A multi-modal cardio-cerebral hemodynamic monitoring method and device

Abstract

The present application relates to a kind of multimodal cardio-cerebral hemodynamics monitoring method and device, belong to medical equipment technical field.The present application utilizes the correlation between human cardiac output, blood pressure, intracranial pressure and cerebral perfusion pressure, obtains brain absorbance information and cerebral artery pulse wave information based on near-infrared spectroscopy technology, obtains cardiac output information and cuffless blood pressure information based on thoracic impedance method, and based on the physiological signals obtained by the two methods, fusion processing is carried out, to obtain multimodal signal, and then construct non-invasive intracranial pressure, cardiac output, blood pressure and cerebral perfusion pressure non-invasive monitoring model, realize the continuous non-invasive monitoring of reflecting human cardio-cerebral hemodynamics parameters.The present application can effectively reveal the mechanism of cardio-cerebral hemodynamics interaction by the fusion application of multimodal signal, to provide a more effective, safe and non-invasive monitoring means for clinic.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of medical equipment, and relates to a multi-modal cardio-cerebral hemodynamic monitoring method and device. BACKGROUND

[0002] Cerebral perfusion pressure (CPP) is a key indicator of cerebral hemodynamic status, representing the effective pressure that drives cerebral blood flow. Its formula is CPP = MAP - ICP (mean arterial pressure minus intracranial pressure). Under normal physiological conditions, CPP needs to be maintained within an appropriate range to ensure that the brain tissue receives adequate blood supply and oxygen delivery, thereby maintaining the normal function of brain cells. The subtle changes in this pressure balance reflect the complex interaction between the cardiovascular system and the cerebral vasculature. After a brain injury, the increase in ICP leads to an increase in cerebral vascular resistance, affecting cerebral perfusion and reducing cerebral blood flow, and the blood flow velocity can change to some extent, showing changes in related parameters of cerebral hemodynamics. Hemodynamics is a science that studies the movement characteristics and regularities of blood and its components in the body. Its main monitoring indicators include blood pressure, central venous pressure, oxygen delivery, heart rate, and cardiac output. According to the laws of physics, combined with physiological and pathophysiological concepts, the regularity of blood movement in the circulatory system is quantitatively, dynamically, and continuously measured and analyzed, with the purpose of understanding the development of the disease and guiding clinical treatment. Through hemodynamic monitoring, medical professionals can obtain real-time information about key physiological parameters such as heart pumping function, vascular resistance, and blood volume status, which is of great significance for diagnosing and managing cardiovascular diseases, shock, heart failure, postoperative recovery, and other conditions.

[0003] In the human physiological system, the correlation between cardiopulmonary blood flow and cerebral middle cerebral artery blood flow, as well as the interaction between cardiopulmonary vessels and cerebral vessels, constitutes a highly coordinated hemodynamic network. Understanding these correlations is of great significance for developing multi-modal physiological signal-based cardio-cerebral hemodynamic monitoring and evaluation methods.

[0004] The heart is the core of the circulatory system, pumping blood through contraction and relaxation to provide oxygen and nutrients to all tissues and organs in the body while removing metabolic waste. Cardiac output (CO) is the amount of blood pumped by the heart per minute, and is a key indicator of heart function and hemodynamic status. The size of cardiac output is affected by heart rate and stroke volume (SV), where stroke volume depends on the contractility of the myocardium, preload, and afterload.

[0005] Blood is pumped from the heart through the aorta into the systemic circulation. The aorta is the main channel for cardiac output, and blood passes through the aortic arch into the head and upper limbs. The blood supply to the brain is mainly from two pairs of arterial systems: the internal carotid artery (Internal Carotid Artery) and the vertebral artery (Vertebral Artery), which form the basilar arterial circle at the base of the brain, ensuring that the brain can still obtain blood supply when different arteries are damaged. The internal carotid artery is divided into the anterior cerebral artery, the middle cerebral artery, the anterior choroidal artery and the posterior communicating artery after entering the intracranial. Among them, the middle cerebral artery (Middle Cerebral Artery, MCA) is an important blood vessel that supplies the front and middle parts of the brain, and its blood flow is crucial for maintaining brain function. It is one of the main arteries supplying the brain, responsible for supplying most of the areas on the lateral surface of the brain, including the frontal lobe, parietal lobe and part of the temporal lobe. The effect of increased ICP on cerebral blood flow velocity is most obvious in the middle cerebral artery (Middle Cerebral Artery, MCA), which is the direct continuation of the internal carotid artery and is the largest artery supplying the cerebral hemisphere, supplying about 80% of the blood flow required by the cerebral hemisphere.

