Big data analysis method and system for noninvasive cardiac excretion monitoring

Abstract

The invention discloses a big data analysis method and system for noninvasive cardiac discharge monitoring, and the method comprises the steps: collecting radial artery multichannel signals through a sensor array signal processing platform, processing and screening effective signals, extracting features through a pulse wave conduction time analysis algorithm, and constructing a time series data set; decomposing characteristic wave components by using a radial artery tension waveform analysis model to obtain parameters, and adjusting a compensation coefficient by combining a vascular elasticity dynamic compensation model to obtain vascular elasticity related parameters; the integrated data is input into a big data analysis module, association mapping is established through multi-feature fusion processing, iterative optimization is carried out, a monitoring result is output, and each key step comprises refining and sub-steps to guarantee the processing precision. The system is provided with six units corresponding to the method. The method and the system solve the problems of loose connection of signal processing and analysis, dependence on a single parameter and lack of dynamic compensation in the prior art, improve the monitoring precision, realize non-invasive operation, are safe and convenient, and meet clinical requirements.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of cardiac output monitoring analysis, and particularly relates to a data big data analysis method and system for non-invasive cardiac output monitoring. BACKGROUND

[0002] In the medical monitoring process, as a key means for evaluating heart function and guiding clinical treatment, the safety and convenience of the monitoring method of cardiac output monitoring are concerned. Traditional invasive cardiac output monitoring needs to obtain physiological data through invasive operation, which may cause complications such as infection and bleeding, and is not suitable for long-term continuous monitoring and fragile population. With the development of sensing technology and big data analysis technology, non-invasive cardiac output monitoring has become a research hotspot. Through the collection of peripheral vascular physiological signals by sensors and the analysis of algorithms, non-invasive cardiac output monitoring has become an important direction. At present, radial artery signals are often used as the signal source for non-invasive cardiac output monitoring because of their easy collection and close relationship with heart function. At the same time, the analysis of parameters such as pulse wave transmission time and vascular elasticity, as well as the application of sensor array signal processing platform, provide technical support for improving the accuracy of non-invasive cardiac output monitoring, and promote the development of non-invasive cardiac output monitoring to be more efficient and safer, so as to meet the needs of real-time and accurate cardiac function evaluation in clinical practice.

[0003] The existing non-invasive cardiac output monitoring technology still has obvious deficiencies in actual application. On the one hand, the analysis of the existing technology on the radial artery signal is mostly limited to a single parameter or a simple model, and cannot fully integrate multi-dimensional parameters such as pulse wave transmission time and dynamic changes of vascular elasticity. Moreover, it lacks a dynamic compensation mechanism for different individual physiological information, which leads to deviations in the monitoring results when the individual physiological state changes, and makes it difficult to adapt to the monitoring needs of different populations. On the other hand, the signal processing and big data analysis of the existing technology are not closely connected. The multi-channel signals collected by the sensor array are not effectively processed in the filtering and feature extraction process in combination with the specific needs of non-invasive cardiac output monitoring. At the same time, the big data analysis module lacks the ability to integrate multi-source data, and cannot fully explore the correlation between data, so that the mapping relationship between the data and the cardiac output monitoring indicators is poor in stability, and it is difficult to continuously output high-precision monitoring results. SUMMARY

[0004] In order to overcome the shortcomings and deficiencies of the existing technology, the present application provides a data big data analysis method and system for non-invasive cardiac output monitoring.

[0005] The technical solution adopted in this invention is a big data analysis method for non-invasive cardiac output monitoring, comprising the following steps: S1, acquiring multi-channel physiological signals of the radial artery region through a sensor array signal processing platform, which performs multi-dimensional filtering and signal enhancement processing on the acquired signals to screen out effective signals that meet the requirements of non-invasive cardiac output monitoring data; S2, extracting features from the effective signals acquired in S1 based on a pulse wave conduction time analysis algorithm to determine the conduction time difference of the pulse wave between different monitoring points and constructing a pulse wave conduction time series dataset; S3, using a radial artery tension waveform analytical model to perform waveform decomposition on the pulse wave conduction time series dataset obtained in S2, separating the systolic wave, diastolic wave, and dicrotic wave features in the radial artery tension waveform. S3 involves obtaining morphological and temporal parameters of different characteristic wave components; S4 uses a vascular elasticity dynamic compensation model to dynamically compensate the parameters of different characteristic wave components extracted in S3, and adjusts the compensation coefficients based on the basic physiological information of the monitored subjects to obtain the compensated vascular elasticity correlation parameters; S5 integrates the compensated vascular elasticity correlation parameters from S4 with the pulse wave conduction time series data from S2, and inputs them into the big data analysis module for non-invasive cardiac output monitoring. This module uses a multi-feature fusion algorithm to perform hierarchical processing on the integrated data and establish a correlation mapping between the data and non-invasive cardiac output monitoring indicators; S6 iteratively optimizes the correlation mapping established in S5 through the big data analysis module, and outputs the final monitoring result data that meets the accuracy requirements of non-invasive cardiac output monitoring.

[0006] Furthermore, the expression used in the pulse wave propagation time analysis algorithm is as follows: ,in, The pulse wave conduction time. The time when the pulse wave feature point is collected at the i-th monitoring point. For the first The time when pulse wave characteristic points were collected at each monitoring point The total number of monitoring points. Let be the signal strength weighting coefficient for the i-th monitoring point. Let be the position correction coefficient for the i-th monitoring point. Let be the signal stability coefficient of the i-th monitoring point. Let be the environmental interference compensation coefficient for the i-th monitoring point.

[0007] Furthermore, the expression used in the analytical model of the radial artery tension waveform is: ,in, The tension value of the radial artery at position r and time t. The amplitude coefficient of the contraction wave. The position attenuation coefficient, Radial position coordinates, a central position coordinate of the radial artery, a pulse wave angular frequency, a time, a systolic wave phase offset, a diastolic wave amplitude coefficient, a time decay coefficient, a diastolic wave start time, a radial phase coefficient, a diastolic wave phase offset.

[0008] Further, the expression adopted by the blood vessel elasticity dynamic compensation model is: wherein, E is the compensated blood vessel elasticity modulus, E0 is the original value of the blood vessel elasticity modulus before compensation, N is the sampling number of the dynamic compensation calculation, Cj is the compensation coefficient of the jth sampling, Pj is the blood pressure value of the jth sampling, P is the average blood pressure value in a set time period, Hj is the heart rate value of the jth sampling, H is the average heart rate value in a set time period, Tj is the time decay factor of the jth sampling.

[0009] Further, the signal processing expression of the sensor array signal processing platform is: wherein, S is the effective signal output by the platform, M is the number of channels of the sensor array, Xp is the original input signal of the pth channel, Gp is the signal gain coefficient of the pth channel, Kp,k is the interference intensity coefficient of the kth type of interference signal of the pth channel, Rp,k is the suppression coefficient of the kth type of interference of the pth channel.

[0010] Further, the multi-feature fusion algorithm expression of the data big data analysis module of the noninvasive cardiac output monitoring is: wherein, Y is the noninvasive cardiac output monitoring result, C is the number of feature categories, N is the number of parameters of each type of feature, Xy is the numerical value of the yth parameter in the xth feature category, Wxy is the weight coefficient of the yth parameter of the xth feature category, Nxy is the normalization coefficient of the yth parameter of the xth feature category, Exy is the error correction coefficient of the yth parameter of the xth feature category, Let y be the stability coefficient of the y-th parameter of the x-th feature.

[0011] Further, step S3 includes the following sub-steps: S31, performing signal segmentation processing on the pulse wave conduction time series dataset obtained in S2, dividing the entire time series into multiple independent pulse wave period segments according to the periodic characteristics of the pulse wave, with each period segment containing a complete pulse wave signal; S32, for each divided pulse wave period segment, using a wavelet transform algorithm to decompose the signal into multiple scales, obtaining wavelet coefficients at different scales, and filtering out signal components containing radial artery tension waveform calibration features through wavelet coefficients; S33, reconstructing the filtered signal components to remove noise interference introduced during the decomposition process, obtaining a relatively smooth original contour of the radial artery tension waveform; S34, setting a characteristic wave recognition threshold based on the physiological characteristics of the radial artery tension waveform, separating the systolic wave, diastolic wave, and dicrotic wave through threshold comparison and waveform slope analysis, while recording the start time, peak time, and trough time time parameters of different characteristic waves, and measuring the peak amplitude and wave width morphological parameters of different characteristic waves.

