Multi-index real-time monitoring cardiopulmonary exercise test method and system

Abstract

The invention discloses a multi-index real-time monitoring exercise cardiopulmonary test method and system, and relates to the technical field of cardiopulmonary function tests.The method comprises the steps that physiological parameters are synchronously collected through a plurality of high-precision physiological sensors, and time synchronization is conducted; performing wavelet transformation on each physiological parameter, extracting multi-scale features, reconstructing normalized physiological parameters, forming a multi-dimensional physiological state vector, performing ventilation compensation point and anaerobic threshold identification, and calculating a plurality of load indexes; and performing standardization processing on the plurality of load indexes, calculating a comprehensive health score, and generating a personalized health report according to the ventilation compensation point, the anaerobic threshold, the comprehensive health score and the time evolution curve. Accurate multi-dimensional data analysis and feature extraction are achieved through multi-scale wavelet transformation and normalization processing, key physiological mutational points are efficiently recognized in combination with dynamic time warping and a multi-dimensional CUSUM algorithm, a personalized health report is generated, real-time health assessment, trend analysis and training suggestions are provided, exercise performance optimization is helped, and exercise injuries are prevented.

Description

Technical Field

[0001] The present invention relates to the technical field of cardiopulmonary function testing, and in particular to a method and system for exercising cardiopulmonary testing with real-time monitoring of multiple indicators. Background Art

[0002] With the development of modern health management and sports medicine, exercise cardiopulmonary function testing has become an important means to evaluate individual exercise ability, health status and develop personalized training programs. Traditional exercise cardiopulmonary function assessment methods, such as maximum oxygen uptake testing, can provide basic information about cardiopulmonary endurance, but are usually limited to a single physiological indicator, such as heart rate, oxygen uptake, etc., and the testing process generally requires laboratory equipment and high-intensity exercise participation, which is difficult to adapt to the needs of extensive daily exercise monitoring and health assessment.

[0003] Currently, many new exercise testing methods have begun to combine multiple physiological parameters to achieve a comprehensive assessment of the body's state during exercise. These methods can provide more information by simultaneously monitoring multiple physiological indicators, thereby more accurately reflecting the individual's physiological response at different exercise intensities. Especially in high-intensity exercise or extreme testing, the dynamic changes in physiological parameters are particularly complex, involving interactions between multiple systems, such as the cardiovascular system, respiratory system, metabolic system, etc.

[0004] Although the existing multi-index physiological monitoring systems are able to collect data synchronously through multiple sensors, these systems still have some key technical problems, which make them face many challenges in practical applications: Difficulty in multi-dimensional data analysis and fusion: Although some existing cardiopulmonary exercise testing methods can collect multiple physiological parameters synchronously, they are often limited to some simple statistical analysis or regression models in the data analysis process, and cannot perform effective multi-dimensional data fusion. How to extract valuable features from multi-dimensional physiological data and conduct in-depth analysis to identify key physiological events such as ventilation compensation points and anaerobic thresholds is a hot issue in current exercise physiology research. There are few methods in the existing technology that can combine these high-dimensional data to accurately identify the key physiological thresholds during exercise and perform accurate health assessments. Lack of personalized health assessment: Although the existing technology can provide test results of certain physiological parameters, these results are mostly static data, lacking personalized health assessments and training recommendations. Each individual's physical condition, exercise ability and physiological response are different. Therefore, providing personalized health reports, exercise recommendations and training adjustments based on individual physiological characteristics and real-time monitoring data is still a difficulty in exercise cardiopulmonary testing technology. Summary of the invention

[0005] Based on the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide a multi-index real-time monitoring cardiopulmonary exercise testing method and system to solve the above-mentioned technical problems.

[0006] To achieve the above object, the present invention provides the following technical solution: a multi-index real-time monitoring cardiopulmonary exercise test method, comprising:

[0007] S1: Synchronously collect physiological parameters through multiple high-precision physiological sensors, and synchronize all physiological parameters through a unified timestamp to ensure that the measurement results of all high-precision physiological sensors correspond to the physiological state at the same time point;

[0008] S2: Perform wavelet transform on each physiological parameter, extract multi-scale features and reconstruct normalized physiological parameters, and form a multi-dimensional physiological state vector with the values ​​of all normalized physiological parameters after time synchronization at a uniform time step;

[0009] S3: identifying the ventilation compensation point and the anaerobic threshold according to the multidimensional physiological state vector, and calculating the cardiovascular comprehensive load index, the metabolic comprehensive load index, and the oxygenation and muscle load index according to the multidimensional physiological state vector;

[0010] S4: The cardiovascular comprehensive load index, metabolic comprehensive load index, oxygenation and muscle load index are standardized, a comprehensive health score is calculated, and a personalized health report is generated according to the ventilation compensation point, anaerobic threshold, comprehensive health score and time evolution curve.

[0011] The present invention is further configured such that the plurality of high-precision physiological sensors include a gas metabolism analyzer connected to the face through a mask; an electrochemical lactate sensor attached to the earlobe through a patch; a near-infrared spectrum sensor attached to the surface of the leg muscles through a patch; a heart rate sensor attached to the chest through a patch; a blood pressure cuff worn on the arm; a blood oxygen saturation meter worn on the ear; and an electrocardiogram patch attached to the chest; the physiological parameters include ventilation, carbon dioxide emissions, oxygen uptake, lactate concentration, muscle oxygen, gas exchange rate, heart rate, blood pressure, blood oxygen saturation and electrocardiogram.

[0012] The present invention is further configured that, in step S1, when there are missing values ​​in the data stream of the high-precision physiological sensor, a high-order time interpolation method is used to supplement them;

[0013] After time synchronization and missing data supplementation, the data of all high-precision physiological sensors are resampled to a uniform time step, and the data are interpolated using a high-order interpolation method to ensure the smoothness and accuracy of the signal. The specific logic of the high-order interpolation method for data interpolation is as follows: Among them, S(nΔT) is the physiological parameter after interpolation processing, ΔT is the time step, n is the number of time steps, m is the order of the interpolation polynomial, c k is the interpolation coefficient, Tk The start time of the current time period on which the interpolation is based.

