A device capable of improving the assistive regulation range of intra-aortic balloon counterpulsation

Abstract

The present invention relates to a device that can improve the auxiliary adjustment range of intra-aortic balloon counterpulsation, aiming to optimize the treatment effect of IABP and improve the accuracy of individualized treatment. The device includes a high-precision physiological signal acquisition unit, an individual characteristic modeling module, a load prediction and evaluation module and an intelligent adjustment control unit. By real-time acquisition of physiological signals such as pulse wave, electrocardiogram, heart rate variability and blood pressure, combined with the patient's individual characteristic data, a personalized physiological model is established to predict changes in cardiac load. The load prediction and evaluation module uses deep learning algorithms and hemodynamic analysis to evaluate cardiac load fluctuations in real time and generate adjustment data. The intelligent adjustment control unit accurately adjusts the inflation time and pressure of the IABP airbag based on the prediction results, ensuring that inflation is synchronized with changes in cardiac load and optimizing the counterpulsation effect. The device can adapt to the individual differences of different patients, reduce the hysteresis effect, and improve the safety and effectiveness of treatment.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical diagnosis and surgical assistance, and in particular relates to a device capable of improving the auxiliary adjustment range of intra-aortic balloon counterpulsation. Background Art

[0002] The intra-aortic balloon pump (IABP) is a common cardiac assist device widely used in the treatment of patients with acute heart disease, particularly those with acute myocardial infarction, heart failure, post-coronary artery bypass grafting, and aortic dissection. Its working principle is to increase coronary blood flow by inflating the balloon during diastole and rapidly deflate it during systole, thereby reducing cardiac workload and improving cardiac function and hemodynamics.

[0003] However, traditional IABP therapy devices have some limitations, especially in terms of personalized treatment and real-time counterpulsation adjustment:

[0004] Lack of Personalized Adjustment: Traditional IABP devices typically rely on fixed counterpulsation modes and preset inflation and deflation parameters, lacking personalized adjustments tailored to individual patient physiological characteristics. This "one-size-fits-all" approach can result in the counterpulsation process being out of sync with the patient's actual cardiac workload, compromising treatment effectiveness and potentially increasing the risk of complications.

[0005] Inadequate real-time monitoring of cardiac workload fluctuations: Traditional IABP devices lack real-time monitoring of changes in a patient's cardiac workload. While some devices can monitor basic signals such as electrocardiogram (ECG) or blood pressure, they lack the real-time collection and analysis of comprehensive physiological signals such as pulse wave (PPG) and heart rate variability (HRV). Consequently, a patient's cardiac workload can fluctuate dramatically over a short period of time, making it difficult for existing devices to respond and adjust in real time, often requiring manual intervention.

[0006] Counterpulsation is out of sync with the cardiac cycle: Traditional IABP inflation and deflation processes rely on simple time synchronization mechanisms that fail to precisely match each phase of the cardiac cycle. This can lead to a hysteresis effect in inflation and deflation, resulting in suboptimal blood flow direction and velocity, which in turn affects blood perfusion efficiency to the heart and the entire body.

[0007] Risk of complications during treatment: Asynchronous counterpulsation with cardiac load fluctuations, or excessive or insufficient counterpulsation amplitude, can lead to adverse reactions. Excessive counterpulsation can cause complications such as aortic rupture and valve damage, while insufficient blood supply can lead to incomplete organ perfusion, impairing patient recovery. Existing equipment often fails to adjust the range of counterpulsation assistance based on the patient's physiological data, resulting in unstable treatment outcomes and increased patient risks.

[0008] Poor adaptability to complex cases: Most existing IABP devices operate under standardized conditions, making them inflexible for the changing conditions of patients with complex heart conditions. For example, in the late stages of heart failure, cardiac workload often fluctuates significantly, and traditional devices are unable to adapt quickly, resulting in varying treatment outcomes and hindering precise clinical intervention. Summary of the Invention

[0009] The purpose of the present invention is: The present invention aims to provide a device that can improve the auxiliary adjustment range of intra-aortic balloon counterpulsation. By introducing multi-dimensional physiological signal acquisition, individual characteristic modeling, load prediction and evaluation, and intelligent adjustment and control technologies, a more accurate, efficient and safe intra-aortic balloon counterpulsation treatment can be achieved, thereby maximizing the improvement of the patient's heart function, reducing the risk of complications during treatment, and improving the patient's treatment effect and comfort.

[0010] The technical solution adopted in the present invention is as follows:

[0011] A device capable of improving the auxiliary adjustment range of intra-aortic balloon counterpulsation, used for intra-aortic balloon counterpulsation treatment, comprising:

[0012] High-precision physiological signal acquisition unit, used to collect the patient's pulse wave (PPG), electrocardiogram (ECG), heart rate variability (HRV) and / or blood pressure physiological signals in real time;

[0013] The individual characteristic modeling module establishes a personalized physiological model based on the heart and vascular structure of each patient, generating load prediction data that is adapted to the patient's heart and blood vessels;

[0014] a load prediction and assessment module, configured to process the physiological signals and individual characteristic data, analyze cardiac load changes in real time and generate load prediction data, thereby assessing instantaneous fluctuations in cardiac load;

[0015] The intelligent adjustment control unit adjusts the inflation time and inflation pressure of the airbag according to the load prediction data to finely control the auxiliary range of the airbag counterpulsation.

[0016] Wherein, the high-precision physiological signal acquisition unit includes:

[0017] Pulse wave sensor (PPG), used to monitor aortic blood flow fluctuations in real time and provide blood flow information;

[0018] Electrocardiogram (ECG) sensors, which are used to obtain information about the heart's electrical activity and assess changes in heart rhythm;

[0019] Blood pressure sensor, used to monitor dynamic blood pressure changes and assist in evaluating hemodynamics.