[0012] Further, S4 includes the following sub-steps: S41, collecting basic physiological information of the monitored subject, including age, height, weight, gender, and history of underlying diseases, and inputting the data into the parameter configuration module of the vascular elasticity dynamic compensation model. This module assigns corresponding initial compensation coefficients to different basic physiological information according to preset mapping rules; S42, extracting calibration parameters related to vascular elasticity from the different characteristic wave component parameters obtained in S3, such as the vascular wall stress value corresponding to the peak value during systole and the vascular wall strain value corresponding to the trough value during diastole, and establishing the correlation between the calibration parameters and the initial compensation coefficients; S43, dynamically adjusting the initial compensation coefficients based on the real-time physiological data changes of the monitored subject during the monitoring process, such as heart rate fluctuations and blood pressure changes, calculating the compensation coefficient deviation value after each adjustment, and re-optimizing the adjustment strategy if the deviation value exceeds the set range; S44, substituting the adjusted compensation coefficients into the vascular elasticity dynamic compensation model, performing compensation calculations on the extracted vascular elasticity-related calibration parameters, generating the compensated vascular elasticity modulus and vascular compliance parameters, and storing them in the data cache module.

[0013] Further, the S5 comprises the following sub-steps: S51, from the data storage unit, call the compensated blood vessel elasticity correlation parameters output in S4 and the pulse wave transmission time sequence data generated in S2, perform time axis alignment processing on the two types of data, ensure that each set of data corresponds to each other in the time dimension, and eliminate time synchronization deviation; S52, perform feature standardization processing on the aligned data set, convert the numerical values of different types of parameters into a unified data interval, avoid interference on subsequent analysis caused by parameter magnitude differences, and mark and separately store the outliers in the data set; S53, input the standardized data set into a multi-feature fusion algorithm, which first performs feature layering on the data, divides the data into time feature layer, shape feature layer and physiological correlation feature layer, then performs feature screening within different layers, and retains feature parameters that have a significant impact on the non-invasive cardiac output monitoring index; S54, through cross-correlation calculation between feature layers, a mathematical mapping relationship between different feature parameters and the non-invasive cardiac output monitoring index is established, a preliminary correlation mapping model is generated, and the fitting degree of the model is preliminarily evaluated.

[0014] A data big data analysis system for non-invasive cardiac output monitoring, which is applied to a data big data analysis method for non-invasive cardiac output monitoring, comprising: a multi-channel radial artery signal acquisition unit connected with a sensor array signal processing platform, used for acquiring multi-channel physiological signals in the radial artery region and transmitting the acquired signals to the sensor array signal processing platform; a signal filtering and enhancement processing unit integrated in the sensor array signal processing platform, receiving the signals transmitted by the multi-channel radial artery signal acquisition unit, performing multi-dimensional filtering and enhancement processing on the signals, screening out effective signals and transmitting the effective signals to a pulse wave transmission time feature extraction unit; the pulse wave transmission time feature extraction unit is connected with the signal filtering and enhancement processing unit and the radial artery tension waveform analysis unit respectively, performs feature extraction on the effective signals based on a pulse wave transmission time analysis algorithm, obtains a pulse wave transmission time sequence data set and transmits it to the radial artery tension waveform analysis unit; the radial artery tension waveform analysis unit is connected with a blood vessel elasticity dynamic compensation unit, uses a radial artery tension waveform analysis model to decompose the pulse wave transmission time sequence data set, obtains different characteristic wave component parameters and transmits them to the blood vessel elasticity dynamic compensation unit; the blood vessel elasticity dynamic compensation unit is connected with a big data analysis integration unit, uses a blood vessel elasticity dynamic compensation model to perform dynamic compensation calculation on the characteristic wave component parameters, obtains compensated blood vessel elasticity correlation parameters and transmits them to the big data analysis integration unit; an analysis and result output unit connected with the blood vessel elasticity dynamic compensation unit receives the compensated blood vessel elasticity correlation parameters and the pulse wave transmission time sequence data, establishes a correlation mapping through a multi-feature fusion algorithm and iteratively optimizes, and outputs the final monitoring result data.

[0015] Beneficial Effects: This invention proposes a data big data analysis method and system for non-invasive cardiac output monitoring. It acquires multi-channel radial artery signals through a sensor array signal processing platform and performs targeted filtering and enhancement, solving the problems of loose integration between signal processing and big data analysis in existing technologies, and the lack of integration of multi-channel signal processing with monitoring requirements. This provides high-quality and effective signals for subsequent analysis. Features are extracted and a time-series dataset is constructed using a pulse wave transit time analysis algorithm. Multi-dimensional parameters are obtained by decomposing characteristic wave components using a radial artery tension waveform analytical model. The compensation coefficient is then adjusted using a vascular elasticity dynamic compensation model combined with individual baseline physiological information. This breaks through the limitations of existing technologies, which are limited to single parameters or simple models and lack dynamic compensation mechanisms. It can adapt to changes in the physiological state of different populations and reduce monitoring result deviations. The big data analysis module integrates multi-source data, and a multi-feature fusion algorithm is used to establish correlation mappings and iteratively optimize them, improving the multi-source data fusion capability, fully exploring data correlations, enhancing the stability of the mapping relationship between data and cardiac output monitoring indicators, and achieving continuous output of high-precision monitoring results. Simultaneously, the entire process requires no invasive operation, balancing safety and convenience, and meeting the clinical needs for real-time and accurate cardiac function assessment. Attached Figure Description

[0016] Figure 1 This is a flowchart of the method steps of the present invention; Figure 2 This is a diagram showing the system unit composition of the present invention. Detailed Implementation

[0017] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0018] like Figure 1 As shown, a big data analysis method for non-invasive cardiac output monitoring includes the following steps: S1, multi-channel physiological signals of the radial artery region are collected through a sensor array signal processing platform. The platform performs multi-dimensional filtering and signal enhancement processing on the collected signals to select effective signals that meet the requirements of non-invasive cardiac output monitoring data. Specifically, the implementation process of step S1 is as follows: first, start the sensor array signal processing platform, which is equipped with an array composed of 16 pressure sensors, the sensor spacing is set to 0.5 millimeters, covering the most obvious 2 centimeters x 2 centimeters area of radial artery pulsation, the sampling frequency is set to 1000 Hz to ensure that the high-frequency pulse wave details can be captured. After starting the platform, the sensor array is closely attached to the radial artery of the subject's wrist, and multi-channel physiological signals are collected through pressure sensing. The initial acquisition time is set to 30 seconds to obtain the basic signal library. Then the platform performs multi-dimensional filtering on the collected raw signals, where the low-pass filter cutoff frequency is set to 50 Hz to filter out high-frequency electromagnetic interference; the high-pass filter cutoff frequency is set to 0.5 Hz to remove low-frequency baseline drift; at the same time, an adaptive filtering algorithm is enabled to adjust the filtering parameters in real time to cope with the interference caused by the subject's limb micro-movement. After filtering, the signal-to-noise ratio of the effective signal is improved through a signal enhancement algorithm, and the channel signals with a signal-to-noise ratio below 20 decibels are marked as invalid and removed. Finally, at least 8 effective channel signals are selected, which must meet the requirements of no obvious signal interruption within 5 seconds and signal amplitude fluctuation range controlled within 5%, to provide a high-quality data basis for subsequent analysis. This step avoids misleading the subsequent feature extraction by the interference in the original signal through precise signal acquisition and processing, and ensures the reliability of the data source of the entire monitoring process.

