Noninvasive hemodynamic heart function monitoring system

Abstract

The invention discloses a non-invasive hemodynamic heart function monitoring system, which comprises a signal acquisition module, a data processing module, a data processing module and a data processing module, wherein the signal acquisition module adopts an electrode patch and conducts an alternating current signal; the impedance measurement module is used for calculating the dynamic impedance change of the chest; measuring and recording impedance change in real time; when the personalized data calibration module is used for the first time, the system guides the user to carry out standardized actions, physiological feature information of the user is collected, and meanwhile corresponding impedance change data is recorded; through the recorded data, the system establishes personal baseline data of the user; and the data processing module comprises the steps of filtering, amplifying and analog-to-digital conversion, and is used for converting the collected analog signal into a digital signal. Measurement can be completed without puncturing or invading the body of a patient, the risk of infection and other complications is reduced, the cardiac function health state can be comprehensively analyzed, customized reports are output according to different individual conditions in combination with an AI intelligent report analysis system, and personalized treatment suggestions are provided.

Description

Technical Field

[0001] The present invention relates to the technical field of medical monitoring, and particularly to a non-invasive hemodynamic cardiac function monitoring system. Background Art

[0002] In the field of medical monitoring, non-invasive hemodynamic cardiac function monitoring systems have important application values. Traditional invasive methods such as the Swan-Ganz catheter method and the PICCO method are restricted in their wide application in common clinical diseases and chronic diseases due to their complex operations, high risks, high costs and other characteristics. While non-invasive cardiac function detection technologies, with their characteristics of safety, non-invasiveness, simple operation, accuracy and reliability, can be better applied to continuously monitor hemodynamic changes and evaluate cardiac function.

[0003] However, current non-invasive cardiac function monitoring systems, although able to meet the detection requirements, lack targeted adjustment and personalized services for different patients.

[0004] Therefore, the present invention proposes a non-invasive hemodynamic cardiac function monitoring system. Summary of the Invention

[0005] In view of the defects in the prior art, the present invention provides a non-invasive hemodynamic cardiac function monitoring system, including:

[0006] A signal acquisition module: using electrode patches and conducting through alternating current signals;

[0007] An impedance measurement module: calculating the dynamic impedance change of the chest; measuring and recording the impedance change in real time;

[0008] A personalized data calibration module: when used for the first time, the system guides the user to perform standardized actions, collects the user's physiological characteristic information, and at the same time records the corresponding impedance change data; through the recorded data, the system establishes the user's personal baseline data;

[0009] A data processing module: including steps of filtering, amplifying and analog-to-digital conversion, converting the collected analog signals into digital signals;

[0010] A cardiac function parameter calculation module: calculating cardiac function parameters according to the measured impedance change;

[0011] A user interface module: displaying real-time data and historical trends, supporting customized alarm settings and data export functions;

[0012] An AI intelligent analysis module: adopting machine learning algorithms, predicting the cardiac function state of patients according to historical data, and providing personalized treatment suggestions and early warning information;

[0013] The personalized data calibration module includes:

[0014] Individual difference compensation unit: Collect the physiological characteristic information of the user, and adjust the monitoring algorithm according to this information to compensate for the differences between individuals;

[0015] Environmental adaptation unit: Dynamically adjust the performance of the monitoring device based on environmental factors;

[0016] Behavior habit analysis unit: Analyze the daily living habits of the user, and adjust and optimize the monitoring plan according to the potential impact of the habits on cardiac function.

[0017] Preferably: The signal acquisition module includes:

[0018] Signal acquisition unit: Collect signals based on electrode patches;

[0019] Signal generation unit: Generate an alternating current signal of 1600 KHz and 7 μA;

[0020] Signal receiving unit: Receive the alternating current signal that has changed after being conducted through the patient's body, and convert it into raw data that can be processed;

[0021] Signal optimization unit: Preprocess the collected raw signals, including noise reduction and signal enhancement.