[0006] In general, the function of the heart and lungs directly affects the oxygen supply to the brain, and any dysfunction of the heart and lungs can lead to insufficient blood supply or oxygenation to the brain, which in turn affects brain function. The heart and lung blood flow and the middle cerebral artery blood flow, as well as the association of the heart and lung blood vessels and the brain blood vessels, is a highly coordinated system. By monitoring physiological parameters such as cardiac output, blood pressure, cerebral blood flow, etc., the state of cardio-cerebral hemodynamics can be better understood and evaluated. However, there is currently no method and device for integrated monitoring and evaluation of cardio-cerebral hemodynamics. SUMMARY

[0007] Therefore, the purpose of the present application is to provide a multi-modal cardio-cerebral hemodynamic monitoring method and device, which considers the cardio-cerebrovascular system as a whole, and realizes comprehensive monitoring of heart and lung function and brain function through non-invasive means (non-invasive continuous monitoring of indicators such as cardiac output, blood pressure, intracranial pressure and cerebral perfusion pressure can be achieved simultaneously), providing important physiological information support for clinical diagnosis and treatment.

[0008] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0009] Scheme 1:

[0010] A multi-modal cardio-cerebral hemodynamic monitoring method, specifically comprising the following steps:

[0011] S1: obtaining brain absorbance information and brain pulse wave information based on near-infrared light method, and obtaining cardiac output information and cuffless blood pressure information based on thoracic impedance method, and then pre-processing and feature extraction of the obtained information;

[0012] S2: Based on the absorbance information and brain pulse wave characteristics, a non-invasive intracranial pressure prediction model M1 is constructed to obtain preliminary non-invasive intracranial pressure prediction results; based on the chest impedance signal characteristic information and the electrocardiogram signal characteristic information, a non-invasive cardiac output and cuff-free blood pressure prediction model M2 is constructed to obtain preliminary non-invasive cardiac output and blood pressure prediction results;

[0013] S3: The physiological information features obtained in step S1 based on the near-infrared light method and the thoracic impedance method are fused and processed to obtain multimodal physiological information; based on the preliminary non-invasive prediction results of intracranial pressure, cardiac output and blood pressure obtained in step S2 and the multimodal physiological information, a non-invasive comprehensive monitoring model M3 of intracranial pressure and cerebral perfusion pressure is constructed to obtain accurate prediction results of intracranial pressure and blood pressure, and then obtain non-invasive prediction results of cerebral perfusion pressure, thereby realizing continuous non-invasive monitoring that synchronously reflects the human cardiocerebral hemodynamic state.

[0014] Furthermore, in step S1, the near-infrared light method utilizes a multi-wavelength sensing monitoring probe to monitor the absorbance changes of the frontal lobe of the brain and the pulse wave signal of the middle cerebral artery.

[0015] Furthermore, in step S1, the thoracic impedance method utilizes a human cardiac hemodynamic parameter monitoring method to obtain a physiological signal reflecting changes in human cardiac hemodynamics.

[0016] Furthermore, in step S2, a non-invasive intracranial pressure prediction model M1 is constructed, which specifically includes the following steps:

[0017] S201: Using a multi-wavelength sensing monitoring probe, obtain n wavelengths λ1, λ2, ..., λ n Absorbance information at the frontal lobe of the brain under the light source: I={i λ1 ,i λ2 ,...,i λ n};

[0018] S202: Using the sensor monitoring probe to obtain the pulse wave time domain signal PPG of the middle cerebral artery, and after preprocessing it, obtain the pulse wave characteristic parameters related to the changes in intracranial pressure and hemodynamics of the brain: P = {p1, p2, ..., p m}, where m represents the number of pulse wave features after preprocessing;

[0019] S203: Construct a non-invasive intracranial pressure prediction model M1 to obtain non-invasive prediction results of intracranial pressure and mean cerebral arterial pressure: M1(ICP0, MAP0) = f(I, P, PPG), where ICP0 represents the preliminary predicted intracranial pressure and MAP0 represents the preliminary predicted mean cerebral arterial pressure.

[0020] Further, in step S2, a non-invasive prediction model M2 of cardiac output and blood pressure is constructed, specifically including the following steps:

[0021] S211: Obtain physiological signals reflecting changes in human cardiac hemodynamics, including thoracic impedance change signal, thoracic impedance change differential signal, baseline impedance signal, electrocardiogram signal and pulse wave signal, and preprocess them;

[0022] S212: Extract characteristic parameters related to cardiac output and hemodynamic changes from the preprocessed signals, and construct a non-invasive prediction model M21 (CO) = f (p1, p2, p3,..., p k ), where k represents the number of characteristic parameters related to cardiac output and hemodynamic changes, and CO represents the predicted cardiac output; the characteristic parameters related to cardiac output and hemodynamic changes include cycle information, strength information, electrical-mechanical conduction information and energy information of thoracic impedance change;

[0023] S213: Extract feature transfer time information of cardiac activity reflected in electrocardiogram signal to thoracic impedance change signal, electrocardiogram signal to pulse wave signal, thoracic impedance signal to pulse wave signal, time, amplitude and energy information of characteristic changes of thoracic impedance change signal and pulse wave signal, form parameter sets of time T, assignment A and energy P, and based on the three parameter sets, construct a non-tubular blood pressure prediction model M22 (SBP, DBP) = f (T, A, P), where SBP represents systolic blood pressure and DBP represents diastolic blood pressure;

[0024] S214: The non-invasive prediction models M21 and M22 obtained from steps S212 and S213 jointly constitute the non-invasive prediction model M2 based on thoracic impedance method M2 = (M21, M22).