[0019] S2, based on the pulse wave transit time analysis algorithm, the effective signals obtained in S1 are extracted, the difference value of the pulse wave transit time between different monitoring points is determined, and the pulse wave transit time sequence data set is constructed; Specifically, the implementation process of step S2 is as follows: based on the preset pulse wave conduction time analysis algorithm, the effective signals screened out in S1 are first subjected to feature point recognition, and the algorithm first locates the rising edge inflection point (i.e. the start point of the systolic period) and the falling edge inflection point (i.e. the start point of the diastolic period) in each effective channel signal, and the recognition accuracy is controlled within 1 millisecond. For each effective channel, the time stamps of the rising edge inflection points in the last 10 pulse cycles are calculated, and then two adjacent effective channels (such as the first channel and the second channel, the third channel and the fourth channel, etc.) are selected, and the difference value of the corresponding rising edge inflection point time stamps is calculated to obtain the preliminary pulse wave conduction time data. Then, statistical analysis is performed on the preliminary conduction time data of each channel combination, and the abnormal values exceeding ±3 times of the average value are removed, and then the average value of the remaining data is taken to obtain the pulse wave conduction time value of the channel combination. Repeat the process to obtain the conduction time values of all effective channel combinations, and construct a pulse wave conduction time sequence data set containing channel number, conduction time value and corresponding pulse cycle serial number. The data set needs to contain effective data of at least 20 consecutive pulse cycles. This step accurately extracts the pulse wave conduction time feature, establishes a quantitative time sequence data set, provides a key time dimension reference for subsequent analysis of the radial artery tension waveform, and improves the accuracy of the conduction time data through cross-validation of multiple channel data, avoiding analysis errors caused by single channel signal deviation.

[0020] S3, using a radial artery tension waveform analysis model to decompose the pulse wave conduction time sequence data set obtained in S2, to separate the systolic wave, diastolic wave and re-pulse wave components in the radial artery tension waveform, and to obtain the morphological parameters and time parameters of different characteristic wave components; Specifically, the implementation process of step S3 is as follows: using the radial artery tension waveform analysis model, the pulse wave conduction time sequence data set constructed in S2 is first split by pulse period, and each pulse period corresponds to a group of conduction time data and the corresponding original signal segment. The model first performs waveform smoothing processing on the original signal segment of each pulse period, adopts the moving average method, and the window size is set to 5 sampling points to reduce the influence of signal noise on waveform decomposition. Then, each smoothed signal segment is decomposed into three characteristic wave components, namely systolic wave, diastolic wave and double beat wave, according to the waveform characteristics. The systolic wave is defined as the waveform part from the rising inflection point to the signal peak value, and the peak value is identified by finding the time point corresponding to the maximum signal amplitude, with an accuracy control of 0.5 milliseconds. The diastolic wave is defined as the waveform part from the peak value to the next rising inflection point. The double beat wave is defined as the secondary small peak waveform in the diastolic wave, which needs to meet the condition that the amplitude reaches 30% or more of the systolic wave peak value. After decomposition, the morphological parameters and time parameters of each characteristic wave component are extracted, including the systolic wave peak amplitude, diastolic wave trough amplitude, and double beat wave peak amplitude, with a measurement accuracy control of 0.1 millivolt. The time parameters include the systolic wave duration (time from the rising inflection point to the peak value), diastolic wave duration (time from the peak value to the next rising inflection point), and double beat wave occurrence time (time from the peak value to the double beat wave peak value), with a measurement accuracy control of 1 millisecond. This step converts the complex radial artery tension waveform into quantifiable feature parameters through fine waveform decomposition and parameter extraction, providing direct waveform feature basis for subsequent analysis of vascular elasticity state. At the same time, by defining the characteristic wave and measurement standard, the consistency and comparability of the parameters are ensured.

[0021] S4, using the vascular elasticity dynamic compensation model to perform dynamic compensation calculation on the different characteristic wave component parameters extracted in S3, adjusting the compensation coefficient combined with the basic physiological information of the monitoring object, to obtain the compensated vascular elasticity correlation parameters; Specifically, step S4 is implemented as follows: Using a dynamic compensation model for vascular elasticity, the basic physiological information of the subject is first collected, including age (accurate to 1 year), height (accurate to 1 cm), weight (accurate to 0.5 kg), gender, and whether the subject has underlying diseases such as hypertension or diabetes. This information is then input into the model's parameter configuration module. The module assigns initial compensation coefficients to different basic physiological information according to preset mapping rules. For example, the initial compensation coefficient for healthy men aged 20-30 is set to 1.0, and the initial compensation coefficient for hypertensive patients over 60 years old is set to 1.2. The adjustment step size for the compensation coefficient is set to 0.05. Subsequently, from the characteristic wave component parameters extracted in S3, three key parameters directly related to vascular elasticity are selected: the peak amplitude of the systolic wave, the trough amplitude of the diastolic wave, and the duration of the systolic wave. The correlation between these parameters and the initial compensation coefficient is established, meaning that the change in the value of each key parameter corresponds to a specific adjustment ratio of the compensation coefficient. During monitoring, the subject's heart rate (sampling frequency set to 1 Hz) and non-invasive blood pressure (measured every 30 seconds, with an accuracy of ±2 mmHg) are collected in real time. When heart rate fluctuations exceed 5 beats / minute or blood pressure fluctuations exceed 10 mmHg, the model automatically adjusts the compensation coefficient according to the fluctuation amplitude. For example, when the heart rate increases by 10 beats / minute, the compensation coefficient increases by 0.1 from the initial value; when the blood pressure decreases by 10 mmHg, the compensation coefficient decreases by 0.08. After adjustment, the compensation coefficient is substituted into the model calculation formula to calculate the compensation for the selected key vascular elasticity parameters, obtaining the compensated vascular elastic modulus, vascular compliance, and other parameters. These parameters need to be stored in the data cache and updated every 10 seconds to ensure the dynamic timeliness of the parameters. This step, by combining individual differences of the subject with real-time physiological state to adjust the compensation coefficient, eliminates the influence of individual physiological characteristics and real-time state changes on vascular elasticity parameters, improves the accuracy of the parameters, and provides reliable vascular status data support for the accurate calculation of subsequent cardiac output monitoring results.

[0022] S5 integrates the compensated vascular elasticity correlation parameters in S4 with the pulse wave conduction time series data in S2, and inputs them into the big data analysis module for non-invasive cardiac output monitoring. This module uses a multi-feature fusion algorithm to perform hierarchical processing on the integrated data and establishes a correlation mapping between the data and non-invasive cardiac output monitoring indicators. Specifically, the implementation process of step S5 is as follows: first, the latest compensated blood vessel elasticity related parameters (including blood vessel elasticity modulus and blood vessel compliance) output in S4 and the pulse wave conduction time sequence data generated in S2 are retrieved from the data storage unit, the time dimensions of the two types of data are unified through a time stamp alignment algorithm, and it is ensured that each set of blood vessel elasticity parameters can correspond to the pulse wave conduction time data in a specific time period, and the time synchronization error is controlled within 50 milliseconds. After alignment, the data set is subjected to feature standardization processing, and the Min-Max standardization method is adopted to uniformly convert the values of the blood vessel elasticity modulus (the original range is usually 1000-5000 kilopascals) and the pulse wave conduction time (the original range is usually 100-300 milliseconds) to the interval of 0-1, and at the same time, the abnormal values in the data set are identified through the 3σ criterion, that is, the data exceeding the average value ± 3 times the standard deviation are marked as abnormal and stored separately in the abnormal data area and do not participate in subsequent fusion analysis. The standardized data set is input into the multi-feature fusion algorithm, which first divides the data into three levels of time feature layer (including pulse wave conduction time, characteristic wave time parameters), morphological feature layer (including characteristic wave amplitude parameters) and physiological correlation feature layer (including blood vessel elasticity parameters, heart rate and blood pressure), sets a feature importance evaluation threshold (set to 0.6) for each level, calculates the feature importance scores of each parameter through the random forest algorithm, removes the parameters with scores lower than the threshold, and retains key parameters such as pulse wave conduction time, systolic peak amplitude and blood vessel elasticity modulus. Then, cross-correlation calculation is performed between the levels, for example, the Pearson correlation coefficient of the pulse wave conduction time in the time feature layer and the blood vessel elasticity modulus in the physiological correlation feature layer is calculated, a mathematical mapping relationship between each feature parameter and the non-invasive cardiac output monitoring index (cardiac output, cardiac index) is established based on the correlation coefficient, and a preliminary correlation mapping model is generated, and the model fitting degree needs to reach 0.85 or higher. If it does not reach, the feature selection threshold and the correlation calculation method are adjusted. Through data integration, standardization and multi-feature fusion, this step establishes a quantitative correlation between the feature parameters and the cardiac output monitoring index, lays a model foundation for subsequent output of accurate monitoring results, and improves the stability and reliability of the model through abnormal value processing and feature selection.

[0023] S6, iteratively optimizing the correlation mapping established in S5 through the big data analysis module, and outputting the final monitoring result data meeting the accuracy requirements of non-invasive cardiac output monitoring.