[0022] Preferably: The impedance measurement module includes:

[0023] Baseline impedance setting unit: Before starting the monitoring, measure the initial impedance value of the patient as the baseline;

[0024] Dynamic monitoring unit: Real-time measure the changes in chest impedance during the systole and diastole of the patient's heart, and capture the dynamic characteristics of the cardiovascular system;

[0025] Environmental correction unit: Monitor the potential impact of the surrounding environment on impedance measurement and perform correction;

[0026] When the impedance measurement module performs monitoring correction, it specifically includes the following steps:

[0027] S11: Integrate temperature, humidity, and electromagnetic field sensors in the monitoring device to monitor the environmental conditions in real time;

[0028] S12: Synchronously integrate the data collected by the environmental sensors with the cardiac function monitoring data;

[0029] S13: Establish a mathematical model for the impact of environmental factors on impedance measurement. The model can describe the specific impact of temperature, humidity, and electromagnetic interference on impedance readings. The specific formula is:

[0030] Z = β0 + β1·T + β2·H + β3·E + c

[0031] Where:

[0032] Z is the measured impedance value;

[0033] T is the temperature;

[0034] H is the relative humidity;

[0035] E is the electromagnetic interference level;

[0036] β0 is the intercept term, representing the base impedance value when all environmental factors are 0;

[0037] β1, β2, β3 are the coefficients of each environmental factor, respectively representing the expected change in impedance value when temperature, humidity, and electromagnetic interference change by one unit;

[0038] c is the error term, representing the impedance change caused by all other factors except these environmental factors;

[0039] S14: Automatically adjust the monitored impedance value according to the environmental factor influence model;

[0040] S15: Verify the accuracy of the corrected result through experiments.

[0041] Preferably: The personalized data calibration module collects the physiological characteristic information of the user to adjust the monitoring algorithm. The specific steps are as follows:

[0042] S21: Collect the physiological information of the user's height, weight, age, and gender;

[0043] S22: Adjust the parameters in the monitoring algorithm according to the collected physiological characteristics, including impedance index calibration and heart rate variability calculation;

[0044] S23: Establish an individualized monitoring model using the adjusted data;

[0045] S24: Continuously verify and optimize the individualized monitoring model by comparing the monitoring results with the clinical evaluation results. Specifically:

[0046] Y = β0 + β1·H + β2·W + β3·A + β4·G + c

[0047] Where:

[0048] Y is the cardiac function parameter;

[0049] H is the height;

[0050] W is the weight;

[0051] A is the age;

[0052] G is the gender;

[0053] β0, β1, β2, β3, β4 are model parameters, representing the influence magnitudes of various physiological characteristics on cardiac function parameters respectively;

[0054] c is the error term, representing other influencing factors not included in the model.

[0055] Preferably: The personalized data calibration module dynamically adjusts the performance of the monitoring device, and the specific steps are as follows:

[0056] S31: The monitoring device senses the influence of environmental factors such as ambient temperature and altitude in real time;

[0057] S32: Dynamically adjusts the signal processing flow according to the influence of environmental factors on physiological signals, including adaptive adjustment of filter parameters;

[0058] S33: Changes the operating parameters of the monitoring device according to environmental conditions.

[0059] Preferably: The personalized data calibration module analyzes the user's daily living habits to optimize the monitoring plan, and the specific steps are as follows:

[0060] S41: Collects the user's living habit information on diet, sleep and exercise;

[0061] S42: Analyzes the correlation between living habits and cardiac function monitoring results to find out health risk factors;

[0062] S43: Formulates a personalized cardiac function monitoring plan according to the user's living habits, including adjusting the monitoring time and frequency;

[0063] S44: Provides suggestions for improving the user's living habits;

[0064] S45: Continuously tracks the changes in the user's living habits and their impact on cardiac function monitoring results, and continuously optimizes the personalized monitoring plan.