[0025] Further, in step S3, a non-invasive comprehensive monitoring model M3 of cardiac and cerebral hemodynamics is constructed, specifically including the following steps:

[0026] S301: Fuse the physiological information features obtained based on near-infrared light method and thoracic impedance method to obtain multi-modal physiological information I fusion ;

[0027] S302: Use the correlation between changes in cardiac and cerebral hemodynamics, intracranial pressure, blood pressure and cardiac output, and based on the intracranial pressure values, cerebral hemodynamic characteristics, cardiac output, blood pressure and cardiac hemodynamic characteristics obtained from prediction models M1 and M2, add multi-modal physiological information I fusion to the non-invasive comprehensive monitoring model M3 of cardiac and cerebral hemodynamics, and construct a non-invasive prediction model M31 (MAP, ICP) = f (I fusion, ICP0, MAP0, CO, SBP, DBP), so that the outputs of the models M1 and M2 influence each other, and the output accuracy of cardiac output, blood pressure and intracranial pressure is improved; wherein, MAP represents the mean arterial pressure predicted by the model M31; ICP represents the intracranial pressure predicted by the model M31;

[0028] S303: In the non-invasive comprehensive monitoring model M3 of cardio-cerebral hemodynamics, based on the result of step S302, a non-invasive prediction model M32 (CPP) of cerebral perfusion pressure CPP is constructed, i.e. CPP = f (CO, MAP, ICP, I fusion ).

[0029] S304: The non-invasive prediction models M31 and M32 obtained from steps S302 and S303 jointly constitute the non-invasive comprehensive monitoring model M3 = (M31, M32) of intracranial pressure and cerebral perfusion pressure.

[0030] Further, in step S301, the fusion processing is specifically based on the correlation of cardio-cerebral hemodynamic parameters, and uses a time synchronization mechanism and a weighted fusion algorithm to combine the near-infrared spectroscopy signal and the thoracic impedance signal to form multi-modal physiological information that can comprehensively reflect the state of cardio-cerebral hemodynamics.

[0031] Scheme 2: A multi-modal cardio-cerebral hemodynamic monitoring device: comprising a signal acquisition module, a signal processing module, a data fusion module, a non-invasive monitoring model module and a display and alarm module; the signal acquisition module comprises a near-infrared spectroscopy sensor and a thoracic impedance electrode.

[0032] The near-infrared spectroscopy sensor and the thoracic impedance electrode are used to be connected to the patient's body surface and are responsible for acquiring multi-modal physiological signals of the human body; the signal processing module performs denoising, filtering and feature extraction on the acquired signals; the data fusion module fuses physiological data from different signal sources; the non-invasive monitoring model module integrates the multi-modal cardio-cerebral hemodynamic monitoring method of scheme 1 and generates non-invasive monitoring results based on the fused data; the display and alarm module is used to present the numerical values of the non-invasive monitoring results, i.e. cardiac output, blood pressure, intracranial pressure and cerebral perfusion pressure, in real time, and automatically triggers an alarm when the parameters exceed the safe range.

[0033] First, the near-infrared spectroscopy sensor and the thoracic impedance electrode are correctly connected to the patient's body surface; after starting the device, the signal acquisition module begins to acquire physiological signals, and the signal processing unit performs preprocessing and feature extraction on the acquired signals; then, the data fusion module fuses the processed signals, and finally the non-invasive monitoring model module generates non-invasive monitoring results; the monitoring model module integrates the multi-modal cardio-cerebral hemodynamic monitoring method in scheme 1; the display and alarm module presents the numerical values and change trend waveforms of cardiac output, blood pressure, intracranial pressure and cerebral perfusion pressure in real time, and automatically triggers an alarm when the parameters exceed the safe range.

[0034] The beneficial effects of the present application are:

[0035] (1) The present application fully considers the individual difference information of the measured person and the correlation and integrity of the cardiovascular and cerebrovascular system, and obtains multi-modal physiological signals reflecting the hemodynamic state of the human body cardiovascular and cerebrovascular system through the comprehensive application of near-infrared spectroscopy technology and thoracic impedance technology.

[0036] (2) Based on the obtained multi-modal physiological signals, the present application constructs a multi-level non-invasive prediction model of different hemodynamic indicators, which helps to improve the non-invasive monitoring accuracy of different cardiac and cerebral hemodynamic indicators while realizing the overall evaluation of cardiac and cerebral hemodynamic indicators, and helps to make more accurate diagnosis and treatment decisions in clinical practice.