[0014] The present invention is further configured that step S2 comprises:

[0015] Each physiological parameter is subjected to wavelet transformation, and the physiological parameters after wavelet transformation are normalized. The specific logic of wavelet transformation is as follows: Among them, S wavelet (nΔT) is the physiological parameter after wavelet transformation, K is the decomposition scale, ψ k is the wavelet basis function, a k is the multi-scaling coefficient;

[0016] The values ​​of all normalized physiological parameters after time synchronization at a uniform time step are combined into a multidimensional physiological state vector.

[0017] The present invention is further configured that, in step S3, the ventilation compensation point and the anaerobic threshold are identified according to the multidimensional physiological state vector, including:

[0018] The ratio of ventilation to carbon dioxide excretion is calculated, and the ventilation compensation mutation point of the ratio of ventilation to carbon dioxide excretion is detected by combining dynamic time warping with cumulative sum control chart, and the current time point of the ventilation compensation mutation point is calibrated as the ventilation compensation point;

[0019] The change rate of the lactate concentration and the gas exchange rate ratio was calculated, and the joint statistic was constructed using the multidimensional CUSUM algorithm. When the joint statistic met the threshold condition, it was determined to be the anaerobic threshold mutation point, and the current time point of the anaerobic threshold mutation point was calibrated as the anaerobic threshold.

[0020] The present invention is further configured such that the calculation logic of the ratio of ventilation volume to carbon dioxide emission is: Among them, R V (n) is the ratio of ventilation volume to carbon dioxide emission, V E (nΔT) is the ventilation volume, is the carbon dioxide emission;

[0021] The logic of ventilation compensation mutation point detection is: Where C(n) is the statistic of the cumulative sum control chart at the current time step, C(n-1) is the statistic of the cumulative sum control chart at the previous time step, and R V (n) is the actual value of the current time step, is the predicted value of the current time step, and k is the sensitivity parameter used to adjust the accumulation and response to changes;

[0022] When C(n) is greater than a preset first threshold, it is determined to be a ventilation compensation mutation point;

[0023] The calculation logic of lactate concentration and gas exchange rate change rate is: in, is the lactate concentration change rate, [La](nΔT) is the lactate concentration at the current time step, and [La](nΔT-ΔT) is the lactate concentration at the previous time step; in, is the rate of change of gas exchange rate, in, is the carbon dioxide emission, is the oxygen uptake, RER(nΔT) is the gas exchange rate of the current time step, and RER(nΔT-ΔT) is the gas exchange rate of the previous time step;

[0024] The logic of anaerobic threshold mutation point detection is: Among them, C joint (n) is the joint statistic of the current time step, C joint (n-1) is the joint statistic of the previous time step, α and β are weight coefficients, and γ is the control parameter;

[0025] When C joint When (n) is greater than a preset second threshold, it is determined to be an anaerobic threshold mutation point.

[0026] The present invention is further configured that, in step S3, the cardiovascular comprehensive load index, the metabolic comprehensive load index, and the oxygenation and muscle load index are calculated according to the multidimensional physiological state vector, including:

[0027] Calculate the comprehensive cardiovascular load index based on heart rate, blood pressure and electrocardiogram;

[0028] The metabolic load index was calculated based on ventilation, carbon dioxide output, gas exchange rate, and lactate concentration;

[0029] Oxygenation and muscle load index were calculated based on muscle oxygen, blood oxygen saturation and lactate concentration.

[0030] The present invention is further configured such that the calculation logic of the cardiovascular comprehensive load index is: Among them, CV(n) is the comprehensive cardiovascular load index at the current time step, HR(nΔT) is the heart rate at the current time step, ECG(nΔT) is the electrocardiogram at the current time step, and BP(nΔT) is the blood pressure at the current time step;

[0031] The calculation logic of the metabolic load index is: Where Met(n) is the metabolic load index of the current time step, V E(nΔT) is the ventilation volume at the current time step, is the carbon dioxide emission at the current time step, RER(nΔT) is the gas exchange rate at the current time step, and [La](nΔT) is the lactate concentration at the current time step;

[0032] The calculation logic of the oxygenation and muscle load index is: Among them, Ox(n) is the oxygenation and muscle load index of the current time step, SmO 2 (nΔT) is the muscle oxygen in the current time step, SpO 2 (nΔT) is the blood oxygen saturation at the current time step.

[0033] The present invention is further configured that step S4 comprises:

[0034] Standardizing the cardiovascular comprehensive load index, metabolic comprehensive load index, and oxygenation and muscle load index;

[0035] The standardized cardiovascular comprehensive load index, metabolic comprehensive load index, oxygenation and muscle load index were weighted and calculated to obtain a comprehensive health score.

[0036] Analyze health status changes based on ventilation compensation point, anaerobic threshold, comprehensive health score and time evolution curve, including trend detection and abnormality detection;

[0037] Generate personalized health reports, including health score time evolution curve, key comprehensive parameter changes, key threshold point calibration, ventilation compensation point and anaerobic threshold time calibration, comprehensive evaluation and future training adjustment suggestions;

[0038] Use automated report generation tools to convert analysis results into visual reports.

[0039] The present invention also provides a multi-index real-time monitoring cardiopulmonary exercise testing system, the system comprising:

[0040] Parameter acquisition module: synchronously collects physiological parameters through multiple high-precision physiological sensors, and synchronizes all physiological parameters through a unified timestamp to ensure that the measurement results of all high-precision physiological sensors correspond to the physiological state at the same time point;

[0041] Vector generation module: Perform wavelet transform on each physiological parameter, extract multi-scale features and reconstruct normalized physiological parameters, and combine the values ​​of all normalized physiological parameters after time synchronization at a uniform time step into a multi-dimensional physiological state vector;

[0042] Index calculation module: identifying ventilation compensation point and anaerobic threshold according to the multidimensional physiological state vector, and calculating cardiovascular comprehensive load index, metabolic comprehensive load index and oxygenation and muscle load index according to the multidimensional physiological state vector;

[0043] Health scoring module: standardizes the cardiovascular comprehensive load index, metabolic comprehensive load index, oxygenation and muscle load index, calculates the comprehensive health score, and generates a personalized health report based on the ventilation compensation point, anaerobic threshold, comprehensive health score and time evolution curve.