[0065] Preferably: The data processing module includes:

[0066] Filtering unit: Uses digital filtering technology to remove noise other than physiological signals;

[0067] Amplification unit: Amplifies weak physiological signals;

[0068] Analog-to-digital conversion unit: Converts the processed analog signal into a digital signal with high precision.

[0069] Preferably: The AI intelligent analysis module includes:

[0070] Pattern recognition unit: Adopts machine learning algorithms to identify normal and abnormal cardiac function patterns;

[0071] Trend prediction unit: Based on the analysis of the long-term change trend of cardiac function parameters from historical data, predict the possible health risks in the future;

[0072] Personalized advice unit: Give personalized health management and treatment advice by combining the patient's living habits, historical conditions and monitoring data.

[0073] Preferably: The method by which the AI intelligent analysis module identifies normal and abnormal cardiac function patterns includes the following steps:

[0074] S51: Collect cardiac function monitoring data and perform preprocessing operations of cleaning and normalization;

[0075] S52: Extract key features from the preprocessed data, including statistical features, frequency features and time series features;

[0076] S53: Select a support vector machine or neural network algorithm and use the labeled normal and abnormal data to train the model;

[0077] S54: Evaluate the accuracy and generalization ability of the model through the cross-validation method;

[0078] S55: Apply the trained model to the actual monitoring data to identify normal and abnormal cardiac function patterns in real time.

[0079] Preferably: The method by which the AI intelligent analysis module analyzes the long-term change trend of cardiac function parameters includes the following steps:

[0080] S61: Track and collect the cardiac function parameter data of the patient in the long term;

[0081] S62: Use ARIMA to analyze the long-term trend, seasonal variation and periodic fluctuation in the data, specifically:

[0082]

[0083] Where:

[0084] L is the lag operator, L i X t = X t-i ;

[0085] X t is the observed value at time t;

[0086] d is the order of differencing, used to make the sequence stationary;

[0087] p is the order of the autoregressive part, is the autoregressive coefficient;

[0088] q is the order of the moving average part, θ iis the moving average coefficient;

[0089] c t is the white noise error term;

[0090] S63: Establish a prediction model based on the analysis results for inferring the possible future trends of cardiac function changes;

[0091] S64: Combine the output of the prediction model and clinical criteria to evaluate the probability of a patient developing a health risk in the future.

[0092] The beneficial effects of the present invention are reflected in:

[0093] 1. The present invention can complete the measurement without puncturing or invading the patient's body, reducing the risk of infection and other complications, and can comprehensively analyze the cardiac function health status. Combined with the AI intelligent report analysis system, it outputs a customized report according to different individual conditions, providing personalized treatment suggestions and warning information.

[0094] 2. Compared with traditional invasive methods, the non-invasive method of the present invention has a lower cost and is more suitable for the needs of long-term multiple detections; it can continuously monitor multiple parameters, detect cardiovascular events in a timely manner and take corresponding intervention measures.

[0095] 3. Through the cardiac function parameter calculation module of the present invention, parameters such as cardiac output, cardiac index, and stroke volume can be calculated and analyzed. These parameters directly reflect the blood supply ability of the heart; it is convenient for evaluation and analysis; by setting the impedance measurement module, the viscosity of the blood will affect the conduction of current in the body, thereby affecting the impedance measurement result, and the viscosity of the blood can be evaluated; the impedance measurement module can capture the dynamic characteristics of the cardiovascular system, including the dynamic changes of blood vessel dilation and constriction, which can reflect the elasticity of the blood vessels.

[0096] 4. The impedance measurement module of the present invention can real-time monitor the changes in chest impedance. For example, based on the detection of the blood flow state in the blood vessels, when the blood vessels are blocked, the blood flow state will change, thereby affecting the impedance measurement result; the personalized data calibration module collects the user's lifestyle information, including diet, sleep, and exercise, etc., in order to evaluate psychological emotions. BRIEF DESCRIPTION OF THE DRAWINGS

[0097] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts do not necessarily draw according to the actual scale.