[0024] Specifically, the implementation process of step S6 is as follows: The big data analysis module calls the preliminary correlation mapping model established in S5. First, it inputs the integrated data of the latest 10 consecutive pulse cycles (including compensated vascular elasticity parameters and pulse wave conduction time data). The model outputs the corresponding non-invasive cardiac output monitoring results (cardiac output value). This result is compared with the preset reference range (the normal range of cardiac output in adults at rest is 4-8 liters / minute) to determine whether it is within a reasonable range. If the result exceeds the reference range, the module automatically starts the iterative optimization process. First, it analyzes the reason for the excess. If it is due to abnormal feature parameters (such as excessive fluctuation in pulse wave conduction time), it returns to S2 to re-extract the conduction time data for that time period. If it is due to model parameter deviation, it adjusts the feature weight coefficient in the multi-feature fusion algorithm by 10% of the initial weight and recalculates the correlation mapping model. After optimization, the same data is input again for verification. If the output result still exceeds the reference range, the iteration process is repeated. The upper limit of the number of iterations is set to 5. If the result is still abnormal after 5 iterations, the module issues a data abnormality prompt. If the results are within a reasonable range, the module continues to input the integrated data for the next 10 pulse cycles, repeating the above verification and optimization process. Simultaneously, the coefficient of variation (COP) of 20 consecutive monitoring results is calculated. When the COP is below 5%, the model is considered to have reached a stable state, and the final non-invasive cardiac output monitoring results are output. The results must include cardiac output, cardiac index, and the COP of the monitoring results, stored in the results database and simultaneously displayed on the monitoring interface. This step ensures the stability and accuracy of the correlation mapping model through iterative optimization, avoiding errors in monitoring results caused by single data bias or model parameter errors, ultimately outputting high-precision and stable monitoring results that meet clinical requirements for the reliability of cardiac output monitoring results.

[0025] Preferably, the expression used in the pulse wave propagation time analysis algorithm is: ,in, The pulse wave conduction time. The time when the pulse wave feature point is collected at the i-th monitoring point. For the first The time when pulse wave characteristic points were collected at each monitoring point The total number of monitoring points. Let be the signal strength weighting coefficient for the i-th monitoring point. Let be the position correction coefficient for the i-th monitoring point. Let be the signal stability coefficient of the i-th monitoring point. Let be the environmental interference compensation coefficient for the i-th monitoring point.

[0026] Specifically, the implementation process of the pulse wave conduction time analysis algorithm is as follows: first, the total number of monitoring points is determined, and according to the channel number setting of the sensor array, usually 8-12 effective monitoring points are selected to ensure data representativeness; when each monitoring point collects the pulse wave feature point time, it is accurately captured through signal feature recognition technology, and the time recording accuracy is controlled within 0.1 milliseconds. The signal strength weight coefficient is determined according to the signal-to-noise ratio of each monitoring point, and the coefficient of the monitoring point with high signal-to-noise ratio (above 30 decibels) is set to 0.9-1.0, and the coefficient of the monitoring point with low signal-to-noise ratio (20-30 decibels) is set to 0.6-0.8; the position correction coefficient is adjusted according to the distance between the monitoring point and the center of the radial artery, and the coefficient is set to 1.0 when the distance is within 0.5 millimeters, and the coefficient decreases by 0.1 when the distance increases by 0.5 millimeters, and the range is controlled within 0.7-1.0. The signal stability coefficient is calculated by the fluctuation amplitude of the signal of 10 consecutive pulse cycles, and the coefficient is set to 0.9-1.0 when the fluctuation amplitude is less than 3%, and the coefficient is set to 0.7-0.8 when the fluctuation amplitude is 3%-5%; the environmental interference compensation coefficient is set according to the electromagnetic interference intensity in the monitoring environment, and the coefficient is set to 0.95-1.0 in the environment with low interference intensity, and the coefficient is set to 0.85-0.95 in the environment with medium interference intensity. When calculating, first multiply the time difference value of each monitoring point by the corresponding coefficient and then sum up, then calculate the sum of the product of the stability coefficient and the interference compensation coefficient of each monitoring point, and finally divide the two to obtain the pulse wave conduction time. Through accurate setting and calculation of multi-dimensional coefficients, the influence of position difference, signal strength and environmental interference on conduction time calculation is eliminated, and the accuracy of pulse wave conduction time data is improved, providing reliable time dimension parameters for subsequent heart output monitoring.

[0027] Preferably, the expression adopted by the radial artery tension waveform analysis model is: wherein, is the tension value of the radial artery at position r and time t, is the systolic wave amplitude coefficient, is the position attenuation coefficient, is the radial position coordinate, is the radial artery center position coordinate, is the pulse wave angular frequency, is the time, is the systolic wave phase shift, is the diastolic wave amplitude coefficient, is the time attenuation coefficient, is the diastolic starting time, is the radial phase coefficient, is the diastolic wave phase shift.

[0028] Specifically, the implementation process of the radial artery tension waveform analysis model is as follows: the systolic wave amplitude coefficient is determined according to the pressure change amplitude of the radial artery in the systolic period, and is usually set to 0.8-1.2 in the resting state of healthy adults, and is adjusted to 0.6-1.0 according to the vascular elasticity of children or the elderly; the position attenuation coefficient is set according to the distance between the radial position and the center of the radial artery, and the coefficient increases by 0.05 for every 0.1 mm increase in distance from the center, and is controlled in the range of 0.1-0.5 to ensure accurate reflection of the tension attenuation law at different positions. The pulse wave angular frequency is calculated according to the heart rate of the subject, and is set to 6.28-8.37 radians per second when the heart rate is 60-80 times per minute, and the angular frequency increases or decreases by 1.05 radians per second for every 10 times per minute deviation of the heart rate; the systolic wave phase shift amount is adjusted according to the time difference between the signal acquisition starting time and the systolic period starting point, and the time difference of 0-50 milliseconds corresponds to a shift amount of 0-0.314 radians. The diastolic wave amplitude coefficient is usually 0.4-0.6 times the systolic wave amplitude coefficient, and is adjusted according to the vascular elasticity; the time attenuation coefficient is set according to the diastolic period duration, and is set to 0.8-1.2 when the diastolic period duration is 0.4-0.6 seconds; the radial phase coefficient is set according to the elastic properties of the radial artery vessel wall, and is set to 0.5-0.8 for better elastic vessels and 1.0-1.3 for less elastic vessels; the diastolic wave phase shift amount and the systolic wave phase shift amount maintain a difference of 0.523-0.785 radians. Through the synergistic effect of each parameter during calculation, the radial artery tension changes at different positions and different times are accurately simulated, and through dynamic adjustment of multiple parameters, the radial artery tension waveform is finely analyzed, and each characteristic wave component is accurately separated, thereby providing detailed waveform data support for subsequent extraction of vascular elasticity related parameters.

[0029] Preferably, the expression used by the vascular elasticity dynamic compensation model is: wherein, is the compensated vascular elasticity modulus, is the original value of the uncompensated vascular elasticity modulus, is the sampling number of the dynamic compensation calculation, is the compensation coefficient of the jth sampling, is the blood pressure value of the jth sampling, is the average blood pressure value in the set time period, is the heart rate value of the jth sampling, is the average heart rate value in the set time period, is the time attenuation factor of the jth sampling.

[0030] Specifically, the implementation process of the blood vessel elasticity dynamic compensation model is as follows: the original value of the blood vessel elasticity modulus before compensation is calculated by the characteristic wave parameters extracted by S3, and is usually 1500-3000 kilopascals in healthy adults in a resting state, and needs to be updated in real time according to the actual waveform parameters of the measured subject. The sampling number of dynamic compensation calculation is set to 10-20 times to ensure that the sampling data is statistically representative; the compensation coefficient is determined according to the basic physiological information of the measured subject, and is set to 0.9-1.1 for healthy people aged 20-40 years old, 1.1-1.3 for people aged 40-60 years old, 1.3-1.5 for people over 60 years old or with underlying diseases, and is adjusted by 0.05 every 5 years. The blood pressure value is collected by the non-invasive blood pressure monitoring module every 30 seconds, and the average blood pressure value is the average value of the results of continuous 5 times collection, and the collection accuracy needs to be ensured within ±2 millimeters of mercury column during calculation; the heart rate value is collected in real time by the heart rate monitoring module, and the sampling frequency is 1 hertz, and the average heart rate value is the average value of the results of continuous 1 minute collection. The time decay factor is set according to the sampling interval, and is set to 0.98-1.0 when the sampling interval is 5 seconds, and is reduced by 0.02 every 5 seconds, and the range is controlled within 0.9-1.0. During calculation, the relative change rate of the blood pressure difference and the heart rate difference of each sampling is calculated first, then multiplied by the corresponding compensation coefficient and time decay factor, and then summed, and finally multiplied by the original elasticity modulus to obtain the compensated elasticity modulus. By adjusting the compensation parameters according to the real-time physiological state and basic information of the measured subject, the influence of individual differences and real-time physiological fluctuations on the blood vessel elasticity parameters is effectively eliminated, the accuracy of the blood vessel elasticity data is improved, and the foundation for accurate calculation of the subsequent heart output monitoring results is laid.