[0044] The present invention provides a multi-index real-time monitoring exercise cardiopulmonary test method and system. The method synchronously collects physiological parameters through multiple high-precision physiological sensors, and synchronizes all physiological parameters through a unified timestamp to ensure that the measurement results of all high-precision physiological sensors correspond to the physiological state at the same time point; wavelet transform is performed on each physiological parameter, multi-scale features are extracted and normalized physiological parameters are reconstructed, and the values ​​of all normalized physiological parameters after time synchronization at a unified time step are composed of a multidimensional physiological state vector; ventilation compensation point and anaerobic threshold are identified according to the multidimensional physiological state vector, and a cardiovascular comprehensive load index, a metabolic comprehensive load index, and an oxygenation and muscle load index are calculated according to the multidimensional physiological state vector; the cardiovascular comprehensive load index, the metabolic comprehensive load index, and the oxygenation and muscle load index are standardized, and a comprehensive health score is calculated, and a personalized health report is generated according to the ventilation compensation point, the anaerobic threshold, the comprehensive health score, and the time evolution curve, and the beneficial effects produced include:

[0045] 1. Accurate multi-dimensional data analysis and feature extraction: By using wavelet transform to extract multi-scale features for each physiological parameter and normalizing it, physiological signals can be effectively analyzed at multiple scales. In addition, by forming a multi-dimensional physiological state vector with the values ​​of the time-synchronized normalized physiological parameters at a uniform time step, the present invention can achieve a comprehensive fusion analysis of multi-dimensional physiological data. This innovation enables more accurate capture and analysis of complex physiological reactions during exercise, and provides effective support for the accurate identification of key physiological events such as ventilation compensation points and anaerobic thresholds;

[0046] 2. Intelligent cardiopulmonary health assessment and personalized report generation: Through the analysis of multi-dimensional physiological state vectors, the present invention can calculate key health indicators such as the comprehensive cardiovascular load index, the comprehensive metabolic load index, and the oxygenation and muscle load index. Combined with the calibration of ventilation compensation points and anaerobic thresholds during exercise, the present invention can generate personalized health reports in real time, showing in detail the user's health score, changes in key comprehensive parameters, health status trends and exercise recommendations. This report not only provides the user's current health assessment, but also can make targeted recommendations for future training adjustments based on individual differences and exercise status, helping users optimize training plans, improve exercise performance and prevent sports injuries;

[0047] 3. Efficient mutation point detection and physiological event identification: In the identification of ventilation compensation point and anaerobic threshold, the present invention combines dynamic time warping and multidimensional CUSUM algorithm to accurately detect key physiological mutation points during exercise. These algorithms can efficiently identify the mutation points of the ratio of ventilation volume to carbon dioxide output, as well as the mutation points of lactate concentration and gas exchange rate change rate, providing strong technical support for the accurate calibration of anaerobic threshold and ventilation compensation point.

[0048] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0050] Figure 1 A flowchart of a multi-index real-time monitoring exercise cardiopulmonary test method is shown as an exemplary embodiment of the present invention;

[0051] Figure 2 The present invention is a schematic structural diagram of an exercise cardiopulmonary test system for real-time monitoring of multiple indicators, showing an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0052] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0053] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0054] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0055] Embodiment 1

[0056] A multi-index real-time monitoring cardiopulmonary exercise test method, such as Figure 1 As shown, including:

[0057] S1: Synchronously collect physiological parameters through multiple high-precision physiological sensors, and synchronize all physiological parameters through a unified timestamp to ensure that the measurement results of all high-precision physiological sensors correspond to the physiological state at the same time point;

[0058] S2: Perform wavelet transform on each physiological parameter, extract multi-scale features and reconstruct normalized physiological parameters, and form a multi-dimensional physiological state vector with the values ​​of all normalized physiological parameters after time synchronization at a uniform time step;

[0059] S3: identifying the ventilation compensation point and the anaerobic threshold according to the multidimensional physiological state vector, and calculating the cardiovascular comprehensive load index, the metabolic comprehensive load index, and the oxygenation and muscle load index according to the multidimensional physiological state vector;

[0060] S4: The cardiovascular comprehensive load index, metabolic comprehensive load index, oxygenation and muscle load index are standardized, a comprehensive health score is calculated, and a personalized health report is generated according to the ventilation compensation point, anaerobic threshold, comprehensive health score and time evolution curve.

