted through weight adaptive logic, and dynamic results of syndromes and critical warning information are generated according to the hierarchical output logic.

2. The method for real-time monitoring of the dynamic evolution of TCM syndromes in cardiovascular and cerebrovascular diseases according to claim 1, characterized in that, When determining whether a patient has a cardiovascular disease, a neurological disease, or a cardiovascular-cerebrovascular comorbidity through disease classification, and activating or deactivating the corresponding acquisition module and setting the acquisition frequency according to the classification results to complete the specific acquisition of multimodal monitoring data, the process includes: The system detects the patient's disease diagnosis results. When coronary heart disease or arrhythmia is diagnosed, it is determined to be a cardiac disease and the ECG and pulse acquisition modules are activated. When cerebral infarction or hypertensive encephalopathy is diagnosed, it is determined to be a brain disease and the brain oxygen, gait, and tongue infrared acquisition modules are activated. When both cardiovascular and neurological diseases are diagnosed simultaneously, it is determined to be a comorbid cardiovascular disease, and the full acquisition module is activated simultaneously, with acquisition bandwidth allocated according to disease priority.

3. The method for real-time monitoring of the dynamic evolution of TCM syndromes in cardiovascular and cerebrovascular diseases according to claim 2, characterized in that, The process of preprocessing and feature selection of diagnostic data by eliminating unqualified data through data validity, screening core features by disease type, and eliminating redundant features includes: The signal-to-noise ratio of the collected data is detected. If the signal-to-noise ratio is lower than the preset signal-to-noise ratio threshold, the invalid monitoring data is directly discarded. When the signal-to-noise ratio meets the standard, further detection of feature attributes is performed. If the feature is a non-core redundant feature, the redundant feature is removed. When the core features are specific to a disease, the core features are retained and the effective features are collected.

4. The method for real-time monitoring of the dynamic evolution of TCM syndromes in cardiovascular and cerebrovascular diseases according to claim 3, characterized in that, The specific syndrome evolution chain model matching the corresponding disease identifies critical turning points through feature combination verification logic. These critical turning points are the critical nodes in the evolution of syndromes into critical conditions. When determining whether all critical warning features are met, the following criteria are considered: When the disease classification results are for cardiovascular diseases, the syndrome evolution chain is matched with Qi stagnation in the heart vessels syndrome, cold coagulation in the heart vessels syndrome, blood stasis in the heart vessels syndrome, phlegm obstruction in the heart vessels syndrome, phlegm and blood stasis intermingling in the heart vessels syndrome, Qi deficiency and blood stasis syndrome, Qi and Yin deficiency syndrome, heart Yang deficiency syndrome, and heart Yang collapse syndrome. When it is a brain disease, it is matched with the syndrome evolution chain of blood stasis in the brain collaterals, qi stagnation and blood stasis, phlegm and blood stasis, wind and phlegm obstructing the collaterals, qi deficiency and blood stasis, liver yang hyperactivity, yang hyperactivity transforming into wind, yin deficiency and wind stirring, and internal closure and external collapse. When there is a comorbidity of heart and brain, the syndrome chains of the two diseases are loaded simultaneously and the syndrome transfer judgment is performed separately.

5. The method for real-time monitoring of the dynamic evolution of TCM syndromes in cardiovascular and cerebrovascular diseases according to claim 4, characterized in that, The specific syndrome evolution chain model matching the corresponding disease identifies critical turning points through feature combination verification logic. These critical turning points are the critical nodes in the evolution of syndromes into critical conditions. When judging whether all critical warning features are met, the model also includes: The detection of critical turning points in cardiovascular diseases is based on the following characteristics: when the decrease in heart rate exceeds a preset heart rate threshold, the decrease in blood pressure exceeds a preset blood pressure threshold, and the pulse becomes extremely weak, the condition is identified as a critical turning point in cardiovascular diseases. If only one or two of the three characteristics meet the criteria, an early warning sign is marked and the data collection frequency is increased; If none of the three characteristics meet the criteria, then routine symptom monitoring will continue and no turning point will be triggered.