[0098] Figure 1 is the flowchart of the impedance measurement module of the present invention for monitoring and calibration;

[0099] Figure 2 Flow chart for the personalized data calibration module of the present invention to collect users' physiological characteristic information and adjust the monitoring algorithm;

[0100] Figure 3 Flow chart for the AI intelligent analysis module of the present invention to analyze the long-term change trend of cardiac function parameters;

[0101] Figure 4 System architecture diagram of the present invention. Detailed implementation manners

[0102] The embodiments of the technical solution of the present invention will be described in detail below with reference to the accompanying drawings. The following embodiments are only used to illustrate the technical solution of the present invention more clearly, so they are only examples and cannot be used to limit the protection scope of the present invention.

[0103] It should be noted that unless otherwise specified, the technical terms or scientific terms used in this application should have the ordinary meaning understood by those skilled in the art to which the present invention belongs.

[0104] Embodiment 1:

[0105] A non-invasive hemodynamic cardiac function monitoring system, comprising:

[0106] Signal acquisition module: Using high-precision electrode patches, through specific positions on the neck and chest, conducting alternating current signals with a high frequency of 1600KHz and a low amplitude (7 microamperes);

[0107] Impedance measurement module: Using Ohm's law to calculate the dynamic impedance change of the chest; when current passes through the chest, the impedance change is mainly caused by the change in blood flow in the aorta; the impedance change is measured and recorded in real time; by setting the impedance measurement module, the blood viscosity will affect the conduction of current in the body, thereby affecting the impedance measurement result, and the blood viscosity can be evaluated; the impedance measurement module can capture the dynamic characteristics of the cardiovascular system, including the dynamic changes such as the dilation and contraction of blood vessels, which can reflect the elasticity of blood vessels;

[0108] Personalized data calibration module: When used for the first time, the system will guide the user to perform a series of standardized actions (such as deep breathing, slight exercise, etc.), and record the corresponding impedance change data at the same time; since everyone's physiological characteristics are different, through these data, the system establishes the user's personal baseline data and adjusts the algorithm parameters of subsequent measurements accordingly to ensure the accuracy of the results; the personalized data calibration module collects the user's living habit information, including diet, sleep, and exercise, etc., in order to evaluate psychological emotions;

[0109] Data processing module: It includes steps such as filtering, amplification, and analog-to-digital conversion, and converts the collected analog signals into digital signals;

[0110] Cardiac function parameter calculation module: Calculates cardiac function parameters based on the measured impedance changes. The specific calculation parameters include, but are not limited to, cardiac output (CO), cardiac index (CI), stroke volume (SV), etc.; The following calculation formulas can be specifically used:

[0111] Cardiac output (CO) = Heart rate (HR) × Stroke volume (SV)

[0112] Cardiac index (CI) = Cardiac output (CO) / Body surface area (BSA)

[0113] The stroke volume (SV) is calculated from the area under the impedance differential graph curve. The specific formula is: SV = ∫[dZ(t) / dt]dt, where Z(t) is the impedance value at time t;

[0114] User interface module: Displays real-time data and historical trends, and supports custom alarm settings and data export functions;

[0115] AI intelligent analysis module: Adopts machine learning algorithms to predict the patient's cardiac function status based on historical data, and provides personalized treatment suggestions and warning information.

[0116] Among them, the signal acquisition module includes:

[0117] Signal acquisition unit: Collects signals based on electrode patches;

[0118] Signal generation unit: Generates a 1600KHz high-frequency, low-amplitude alternating current signal;

[0119] Signal receiving unit: Receives the alternating current signal that has changed after being conducted through the patient's body, and converts it into raw data that can be processed;

[0120] Signal optimization unit: Preprocesses the collected raw signals, including noise reduction and signal enhancement.