[0061] The present invention is further configured such that the plurality of high-precision physiological sensors include a gas metabolism analyzer connected to the face through a mask; an electrochemical lactate sensor attached to the earlobe through a patch; a near-infrared spectrum sensor attached to the surface of the leg muscles through a patch; a heart rate sensor attached to the chest through a patch; a blood pressure cuff worn on the arm; a blood oxygen saturation meter worn on the ear; and an electrocardiogram patch attached to the chest; the physiological parameters include ventilation, carbon dioxide emissions, oxygen uptake, lactate concentration, muscle oxygen, gas exchange rate, heart rate, blood pressure, blood oxygen saturation and electrocardiogram. Specifically, ventilation volume refers to the amount of air ventilated by the respiratory tract per unit time, and the size of ventilation volume reflects the efficiency of the respiratory system and the ability to absorb oxygen during exercise; carbon dioxide emission refers to the amount of carbon dioxide emitted by an individual per unit time, and the emission of carbon dioxide reflects the degree of metabolism in the body, especially the balance between aerobic and anaerobic metabolism; oxygen uptake refers to the amount of oxygen ingested by an individual per unit time, and oxygen uptake reflects the individual's metabolic level, especially during exercise, the amount of oxygen intake directly affects athletic performance and cardiopulmonary endurance; it is monitored by a gas metabolism analyzer, which is connected to the face through a mask. The gas metabolism analyzer can accurately measure the amount of air inhaled and exhaled during breathing, as well as the related oxygen and carbon dioxide content; lactate concentration refers to the lactate content in the blood. Lactate concentration is a marker of anaerobic metabolism. Usually, lactate concentration increases during high-intensity exercise, reflecting the individual's anaerobic threshold. It is measured by an electrochemical lactate sensor, which is attached to the earlobe. The sensor detects the concentration of lactate by contacting the blood. The sensor generally uses electrochemical reactions to measure changes in lactate concentration and provide real-time lactate levels. Muscle oxygenation reflects the oxygenation level of muscle tissue. The muscle oxygenation level reflects the oxygen consumption and oxygen supply of the muscles during exercise. Hypoxia may indicate excessive exercise intensity or insufficient oxygen supply. It is measured by a near-infrared spectroscopy sensor. The patch is installed on the surface of the leg muscles. The sensor uses near-infrared spectroscopy technology to analyze the oxygenation status of the muscles through changes in the intensity of reflected light.Near-infrared spectroscopy uses light of different wavelengths to penetrate the skin and muscle layers, measure the ratio of oxygenated hemoglobin to deoxygenated hemoglobin, and thus obtain the degree of muscle oxygenation; the gas exchange rate is the ratio of carbon dioxide emissions to oxygen intake during breathing. The gas exchange rate reflects the type of metabolic process, especially under different exercise intensities. Changes in the gas exchange rate reveal whether aerobic metabolism or anaerobic metabolism is dominant. Real-time data of oxygen intake and carbon dioxide emissions are obtained through a gas metabolism analyzer to calculate the gas exchange rate; heart rate refers to the number of heart beats per unit time. Heart rate is an important indicator reflecting heart function and the body's adaptation to exercise intensity. A higher heart rate usually means a greater exercise intensity. It is obtained through a heart rate sensor, which is usually installed on the chest in patch form. Based on photoelectric volumetric pulse wave technology, it monitors the heart's electrical activity or pulse wave in real time to calculate the heart rate; blood pressure refers to the pressure of blood on blood vessels Blood pressure is the pressure exerted by the wall of the heart. Blood pressure reflects the workload of the heart and the elasticity of blood vessels. Too high or too low blood pressure may affect athletic performance and health. It is measured by a blood pressure cuff. The blood pressure cuff is worn on the arm. The cuff temporarily closes the blood vessels by inflation, and then gradually releases the pressure. An electronic sphygmomanometer is used to detect the vascular reflux sound to calculate blood pressure. Blood oxygen saturation is the ratio of hemoglobin bound to oxygen in the blood to the total hemoglobin. The value of blood oxygen saturation reflects the oxygen transport capacity of the blood. Low blood oxygen saturation means insufficient oxygen supply, which affects athletic performance. It is measured by a blood oxygen saturation meter. The blood oxygen saturation meter is worn on the ear, including being attached to the earlobe and clamped on the auricle. The blood oxygen meter detects the ratio of oxygenated hemoglobin to deoxygenated hemoglobin in the blood by emitting and receiving red light and infrared light, thereby calculating blood oxygen saturation. An electrocardiogram is an image that records the electrical activity of the heart, reflecting the rhythm, frequency and electrical axis information of the heart. By analyzing the electrocardiogram, heart function and cardiovascular health can be evaluated, which can be obtained through an electrocardiogram patch. The electrocardiogram patch contacts the skin through electrodes, monitors the electrical signals generated by the heart and converts them into waveforms. The electrocardiogram signal can be used to calculate heart rate, heart rhythm and other related heart health indicators; the present invention further includes respiratory reserve, exercise load, oxygen pulse, and the above parameters can be measured by existing equipment, which will not be elaborated here.

[0062] The present invention is further configured that, in step S1, when there are missing values ​​in the data stream of the high-precision physiological sensor, a high-order time interpolation method is used to supplement them;

[0063] After time synchronization and missing data supplementation, the data of all high-precision physiological sensors are resampled to a uniform time step, and the data are interpolated using a high-order interpolation method to ensure the smoothness and accuracy of the signal. The specific logic of the high-order interpolation method for data interpolation is as follows: Among them, S(nΔT) is the physiological parameter after interpolation processing, ΔT is the time step, n is the number of time steps, m is the order of the interpolation polynomial, c k is the interpolation coefficient, T k is the start time of the current time period on which the interpolation is based. Specifically, the high-order time interpolation method is used to supplement and correct missing values ​​in the data stream of high-precision physiological sensors. Missing data may be due to various reasons, such as sensor signal loss, equipment failure or other interference, resulting in the inability to obtain physiological data at certain time points. In this case, appropriate interpolation methods must be adopted to fill these gaps and ensure the consistency and accuracy of subsequent analysis. The high-order time interpolation method is based on existing observational data and uses a polynomial interpolation algorithm to predict and fill missing data. It can construct reasonable values ​​between missing data points, rather than simply using linear interpolation or ignoring data missingness. The interpolation result will make the data smoother and closer to the continuous changes of the actual physiological process; after the data of all high-precision physiological sensors are time-synchronized and missing data are supplemented, they are resampled to a uniform time step, and then the data is interpolated using a high-order interpolation method to ensure the smoothness and accuracy of the signal; the high-order interpolation method can accurately fill in the missing data, so that the missing physiological parameters are restored to a reasonable continuity state, reduce the analysis errors caused by data gaps, and improve the accuracy of the analysis results. At the same time, the use of high-order interpolation methods makes the interpolation process not only smooth, but also better adapt to complex physiological data changes.