[0020] Wherein, the individual feature modeling module further includes:

[0021] Imaging data acquisition module, used to collect CT, MRI or echocardiography data of patients and provide information on the patient's heart and blood vessel structure;

[0022] Computational fluid dynamics (CFD) simulation module, used to calculate the velocity, pressure, and resistance parameters of blood flow in the aorta based on the patient's individual characteristic data, and generate instantaneous change data of cardiac load;

[0023] The biomechanical modeling module analyzes the response characteristics of the patient's heart and vascular system by simulating the mechanical properties of the heart and blood vessels.

[0024] The load forecasting and evaluation module further includes:

[0025] A machine learning module is used to analyze real-time collected physiological signals and historical data, and predict the fluctuation trend of cardiac load through deep learning algorithms;

[0026] The hemodynamic analysis module calculates the real-time fluctuation of cardiac load by combining computational fluid dynamics (CFD) and real-time physiological data.

[0027] Wherein, the intelligent adjustment control unit includes:

[0028] The feedback control module automatically adjusts the airbag inflation time and pressure based on real-time load prediction data to ensure that the inflation and deflation processes are highly synchronized with changes in cardiac load;

[0029] The adaptive control module can learn and adapt to the individual differences of different patients, adjust the counterpulsation assistance adjustment range through machine learning algorithms, and optimize the airbag inflation and deflation strategies.

[0030] Among them, the load prediction and evaluation module can monitor and analyze cardiac load fluctuations in real time, and immediately send a signal when a sudden and drastic change in cardiac load is detected, triggering the intelligent adjustment control unit to adjust the airbag inflation pressure and inflation time to adapt to the rapidly changing load requirements.

[0031] The device uses a PID control or fuzzy control algorithm to adjust the response time of the airbag expansion through a feedback control module to avoid a hysteresis effect and ensure that the airbag inflation and deflation process is synchronized with changes in cardiac load.

[0032] The device uses synchronous control technology to ensure that the inflation and deflation time of the airbag are coordinated with the various stages of the cardiac cycle, optimize the direction and speed of blood flow, and maximize the efficiency of counterpulsation.

[0033] The device avoids excessive counterpulsation or insufficient blood supply during the automatic adjustment process by comparing the patient's historical data and current physiological signals regularly or in real time.

[0034] The method for improving the assistive regulation range of the intra-aortic balloon counterpulsation by the device includes:

[0035] Real-time collection of patients' pulse wave, electrocardiogram, heart rate variability and other physiological signals;

[0036] Combine the patient's individual characteristic data to establish a personalized physiological model;

[0037] Processing the physiological signals and individual characteristic data to generate instantaneous change data of cardiac load;

[0038] Adjust the inflation pressure and time of the airbag according to the load change prediction data to accurately match the cardiac counterpulsation process;

[0039] The adaptive control module ensures that the balloon inflation process is synchronized with the cardiac load, reducing lag and optimizing the counterpulsation effect.

[0040] The present invention relates to a device that can improve the assisted regulation range of intra-aortic balloon counterpulsation. Through precise physiological signal acquisition, individual characteristic modeling, load prediction and evaluation, and intelligent regulation and control, the device optimizes the assisted regulation range during intra-aortic balloon counterpulsation therapy. The following are the main beneficial effects of the invention:

[0041] 1. Individualized adjustment

[0042] Precise Adjustment Based on Individual Characteristics: This invention generates a personalized patient physiological model through physiological signal acquisition, imaging data, and computational fluid dynamics (CFD) simulation. This model accurately predicts changes in cardiac load based on the patient's cardiac and vascular characteristics. This process avoids the traditional "one-size-fits-all" treatment approach, enabling each patient to receive tailored counterpulsation assistance, significantly improving the accuracy and effectiveness of treatment.

[0043] Adaptability to individual differences: Through the adaptive control module, the device can learn and adjust according to the physiological characteristics of different patients, so that the IABP counterpulsation assistance range can dynamically adapt to changes in the patient's condition to ensure maximum treatment effect.

[0044] 2. Real-time monitoring and adjustment

[0045] Real-time physiological data monitoring: The device uses high-precision physiological signal acquisition units (such as PPG, ECG, and ambulatory blood pressure monitoring) to monitor the patient's cardiac load and blood flow status in real time. This data is transmitted in real time and used in the load prediction and assessment module, allowing timely adjustments to treatment plans as the patient's condition changes.

[0046] Accurate prediction of load fluctuations: The load prediction and assessment module combines real-time physiological signals and historical data, and uses deep learning algorithms to accurately predict fluctuations in cardiac load. This allows for early detection of possible drastic load changes, ensuring timely adjustment of the counterpulsation process in emergencies to avoid the risk of excessive counterpulsation or insufficient blood supply.

[0047] 3. Precise synchronization of counterpulsation and cardiac cycle

[0048] Synchronized optimization of inflation and deflation: This invention utilizes a feedback control module (e.g., PID control or fuzzy control algorithms) to ensure that the inflation time and pressure of the airbag are highly synchronized with cardiac load fluctuations. This precise synchronization avoids the hemodynamic imbalances caused by delayed or premature airbag inflation in traditional counterpulsation therapy, thereby improving counterpulsation efficiency and patient comfort.

[0049] Real-time adjustment of the counterpulsation assistance range: The intelligent adjustment control unit can adjust the time and pressure of the airbag inflation in real time according to load changes, ensuring that the counterpulsation process is always in the optimal state, maximizing the treatment effect.

[0050] 4. Improve treatment outcomes and reduce the risk of complications

[0051] Optimize the direction and speed of blood flow: By precisely adjusting the inflation and deflation process of the IABP bag, the direction and speed of blood flow can be optimized, reducing the cardiac load, alleviating complications caused by insufficient cardiac pumping (such as ischemic heart disease, heart failure, etc.), and reducing the risk of hemodynamic instability.