[0121] Among them, the impedance measurement module includes:

[0122] Baseline impedance setting unit: Before starting the monitoring, measures the patient's initial impedance value as the baseline for subsequent measurement comparison to improve the accuracy of relative measurement;

[0123] Dynamic monitoring unit: Real-time measures the changes in chest impedance during the patient's cardiac systole and diastole, and captures the dynamic characteristics of the cardiovascular system;

[0124] Environmental correction unit: Monitor the potential impact of the surrounding environment (such as electromagnetic interference, temperature, and humidity changes) on impedance measurement and perform correction to ensure the accuracy of the results;

[0125] When the impedance measurement module performs monitoring and correction, it specifically includes the following steps:

[0126] S11: Integrate temperature, humidity, and electromagnetic field sensors in the monitoring device to monitor environmental conditions in real time;

[0127] S12: Synchronize and integrate the data collected by the environmental sensors with the cardiac function monitoring data for joint analysis;

[0128] S13: Establish a mathematical model of the impact of environmental factors on impedance measurement. The model can describe the specific impact of temperature, humidity, and electromagnetic interference on impedance readings. The specific formula is:

[0129] Z = β0 + β1·T + β2·H + β3·E + c

[0130] Where:

[0131] Z is the measured impedance value;

[0132] T is the temperature;

[0133] H is the relative humidity;

[0134] E is the electromagnetic interference level;

[0135] β0 is the intercept term, representing the base impedance value when all environmental factors are 0;

[0136] β1, β2, β3 are the coefficients of each environmental factor, respectively representing the expected change in impedance value when temperature, humidity, and electromagnetic interference change by one unit;

[0137] c is the error term, representing the impedance change caused by all other factors except these environmental factors;

[0138] S14: Automatically adjust the measured impedance value according to the environmental factor impact model;

[0139] S15: Verify the accuracy of the corrected results through experiments.

[0140] Among them, the personalized data calibration module includes:

[0141] Individual difference compensation unit: Collect the physiological characteristic information of the user (such as height, weight, age, gender, etc.), and adjust the monitoring algorithm according to this information to compensate for the differences between individuals;

[0142] Environmental adaptation unit: Considering the influence of environmental factors (such as temperature, altitude, etc.) on physiological signals, dynamically adjust the performance of the monitoring device to adapt to different environmental conditions;

[0143] Behavior habit analysis unit: Analyze the user's daily living habits (such as diet, sleep, exercise, etc.), and adjust and optimize the monitoring plan according to the potential impact of the habits on cardiac function.

[0144] Among them, the personalized data calibration module collects the user's physiological characteristic information to adjust the monitoring algorithm, and the specific steps are as follows:

[0145] S21: Collect the user's physiological information such as height, weight, age, gender, etc.;

[0146] S22: According to the collected physiological characteristics, adjust the parameters in the monitoring algorithm, including impedance index calibration, heart rate variability calculation, etc.;

[0147] S23: Use the adjusted data to establish an individualized monitoring model;

[0148] S24: By comparing the monitoring results with the clinical evaluation results, continuously verify and optimize the individualized monitoring model, specifically:

[0149] Y = β0 + β1·H + β2·W + β3·A + β4·G + c

[0150] Among them:

[0151] Y is a cardiac function parameter (such as cardiac output);

[0152] H is height;

[0153] W is weight;

[0154] A is age;

[0155] G is gender (which can be used as a dummy variable, for example, 0 for male and 1 for female);

[0156] β0, β1, β2, β3, β4 are model parameters, respectively representing the influence magnitudes of each physiological characteristic on the cardiac function parameter;

[0157] c is the error term, representing other influencing factors not included in the model.

[0158] Among them, the personalized data calibration module dynamically adjusts the performance of the monitoring device, and the specific steps are as follows:

[0159] S31: The monitoring device senses the influence of environmental factors such as ambient temperature and altitude in real time;

[0160] S32: According to the influence of environmental factors on physiological signals, dynamically adjust the signal processing flow, including adaptive adjustment of filter parameters;

[0161] S33: Change the operating parameters of the monitoring device according to environmental conditions.