[0064] The present invention is further configured that step S2 comprises:

[0065] Each physiological parameter is subjected to wavelet transformation, and the physiological parameters after wavelet transformation are normalized. The specific logic of wavelet transformation is as follows: Among them, S wavelet (nΔT) is the physiological parameter after wavelet transformation, K is the decomposition scale, ψ k is the wavelet basis function, a k is a multi-scale coefficient; specifically, each physiological parameter is subjected to wavelet transform, and then the transformed result is normalized. As a signal processing technology, wavelet transform is used to extract the characteristics of signals at different scales, and can simultaneously analyze the time domain and frequency domain characteristics of signals. Wavelet transform is to perform multi-scale analysis on signals by using wavelet basis functions. Specifically, the wavelet basis function ψ k It is obtained by changing the scale and position of the mother wavelet function. The smaller the scale, the higher the frequency corresponding to the basis function, which can analyze the high-frequency components of the signal; the larger the scale, the lower the frequency corresponding to the basis function, which can analyze the low-frequency components of the signal. The wavelet transform decomposes the signal into components of different frequencies, forming a series of multi-scale coefficients a k, these coefficients can reveal the details and trends of the signal. Therefore, wavelet transform can not only analyze the signal in the time domain, but also extract the features at different frequencies in the frequency domain.

[0066] The values ​​of all normalized physiological parameters after time synchronization at a uniform time step form a multi-dimensional physiological state vector. Specifically, the physiological signal is decomposed into multi-scale features through wavelet transform, and after normalization, a multi-dimensional physiological state vector is formed, which can provide more refined and stable data and provide high-quality signal input for health assessment and personalized report generation.

[0067] The present invention is further configured that, in step S3, the ventilation compensation point and the anaerobic threshold are identified according to the multidimensional physiological state vector, including:

[0068] The ratio of ventilation to carbon dioxide emission is calculated, and the ventilation compensation mutation point of the ratio of ventilation to carbon dioxide emission is detected by combining dynamic time warping with cumulative sum control chart, and the current time point of the ventilation compensation mutation point is calibrated as the ventilation compensation point; the present invention is further configured that the calculation logic of the ratio of ventilation to carbon dioxide emission is: Among them, R V (n) is the ratio of ventilation volume to carbon dioxide emission, V E (nΔT) is the ventilation volume, is the amount of carbon dioxide emitted; specifically, the ratio of ventilation to carbon dioxide emission is an important physiological indicator used to evaluate the working state of the respiratory system during exercise. This ratio reflects the relationship between ventilation and carbon dioxide emission, and is used to evaluate the efficiency of breathing and metabolism; through this ratio, we can monitor how the respiratory and metabolic systems work during exercise, and then identify changes in physiological state. It not only reflects the relationship between ventilation (i.e. the activity level of the respiratory system) and carbon dioxide emission (the emission of metabolic products), but also can deeply reveal the metabolic efficiency and respiratory adaptability of individuals under different exercise intensities;

[0069] The logic of ventilation compensation mutation point detection is: Where C(n) is the statistic of the cumulative sum control chart at the current time step, C(n-1) is the statistic of the cumulative sum control chart at the previous time step, and R V (n) is the actual value of the current time step, is the predicted value of the current time step, k is the sensitivity parameter, which is used to adjust the response of the cumulative sum to the change; when C(n) is greater than the preset first threshold, it is determined to be a ventilation compensation mutation point; specifically, in order to determine the ventilation compensation point during exercise, we use the cumulative sum control chart (CUSUM) method to detect the mutation point of the ratio of ventilation to carbon dioxide output. Specifically, the mutation point refers to the moment when the physiological state suddenly changes, which is usually reflected in the turning point of metabolism. The cumulative sum control chart is a statistical method based on the trend of data changes, which is used to monitor whether there is a mutation in the data. The CUSUM method accumulates the deviation of the observed value (that is, the difference from the predicted value). If this accumulated deviation exceeds a certain threshold, it is marked as a mutation point; the sensitivity parameter k is used to adjust the response of the cumulative sum to the mutation, and the value range is [0.01, 0.1]; combining the method of dynamic time warping and cumulative sum control chart, when detecting the ventilation compensation mutation point of the ratio of ventilation to carbon dioxide output, the ventilation compensation point can be accurately calibrated, further improving the accuracy of physiological state assessment during exercise;

[0070] The lactate concentration and the rate of change of the gas exchange rate are calculated, and a joint statistic is constructed using a multidimensional CUSUM algorithm. When the joint statistic meets the threshold condition, it is determined to be an anaerobic threshold mutation point, and the current time point of the anaerobic threshold mutation point is calibrated as the anaerobic threshold. The present invention is further configured that the calculation logic of the lactate concentration and the rate of change of the gas exchange rate is: in, is the lactate concentration change rate, [La](nΔT) is the lactate concentration at the current time step, and [La](nΔT-ΔT) is the lactate concentration at the previous time step; in, is the rate of change of gas exchange rate, in, is the carbon dioxide emission, is the oxygen uptake, RER(nΔT) is the gas exchange rate of the current time step, and RER(nΔT-ΔT) is the gas exchange rate of the previous time step; specifically, by calculating the lactate concentration and the rate of change of the gas exchange rate, and combining the multidimensional CUSUM algorithm to construct a joint statistic to realize the detection of the anaerobic threshold mutation point, and further calibrate the anaerobic threshold. The anaerobic threshold refers to the critical point where metabolism changes from aerobic to anaerobic, which is usually related to the beginning of lactate accumulation. In this process, the rate of change of lactate concentration and gas exchange rate are important physiological indicators, reflecting the change in metabolic mode when the intensity of exercise gradually increases;

[0071] The logic of anaerobic threshold mutation point detection is: Among them, C joint (n) is the joint statistic of the current time step, C joint(n-1) is the joint statistic of the previous time step, α and β are weight coefficients, and γ is the control parameter; when C joint When (n) is greater than a preset second threshold value, it is determined to be an anaerobic threshold mutation point; specifically, in order to combine the lactate concentration change rate and the gas exchange rate change rate to determine whether an anaerobic threshold mutation point (i.e., anaerobic threshold) occurs, the present invention adopts a joint statistic and detects this change through a multidimensional CUSUM algorithm, wherein the weight coefficients α and β are both positive numbers, and the sum is 1, and the control parameter γ is used to adjust the response sensitivity, and the value range is [0.01, 0.1]. A joint statistic is constructed through a multidimensional CUSUM algorithm, and the anaerobic threshold mutation point is accurately calibrated by combining the lactate concentration and the gas exchange rate change rate, thereby identifying the anaerobic threshold during exercise, which can provide high-precision physiological evaluation and provide a scientific basis for personalized health management and sports training.