[0031] Preferably, the signal processing expression of the sensor array signal processing platform is: , wherein, is the effective signal output by the platform, is the number of channels of the sensor array, is the original input signal of the pth channel, is the signal gain coefficient of the pth channel, is the interference strength coefficient of the kth type of interference signal of the pth channel, is the suppression coefficient of the kth type of interference of the pth channel.

[0032] Specifically, the implementation process of signal processing of the sensor array signal processing platform is as follows: the number of channels of the sensor array is set to 16-32 according to the monitoring requirements, ensuring that the key area of the radial artery is covered and signal redundancy is avoided; the original input signal of each channel is collected by a pressure sensor, the signal amplitude range is controlled within 0.1-5 millivolts, and the sensor should be in good contact with the skin during collection to avoid signal distortion caused by poor contact. The signal gain coefficient is adjusted according to the original signal amplitude, the channels with an amplitude less than 0.5 millivolts are set to 1.5-2.0, the channels with an amplitude of 0.5-2 millivolts are set to 1.0-1.5, and the channels with an amplitude greater than 2 millivolts are set to 0.8-1.0, to ensure that the signal amplitude of each channel after adjustment is within the ideal analysis interval of 0.5-3 millivolts. Interference signals are divided into three categories: electromagnetic interference, limb micro-motion interference, and power frequency interference. The interference intensity coefficient of each type of interference is detected in real time by the interference monitoring module, and is set to 0.1-0.3 when the interference intensity is low, 0.3-0.5 when the interference intensity is moderate, and 0.5-0.8 when the interference intensity is high. The corresponding suppression coefficient is adjusted according to the type of interference, and is set to 0.8-1.0 for electromagnetic interference, 0.7-0.9 for limb micro-motion interference, and 0.9-1.0 for power frequency interference. During calculation, the original signal of each channel is first multiplied by the gain coefficient, then multiplied by the product of the interference types (1-interference intensity coefficient x suppression coefficient), and finally the results of all channels are summed to obtain the output effective signal. Through the cooperative processing of multi-channel signals and targeted interference suppression, the signal-to-noise ratio and quality of the output signal are greatly improved, and various types of interference signals are effectively filtered out, providing a high-quality signal source for subsequent feature extraction and analysis, and avoiding misleading of the subsequent process by interference signals.

[0033] Preferably, the multi-feature fusion algorithm expression of the data big data analysis module of the non-invasive cardiac output monitoring is: wherein, is the non-invasive cardiac output monitoring result, is the number of feature categories, is the number of parameters of each feature category, is the value of the yth parameter in the xth feature category, is the weight coefficient of the yth parameter in the xth feature category, is the normalization coefficient of the yth parameter in the xth feature category, is the error correction coefficient of the yth parameter in the xth feature category, is the stability coefficient of the yth parameter in the xth feature category.

[0034] Specifically, the implementation process of the multi-feature fusion algorithm of the data big data analysis module of the non-invasive cardiac output monitoring is as follows: the number of feature categories is divided into three categories: time features, shape features, and physiological correlation features. The number of parameters for each category of features is set according to actual analysis requirements. The time features include 3-5 parameters (such as pulse wave transmission time, systolic duration, etc.), the shape features include 4-6 parameters (such as systolic peak amplitude, double wave amplitude, etc.), and the physiological correlation features include 2-4 parameters (such as vascular elasticity modulus, heart rate, etc.). The numerical values of each feature parameter are obtained through the extraction and processing in the previous steps, and the accuracy and timeliness of the parameters need to be ensured. The real-time update frequency is set to 10 seconds / time. The weight coefficients are set according to the influence of the features on the cardiac output monitoring results. The key parameters such as pulse wave transmission time and vascular elasticity modulus are set to 0.2-0.3, and the secondary parameters are set to 0.05-0.15. The sum of all parameter weight coefficients is 1.0. The normalization coefficient is set according to the value range of the parameter, which uniformly converts parameters of different magnitudes to the 0-1 interval, ensuring that the weights of all parameters are balanced in the fusion process. The error correction coefficient is set according to the measurement accuracy of the parameter. The parameters with high measurement accuracy (error less than 5%) are set to 0.95-1.0, the parameters with medium accuracy (error 5%-10%) are set to 0.9-0.95, and the parameters with low accuracy (error 10%-15%) are set to 0.85-0.9. The stability coefficient is set according to the fluctuation amplitude of the parameter. The parameters with a fluctuation amplitude less than 3% are set to 0.95-1.0, and the parameters with a fluctuation amplitude of 3%-5% are set to 0.9-0.95. When calculating, first multiply each parameter in each category of features by the corresponding weight coefficient and normalization coefficient, then sum them up, and then calculate the product of the error correction coefficient and the stability coefficient of all parameters. Finally, the cardiac output monitoring result is obtained by dividing the two, which fully utilizes the information value of each dimension parameter, effectively reduces the influence of single parameter error on the monitoring result, improves the accuracy and stability of the cardiac output monitoring result, and meets the requirements of clinical reliability of the cardiac output monitoring result.

[0035] Preferably, the S3 comprises the following steps: S31, performing signal segmentation processing on the pulse wave conduction time sequence data set obtained in S2, dividing the entire time sequence into a plurality of independent pulse wave period segments according to the periodic characteristics of the pulse wave, each period segment containing a complete pulse wave signal; S32, for each divided pulse wave period segment, performing multi-scale decomposition on the signal by using a wavelet transform algorithm to obtain wavelet coefficients at different scales, and screening out signal components containing radial artery tension waveform calibration features through the wavelet coefficients; S33, performing reconstruction processing on the screened signal components to remove noise interference introduced in the decomposition process, and obtaining a relatively smooth radial artery tension waveform original profile; S34, setting a characteristic wave recognition threshold according to the physiological characteristics of the radial artery tension waveform, separating the systolic wave, diastolic wave and double beat wave through threshold comparison and waveform slope analysis, and recording the starting time, peak time and trough time parameters of different characteristic waves, and measuring the peak amplitude and wave width morphological parameters of different characteristic waves.

[0036] Specifically, step S3 comprises four sub-steps: in S31, when performing signal segmentation on the pulse wave conduction time sequence data set obtained in S2, first determine the starting and ending points of each period by using a pulse wave period recognition algorithm, and control the period recognition accuracy within 1 millisecond, then divide the entire time sequence into independent period segments according to the standard that each period segment contains a complete pulse wave signal, and ensure that the signal length of each period segment is consistent with the actual duration of the period to avoid signal truncation or redundancy; in S32, when performing multi-scale decomposition on each period segment signal by using a wavelet transform algorithm, the decomposition scale is set to 5-8 layers, signal components containing key features are screened out through the energy distribution of wavelet coefficients at each layer, and the screening standard is that components with a coefficient energy proportion exceeding 30% of the total energy are retained; in S33, when reconstructing the screened components, a wavelet inverse transform algorithm is used, and noise introduced in the decomposition process needs to be removed to make the smoothness of the reconstructed radial artery tension waveform original profile meet the requirement that the signal fluctuation amplitude is less than 5%; in S34, when setting the characteristic wave recognition threshold, the threshold is determined according to the peak amplitude of the reconstructed waveform, and is usually set to 10%-15% of the peak amplitude, each characteristic wave is separated through threshold comparison and waveform slope analysis (a slope change rate exceeding 50% / millisecond is determined as a characteristic point), and the time parameters are recorded with an accuracy of 0.5 millisecond, and the morphological parameters are measured with an accuracy of 0.1 millivolt, through the detailed sub-steps, the accuracy of radial artery tension waveform decomposition and parameter extraction is ensured, and reliable feature data is provided for subsequent blood vessel elasticity analysis.