[0052] Reduce the risk of excessive counterpulsation and insufficient blood supply: The device avoids excessive counterpulsation or insufficient blood supply through intelligent adjustment, further reducing the risk of complications caused by unreasonable counterpulsation during treatment, such as aortic rupture or insufficient organ perfusion.

[0053] 5. Enhance patient comfort and safety

[0054] Personalized and dynamic adjustment to improve patient comfort: Compared with traditional IABP devices, the present invention can more accurately grasp the changes in each patient's condition and automatically adjust the counterpulsation parameters through real-time monitoring and adjustment of individual physiological signals, thereby reducing the patient's discomfort caused by treatment and enhancing the patient's comfort.

[0055] Improved safety: Through real-time load assessment and intelligent adjustment, the system can respond promptly to drastic fluctuations in cardiac load, avoiding cardiac load imbalances that may be caused by counterpulsation lag or overinflation in traditional treatments, greatly improving the safety of the treatment process.

[0056] 6. Improve treatment efficiency and reduce medical staff intervention

[0057] Automated adjustment reduces manual intervention: Through the automated control of the intelligent adjustment module, the present invention can automatically adjust the inflation time and pressure of the IABP according to real-time load prediction data and the patient's physiological status, thereby reducing the need for medical staff to intervene and alleviating their workload.

[0058] Reduce treatment cycles: Precisely synchronized IABP counterpulsation therapy not only helps optimize treatment outcomes, but also accelerates patient recovery, reduces unnecessary hospitalization time and treatment cycles, and lowers medical costs.

[0059] 7. Convenience and compatibility

[0060] Compatibility with Existing Medical Devices: This system utilizes existing medical equipment (such as PPG sensors, ECG instruments, and ambulatory blood pressure monitors), eliminating the need for new hardware development and reducing the cost and complexity of device upgrades. Standardized interfaces and wireless connectivity facilitate data collection and transmission, enabling seamless integration with existing hospital information systems (such as PACS and electronic medical records), enhancing the convenience and compatibility of clinical applications.

[0061] 8. Clinical Validation and Universal Applicability

[0062] Applicable to a variety of clinical situations: This invention is not only suitable for traditional IABP indications such as acute myocardial infarction, post-CABG surgery, and aortic dissection, but can also provide precise treatment support in complex cases such as advanced heart failure and severe heart disease. It can cope with complex and changing clinical scenarios and has strong adaptability and universality. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 Schematic diagram of the structure of the invented device. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0065] See also Figure 1The present invention relates to a device for improving the auxiliary adjustment range of intra-aortic balloon counterpulsation, which is used for intra-aortic balloon counterpulsation treatment. The device comprises:

[0066] ① High-precision physiological signal acquisition unit, used to collect the patient's pulse wave (PPG), electrocardiogram (ECG), heart rate variability (HRV) and / or blood pressure physiological signals in real time;

[0067] Among them, the high-precision physiological signal acquisition unit includes:

[0068] Pulse wave sensor (PPG), used to monitor aortic blood flow fluctuations in real time and provide blood flow information;

[0069] Electrocardiogram (ECG) sensors, which are used to obtain information about the heart's electrical activity and assess changes in heart rhythm;

[0070] Blood pressure sensor, used to monitor dynamic blood pressure changes and assist in evaluating hemodynamics.

[0071] Specifically:

[0072] Pulse wave (PPG) acquisition: Use existing PPG sensors (such as fingertip or earlobe photoelectric sensors) to collect pulse wave information in real time. These sensors are already widely used in health monitoring devices such as smartwatches and portable oximeters. Connect existing PPG sensors to the system via wireless technology and transmit data to the system for processing.

[0073] Electrocardiogram (ECG) acquisition: Use existing ECG equipment, such as a standard 12-lead ECG machine or a portable ECG device. Existing ECG equipment transmits real-time data to the processing system via Bluetooth or USB interface for subsequent analysis.

[0074] Blood pressure monitoring: Use existing ambulatory blood pressure monitoring equipment (such as wrist or upper arm automatic blood pressure monitors, or commonly used blood pressure monitoring systems). The automatic blood pressure monitor regularly collects blood pressure data from the patient and synchronizes with the control system using existing APIs to provide real-time blood pressure data.

[0075] These devices are already commonly used in clinical practice and can be connected through data interfaces to enable real-time data acquisition and analysis without the need to develop new hardware.

[0076] ② Individual characteristic modeling module, which establishes a personalized physiological model based on each patient's heart and vascular structure, and generates load prediction data adapted to the patient's heart and blood vessels;

[0077] Among them, the individual feature modeling module further includes:

[0078] Imaging data acquisition module, used to collect CT, MRI or echocardiography data of patients and provide information on the patient's heart and blood vessel structure;

[0079] Computational fluid dynamics (CFD) simulation module, used to calculate the velocity, pressure, and resistance parameters of blood flow in the aorta based on the patient's individual characteristic data, and generate instantaneous change data of cardiac load;

[0080] The biomechanical modeling module analyzes the response characteristics of the patient's heart and vascular system by simulating the mechanical properties of the heart and blood vessels.

[0081] The individual characteristic modeling module is one of the core components of this device. Its purpose is to establish a personalized physiological model based on the heart and vascular structure of each patient to generate load prediction data that is suitable for the patient's heart and blood vessels. This module collects imaging data and applies computational fluid dynamics (CFD) simulation and biomechanical modeling to calculate the velocity, pressure, resistance and other parameters of blood flow in the aorta. It also generates instantaneous change data of the patient's cardiac load, providing an accurate basis for subsequent counterpulsation adjustment. Specifically, it includes the following steps:

[0082] a. Imaging Data Acquisition

[0083] Imaging data acquisition forms the foundation of the individual feature modeling module, aiming to obtain data on the patient's heart and vascular structure. This data will serve as the basis for subsequent modeling and simulation, helping us build a personalized physiological model.