[0072] The present invention is further configured that, in step S3, the cardiovascular comprehensive load index, the metabolic comprehensive load index, and the oxygenation and muscle load index are calculated according to the multidimensional physiological state vector, including:

[0073] The cardiovascular comprehensive load index is calculated according to the heart rate, blood pressure and electrocardiogram; the present invention is further configured that the calculation logic of the cardiovascular comprehensive load index is: Among them, CV(n) is the cardiovascular comprehensive load index of the current time step, HR(nΔT) is the heart rate of the current time step, ECG(nΔT) is the electrocardiogram of the current time step, and BP(nΔT) is the blood pressure of the current time step; Specifically, by combining the three physiological parameters of heart rate, blood pressure and electrocardiogram, the cardiovascular comprehensive load index is calculated, which is used to quantify the comprehensive load of the cardiovascular system of an individual during exercise. Through this indicator, the health status of the cardiovascular system during exercise can be better evaluated, and then provide a basis for personalized exercise training and health management. In this calculation logic, the value of the electrocardiogram at the current time step is the R wave amplitude of the electrocardiogram. The R wave is the highest point of the QRS complex wave in the electrocardiogram, indicating the excitement and contraction of the heart. The amplitude of the R wave is related to the intensity of the electrical activity of the heart. The R wave amplitude of the electrocardiogram can be used to estimate the electrical activity state of the heart. Especially during exercise, the amplitude change of the R wave can reflect the health status and work intensity of the heart; by multiplying the heart rate with the electrocardiogram ratio and then with the blood pressure, the load level of the cardiovascular system can be comprehensively evaluated. During high-intensity exercise, the cardiovascular load index will increase, reflecting the intensity of the heart's work. This index can be used to monitor whether the cardiovascular system is in an overloaded state and help determine the appropriate intensity of exercise;

[0074] The metabolic load index is calculated based on ventilation, carbon dioxide output, gas exchange rate and lactate concentration; the calculation logic of the metabolic load index is: Among them, Met(n) is the comprehensive metabolic load index of the current time step, V E (nΔT) is the ventilation volume at the current time step, is the carbon dioxide emission at the current time step, RER(nΔT) is the gas exchange rate at the current time step, and [La](nΔT) is the lactate concentration at the current time step; specifically, the metabolic load index is calculated by combining ventilation, carbon dioxide emission, gas exchange rate and lactate concentration, which is used to evaluate the overall metabolic load of an individual during exercise. The metabolic load index can reflect the metabolic capacity of the body under a specific exercise intensity, especially the changes in physiological state when the exercise intensity gradually increases; ventilation reflects the working intensity of the respiratory system, and carbon dioxide emission is closely related to the body's metabolic products. The product of the two represents the respiratory burden that the body needs to deal with during exercise, and the gas exchange rate is a key parameter for evaluating the ratio of aerobic and anaerobic metabolism. During exercise, the gas exchange rate changes with the increase in exercise intensity. When the gas exchange rate is high, it means that anaerobic metabolism is dominant; while a low gas exchange rate means that aerobic metabolism is dominant. Lactate concentration is an important physiological indicator reflecting the degree of anaerobic metabolism, which usually rises sharply near the anaerobic threshold. The combination of lactate concentration and gas exchange rate can help us more accurately assess the body's metabolic state during exercise, especially during high-intensity exercise. By combining ventilation, carbon dioxide output, gas exchange rate and lactate concentration, the metabolic load index can more comprehensively reflect the individual's metabolic state, especially during high-intensity exercise, and can accurately assess the body's metabolic burden.

[0075] The oxygenation and muscle load index is calculated based on muscle oxygen, blood oxygen saturation and lactate concentration. The calculation logic of the oxygenation and muscle load index is: Among them, Ox(n) is the oxygenation and muscle load index of the current time step, SmO 2 (nΔT) is the muscle oxygen in the current time step, SpO 2 (nΔT) is the blood oxygen saturation at the current time step; specifically, the oxygenation and muscle load index comprehensively evaluates the oxygenation status and muscle load of an individual during exercise by combining muscle oxygen, blood oxygen saturation and lactate concentration. The oxygenation and muscle load index can reflect the balance between the demand and supply of oxygen for muscles during exercise, and help evaluate exercise intensity, muscle fatigue and exercise capacity; It reflects the efficiency of muscle oxygenation relative to the systemic oxygenation capacity. If muscle oxygenation is high and blood oxygen saturation is low, it means that although the muscle has more oxygen, the systemic oxygenation capacity may be insufficient, resulting in a relatively insufficient supply of oxygen to the muscle. The product of lactate concentration can adjust the balance between oxygenation status and muscle load. When the lactate concentration is high, it means that the muscle is in a higher load state, which may lead to a decrease in oxygenation efficiency. The oxygenation and muscle load index comprehensively considers the oxygenation efficiency of the muscle, the oxygen transport capacity of the whole body and the lactate concentration, and can quantify the oxygenation and load status of the muscle during exercise. This index will increase when the exercise intensity is high, reflecting the contradiction between muscle oxygen supply and oxygen consumption.

[0076] The present invention is further configured that step S4 comprises:

[0077] The cardiovascular comprehensive load index, metabolic comprehensive load index, and oxygenation and muscle load index are standardized; specifically, the standardization process is to convert physiological data of different dimensions and different value ranges into data of the same dimension and similar range, so that they can be effectively compared and weighted. After standardization, each index is on the same scale, which can eliminate the unit differences between different indexes and improve the comparability of data and the fairness of calculation;

[0078] The standardized cardiovascular comprehensive load index, metabolic comprehensive load index, and oxygenation and muscle load index are weighted and calculated to obtain a comprehensive health score; specifically, the purpose of the weighted calculation is to assign appropriate weights to each indicator based on the relative importance of different indicators. The choice of weights can be adjusted based on experimental data, clinical research, or user needs;

[0079] According to the ventilation compensation point, anaerobic threshold, comprehensive health score and time evolution curve, the changes in health status are analyzed, including trend detection and abnormality detection; by analyzing the trend of the comprehensive health score over time, the gradual improvement or deterioration of health status can be detected. A continuous increase in the health score may indicate an improvement in exercise capacity and health status; while a decrease in the health score may indicate overtraining or health problems.