[0037] Preferably, the S4 comprises the following steps: S41, collecting basic physiological information of the monitoring object, including age, height, weight, gender and basic disease history data, inputting the data into a parameter configuration module of the blood vessel elasticity dynamic compensation model, and assigning corresponding initial compensation coefficients to different basic physiological information according to a preset mapping rule; S42, extracting calibration parameters associated with blood vessel elasticity from the different characteristic wave group parameters obtained in S3, such as blood vessel wall stress value corresponding to systolic peak value and blood vessel wall strain value corresponding to diastolic trough, and establishing an association between the calibration parameters and the initial compensation coefficients; S43, dynamically adjusting the initial compensation coefficients based on real-time physiological data changes of the monitoring object during the monitoring process, such as heart rate fluctuation and blood pressure change, calculating the compensation coefficient deviation value after each adjustment, and re-optimizing the adjustment strategy if the deviation value exceeds the set range; S44, substituting the adjusted compensation coefficients into the blood vessel elasticity dynamic compensation model to compensate and calculate the extracted blood vessel elasticity associated calibration parameters, generate compensated blood vessel elasticity modulus and blood vessel compliance parameters, and store them in the data cache module.

[0038] Specifically, step S4 comprises four sub-steps: S41, when collecting the basic physiological information of the subject, the age is recorded to 1 year, the height to 1 cm, the weight to 0.5 kg, and the basic disease history needs to be clear about the disease type and the length of time of the disease. After inputting these information into the parameter configuration module, the module assigns initial compensation coefficients according to the preset mapping rule, and the difference between the coefficients of healthy people and patients with basic diseases in the rule is controlled within 0.2-0.3; S42, when extracting blood vessel elasticity related key parameters from the characteristic wave parameters in S3, the blood vessel wall stress value corresponding to the systolic peak value (measurement accuracy 0.1 kPa) and the blood vessel wall strain value corresponding to the diastolic trough (measurement accuracy 0.001) are selected as the key parameters, and the association between these parameters and the initial compensation coefficients is established. The association is determined by a linear fitting algorithm, and the fitting degree needs to be above 0.85; S43, when adjusting the initial compensation coefficients according to the real-time physiological data, the heart rate fluctuation monitoring frequency is 1 Hz, and the blood pressure is measured every 30 seconds. When the fluctuation exceeds the set range (heart rate ± 5 times / minute, blood pressure ± 10 mmHg), the adjustment is started, the adjustment step is set to 0.05, and the deviation value is calculated. When the deviation value exceeds 0.1, the adjustment strategy is re-optimized; S44, when substituting the adjusted compensation coefficients into the model for calculation, the iteration number of compensation calculation is set to 3-5 times to ensure that the error of the compensated blood vessel elasticity parameters (elastic modulus, compliance) is less than 5%, and the data is stored in the data cache module. The cache update frequency is consistent with the parameter calculation frequency (every 10 seconds), the compensation process is controlled by sub-steps, the accuracy of the blood vessel elasticity parameters is improved, and the physiological state differences of different subjects are adapted.

[0039] Preferably, S5 comprises the following steps: S51, from the data storage unit, call the compensated blood vessel elasticity correlation parameters output by S4 and the pulse wave transmission time sequence data generated by S2, perform time axis alignment processing on the two types of data, ensure that each set of data corresponds to each other in the time dimension, and eliminate time synchronization deviation; S52, perform feature standardization processing on the aligned data set, convert the numerical values of different types of parameters into a unified data interval, avoid interference caused by parameter magnitude differences on subsequent analysis, and mark and separately store the outliers in the data set; S53, input the standardized data set into a multi-feature fusion algorithm, which first performs feature layering on the data, divides the data into time feature layer, shape feature layer and physiological correlation feature layer, then performs feature screening within different layers, and retains feature parameters that have a significant impact on non-invasive cardiac output monitoring indicators; S54, through cross-correlation calculation between feature layers, a mathematical mapping relationship between different feature parameters and non-invasive cardiac output monitoring indicators is established, a preliminary correlation mapping model is generated, and the fitting degree of the model is preliminarily evaluated.

[0040] Specifically, step S4 comprises four sub-steps: S41, when collecting the basic physiological information of the subject, the age is recorded to 1 year, the height is recorded to 1 cm, the weight is recorded to 0.5 kg, and the basic disease history needs to be clear about the disease type and the length of time since the disease occurred. After inputting these information into the parameter configuration module, the module assigns an initial compensation coefficient according to the preset mapping rule, and the difference between the coefficients of healthy people and patients with basic diseases in the rule is controlled within 0.2-0.3; S42, when extracting the blood vessel elasticity related key parameters from the characteristic wave parameters in S3, the blood vessel wall stress value corresponding to the systolic peak value (measurement accuracy 0.1 kPa) and the blood vessel wall strain value corresponding to the diastolic trough (measurement accuracy 0.001) are selected, and the association between these parameters and the initial compensation coefficient is established. The association is determined by a linear fitting algorithm, and the fitting degree needs to be above 0.85; S43, when adjusting the initial compensation coefficient according to the real-time physiological data, the heart rate fluctuation monitoring frequency is 1 Hz, and the blood pressure is measured every 30 seconds. When the fluctuation exceeds the set range (heart rate ± 5 times / minute, blood pressure ± 10 mmHg), the adjustment is started. The adjustment step is set to 0.05, and the deviation value is calculated. When the deviation value exceeds 0.1, the adjustment strategy is re-optimized; S44, when the adjusted compensation coefficient is substituted into the model for calculation, the iteration number of compensation calculation is set to 3-5 times to ensure that the error of the compensated blood vessel elasticity parameters (elastic modulus, compliance) is less than 5%, and the compensated blood vessel elasticity parameters are stored in the data cache module. The cache update frequency is consistent with the parameter calculation frequency (every 10 seconds), the compensation process is controlled through sub-steps, and the accuracy of the blood vessel elasticity parameters is improved to adapt to the physiological state differences of different subjects.

[0041] The pulse wave conduction time analysis algorithm in the application is a technical means for extracting the conduction time characteristics of the pulse wave between different monitoring points from the radial artery signal. The implementation process is as follows: first, rely on the sensor array signal processing platform to obtain effective multi-channel signals, accurately locate the key feature points such as the systolic phase starting point of the pulse wave of each channel through feature point recognition technology, and record the time of each feature point (accuracy within 0.1 milliseconds); then select adjacent effective monitoring points (usually 8-12), calculate the time difference of the corresponding feature points, remove outliers and take the average to obtain the conduction time value of each channel combination, and finally construct a time sequence data set containing channel number, conduction time value and pulse period sequence number. In the calculation, multi-dimensional coefficient optimization results such as signal intensity weight coefficient (0.6-1.0), position correction coefficient (0.7-1.0) and the like are combined. The algorithm provides quantitative pulse wave time dimension data for subsequent analysis, eliminates the influence of signal intensity difference, monitoring point position deviation and environmental interference on the calculation of conduction time through multi-channel cross verification and coefficient correction, improves data accuracy, and provides reliable time feature support for radial artery tension waveform analysis and heart output monitoring result calculation. The radial artery tension waveform analysis model in the application is an analysis model for decomposing the radial artery signal waveform and extracting characteristic wave component parameters. The implementation process is as follows: first, receive the pulse wave conduction time sequence data set, split the signal according to the pulse period and perform smoothing processing (moving average window of 5 sampling points); then decompose the smoothed signal into systolic wave, diastolic wave and double beat wave through the model, and combine the systolic wave amplitude coefficient (0.6-1.2), position attenuation coefficient (0.1-0.5) and pulse wave angular frequency (6.28-8.37 rad / s) and other dynamic adjustment parameters to accurately simulate the tension changes at different positions and times; then extract the morphological parameters (peak amplitude accuracy 0.1 millivolt) and time parameters (duration accuracy 1 millisecond) of each characteristic wave, wherein the double beat wave needs to meet the recognition condition that the amplitude reaches 30% of the systolic wave peak value. The model converts the complex radial artery tension waveform into quantifiable characteristic parameters, avoids the subjective error of manual recognition through fine waveform decomposition and parameter definition, ensures the consistency and comparability of the characteristic parameters, provides direct waveform feature basis for the vascular elasticity dynamic compensation model, and helps subsequent vascular elasticity state analysis and heart output monitoring index association.