6. The method for real-time monitoring of the dynamic evolution of TCM syndromes in cardiovascular and cerebrovascular diseases according to claim 5, characterized in that, The specific syndrome evolution chain model matching the corresponding disease identifies critical turning points through feature combination verification logic. These critical turning points are the critical nodes in the evolution of syndromes into critical conditions. When judging whether all critical warning features are met, the model also includes: The system continuously monitors the characteristics of critical turning points in brain diseases for 72 hours. When the fluctuation of blood pressure exceeds the preset blood pressure threshold, the facial thermogram asymmetry exceeds the preset thermogram threshold, and the gait rhythm disorder meets the criteria at the same time, it is judged as a critical turning point in brain diseases. If any of the three features is abnormal, a trend warning is issued and the sampling frequency is increased. If none of the three features are abnormal, then regular monitoring will continue and no inflection point will be triggered.

7. The method for real-time monitoring of the dynamic evolution of TCM syndromes in cardiovascular and cerebrovascular diseases according to claim 6, characterized in that, When adjusting the proportion of dialectical elements through weighted adaptive logic based on the determination result of whether a turning point has been triggered, and generating dynamic results of syndromes and critical warning information according to hierarchical output logic, the following are included: The test determines whether the critical turning point meets the corresponding judgment rules. When a critical turning point is determined, the diagnostic weight of the core characteristics of the corresponding disease is increased. When a turning point is not identified but there are early warning signs, the weight of the core features is increased to strengthen monitoring. When there is no warning and the turning point has not been determined, the basic dialectical weights are maintained and the dialectical process is carried out normally.

8. The method for real-time monitoring of the dynamic evolution of TCM syndromes in cardiovascular and cerebrovascular diseases according to claim 7, characterized in that, The specific syndrome evolution chain model matching the corresponding disease identifies critical turning points through feature combination verification logic. These critical turning points are the critical nodes in the evolution of syndromes into critical conditions. When determining whether all critical warning features are met, the model also includes: Parallel detection of critical turning points in the cardiac and cerebral systems of comorbid cardiovascular disease; when a critical turning point in the cardiac system is identified, it is determined to be a critical turning point in comorbid cardiovascular disease. When a critical turning point in the cerebral system is identified, it is determined to be a critical turning point in cardiac-cerebral comorbidity. If no turning point is identified for either of the two diseases, then routine comorbidity diagnosis and continuous monitoring should be performed.

9. The method for real-time monitoring of the dynamic evolution of TCM syndromes in cardiovascular and cerebrovascular diseases according to claim 8, characterized in that, The specific syndrome evolution chain model matching the corresponding disease identifies critical turning points through feature combination verification logic. These critical turning points are the critical nodes in the evolution of syndromes into critical conditions. When determining whether all critical warning features are met, the model also includes: Detect the probability of the current syndrome attribution. When the probability of attribution is higher than a preset probability threshold, the current syndrome is directly locked. When the probability of attribution is between a low preset probability threshold and a high preset probability threshold, it is marked as a syndrome transition period and the collection frequency is increased. When the probability of attribution is lower than the low preset probability threshold, the feature is deemed insufficient and monitoring data is re-collected.

10. The method for real-time monitoring of the dynamic evolution of TCM syndromes in cardiovascular and cerebrovascular diseases according to claim 9, characterized in that, When adjusting the proportion of dialectical elements through weighted adaptive logic based on the determination result of whether a turning point has been triggered, and generating dynamic results of syndromes and critical warning information according to hierarchical output logic, the method further includes: The system detects whether a critical turning point has been identified. If a critical turning point is identified, a Level 1 critical warning is issued. If the characteristics do not return to normal within the preset monitoring time after the warning, the warning level will be upgraded and intervention prompts will be strengthened. If the characteristics are determined to return to normal within the preset monitoring time after the warning, the warning will be lifted and regular monitoring will resume.

Images