[0080] Generate personalized health reports, including the time evolution curve of health score, changes in key comprehensive parameters, calibration of key threshold points, time calibration of ventilation compensation points and anaerobic thresholds, comprehensive evaluation and future training adjustment suggestions; when the health score changes exceed the preset normal range, the system can automatically mark it as abnormal, reminding the user of possible health risks. Abnormal conditions may include excessive cardiovascular load caused by excessive exercise, or abnormal anaerobic threshold and metabolic load index; ventilation compensation points and anaerobic thresholds are key indicators for judging the turning point of cardiopulmonary function during exercise. By calibrating these threshold points, you can clearly understand the physiological transformation moments during exercise;

[0081] The automated report generation tool is used to convert the analysis results into a visual report. Specifically, the report generated by the automated tool will visualize the health score, the trend of changes in various physiological parameters, the calibration of key threshold points, and personalized training suggestions. The visual report can help users understand their health status and athletic ability more intuitively and make more scientific training decisions.

[0082] Embodiment 2

[0083] See also Figure 2 The exemplary multi-index real-time monitoring cardiopulmonary exercise testing system includes:

[0084] Parameter acquisition module: synchronously collects physiological parameters through multiple high-precision physiological sensors, and synchronizes all physiological parameters through a unified timestamp to ensure that the measurement results of all high-precision physiological sensors correspond to the physiological state at the same time point;

[0085] Vector generation module: Perform wavelet transform on each physiological parameter, extract multi-scale features and reconstruct normalized physiological parameters, and combine the values ​​of all normalized physiological parameters after time synchronization at a uniform time step into a multi-dimensional physiological state vector;

[0086] Index calculation module: identifying ventilation compensation point and anaerobic threshold according to the multidimensional physiological state vector, and calculating cardiovascular comprehensive load index, metabolic comprehensive load index and oxygenation and muscle load index according to the multidimensional physiological state vector;

[0087] Health score module: standardize the cardiovascular comprehensive load index, metabolic comprehensive load index, oxygenation and muscle load index, calculate the comprehensive health score, and generate a personalized health report based on the ventilation compensation point, anaerobic threshold, comprehensive health score and time evolution curve. Specifically, in a feasible embodiment of the present invention, the above modules can be integrated into a wearable vest, at which time, the heart rate and electrocardiogram can be measured without the need for patch measurement.

[0088] It should be noted that the multi-index real-time monitoring cardiopulmonary test system provided in the above embodiment and the multi-index real-time monitoring cardiopulmonary test method provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs the operation has been described in detail in the method embodiment and will not be repeated here. In actual application, the multi-index real-time monitoring cardiopulmonary test system provided in the above embodiment can distribute the above functions to different functional modules as needed, that is, divide the internal structure of the system into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0089] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0090] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0091] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0092] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0093] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0094] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0095] In the several embodiments provided in the present application, it should be understood that the disclosed system can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0096] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0097] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0098] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0099] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A multi-index real-time monitoring cardiopulmonary exercise testing method, characterized in that: include: S1: Synchronously collect physiological parameters through multiple high-precision physiological sensors, and synchronize all physiological parameters through a unified timestamp to ensure that the measurement results of all high-precision physiological sensors correspond to the physiological state at the same time point; S2: Perform wavelet transform on each physiological parameter, extract multi-scale features and reconstruct normalized physiological parameters, and form a multi-dimensional physiological state vector with the values ​​of all normalized physiological parameters after time synchronization at a uniform time step; S3: identifying the ventilation compensation point and the anaerobic threshold according to the multidimensional physiological state vector, and calculating the cardiovascular comprehensive load index, the metabolic comprehensive load index, and the oxygenation and muscle load index according to the multidimensional physiological state vector; S4: The cardiovascular comprehensive load index, metabolic comprehensive load index, oxygenation and muscle load index are standardized, a comprehensive health score is calculated, and a personalized health report is generated according to the ventilation compensation point, anaerobic threshold, comprehensive health score and time evolution curve.

2. The multi-index real-time monitoring exercise cardiopulmonary test method according to claim 1, characterized in that: The multiple high-precision physiological sensors include a gas metabolism analyzer connected to the face through a mask; an electrochemical lactate sensor, attached to the earlobe through a patch; a near-infrared spectrum sensor, attached to the surface of the leg muscles through a patch; a heart rate sensor, attached to the chest through a patch; a blood pressure cuff, worn on the arm; a blood oxygen saturation meter, worn on the ear; an electrocardiogram patch, attached to the chest; the physiological parameters include ventilation, carbon dioxide emissions, oxygen uptake, lactate concentration, muscle oxygen, gas exchange rate, heart rate, blood pressure, blood oxygen saturation and electrocardiogram.

3. The multi-index real-time monitoring exercise cardiopulmonary test method according to claim 2, characterized in that: In step S1, when there are missing values ​​in the data stream of the high-precision physiological sensor, a high-order time interpolation method is used to supplement them; After time synchronization and missing data supplementation, the data of all high-precision physiological sensors are resampled to a uniform time step, and the data are interpolated using a high-order interpolation method to ensure the smoothness and accuracy of the signal. The specific logic of the high-order interpolation method for data interpolation is as follows: Among them, S(nΔT) is the physiological parameter after interpolation processing, ΔT is the time step, n is the number of time steps, m is the order of the interpolation polynomial, c k is the interpolation coefficient, T k The start time of the current time period on which the interpolation is based.

4. The multi-index real-time monitoring cardiopulmonary exercise testing method according to claim 1, characterized in that: Step S2 includes: Each physiological parameter is subjected to wavelet transformation, and the physiological parameters after wavelet transformation are normalized. The specific logic of wavelet transformation is as follows: Among them, S wavelet (nΔT) is the physiological parameter after wavelet transformation, K is the decomposition scale, ψ k is the wavelet basis function, a k is the multi-scaling coefficient; The values ​​of all normalized physiological parameters after time synchronization at a uniform time step are combined into a multidimensional physiological state vector.