[0037] (3) The present application improves the accuracy and real-time performance of monitoring: by fusing multi-modal physiological signals, the device of the present application can accurately reflect the changes of cardiac and cerebral hemodynamic parameters and provide key physiological data to medical staff in real time. Compared with the traditional single signal monitoring method, the multi-modal fusion method significantly improves the accuracy of monitoring and reduces the monitoring errors caused by single signal interference or loss.

[0038] (4) The present application reduces the pain and monitoring risk of patients: traditional invasive monitoring methods often require the insertion of catheters or sensors, which not only increases the risk of infection and complications, but also brings discomfort and pain to patients. The present application monitors in a non-invasive way, completely avoiding the risk of invasive operation, providing patients with a more comfortable and safe monitoring experience, especially suitable for critically ill patients who need long-term continuous monitoring.

[0039] (5) The present application provides more quantifiable physiological parameters: the device of the present application can not only monitor cardiac output, blood pressure and other cardiovascular hemodynamic parameters, but also provide important cerebral hemodynamic indicators such as mean arterial pressure, intracranial pressure and cerebral perfusion pressure. The provision of these parameters enables doctors to make a more comprehensive assessment and diagnosis of the cardiac and cerebral blood flow state of patients, so as to develop a more precise treatment plan.

[0040] Other advantages, objects, and features of the present application will be apparent from the following specification, and in some respects, as the pertinent art will be construed from the examination of the following specification, or can be learned from the practice of the present application. The objects and other advantages of the present application can be realized and attained by the means recited in the following description. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to make the purpose, technical scheme and advantages of the present application more clear, the preferred detailed description of the present application will be combined with the drawings as follows, in which:

[0042] Figure 1 A multi-modal cardio-cerebral hemodynamic monitoring flowchart is provided for the present application.

[0043] Figure 2 A cardio-cerebral hemodynamic signal acquisition hardware implementation is provided for the present application.

[0044] Figure 3 A multi-modal physiological signal fusion software implementation is provided for the present application.

[0045] Figure 4 A multi-level cardio-cerebral hemodynamic parameter non-invasive prediction model is provided for the present application.

[0046] Figure 5 A cardio-cerebral hemodynamic non-invasive monitoring device block diagram is provided for the present application. DETAILED DESCRIPTION

[0047] The present application is described below by way of specific embodiments, and those skilled in the art can easily understand other advantages and effects of the present application from the disclosure. The present application can also be implemented or applied by different specific embodiments, and various modifications or changes can be made to the details in the specification based on different views and applications without departing from the spirit of the present application. It should be noted that the drawings provided in the following embodiments only illustrate the basic concept of the present application in a schematic manner, and the following embodiments and features in the embodiments can be combined with each other without conflict.

[0048] Referring to Figures 1-5 , the present application designs a multi-modal cardio-cerebral hemodynamic monitoring method and device, and the purpose is to realize continuous monitoring of cardio-cerebral hemodynamic parameters such as cardiac output, blood pressure, intracranial pressure, and cerebral perfusion pressure by non-invasive means.

[0049] The method of the present application utilizes the correlation between human cardiac output, blood pressure, intracranial pressure, and cerebral perfusion pressure, obtains brain absorbance information and middle cerebral artery pulse wave information based on near-infrared spectroscopy technology, obtains cardiac output information and cuffless blood pressure information based on thoracic impedance method, and based on the physiological signals obtained by the two methods, performs fusion processing to obtain multi-modal signals, and further constructs a non-invasive intracranial pressure, cardiac output, blood pressure, and cerebral perfusion pressure non-invasive monitoring model, to realize continuous non-invasive monitoring of human cardio-cerebral hemodynamic parameters.

[0050] As Figure 1 shown, the device of the present application obtains human physiological signals by combining near-infrared spectroscopy technology and thoracic impedance technology, and constructs a multi-modal non-invasive monitoring model based on these signals, thereby providing an effective clinical monitoring method.

[0051] In the implementation process, the device of the application mainly consists of a signal acquisition module, a signal processing module, a data fusion module, a non-invasive monitoring model module, and a display and alarm module, as shown in Figure 5 The signal acquisition module is responsible for acquiring the multi-modal physiological signals of the human body, the signal processing unit performs denoising, filtering and feature extraction on the acquired signals, the data fusion module fuses the physiological data from different signal sources, the non-invasive monitoring model module generates non-invasive monitoring results based on the fused data, and the display and alarm module is used for real-time display of the monitoring results and alarm when necessary.