[0084] Specific implementation steps:

[0085] Imaging equipment options: CT (Computed Tomography): Provides high-resolution, three-dimensional structural data, accurately depicting the patient's aorta and heart structure, helping to extract geometric information such as vascular morphology and diameter. MRI (Magnetic Resonance Imaging): Provides functional information about the heart and blood vessels (such as blood flow velocity and cardiac wall motion), making it particularly suitable for dynamic assessment of blood flow and vascular elasticity. Echocardiography: Provides real-time, dynamic images, particularly important for evaluating heart valve and ventricular function.

[0086] Data Acquisition: Imaging data is imported into a medical imaging system (PACS) through a standard interface. The data is then imported into a modeling system for further processing. Using existing medical imaging software (such as OsiriX, 3D Slicer, and Mimics), 3D structural data of blood vessels and the heart are extracted from the raw image data and a precise 3D model is generated.

[0087] Image Data Processing: Imaging data (CT, MRI, echocardiography) is reconstructed in processing software to extract parameters such as the geometry of the heart and aorta, vessel diameter, and wall thickness. This data provides the foundation for subsequent CFD simulations and biomechanical modeling.

[0088] b. Computational Fluid Dynamics (CFD) Simulation

[0089] CFD simulation is a key process for calculating parameters such as blood flow velocity, pressure, and resistance in the aorta based on imaging data. It can help us infer the dynamic behavior of blood flow in the aorta and generate a load prediction model based on this data.

[0090] Specific implementation steps:

[0091] Modeling: Converting imaging data into a CFD model. This process is performed using medical image processing software, which converts imaging data into a computational grid, creating a precise three-dimensional geometric model of the blood vessels and heart. The model is meshed so that each computational unit can simulate physical parameters such as blood flow velocity, pressure, and temperature. The fineness of the grid determines the accuracy of the simulation; a finer grid provides more accurate results.

[0092] Fluid dynamics simulation: Use professional CFD software (such as Ansys Fluent, COMSOL Multiphysics, etc.) to perform fluid dynamics simulation to simulate the flow behavior of blood in the aorta.

[0093] Fluid dynamics calculation: Input the patient's vascular structure data, blood rheology parameters (such as blood viscosity and density), etc., and use the software to calculate the blood flow velocity distribution, pressure distribution and vascular resistance.

[0094] Blood flow calculation: CFD simulation can carefully analyze the stability and turbulence of blood flow and the interaction between blood flow and blood vessel walls, generating real-time blood flow velocity, blood pressure, resistance and other important data.

[0095] Result output:

[0096] CFD simulation outputs include information such as blood flow velocity, pressure distribution, and vessel wall shear stress. This data can be used to calculate the patient's hemodynamic characteristics at different stages of the cardiac cycle, providing data support for subsequent counterpulsation adjustments. The output simulation data typically includes pressure distribution diagrams, velocity vector diagrams, and blood flow trajectories, helping physicians and control systems understand instantaneous changes in blood flow.

[0097] c. Biomechanical modeling

[0098] Biomechanical modeling simulates the mechanical properties of the heart and blood vessels, analyzing their response characteristics and further refining personalized load prediction data. This section primarily analyzes the mechanical response of the heart in hemodynamics, as well as the elasticity and contractility of blood vessels.

[0099] Specific implementation steps:

[0100] Mechanical modeling: Based on patient imaging data, a biomechanical model of the heart and blood vessels is constructed. This model must include the heart's contraction and relaxation behavior, the elastic properties of the aorta, and other parameters, simulating how the heart and blood vessels respond to pressure changes during blood flow.

[0101] Mechanical properties of the heart and blood vessels: The model needs to account for factors such as changes in the volume of each cardiac chamber, changes in cardiac contractility, and the elasticity of blood vessels. These parameters are calibrated using biomechanical experimental data.

[0102] Biomechanical simulation: Finite element analysis (FEA) is used to perform biomechanical simulations. The mechanical responses of the heart and blood vessels are analyzed using existing software (such as ABAQUS and COMSOL). The simulations must consider the physical characteristics of blood flow, such as blood rheology (viscosity, elasticity, etc.), the nonlinear elasticity of blood vessels, and the stiffness of the vessel walls.

[0103] Response Characteristic Analysis: Biomechanical modeling analyzes the vascular and cardiac responses to varying loads, estimating how the patient's heart and vascular system respond to varying counterpulsation pressures. This data can be used to adjust the IABP inflation strategy, ensuring that balloon inflation is closely synchronized with the mechanical response of the heart and blood vessels.

[0104] d. Individual characteristic modeling and load forecasting

[0105] By combining imaging data, CFD simulation results, and biomechanical simulation data, a personalized physiological model is formed. This model is used to generate patient cardiac load prediction data, monitor instantaneous changes in cardiac load in real time, and predict cardiac load fluctuations.

[0106] Specific implementation steps:

[0107] Comprehensive modeling: Utilizing various parameters derived from imaging data, CFD simulations, and biomechanical modeling, combined with the patient's historical medical history, we construct a personalized cardiac load model through mathematical modeling techniques (such as the finite element method and multiscale modeling). By integrating multi-source data, we generate a cardiac load fluctuation model for each patient, predicting changes in cardiac load under different circumstances.

[0108] Real-time Monitoring and Feedback: The personalized model continuously adjusts and optimizes based on real-time physiological signals. Using real-time data inputs (e.g., PPG, ECG, blood pressure, etc.), the system dynamically updates the individual characteristic model and optimizes load prediction with each measurement. The load prediction model provides real-time feedback for subsequent counterpulsation adjustments, helping to adjust the inflation time and pressure of the airbag to maximize counterpulsation effectiveness.