5. The multi-index real-time monitoring exercise cardiopulmonary test method according to claim 2, characterized in that: In step S3, the ventilation compensation point and the anaerobic threshold are identified according to the multi-dimensional physiological state vector, including: The ratio of ventilation to carbon dioxide excretion is calculated, and the ventilation compensation mutation point of the ratio of ventilation to carbon dioxide excretion is detected by combining dynamic time warping with cumulative sum control chart, and the current time point of the ventilation compensation mutation point is calibrated as the ventilation compensation point; The change rate of lactate concentration and gas exchange rate was calculated, and a joint statistic was constructed using the multidimensional CUSUM algorithm. When the joint statistic met the threshold condition, it was determined to be an anaerobic threshold mutation point, and the current time point of the anaerobic threshold mutation point was calibrated as the anaerobic threshold.

6. The multi-index real-time monitoring cardiopulmonary exercise testing method according to claim 5, characterized in that: The calculation logic of the ratio of ventilation volume to carbon dioxide excretion is: Among them, R V (n) is the ratio of ventilation volume to carbon dioxide emission, V E (nΔT) is the ventilation volume, is the carbon dioxide emission; The logic of ventilation compensation mutation point detection is: Where C(n) is the statistic of the cumulative sum control chart at the current time step, C(n-1) is the statistic of the cumulative sum control chart at the previous time step, and R V (n) is the actual value of the current time step, is the predicted value of the current time step, and k is the sensitivity parameter used to adjust the accumulation and response to changes; When C(n) is greater than a preset first threshold, it is determined to be a ventilation compensation mutation point; The calculation logic of lactate concentration and gas exchange rate change rate is: in, is the lactate concentration change rate, [La](nΔT) is the lactate concentration at the current time step, and [La](nΔT-ΔT) is the lactate concentration at the previous time step; in, is the rate of change of gas exchange rate, in, is the carbon dioxide emission, is the oxygen uptake, RER(nΔT) is the gas exchange rate of the current time step, and RER(nΔT-ΔT) is the gas exchange rate of the previous time step; The logic of anaerobic threshold mutation point detection is: Among them, C joint (n) is the joint statistic of the current time step, C joint (n-1) is the joint statistic of the previous time step, α and β are weight coefficients, and γ is the control parameter; When C joint When (n) is greater than a preset second threshold, it is determined to be an anaerobic threshold mutation point.

7. The multi-index real-time monitoring exercise cardiopulmonary test method according to claim 2, characterized in that: In step S3, the cardiovascular comprehensive load index, the metabolic comprehensive load index, and the oxygenation and muscle load index are calculated according to the multidimensional physiological state vector, including: Calculate the comprehensive cardiovascular load index based on heart rate, blood pressure and electrocardiogram; The metabolic load index was calculated based on ventilation, carbon dioxide output, gas exchange rate, and lactate concentration; Oxygenation and muscle load index were calculated based on muscle oxygen, blood oxygen saturation and lactate concentration.

8. The multi-index real-time monitoring cardiopulmonary exercise test method according to claim 7, characterized in that: The calculation logic of the cardiovascular comprehensive load index is: Among them, CV(n) is the cardiovascular comprehensive load index at the current time step, HR(nΔT) is the heart rate at the current time step, ECG(nΔT) is the electrocardiogram at the current time step, and BP(nΔT) is the blood pressure at the current time step; The calculation logic of the metabolic comprehensive load index is: Among them, Met(n) is the comprehensive metabolic load index of the current time step, V E (nΔT) is the ventilation volume at the current time step, is the carbon dioxide emission at the current time step, RER(nΔT) is the gas exchange rate at the current time step, and [La](nΔT) is the lactate concentration at the current time step; The calculation logic of the oxygenation and muscle load index is: Among them, Ox(n) is the oxygenation and muscle load index of the current time step, SmO2(nΔT) is the muscle oxygen of the current time step, and SpO2(nΔT) is the blood oxygen saturation of the current time step.

9. The multi-index real-time monitoring exercise cardiopulmonary test method according to claim 2, characterized in that: Step S4 includes: Standardizing the cardiovascular comprehensive load index, metabolic comprehensive load index, and oxygenation and muscle load index; The standardized cardiovascular comprehensive load index, metabolic comprehensive load index, oxygenation and muscle load index were weighted and calculated to obtain a comprehensive health score. Analyze health status changes based on ventilation compensation point, anaerobic threshold, comprehensive health score and time evolution curve, including trend detection and abnormality detection; Generate personalized health reports, including health score time evolution curve, key comprehensive parameter changes, key threshold point calibration, ventilation compensation point and anaerobic threshold time calibration, comprehensive evaluation and future training adjustment suggestions; Use automated report generation tools to convert analysis results into visual reports.

10. A multi-index real-time monitoring cardiopulmonary exercise test system, used to implement a multi-index real-time monitoring cardiopulmonary exercise test method according to any one of claims 1 to 9, characterized in that: include: Parameter acquisition module: synchronously collects physiological parameters through multiple high-precision physiological sensors, and synchronizes all physiological parameters through a unified timestamp to ensure that the measurement results of all high-precision physiological sensors correspond to the physiological state at the same time point; Vector generation module: Perform wavelet transform on each physiological parameter, extract multi-scale features and reconstruct normalized physiological parameters, and combine the values ​​of all normalized physiological parameters after time synchronization at a uniform time step into a multi-dimensional physiological state vector; Index calculation module: identifying ventilation compensation point and anaerobic threshold according to the multidimensional physiological state vector, and calculating cardiovascular comprehensive load index, metabolic comprehensive load index and oxygenation and muscle load index according to the multidimensional physiological state vector; Health scoring module: standardizes the cardiovascular comprehensive load index, metabolic comprehensive load index, oxygenation and muscle load index, calculates the comprehensive health score, and generates a personalized health report based on the ventilation compensation point, anaerobic threshold, comprehensive health score and time evolution curve.

Images