[0052] 1. Signal acquisition (as shown in Figure 2

[0053] 1) Acquisition of near-infrared spectrum signals

[0054] The application adopts near-infrared spectrum technology to acquire the absorbance changes of the frontal lobe of the brain and the pulse wave information of the middle cerebral artery through a multi-wavelength sensing monitoring probe. The probe is configured with multiple near-infrared light sources made of flexible material to closely adhere to the scalp and reduce motion artifacts. The probe also integrates a high-sensitivity photodiode for receiving the reflected near-infrared light signals. The sensor probe is arranged on the frontal lobe and temporal window of the patient respectively, and the multi-wavelength light beams penetrate the scalp, part of the light is absorbed by the brain tissue, and the unabsorbed light is received by the probe and converted into an electrical signal. After the photoelectric signal is amplified by the preamplifier circuit, it enters the analog-to-digital converter (ADC) for digitization, and the digitized signal is input into the embedded processor for subsequent signal processing and feature extraction to obtain absorbance data and pulse wave signals reflecting the hemodynamic state of the brain.

[0055] 2) Acquisition of thoracic impedance signals

[0056] The thoracic impedance measurement adopts a four-electrode configuration, in which two pairs of electrodes are used to apply a constant weak alternating current and measure the voltage difference respectively. By measuring the voltage difference and the known current value, the impedance change of the thoracic cavity can be calculated. The module also includes a high-precision amplifier and a filter for amplifying and filtering noise in the measurement signal. After processing, the signal also enters the ADC for digital processing. Because the impedance changes of blood and other tissues during the contraction and relaxation of the heart have regularity, the cardiac output and cuffless blood pressure information can be extracted by analyzing these changes. The signal processing unit filters and extracts features from these collected impedance signals to ensure the accuracy and effectiveness of the signals.

[0057] 2. Signal processing and data fusion (as shown in Figure 3

[0058] 1) Signal preprocessing and feature extraction

[0059] ​​The signal processing module preprocesses the signals collected from near-infrared spectroscopy and transthoracic impedance, primarily including denoising, baseline correction, and feature extraction. For near-infrared spectroscopy signals, the module primarily extracts waveform features related to absorbance and pulse wave; for transthoracic impedance signals, it primarily extracts features related to cardiac output and blood pressure. Furthermore, relevant physiological parameter features are extracted from these preprocessed signals. For example, pulse wave amplitude, rise time, and absorbance variation in near-infrared spectroscopy signals; and ECG R-wave spacing and impedance variation in transthoracic impedance signals.

[0060] 2) Multimodal data fusion

[0061] In the data fusion module, signals from different physiological sources are fused. Specifically, using a time synchronization mechanism and a weighted fusion algorithm, the near-infrared spectral signal and the chest impedance signal characteristics are combined to form multimodal physiological data that can comprehensively reflect the cardiocerebral hemodynamic state. The fusion process mainly includes the following steps:

[0062] (1) Time-align the signals to ensure that physiological data from different signal sources are processed on the same timeline.

[0063] (2) Based on the correlation between cardiocerebral hemodynamic parameters, a weighted fusion algorithm based on machine learning is applied to combine the feature weights of different signals to generate a unified physiological data output.

[0064] 3. Construction of non-invasive monitoring model (such as Figure 4 shown)

[0065] 1) Non-invasive intracranial pressure prediction model (M1)

[0066] Based on the absorbance information obtained from near-infrared spectroscopy technology and the characteristics of brain pulse waves, the present application constructs a non-invasive intracranial pressure prediction model, called M1 model. The original intention of this model is to realize the non-invasive real-time monitoring of intracranial pressure, so as to avoid the risks and discomfort brought by traditional invasive detection methods. The core of M1 model lies in the use of machine learning algorithm to deeply analyze and process the collected absorbance information and pulse wave characteristics. These physiological signals are non-invasively obtained by near-infrared spectroscopy technology, reflecting the changes of cerebral hemodynamics. Through feature extraction, the key information in the signal is extracted as the input of M1 model. In the training stage of the model, M1 model uses a large number of historical data from the clinic, which covers the intracranial pressure measurement values and corresponding near-infrared spectroscopy and pulse wave signal characteristics of different patient groups. The trained M1 model can make real-time prediction for unknown patients in a new clinical environment. By inputting the real-time collected absorbance information and cerebral pulse wave characteristics, the model can quickly output the non-invasive measurement value of intracranial pressure. This predicted value not only reflects the current intracranial pressure state of the patient, but also helps clinicians obtain important physiological information without invasive operation, thereby providing a basis for the treatment and management of patients.

[0067] 2) Non-invasive cardiac output and blood pressure prediction model (M2)

[0068] The construction of non-invasive cardiac output and blood pressure prediction model (M2) is based on the cardiac hemodynamic signals obtained by thoracic impedance technology. These signals contain rich physiological information, and through signal processing technology, feature data closely related to cardiac output and blood pressure can be extracted. Specifically, thoracic impedance signals can reflect the hemodynamic changes of the heart with each beat, including impedance changes during ventricular systole and diastole. These information is an important basis for predicting cardiac output and blood pressure.