[0162] Among them, the personalized data calibration module analyzes the user's daily living habits to optimize the monitoring plan. The specific steps are as follows:

[0163] S41: Collect information on the user's living habits such as diet, sleep, and exercise;

[0164] S42: Analyze the correlation between living habits and the results of cardiac function monitoring, and identify health risk factors;

[0165] S43: Develop a personalized cardiac function monitoring plan according to the user's living habits, such as adjusting the monitoring time and frequency;

[0166] S44: Provide suggestions for improving the user's living habits to help optimize their lifestyle and thus improve the cardiac function health status;

[0167] S45: Continuously track the changes in the user's living habits and their impact on the results of cardiac function monitoring, and continuously optimize the personalized monitoring plan.

[0168] Among them, the data processing module includes:

[0169] Filtering unit: Use digital filtering technology to remove noise other than physiological signals, such as power line noise, motion artifacts, etc.;

[0170] Amplification unit: Amplify weak physiological signals to facilitate the extraction of useful information;

[0171] Analog-to-digital conversion unit: Convert the processed analog signal into a digital signal with high precision.

[0172] Among them, the cardiac function parameter calculation module includes:

[0173] Algorithm selection unit: Select a suitable algorithm model to calculate cardiac function parameters according to the specific conditions of different patients (such as age, gender, weight, etc.);

[0174] Statistical analysis unit: Conduct statistical analysis on multiple measurement results, calculate statistical parameters such as mean and standard deviation, and evaluate the stability and reliability of the results;

[0175] Result output unit: Display the calculated cardiac function parameters in the form of charts or digital formats.

[0176] Among them, the AI intelligent analysis module includes:

[0177] Pattern recognition unit: Use machine learning algorithms to identify normal and abnormal cardiac function patterns to provide a reference for diagnosis;

[0178] Trend prediction unit: Based on the analysis of the long-term change trend of cardiac function parameters from historical data, predict the possible future health risks;

[0179] Personalized advice unit: Give personalized health management and treatment advice by combining the patient's living habits, historical conditions and monitoring data.

[0180] Among them, the way for the AI intelligent analysis module to identify normal and abnormal cardiac function patterns includes the following steps:

[0181] S51: Collect cardiac function monitoring data and perform preprocessing operations such as cleaning and normalization;

[0182] S52: Extract key features from the preprocessed data, including statistical features, frequency features and time series features, etc.;

[0183] S53: Select a support vector machine or neural network algorithm and use the labeled normal and abnormal data to train the model;

[0184] S54: Evaluate the accuracy and generalization ability of the model through methods such as cross-validation;

[0185] S55: Apply the trained model to the actual monitoring data to identify normal and abnormal cardiac function patterns in real time.

[0186] Among them, the steps for the AI intelligent analysis module to analyze the long-term change trend of cardiac function parameters are as follows:

[0187] S61: Track and collect the cardiac function parameter data of patients in the long term;

[0188] S62: Use ARIMA to analyze the long-term trend, seasonal variation and periodic fluctuation in the data, specifically:

[0189]

[0190] Among them:

[0191] L is the lag operator, L i X t = X t-i ;

[0192] X t is the observed value at time t;

[0193] d is the order of differencing, used to make the sequence stationary;

[0194] p is the order of the autoregressive part, φ i is the autoregressive coefficient;

[0195] q is the order of the moving average part, θi is the moving average coefficient;

[0196] c t is the white noise error term;

[0197] S63: Establish a prediction model based on the analysis results for inferring the possible future trends of cardiac function changes;

[0198] S64: Combine the output of the prediction model and clinical criteria to evaluate the probability of the patient having future health risks.

[0199] Finally, it should be noted that: The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: They can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered by the scope of the claims and the description of the present invention.