[0109] ③ Load prediction and assessment module, which is used to process physiological signals and individual characteristic data, analyze cardiac load changes in real time and generate load prediction data, thereby evaluating instantaneous fluctuations in cardiac load. The load prediction and assessment module further includes:

[0110] A machine learning module is used to analyze real-time collected physiological signals and historical data, and predict the fluctuation trend of cardiac load through deep learning algorithms;

[0111] The hemodynamic analysis module calculates the real-time fluctuation of cardiac load by combining computational fluid dynamics (CFD) and real-time physiological data.

[0112] The load prediction and assessment module can monitor and analyze cardiac load fluctuations in real time, and immediately send a signal when a sudden and drastic change in cardiac load is detected, triggering the intelligent adjustment control unit to adjust the airbag inflation pressure and inflation time to adapt to the rapidly changing load requirements.

[0113] The load prediction and assessment module plays a crucial role in intra-aortic balloon pump (IABP) therapy. It monitors the patient's physiological signals in real time, analyzes changes in cardiac load, and predicts fluctuations, providing accurate predictive data for subsequent balloon adjustments. Based on real-time physiological signal acquisition, this module also integrates the output of the individual feature modeling module. Through deep learning, machine learning, and hemodynamic analysis, it accurately assesses instantaneous changes in cardiac load and generates personalized adjustment plans for each patient.

[0114] The basic architecture of the load forecasting and assessment module mainly includes the following key parts:

[0115] Real-time physiological signal analysis: Through high-precision physiological signal acquisition units (pulse wave, electrocardiogram, blood pressure signals, etc.), the patient's heart health data is obtained in real time.

[0116] Machine Learning Module: Combining real-time physiological signals and historical data, using machine learning algorithms, predicts the patient's cardiac load change trend, especially the fluctuation of cardiac load.

[0117] Hemodynamic analysis module: Combined with the CFD (computational fluid dynamics) simulation results output by the individual feature modeling module, the real-time fluctuations of cardiac load are calculated through hemodynamic analysis.

[0118] Load fluctuation assessment and prediction: All physiological signals are combined with simulation data to evaluate the instantaneous fluctuation of cardiac load and generate future load fluctuation prediction data to provide a basis for counterpulsation regulation.

[0119] Specifically, they include:

[0120] a. Real-time physiological signal analysis

[0121] Physiological signals collected in real time are the basis of the load prediction and assessment module. These signals can reflect the dynamic information of heart function, blood pressure changes and blood flow.

[0122] Specific implementation steps:

[0123] Pulse wave (PPG) signals: The patient's pulse wave is monitored in real time using existing pulse wave sensors (such as fingertip or earlobe PPG sensors). PPG sensors can reflect blood flow fluctuations and provide blood flow information, especially in dynamic conditions, recording blood flow changes as the heart pumps in real time. PPG signals are transmitted via wireless communication to the system backend for analysis and processing.

[0124] Electrocardiogram (ECG) signals: ECG sensors (such as 12-lead ECGs or portable ECG devices) monitor the heart's electrical activity in real time, recording information such as heart rate, rhythm, and cardiac cycle. The system transmits real-time ECG signals via Bluetooth or USB to the backend for analysis and assessment of changes in the heart's electrical activity and rhythm.

[0125] Blood pressure signals: Utilize existing ambulatory blood pressure monitoring equipment (wrist blood pressure monitors, upper arm automatic blood pressure monitors, etc.) to monitor the patient's ambulatory blood pressure changes. Blood pressure data is synchronized wirelessly or via a data interface to a backend system for real-time processing and analysis.

[0126] Signal processing: All physiological signal data are processed through filtering, denoising, feature extraction and other algorithms to extract useful cardiac load-related features (heart rate, pulse waveform, systolic blood pressure, diastolic blood pressure, etc.).

[0127] b. Machine Learning Module

[0128] The machine learning module analyzes real-time physiological signals and historical data to predict fluctuations in cardiac load. Through continuous learning and optimization, it accurately predicts load fluctuations and provides appropriate adjustment solutions.

[0129] Specific implementation steps:

[0130] Data preprocessing and feature extraction: The collected real-time physiological signals require preprocessing, including denoising, signal resampling, and time alignment. The processed signals are then fed into a machine learning model for analysis. Key features such as heart rate variability (HRV), pulse waveform, and blood pressure fluctuations are extracted from PPG, ECG, and blood pressure data.

[0131] Training data and model building:

[0132] Training Data: A training set is constructed using a large amount of historical case data and physiological signals from real-time patient monitoring. The training data includes basic patient information, medical history, imaging data, individual characteristics, and actual IABP treatment feedback.

[0133] Machine Learning Algorithm Selection:

[0134] Deep learning models: You can choose to use LSTM (Long Short-Term Memory Network), RNN (Recurrent Neural Network), etc. These models are good at processing time series data and can capture complex patterns in time series.

[0135] Regression model: Support vector regression (SVR), random forest regression (Random Forest Regression), etc. can be used to predict the changing trend of cardiac load based on physiological signals.

[0136] Reinforcement learning: used to automatically adjust counterpulsation strategies and optimize the accuracy of load prediction through adaptive optimization.

[0137] Real-time predictions:

[0138] Based on real-time collected physiological signals, machine learning models can predict the fluctuation trend of a patient's cardiac workload over time. In particular, transient fluctuations in cardiac workload (such as increased heart rate and blood pressure) can be predicted and adjusted in advance.

[0139] Load fluctuation trend prediction:

[0140] Through the trained machine learning model, the system can predict the changing trend of the patient's cardiac load, such as fluctuations in blood pressure, heart rate, etc. in the future, and provide early warning of possible drastic changes in load.