[0042] The blood vessel elasticity dynamic compensation model in the application is a compensation model for correcting blood vessel elasticity related parameters, eliminating individual differences and real-time physiological fluctuation effects. The implementation process is as follows: first, collect the basic physiological information (age, height, weight, etc.) of the subject, and distribute the initial compensation coefficient (0.9-1.1 for healthy people, 1.3-1.5 for patients with basic diseases, etc.) through the parameter configuration module; then, extract key parameters such as blood vessel wall stress value (accuracy 0.1 kPa) and strain value (accuracy 0.001) from the radial artery tension waveform analysis results, and establish an association with the initial coefficient (fitting degree ≥0.85); then, adjust the coefficient according to real-time physiological data (heart rate sampling frequency 1 Hz, blood pressure measured every 30 seconds), and when the fluctuation exceeds the threshold (heart rate ±5 times / minute, blood pressure ±10 mmHg), adjust by 0.05 steps, while calculating the deviation value (more than 0.1, then optimize the strategy); finally, calculate the compensated blood vessel elasticity modulus and compliance (error <5%) by substituting the coefficient, and update the data every 10 seconds. The model dynamically corrects the blood vessel elasticity parameters, breaks through the limitations of traditional fixed parameter analysis by combining individual basic information and real-time state, adapts to physiological differences of different populations, improves the accuracy of blood vessel elasticity data, and lays a foundation for the big data analysis module to establish accurate blood vessel state and cardiac output indicators association.

[0043] The sensor array signal processing platform in the application is a hardware and algorithm integrated platform for collecting and processing radial artery multi-channel signals. The implementation process is as follows: first, collect signals by an array composed of 16-32 pressure sensors (spacing 0.5 mm, covering an area of 2 cm x 2 cm), sampling frequency 1000 Hz, and collecting time 30 seconds to establish a basic library; then, perform multi-dimensional filtering (low pass 50 Hz, high pass 0.5 Hz, adaptive filtering) on the original signal to filter out electromagnetic, limb micro-motion and other interference; then, improve the signal-to-noise ratio through a signal enhancement algorithm, normalize the amplitude of each channel signal to 0.5-3 mV by combining the signal gain coefficient (0.8-2.0 dynamic adjustment), calculate the interference intensity coefficient (0.1-0.8) and the suppression coefficient (0.7-1.0), and process the multi-channel signals through the formula, eliminate the invalid channels with signal-to-noise ratio <20 decibels, and finally output the signals of at least 8 valid channels. The platform provides a high-quality, low-interference radial artery signal source, solves the problems of poor signal quality and multiple interference in traditional single-channel signal collection, ensures reliable data source support for subsequent algorithms and models through multi-channel cooperation and targeted processing, avoids the deviation of subsequent analysis caused by original signal interference, and is the basic guarantee for the entire non-invasive cardiac output monitoring process.

[0044] As Figure 2As shown, a data big data analysis system for non-invasive cardiac output monitoring, the system is applied to a data big data analysis method for non-invasive cardiac output monitoring, comprising: a multi-channel radial artery signal acquisition unit connected with a sensor array signal processing platform, for acquiring multi-channel physiological signals in the radial artery area and transmitting the collected signals to the sensor array signal processing platform; a signal filtering and enhancement processing unit integrated in the sensor array signal processing platform, receiving the signals transmitted by the multi-channel radial artery signal acquisition unit, performing multi-dimensional filtering and enhancement processing on the signals, screening out effective signals and transmitting the effective signals to a pulse wave transit time feature extraction unit; a pulse wave transit time feature extraction unit connected with the signal filtering and enhancement processing unit and the radial artery tension waveform analysis unit respectively, based on the pulse wave transit time analysis algorithm, the effective signals are extracted to obtain the pulse wave transit time sequence data set and transmitted to the radial artery tension waveform analysis unit; a radial artery tension waveform analysis unit connected with a vascular elasticity dynamic compensation unit, using a radial artery tension waveform analysis model to decompose the pulse wave transit time sequence data set, obtain different characteristic wave component parameters and transmit them to the vascular elasticity dynamic compensation unit; a vascular elasticity dynamic compensation unit connected with a big data analysis integration unit, using a vascular elasticity dynamic compensation model to dynamically compensate the characteristic wave component parameters, obtaining the compensated vascular elasticity correlation parameters and transmitting them to the big data analysis integration unit; an analysis and result output unit connected with the vascular elasticity dynamic compensation unit, receiving the compensated vascular elasticity correlation parameters and the pulse wave transit time sequence data, establishing correlation mapping and iterative optimization through multi-feature fusion algorithm, and outputting the final monitoring result data.

[0045] A data big data analysis method and system for non-invasive cardiac output monitoring, through the sensor array signal processing platform, the multi-channel radial artery signal is filtered and enhanced in multiple dimensions, and the effective signal is screened for the demand of non-invasive cardiac output monitoring, solving the problem of loose connection between signal processing and big data analysis in the prior art, and the problem of not processing multi-channel signals as needed, laying a high-quality data foundation for subsequent analysis; with the help of pulse wave transit time analysis algorithm to extract features and construct time series data set, combined with radial artery tension waveform analysis model to separate systolic wave, diastolic wave and double beat wave components to obtain multi-dimensional parameters, and then through the vascular elasticity dynamic compensation model to adjust the compensation coefficient combined with the basic physiological information of the monitoring object, breaking the limitation of relying on single parameter or simple model and lacking dynamic compensation in the prior art, which can be flexibly adapted according to the physiological state changes of different groups of people, greatly reducing the deviation of monitoring results.

[0046] The method and system integrate the compensated blood vessel elasticity parameters and pulse wave transmission time data through a big data analysis module, adopt a multi-feature fusion algorithm to perform hierarchical processing on the data and establish a correlation mapping, can also improve the mapping stability through iterative optimization, effectively solve the problems of weak multi-source data fusion capability and insufficient data correlation mining of the prior art, and ensure the continuous output of high-precision monitoring results; at the same time, the signals and analysis data are collected and analyzed by relying on a non-invasive mode throughout the process, without the need for invasive operation, which guarantees the monitoring accuracy while taking into account the safety and convenience, avoids the complication risk of traditional invasive monitoring, and meets the clinical demand for long-term continuous monitoring and real-time evaluation of heart function, and is suitable for monitoring applications in different scenarios.

[0047] In the description of the present application, it should be noted that, unless otherwise explicitly specified and limited, the terms "arrangement", "installation", "connection", "link", "fixation" should be understood broadly, for example, can be fixed connection, can also be detachable connection, or integrally connected; can be mechanical connection, can also be electrical connection; can be directly connected, can also be indirectly connected through an intermediate medium, can be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0048] Although the embodiments of the present application have been shown and described, it can be understood by those skilled in the art that various equivalent changes, modifications, replacements and variations of the embodiments can be made without departing from the principles and spirits of the present application, and the scope of the present application is defined by the appended claims and their equivalent scope.

Claims

1. A data big data analytics method for non-invasive cardiac output monitoring, characterized in that, Includes the following steps: S1. Multi-channel physiological signals from the radial artery region are acquired using a sensor array signal processing platform. This platform performs multi-dimensional filtering and signal enhancement on the acquired signals to select valid signals that meet the requirements for non-invasive cardiac output monitoring data. S2. Based on a pulse wave transit time analysis algorithm, features are extracted from the valid signals acquired in S1 to determine the transit time difference between different monitoring points, thus constructing a pulse wave transit time series dataset. S3. A radial artery tension waveform analytical model is used to decompose the pulse wave transit time series dataset obtained in S2, separating the systolic, diastolic, and dicrotic wave characteristic wave components from the radial artery tension waveform, and obtaining the morphological parameters and temporal parameters of different characteristic wave components. S4: Dynamic compensation calculation is performed on the different characteristic wave component parameters extracted in S3 using the vascular elasticity dynamic compensation model. The compensation coefficient is adjusted in combination with the basic physiological information of the monitored object to obtain the compensated vascular elasticity correlation parameters. S5: The compensated vascular elasticity correlation parameters in S4 are integrated with the pulse wave conduction time series data in S2 and input into the big data analysis module of non-invasive cardiac output monitoring. This module uses a multi-feature fusion algorithm to perform hierarchical processing on the integrated data and establish a correlation mapping between the data and non-invasive cardiac output monitoring indicators. S6: The correlation mapping established in S5 is iteratively optimized through the big data analysis module to output the final monitoring result data that meets the accuracy requirements of non-invasive cardiac output monitoring.