Claims

1. A non-invasive hemodynamic cardiac function monitoring system, characterized in that: Including: Signal acquisition module: Using electrode patches to conduct through alternating current signals; Impedance measurement module: Calculating the dynamic impedance changes of the chest; Measuring and recording impedance changes in real time; Personalized data calibration module: When used for the first time, the system guides the user to perform standardized actions, collects the user's physiological characteristic information, and simultaneously records the corresponding impedance change data; Based on the recorded data, the system establishes the user's personal baseline data; Data processing module: Including steps of filtering, amplification, and analog-to-digital conversion, converting the collected analog signals into digital signals; Cardiac function parameter calculation module: Calculating cardiac function parameters based on the measured impedance changes; User interface module: Displaying real-time data and historical trends, supporting custom alarm settings and data export functions; AI intelligent analysis module: Using machine learning algorithms to predict the patient's cardiac function status based on historical data, providing personalized treatment suggestions and warning information; The personalized data calibration module includes: Individual difference compensation unit: Collecting the user's physiological characteristic information and adjusting the monitoring algorithm according to this information to compensate for differences between individuals; Environment adaptation unit: Dynamically adjusting the performance of the monitoring device based on environmental factors; Behavior habit analysis unit: Analyzing the user's daily living habits and adjusting and optimizing the monitoring plan according to the potential impact of the habits on cardiac function.

2. The non-invasive hemodynamic cardiac function monitoring system according to claim 1, wherein: The signal acquisition module includes: Signal acquisition unit: Collecting signals based on electrode patches; Signal generation unit: Generating an alternating current signal of 1600KHz and 7 microamps; Signal receiving unit: Receiving the alternating current signal that has changed after being conducted through the patient's body and converting it into raw data for processing; Signal optimization unit: Preprocessing the collected raw signals, including noise reduction and signal enhancement.

3. The non-invasive hemodynamic cardiac function monitoring system according to claim 1, wherein: The impedance measurement module includes: Baseline impedance setting unit: Measuring the patient's initial impedance value as the baseline before starting monitoring; Dynamic monitoring unit: Measuring in real time the changes in chest impedance during the patient's cardiac systole and diastole, capturing the dynamic characteristics of the cardiovascular system; Environment correction unit: Monitoring the potential impact of the surrounding environment on impedance measurement and performing correction; When the impedance measurement module performs monitoring correction, it specifically includes the following steps: S11: Integrating temperature, humidity, and electromagnetic field sensors in the monitoring device to monitor environmental conditions in real time; S12: Synchronously integrating the data collected by the environmental sensors with the cardiac function monitoring data; S13: Establishing a mathematical model of the impact of environmental factors on impedance measurement, and the model can describe the specific impact of temperature, humidity, and electromagnetic interference on impedance readings. The specific formula is: Z = β0 + β1·T + β2·H + β3·E + c Where: Z is the measured impedance value; T is the temperature; H is the relative humidity; E is the electromagnetic interference level; β0 is the intercept term, representing the basic impedance value when all environmental factors are 0; β1, β2, β3 are the coefficients of each environmental factor, respectively representing the expected change in impedance value when the temperature, humidity, and electromagnetic interference change by one unit; c is the error term, representing the impedance change caused by all other factors except these environmental factors; S14: Automatically adjust the monitored impedance value according to the environmental factor influence model; S15: Verify the accuracy of the corrected result through experiments.

4. The non-invasive hemodynamic cardiac function monitoring system according to claim 1, wherein: The personalized data calibration module collects the physiological characteristic information of the user to adjust the monitoring algorithm. The specific steps are as follows: S21: Collect the physiological information of the user's height, weight, age, and gender; S22: Adjust the parameters in the monitoring algorithm according to the collected physiological characteristics, including impedance index calibration and heart rate variability calculation; S23: Establish an individualized monitoring model using the adjusted data; S24: Continuously verify and optimize the individualized monitoring model by comparing the monitoring results with the clinical evaluation results. Specifically: Y = β0 + β1·H + β2·W + β3·A + β4·G + c Where: Y is the cardiac function parameter; H is the height; W is the weight; A is the age; G is the gender; β0, β1, β2, β3, β4 are model parameters, respectively representing the influence magnitudes of each physiological characteristic on the cardiac function parameter; c is the error term, representing other influencing factors not included in the model.