[0141] c. Hemodynamic analysis module

[0142] The hemodynamic analysis module combines CFD (computational fluid dynamics) simulation results with real-time physiological signals to calculate the real-time fluctuations of cardiac load, providing more accurate data support for load prediction and evaluation.

[0143] Specific implementation steps:

[0144] Data Input: This module uses the CFD simulation results output by the Individual Feature Modeling Module, such as blood flow velocity, pressure distribution, and vascular resistance. These results are combined with real-time PPG, ECG, and blood pressure data to obtain a more accurate cardiac load assessment.

[0145] Real-time blood flow analysis: Use real-time data to revise and adjust CFD simulation results in real time, ensuring that load predictions reflect the true cardiac load at each stage. Compare historical data with real-time data to assess changes in cardiac load and estimate the magnitude and rate of load fluctuations.

[0146] Fluctuation analysis and evaluation: Blood flow analysis based on CFD simulation, combined with load fluctuation prediction of the machine learning module, can evaluate the instantaneous fluctuation of the patient's cardiac load in real time to determine whether the counterpulsation strategy needs to be adjusted.

[0147] d. Load fluctuation assessment and prediction

[0148] Combining physiological signal data, machine learning analysis, hemodynamic analysis, and individual characteristic models, the Load Prediction and Assessment Module accurately assesses and predicts cardiac load fluctuations. This module not only monitors load changes in real time but also predicts significant fluctuations in cardiac load in advance, providing a basis for counterpulsation adjustments.

[0149] Specific implementation steps:

[0150] Load Assessment: The module receives and processes various physiological signals and CFD simulation results in real time to assess the patient's cardiac load. Evaluation metrics include cardiac load index, hemodynamic stability, and cardiac pumping capacity. If cardiac load fluctuates dramatically (such as a sharp increase in blood pressure or heart rate), the system will issue a warning signal, indicating that the IABP counterpulsation strategy may need to be adjusted.

[0151] Load Prediction: Based on analysis of real-time signals and historical data, the load prediction module provides short-term predictions of cardiac load (fluctuations within minutes to tens of minutes), providing precise adjustment strategies for the IABP control system. Prediction results include cardiac load trends, fluctuation amplitude, and rate of change, helping the counterpulsation system precisely adjust inflation and deflation timing.

[0152] Summary: Load forecasting and assessment module implementation process:

[0153] Real-time physiological signal analysis: Real-time monitoring of patients' physiological data through PPG, ECG, blood pressure and other signal acquisition equipment.

[0154] Machine learning analysis: Based on real-time data and historical medical records, machine learning models (such as deep learning and regression models) are used to predict cardiac load fluctuation trends.

[0155] Hemodynamic analysis: Combine CFD simulation results with real-time data to estimate cardiac load fluctuations and assess instantaneous changes in cardiac load.

[0156] Load assessment and prediction: Based on real-time signals and model prediction data, load changes are evaluated and future load fluctuations are predicted in advance to provide a basis for counterpulsation regulation.

[0157] This module combines multiple technical means to accurately assess and predict the patient's cardiac load, optimize the effectiveness of IABP treatment, and reduce the risk of adverse events.

[0158] ④ Intelligent adjustment control unit, which adjusts the airbag inflation time and inflation pressure according to load prediction data to finely control the auxiliary range of airbag counterpulsation;

[0159] Among them, the intelligent adjustment control unit includes:

[0160] The feedback control module automatically adjusts the airbag inflation time and pressure based on real-time load prediction data to ensure that the inflation and deflation processes are highly synchronized with changes in cardiac load;

[0161] The adaptive control module can learn and adapt to the individual differences of different patients, adjust the counterpulsation assistance adjustment range through machine learning algorithms, and optimize the airbag inflation and deflation strategies.

[0162] The device uses a feedback control module, employing PID or fuzzy control algorithms, to adjust the balloon's response time, avoiding hysteresis and ensuring that balloon inflation and deflation are synchronized with changes in cardiac load. Synchronous control technology ensures that balloon inflation and deflation are coordinated with each phase of the cardiac cycle, optimizing the direction and velocity of blood flow and maximizing counterpulsation efficiency. The device also automatically adjusts itself by periodically or in real time comparing historical patient data with current physiological signals, preventing over-counterpulsation or insufficient blood flow.

[0163] The Intelligent Adjustment Control Unit (hereinafter referred to as the Control Unit) is the core component of the entire intra-aortic balloon pump (IABP) treatment system. Its primary function is to automatically adjust the balloon's inflation pressure and timing based on real-time load prediction data and physiological signals, precisely aligning it with the heart's counterpulsation process and optimizing treatment effectiveness. This unit not only responds to fluctuations in cardiac load in real time but also adapts to individual patient differences, avoiding over-counterpulsation or insufficient blood flow, ensuring optimal blood flow regulation.

[0164] The basic architecture of the control unit consists of multiple modules, mainly including the following key parts:

[0165] Feedback control module: Based on real-time physiological signals and load prediction data, it automatically adjusts the inflation pressure and inflation time of the airbag to ensure that the inflation and deflation processes are highly synchronized with changes in cardiac load.

[0166] Adaptive control module: Through machine learning algorithms, the airbag inflation strategy is automatically optimized based on the individual differences of patients and the data obtained during the treatment process, and the auxiliary range of counterpulsation is gradually adjusted.

[0167] Synchronous control module: ensures that the inflation and deflation process of the airbag is coordinated with each phase of the cardiac cycle, maximizes the efficiency of blood flow counterpulsation and avoids hysteresis effect.

[0168] Algorithm module: Contains PID control, fuzzy control, reinforcement learning and other algorithms, used to accurately adjust the inflation time and pressure of the airbag.

[0169] Specifically:

[0170] a. Feedback control module

[0171] The main task of the feedback control module is to dynamically adjust the time and pressure of airbag inflation in real time according to load prediction data and physiological signals to ensure that the inflation process is synchronized with the contraction and relaxation cycle of the heart, thereby achieving the best counterpulsation effect.