[0069] In order to accurately predict cardiac output and blood pressure, M2 model uses machine learning algorithm to deeply learn and train these feature data, and corrects and optimizes them through a large amount of clinical data to improve the accuracy and reliability of prediction. The trained M2 model can realize real-time prediction of cardiac output and non-tourniquet blood pressure, and these predicted values are non-invasive, which can be obtained without directly measuring blood or arterial pressure, thereby reducing the discomfort and medical risks of patients.

[0070] 3) Comprehensive cardiac and cerebral hemodynamic monitoring model (M3)

[0071] The prediction results of the M1 and M2 models are further input into the comprehensive cardio-cerebral hemodynamic monitoring model (M3). The comprehensive cardio-cerebral hemodynamic monitoring model (M3) is a high-level prediction model developed on the basis of the M1 and M2 models. The M3 model is designed to provide more comprehensive and accurate cardio-cerebral hemodynamic monitoring to meet the clinical demand for comprehensive evaluation of multiple physiological parameters. Specifically, the M1 model is responsible for predicting intracranial pressure, while the M2 model predicts cardiac output and blood pressure. The M3 model deeply integrates the prediction results of these two models to generate more accurate and comprehensive cardio-cerebral hemodynamic parameters.

[0072] The uniqueness of the M3 model lies in that it not only simply integrates the outputs of M1 and M2, but also considers the mutual influence and correlation between intracranial pressure, cardiac output, and blood pressure through a multi-modal signal fusion algorithm. For example, cerebral perfusion pressure (CPP) is determined by intracranial pressure and mean arterial pressure, and the M3 model can provide more accurate CPP prediction results than single models through comprehensive analysis of these parameters.

[0073] To ensure the accuracy and applicability of the model, the M3 model is also trained and verified with extensive clinical data. The ultimate goal of the M3 model is to provide a more comprehensive and accurate non-invasive monitoring system by fusing multi-modal signals, helping clinicians better understand and manage the cardio-cerebral hemodynamic status of patients. Its application can not only improve the treatment effect of patients, but also reduce the risk and discomfort brought by monitoring, thereby greatly improving the overall quality of patient care.

[0074] 4. Monitoring device and operation

[0075] 1) Structure and function of the device

[0076] As shown in Figure 5 , the monitoring device of the present application includes a signal acquisition module, a signal processing module, a data fusion module, a non-invasive monitoring model module, and a display and alarm module. These modules are designed through integration to jointly complete real-time monitoring of cardio-cerebral hemodynamic parameters.

[0077] 2) Operation process

[0078] When operating the device, first connect the near-infrared spectroscopy sensor and the thoracic impedance electrode correctly to the patient's body surface. After starting the device, the signal acquisition module begins to acquire physiological signals, and the signal processing unit pre-processes and extracts features from these signals. Subsequently, the data fusion module fuses the processed signals, and finally the non-invasive monitoring model module generates non-invasive monitoring results. The display and alarm module presents the values of cardiac output, blood pressure, intracranial pressure, and cerebral perfusion pressure in real time, and automatically triggers an alarm when the parameters exceed the safe range.

[0079] 3) Clinical application

[0080] The device of the present application is particularly suitable for scenarios requiring real-time monitoring of cardio-cerebral hemodynamics, such as intensive care, cardiovascular and cerebrovascular surgery, and acute brain injury. Non-invasive, continuous monitoring can significantly reduce patient pain and improve the safety and effectiveness of monitoring.

[0081] 5) Experimental verification and effect

[0082] 1) Experimental verification

[0083] In clinical experiments, the device of the present application is applied to intensive care patients or healthy subjects to verify the monitoring accuracy and reliability of the device. The monitoring device of the present application is compared with standard monitoring equipment (such as invasive monitoring equipment for brain puncture intracranial pressure, flash-induced visual potential measurement intracranial pressure system, and cardiac blood flow hemodynamics detector based on thoracic impedance method) to focus on the monitoring accuracy of the device for cardiac output, intracranial pressure, blood pressure, and cerebral perfusion pressure, etc.

[0084] 2) Implementation effect

[0085] The monitoring device of the present application realizes non-invasive, continuous monitoring of cardio-cerebral hemodynamic parameters through the fusion of multi-modal signals. Compared with the prior art, the present application has the following advantages:

[0086] (1) Improved monitoring accuracy and real-time performance: By fusing multi-modal physiological signals, the device of the present application can accurately reflect the changes in cardio-cerebral hemodynamic parameters and provide key physiological data to medical personnel in real time. Compared with traditional single signal monitoring methods, the multi-modal fusion method significantly improves the accuracy of monitoring and reduces the monitoring errors caused by single signal interference or loss.