5. An non-invasive hemodynamic cardiac function monitoring system according to claim 1, characterized in that: The personalized data calibration module dynamically adjusts the performance of the monitoring device. The specific steps are as follows: S31: The monitoring device senses the influence of environmental factors such as ambient temperature and altitude in real time; S32: Dynamically adjust the signal processing flow according to the influence of environmental factors on physiological signals, including adaptive adjustment of filter parameters; S33: Change the operating parameters of the monitoring device according to environmental conditions.

6. The non-invasive hemodynamic cardiac function monitoring system according to claim 1, characterized in that: The personalized data calibration module analyzes the user's daily living habits to optimize the monitoring plan. The specific steps are as follows: S41: Collect the living habit information of the user's diet, sleep, and exercise; S42: Analyze the association between living habits and cardiac function monitoring results to find out health risk factors; S43: Develop an individualized cardiac function monitoring plan according to the user's living habits, including adjusting the monitoring time and frequency; S44: Provide suggestions for improving the user's living habits; S45: Continuously track the changes in the user's living habits and their impact on cardiac function monitoring results, and continuously optimize the individualized monitoring plan.

7. An non-invasive hemodynamic cardiac function monitoring system according to claim 1, characterized in that: The data processing module includes: Filtering unit: Use digital filtering technology to remove the noise other than physiological signals; Amplification unit: Amplify the weak physiological signals; Analog-to-digital conversion unit: Convert the processed analog signal into a digital signal with high precision.

8. The non-invasive hemodynamic cardiac function monitoring system according to claim 1, wherein: The AI intelligent analysis module includes: Pattern recognition unit: Use machine learning algorithms to identify normal and abnormal cardiac function patterns; Trend prediction unit: Analyze the long-term change trend of cardiac function parameters based on historical data to predict possible future health risks; Personalized advice unit: Give personalized health management and treatment advice in combination with the patient's living habits, historical condition, and monitoring data.

9. An non-invasive hemodynamic cardiac function monitoring system according to claim 8, characterized in that: The ways for the AI intelligent analysis module to identify normal and abnormal cardiac function patterns include the following steps: S51: Collect cardiac function monitoring data and perform preprocessing operations such as cleaning and normalization; S52: Extract key features from the preprocessed data, including statistical features, frequency features, and time series features; S53: Select a support vector machine or neural network algorithm, and use the labeled normal and abnormal data to train the model; S54: Evaluate the accuracy and generalization ability of the model through the cross-validation method; S55: Apply the trained model to the actual monitoring data to identify normal and abnormal cardiac function patterns in real time.

10. An non-invasive hemodynamic cardiac function monitoring system according to claim 9, characterized in that: The AI intelligent analysis module analyzes the long-term change trend of cardiac function parameters, including the following steps: S61: Long-term track and collect the cardiac function parameter data of patients; S62: Use ARIMA to analyze the long-term trend, seasonal variation and periodic fluctuation in the data, specifically: Where: L is the lag operator, L i X t = X t-i ; X t is the observed value at time t; d is the order of differencing, which is used to make the sequence stationary; p is the order of the autoregressive part, are the autoregressive coefficients; q is the order of the moving average part, and θ i is the moving average coefficient; c t is a white noise error term; S63: Establish a prediction model based on the analysis results to infer the possible future change trend of cardiac function; S64: Combine the output of the prediction model and clinical criteria to evaluate the probability of the patient having a health risk in the future.

Images