[0172] Specific implementation steps:

[0173] Signal input and processing: The feedback control module receives real-time data from the load prediction and assessment module, including pulse wave (PPG), electrocardiogram (ECG), blood pressure signals, etc. Based on these signals, it calculates the current heart load state and its fluctuations.

[0174] Inflation Pressure Regulation: Based on real-time load fluctuation predictions, the control unit adjusts the inflation pressure of the airbag. The inflation pressure should match the fluctuations in the patient's cardiac load. For example, when the cardiac load is high, the airbag needs to provide a higher counterpulsation force, while when it is low, the pressure should be appropriately reduced. The control unit uses a PID control algorithm to dynamically adjust the airbag's inflation pressure, ensuring a sensitive and stable response.

[0175] Inflation time adjustment: The adjustment of inflation time is also key, especially during the switching process between systole and diastole. Through real-time ECG signals, the control unit can judge the electrical activity and rhythm of the heart, and then adjust the length of inflation time. Specifically, the inflation of the airbag should be completed during diastole and released quickly during systole to maximize the efficiency of counterpulsation. Using fuzzy control methods, the length of inflation and the start time can be automatically adjusted according to the different stages of the cardiac cycle, thereby avoiding excessive counterpulsation or hysteresis effects.

[0176] Hysteresis Compensation: The control unit also needs to compensate for the hysteresis effect caused by delayed airbag inflation in real time. By monitoring the predicted load change data and the ECG signal, the system can predict the timing of airbag inflation and trigger the inflation process in advance, thus avoiding the impact of hysteresis on the counterpulsation effect.

[0177] b. Adaptive control module

[0178] The adaptive control module aims to gradually optimize the balloon inflation strategy based on individual patient differences and feedback data during treatment to better suit the needs of different patients. This module uses a machine learning algorithm to continuously adjust the inflation strategy to ensure the optimal counterpulsation process.

[0179] Specific implementation steps:

[0180] Learning individual differences: Each patient's heart and vascular system differs, requiring corresponding adjustments to the counterpulsation strategy. The control unit collects real-time patient data (ECG, blood pressure, PPG, etc.) as well as historical data to perform personalized adjustments and optimization. Machine learning algorithms (such as reinforcement learning) continuously optimize the inflation strategy during treatment. By analyzing feedback data from different patients, the system learns the optimal counterpulsation parameters (such as inflation pressure, inflation time, and inflation cycle) for each patient.

[0181] Dynamic Adaptation and Adjustment: During treatment, the control unit dynamically adjusts the inflation pressure and duration based on changes in the patient's physiological state. For example, during acute changes in the patient's condition, the control unit can automatically increase the balloon's inflation response speed and shorten the inflation time to quickly adapt to dramatic fluctuations in cardiac workload. Through continuous adaptive optimization, the system can avoid issues such as excessive or insufficient counterpulsation and gradually improve treatment effectiveness.

[0182] Intelligent Optimization: The control unit also combines real-time hemodynamic data (such as blood flow velocity and blood pressure fluctuations) to further optimize the balloon's inflation and deflation strategies by comparing simulated and actual results. After each treatment, the system records the adjusted parameters and uses them as a reference for future treatments.

[0183] c. Synchronous control module

[0184] The synchronization control module's primary task is to ensure that the inflation and deflation of the airbag are coordinated with the heart's cyclical activity. Using a precise synchronization algorithm, this module ensures that the timing of the airbag's inflation matches the heart's contraction and relaxation, eliminating any lag between the inflation process and cardiac load, thereby maximizing the efficiency of blood counterpulsation.

[0185] Specific implementation steps:

[0186] Synchronization of electrocardiogram (ECG) and balloon inflation: Utilizing real-time ECG signals, the control unit accurately identifies each cardiac cycle (e.g., the PQRST waveform) and precisely synchronizes the inflation and deflation of the balloon. The balloon inflates during diastole and deflates rapidly during systole. This synchronized control ensures that the balloon's counterpulsation process is perfectly aligned with the cardiac rhythm.

[0187] Precise Timing: By accurately monitoring the heart's electrical activity, the control unit adjusts the balloon's inflation time to coincide with the onset of diastole, ensuring no delays and maximizing blood flow to the heart. The control unit precisely controls the balloon's inflation and deflation, switching between inflation and deflation at each stage of the cardiac cycle.

[0188] d. Algorithm module

[0189] The control unit incorporates multiple control algorithms for precisely regulating the airbag's inflation and deflation. These algorithms include PID control, fuzzy control, and reinforcement learning, each with distinct advantages and applicable scenarios.

[0190] Specific implementation steps:

[0191] PID Control Algorithm: The PID control algorithm synchronizes balloon inflation with changes in cardiac load by adjusting inflation pressure and timing in real time. This algorithm dynamically adjusts based on real-time load fluctuation data to optimize counterpulsation efficiency. If inflation pressure is excessive, the PID algorithm adjusts inflation timing to avoid over-pressure; if pressure is insufficient, the algorithm increases inflation pressure to ensure optimal counterpulsation effectiveness.

[0192] Fuzzy control: Fuzzy control systems can adjust inflation strategies based on individual patient differences using fuzzy rules. Based on fuzzy inputs (such as load trends and patient-specific conditions), they can output appropriate adjustment parameters, gradually improving treatment outcomes.

[0193] Reinforcement Learning: Using a reinforcement learning algorithm, the control unit optimizes the airbag inflation strategy based on feedback during treatment (such as counterpulsation effectiveness and load changes). During treatment, the reinforcement learning model continuously adjusts the airbag inflation timing, pressure, and duration to gradually improve treatment effectiveness.