[0087] (2) Reduces patient pain and monitoring risk: Traditional invasive monitoring methods often require the insertion of catheters or sensors, which not only increases the risk of infection and complications, but also causes discomfort and pain to patients. The present application monitors non-invasively, completely avoiding the risk of invasive operation, providing a more comfortable and safe monitoring experience for patients, especially for critically ill patients who need long-term continuous monitoring.

[0088] (3) Provides more quantifiable physiological parameters: The device of the present application can not only monitor cardiac output, blood pressure, and other cardiac hemodynamic parameters, but also provide important cerebral hemodynamic indicators such as intracranial pressure and cerebral perfusion pressure. The provision of these parameters enables doctors to more comprehensively assess and diagnose the cardio-cerebral blood flow state of patients, thereby developing more accurate treatment plans.

[0089] Through the embodiments of the application, non-invasive and continuous monitoring of the heart and brain blood flow dynamics of the human body can be realized, a safer and more effective monitoring means is provided, and the application has wide clinical application value.

[0090] Finally, it should be pointed out that the above examples are only used to illustrate the technical solutions of the application and are not limiting. Although the application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the application can be modified or replaced equivalently without departing from the purpose and scope of the technical solutions, and all should be covered in the scope of the claims of the application.

Claims

1. A multimodal cardiocerebral hemodynamic monitoring method, characterized in that: The method specifically comprises the following steps: S1: Based on the near-infrared light method, the absorbance information and pulse wave time domain signal of the brain are obtained, and then the pulse wave time domain signal is preprocessed to obtain the pulse wave characteristic parameters related to the intracranial pressure and hemodynamic changes of the brain; based on the thoracic impedance method, physiological signals reflecting the hemodynamic changes of the human heart are obtained, including the thoracic impedance change signal, the thoracic impedance change differential signal, the thoracic impedance signal and the electrocardiogram signal, and then preprocessed to extract the characteristic parameters related to the cardiac output and hemodynamic changes from the preprocessed signals, as well as the characteristic transmission time information from the electrocardiogram signal to the thoracic impedance change signal, the electrocardiogram signal to the pulse wave signal, and the thoracic impedance signal to the pulse wave signal, and the time, amplitude and energy information of the characteristic changes of the thoracic impedance change signal and the pulse wave signal, to form a parameter set of time, amplitude and energy; S2: Based on absorbance information, pulse wave time domain signal and pulse wave characteristic parameters, a non-invasive intracranial pressure prediction model M1 is constructed to obtain preliminary predicted intracranial pressure and cerebral mean arterial pressure; based on characteristic parameters related to cardiac output and hemodynamic changes, a non-invasive cardiac output prediction model M21 is constructed to obtain predicted cardiac output; based on the parameter set of time, amplitude and energy, a non-invasive cuff-free blood pressure prediction model M22 is constructed to obtain systolic and diastolic pressure; the non-invasive prediction models M21 and M22 are jointly constructed into a non-invasive prediction model M2 based on the thoracic impedance method; S3: The physiological information features obtained in step S1 based on the near-infrared light method and the chest impedance method are fused to obtain multimodal physiological information; based on the preliminary predicted intracranial pressure, preliminary predicted cerebral mean arterial pressure, predicted cardiac output, systolic pressure and diastolic pressure obtained in step S2, the multimodal physiological information I is combined with the physiological information fusion , a non-invasive comprehensive monitoring model M3 for cardiocerebral hemodynamics was constructed to obtain accurate prediction results of intracranial pressure and mean cerebral arterial pressure. The predicted intracranial pressure and mean cerebral arterial pressure were further combined with the predicted cardiac output and multimodal physiological information to obtain non-invasive prediction results of intracranial pressure and cerebral perfusion pressure.

2. The multimodal cardiocerebral hemodynamic monitoring method according to claim 1, characterized in that: In step S1, the near-infrared light method utilizes a multi-wavelength sensing monitoring probe to monitor the absorbance changes of the frontal lobe of the brain and the pulse wave signal of the middle cerebral artery.

3. The multimodal cardiocerebral hemodynamic monitoring method according to claim 1, characterized in that: In step S1, the thoracic impedance method utilizes a human cardiac hemodynamic parameter monitoring method to obtain a physiological signal reflecting changes in human cardiac hemodynamics.

4. The multimodal cardiocerebral hemodynamic monitoring method according to claim 2, characterized in that: In step S2, a non-invasive intracranial pressure prediction model M1 is constructed, which specifically includes the following steps: S201: Use multi-wavelength sensing monitoring probe to obtain n wavelengths Absorbance information at the frontal lobe of the brain under the light source: ; S202: The pulse wave time domain signal PPG of the middle cerebral artery is obtained by using the sensor monitoring probe, and after preprocessing, the pulse wave characteristic parameters related to the changes in intracranial pressure and hemodynamics are obtained: P = {p1,p2,...,p m }, where m represents the number of pulse wave features after preprocessing; S203: Construct a non-invasive intracranial pressure prediction model M1 to obtain non-invasive prediction results of intracranial pressure and mean cerebral arterial pressure: M1(ICP0,MAP0) = f(I,P,PPG), where ICP0 represents the preliminary predicted intracranial pressure and MAP0 represents the preliminary predicted mean cerebral arterial pressure.