2. The big data analysis method for non-invasive cardiac output monitoring according to claim 1, characterized in that, The expression adopted by the pulse wave transit time analysis algorithm is: Wherein, is the pulse wave transit time, is the time when the pulse wave feature point is collected at the i th monitoring point, is the time when the pulse wave feature point is collected at the i th monitoring point, is the time when the pulse wave feature point is collected at the i th monitoring point, is the total number of monitoring points, is the signal intensity weight coefficient of the i th monitoring point, is the position correction coefficient of the i th monitoring point, is the signal stability coefficient of the i th monitoring point, is the environmental interference compensation coefficient of the i th monitoring point.

3. The big data analysis method for non-invasive cardiac output monitoring according to claim 1, characterized in that, The expression used by the radial artery tension waveform analysis model is: wherein, is the tension value of the radial artery at position r and time t, is the systolic wave amplitude coefficient, is the position attenuation coefficient, is the radial position coordinate, is the radial artery center position coordinate, is the pulse wave angular frequency, is the time, is the systolic wave phase offset, is the diastolic wave amplitude coefficient, is the time attenuation coefficient, is the diastolic wave start time, is the radial phase coefficient, is the diastolic wave phase offset.

4. The big data analysis method for non-invasive cardiac output monitoring according to claim 1, characterized in that, The expression used in the dynamic compensation model for vascular elasticity is: ,in, The compensated vascular elastic modulus, The original value of vascular elastic modulus before compensation. The number of samples is calculated for dynamic compensation. Let be the compensation coefficient for the j-th sampling. The blood pressure value is from the j-th sample. To set the average blood pressure value over a given time period, Let j be the heart rate value from the j-th sample. To set the average heart rate value over a given time period, is the time decay factor for the j-th sampling.

5. A big data analysis method for non-invasive cardiac output monitoring according to claim 1, characterized in that, The signal processing expression of the sensor array signal processing platform is: ,in, For the platform to output valid signals, This refers to the number of channels in the sensor array. Let p be the original input signal of the p-th channel. Let p be the signal gain coefficient of the p-th channel. Let be the interference intensity coefficient of the k-th type of interference signal in the p-th channel. This is the suppression coefficient for the k-th type of interference in the p-th channel.

6. The big data analysis method for non-invasive cardiac output monitoring according to claim 1, characterized in that, The multi-feature fusion algorithm expression of the data big data analysis module for non-invasive cardiac output monitoring is as follows: ,in, This is the result of non-invasive cardiac output monitoring. The number of feature categories, The number of parameters for each type of feature. Let be the value of the y-th parameter in the x-th feature class. Let y be the weight coefficient of the y-th parameter of the x-th feature. Let y be the normalized coefficient of the y-th parameter of the x-th feature. Let y be the error correction coefficient for the y-th parameter of the x-th feature. Let y be the stability coefficient of the y-th parameter of the x-th feature.

7. A big data analysis method for non-invasive cardiac output monitoring according to claim 1, characterized in that, S3 includes the following sub-steps: S31, performing signal segmentation processing on the pulse wave conduction time series dataset obtained in S2, dividing the entire time series into multiple independent pulse wave period segments according to the periodic characteristics of the pulse wave, with each period segment containing a complete pulse wave signal; S32, for each segmented pulse wave period, using a wavelet transform algorithm to decompose the signal into multiple scales, obtaining wavelet coefficients at different scales, and filtering out signal components containing radial artery tension waveform calibration features through wavelet coefficients; S33, reconstructing the filtered signal components to remove noise interference introduced during the decomposition process, obtaining a relatively smooth original contour of the radial artery tension waveform; S34, setting a characteristic wave recognition threshold based on the physiological characteristics of the radial artery tension waveform, separating the systolic wave, diastolic wave, and dicrotic wave through threshold comparison and waveform slope analysis, while recording the start time, peak time, and trough time time parameters of different characteristic waves, and measuring the peak amplitude and wave width morphology parameters of different characteristic waves.

8. A big data analysis method for non-invasive cardiac output monitoring according to claim 1, characterized in that, S4 includes the following sub-steps: S41, collecting basic physiological information of the monitored subjects, including age, height, weight, gender, and history of underlying diseases, and inputting the data into the parameter configuration module of the vascular elasticity dynamic compensation model. This module assigns corresponding initial compensation coefficients to different basic physiological information according to preset mapping rules; S42, extracting calibration parameters related to vascular elasticity from the different characteristic wave component parameters obtained in S3, such as the vascular wall stress value corresponding to the peak value during systole and the vascular wall strain value corresponding to the trough value during diastole, and establishing the correlation between the calibration parameters and the initial compensation coefficients; S43, Based on the real-time physiological data changes of the monitored object during the monitoring process, such as heart rate fluctuations and blood pressure changes, the initial compensation coefficient is dynamically adjusted, and the deviation value of the compensation coefficient after each adjustment is calculated. If the deviation value exceeds the set range, the adjustment strategy is re-optimized. S44, The adjusted compensation coefficient is substituted into the vascular elasticity dynamic compensation model, and the extracted vascular elasticity correlation calibration parameters are compensated to generate the compensated vascular elasticity modulus and vascular compliance parameters, and stored in the data cache module.

9. A big data analysis method for non-invasive cardiac output monitoring according to claim 1, characterized in that, S5 includes the following sub-steps: S51, retrieve the compensated vascular elasticity correlation parameters output from S4 and the pulse wave conduction time series data generated in S2 from the data storage unit, and perform time axis alignment processing on the two types of data to ensure that each set of data corresponds one-to-one in the time dimension and eliminate time synchronization deviation; S52, perform feature standardization processing on the aligned dataset, convert the values ​​of different types of parameters into a unified data range to avoid interference to subsequent analysis due to differences in parameter magnitudes, and mark outliers in the dataset and store them separately; S53, input the standardized dataset into a multi-feature fusion algorithm, which first performs feature layering on the data, dividing the data into a time feature layer, a morphological feature layer, and a physiological correlation feature layer, and then performs feature filtering within different layers to retain feature parameters that have a significant impact on non-invasive cardiac output monitoring indicators; S54, establish a mathematical mapping relationship between different feature parameters and non-invasive cardiac output monitoring indicators through cross-correlation calculation between feature layers, generate a preliminary correlation mapping model, and perform a preliminary evaluation of the model's fit.

10. A big data analysis system for non-invasive cardiac output monitoring, characterized in that, This system is applied to a data big data analysis method for non-invasive cardiac output monitoring as described in claim 1, comprising: a multi-channel radial artery signal acquisition unit, which is connected to a sensor array signal processing platform for acquiring multi-channel physiological signals from the radial artery region and transmitting the acquired signals to the sensor array signal processing platform; a signal filtering and enhancement processing unit, which is integrated within the sensor array signal processing platform, receives the signals transmitted from the multi-channel radial artery signal acquisition unit, performs multi-dimensional filtering and enhancement processing on the signals, filters out effective signals, and transmits the effective signals to a pulse wave conduction time feature extraction unit; and a pulse wave conduction time feature extraction unit, which is connected to both the signal filtering and enhancement processing unit and the radial artery tension waveform analysis unit, and extracts features from the effective signals based on a pulse wave conduction time analysis algorithm to obtain the pulse wave. The pulse wave conduction time series dataset is transmitted to the radial artery tension waveform analysis unit. This unit, connected to the vascular elasticity dynamic compensation unit, uses the radial artery tension waveform analysis model to decompose the pulse wave conduction time series dataset, obtaining parameters of different characteristic wave components, which are then transmitted to the vascular elasticity dynamic compensation unit. The vascular elasticity dynamic compensation unit, connected to the big data analysis and integration unit, uses the vascular elasticity dynamic compensation model to dynamically compensate the characteristic wave component parameters, obtaining compensated vascular elasticity correlation parameters, which are then transmitted to the big data analysis and integration unit. The analysis and result output unit, connected to the vascular elasticity dynamic compensation unit, receives the compensated vascular elasticity correlation parameters and pulse wave conduction time series data, establishes a correlation mapping through a multi-feature fusion algorithm, iteratively optimizes it, and outputs the final monitoring result data.

Images