5. The multimodal cardiocerebral hemodynamic monitoring method according to claim 3, characterized in that: In step S2, a non-invasive prediction model M2 based on the thoracic impedance method is constructed, which specifically includes the following steps: S211: Acquire physiological signals reflecting changes in human cardiac hemodynamics, including thoracic impedance change signals, thoracic impedance change differential signals, thoracic impedance signals, and electrocardiogram signals, and preprocess the signals; S212: Extract characteristic parameters related to cardiac output and hemodynamic changes from the preprocessed signal and construct a non-invasive cardiac output prediction model M21(CO) = f(p1,p2,p3,...,p k ), where k represents the number of characteristic parameters related to cardiac output and hemodynamic changes, and CO represents the predicted cardiac output; the characteristic parameters related to cardiac output and hemodynamic changes include periodic information, strength information, electro-mechanical conduction information, and energy information of thoracic impedance changes; S213: Extracting characteristic transmission time information from the ECG signal to the chest impedance change signal, the ECG signal to the pulse wave signal, and the chest impedance signal to the pulse wave signal, as well as the time, amplitude, and energy information of the characteristic changes of the chest impedance change signal and the pulse wave signal from the preprocessed signal, to form a parameter set of time T, amplitude A, and energy P. Based on these three parameter sets, a non-invasive prediction model M22(SBP, DBP) = f(T, A, P) for cuffless blood pressure is constructed, where SBP represents systolic blood pressure and DBP represents diastolic blood pressure. S214: The non-invasive prediction models M21 and M22 obtained in steps S212 and S213 together constitute a non-invasive prediction model M2 = (M21, M22) based on the thoracic impedance method.

6. The multimodal cardiocerebral hemodynamic monitoring method according to claim 1, characterized in that: In step S3, a non-invasive comprehensive monitoring model M3 for cardiocerebral hemodynamics is constructed, which specifically includes the following steps: S301: Fusing the physiological information features obtained based on the near-infrared light method and the chest impedance method to obtain multimodal physiological information I fusion ; S302: Using the correlation between changes in cardiocerebral hemodynamics, intracranial pressure, blood pressure, and cardiac output, multimodal physiological information is added to the non-invasive comprehensive monitoring model M3 for cardiocerebral hemodynamics based on the preliminary predicted intracranial pressure value, preliminary predicted cerebral mean arterial pressure, predicted cardiac output, systolic blood pressure, and diastolic blood pressure obtained by prediction models M1 and M2. fusion , construct a non-invasive intracranial pressure prediction model M31(MAP,ICP)=f(I fusion ,ICP0,MAP0,CO,SBP,DBP); where MAP represents the mean cerebral arterial pressure predicted by model M31; ICP represents the intracranial pressure predicted by model M31; S303: In the non-invasive comprehensive monitoring model M3 for cardiocerebral hemodynamics, based on the result of step S302, a non-invasive prediction model M32 (CPP) = f(CO, MAP, ICP, I fusion ); S304: The non-invasive prediction models M31 and M32 obtained from steps S302 and S303 together constitute a non-invasive comprehensive monitoring model of cardiocerebral hemodynamics M3 = (M31, M32).

7. The multimodal cardiocerebral hemodynamic monitoring method according to claim 6, characterized in that: In step S301, the fusion processing is specifically based on the correlation of cardiocerebral hemodynamic parameters, using a time synchronization mechanism and a weighted fusion algorithm to combine near-infrared spectral signals and chest impedance signals to form multimodal physiological information that can comprehensively reflect the cardiocerebral hemodynamic state.

8. A multimodal cardiocerebral hemodynamic monitoring device, characterized in that: It includes a signal acquisition module, a signal processing module, a data fusion module, a non-invasive monitoring model module and a display and alarm module; the signal acquisition module includes a near-infrared spectrum sensor and a chest impedance electrode; The near-infrared spectral sensor and chest impedance electrode are used to be connected to the patient's body surface and are responsible for acquiring multimodal physiological signals of the human body; the signal processing module denoises, filters and extracts features of the acquired signals; the data fusion module fuses the physiological data of different signal sources; the non-invasive monitoring model module integrates the multimodal cardiocerebral hemodynamic monitoring method described in any one of claims 1 to 7, and generates non-invasive monitoring results based on the fused data; the display and alarm module is used to present the non-invasive monitoring results, namely the numerical values ​​and change trend waveforms of cardiac output, blood pressure, intracranial pressure and cerebral perfusion pressure in real time, and automatically trigger an alarm when the parameters exceed the safety range.

Images