[0194] Summary: Implementation process of intelligent adjustment control unit:

[0195] Signal input and feedback: Receive the patient's physiological signal data in real time, and use the output of the load prediction and evaluation module as feedback signal input.

[0196] Inflation pressure and time adjustment: Through PID control and fuzzy control, the inflation pressure and inflation time of the airbag are adjusted in real time to adapt to changes in cardiac load.

[0197] Adaptive learning and optimization: Through machine learning (such as reinforcement learning), the inflation strategy is dynamically optimized based on the individual differences of patients.

[0198] Synchronous control and timing adjustment: ensure the synchronization of balloon inflation with the cardiac cycle to maximize counterpulsation efficiency.

[0199] Intelligent optimization and effect evaluation: Through continuous data collection and feedback, the airbag inflation strategy is adjusted to further optimize the treatment effect.

[0200] Through the above implementation process, the intelligent adjustment control unit can automatically adjust the balloon inflation pressure and time according to real-time data, historical information and machine learning algorithms, thereby improving the accuracy and effectiveness of intra-aortic balloon counterpulsation therapy.

[0201] The following are five clinical case studies of the intra-aortic balloon pump (IABP) assist device, demonstrating how it can improve treatment outcomes and ensure safety in different patient settings:

[0202] Clinical Case 1: Intra-aortic Balloon Counterpulsation in a Patient with Acute Myocardial Infarction

[0203] Patient Background:

[0204] Gender: Male, 58 years old

[0205] Diagnosis: Acute myocardial infarction (ST-segment elevation myocardial infarction)

[0206] Concomitant medical history: hypertension, diabetes

[0207] Clinical manifestations: chest pain, bradycardia, hypotension

[0208] Treatment process: After an acute myocardial infarction, the patient is quickly rushed to the hospital and begins receiving IABP therapy to support the heart's pumping function. A device collects the patient's real-time physiological signals, including PPG, ECG, and ambulatory blood pressure data. The individual characteristic modeling module generates a personalized physiological model to infer instantaneous changes in cardiac load. The load prediction and assessment module analyzes the fluctuating trend of cardiac load in real time and adjusts the inflation pressure and timing of the IABP to ensure synchronization with changes in cardiac load. The intelligent adjustment control unit adjusts the inflation pressure of the airbag, reducing the lag effect of counterpulsation and optimizing the blood flow counterpulsation effect.

[0209] Treatment Results: During treatment, the patient's blood pressure stabilized within normal range, cardiac pumping function was supported, and chest pain was significantly relieved. The system responded to dramatic changes in cardiac workload in real time, adjusting the IABP inflation pressure and timing promptly to avoid excessive counterpulsation or insufficient blood flow. The patient ultimately successfully survived the acute myocardial infarction crisis with no further signs of cardiac deterioration.

[0210] Clinical Case 2: Intra-aortic Balloon Counterpulsation in a Patient with Severe Heart Failure

[0211] Patient Background:

[0212] Gender: Female, 72 years old

[0213] Diagnosis: Severe heart failure (NYHA class III) with coronary artery disease

[0214] Clinical manifestations: shortness of breath, edema, fatigue

[0215] Treatment Process: The patient was admitted to the hospital with acute heart failure, a significant decrease in cardiac pumping function, and severe pulmonary edema. During IABP treatment, a device monitored pulse wave (PPG) and electrocardiogram (ECG) signals in real time, and a biomechanical modeling module simulated the response characteristics of the heart and blood vessels. The load prediction module analyzed the patient's cardiac load fluctuations and adjusted the inflation time and pressure of the airbag to ensure effective support for cardiac load fluctuations. An adaptive control module was used for individualized adjustments, making the IABP inflation and deflation process more precise and flexible.

[0216] Treatment Effect: The patient's heart rate stabilized, blood pressure returned to normal, and pulmonary edema symptoms were significantly alleviated. Through the system's real-time monitoring and regulation, excessive counterpulsation and hysteresis effects were successfully avoided, significantly improving cardiac hemodynamics. Within 48 hours of treatment, the patient's shortness of breath and fatigue symptoms were significantly alleviated, and cardiac function improved as assessed clinically.

[0217] Clinical Case 3: Intra-aortic Balloon Counterpulsation Adjustment after High-Risk Coronary Artery Bypass Grafting

[0218] Patient Background:

[0219] Gender: Male, 64 years old

[0220] Diagnosis: Coronary atherosclerotic heart disease, requiring coronary artery bypass grafting (CABG)

[0221] Clinical manifestations: chest pain, acute heart failure

[0222] Treatment Process: The patient developed symptoms of acute heart failure after coronary artery bypass grafting surgery, and the physician decided to use an IABP for postoperative adjunctive therapy. The device collected the patient's PPG and ECG signals in real time, combined with imaging data (CT) to establish a personalized physiological model and estimate blood flow velocity and pressure within the aorta. The load prediction and assessment module monitored cardiac load fluctuations in real time and optimized the timing and pressure of balloon inflation to precisely meet the patient's cardiac needs. The adaptive control module adjusted the counterpulsation assistance range to ensure optimal synchronization of balloon inflation time and pressure at each stage of the heart's cycle.

[0223] Treatment outcome: The patient's cardiac pumping function was well supported, and postoperative recovery was smooth, with significant improvement in hemodynamics. The counterpulsation process was synchronized with cardiac workload, avoiding over-counterpulsation and insufficient blood flow during treatment. The patient stabilized within 48 hours after surgery and showed no significant recurrence of heart failure during follow-up.

[0224] Clinical Case 4: Intra-aortic Balloon Counterpulsation in a Patient with Aortic Dissection

[0225] Patient Background:

[0226] Gender: Male, 55 years old

[0227] Diagnosis: Acute aortic dissection (Stanford type A)

[0228] Clinical manifestations: severe chest pain, confusion, and hypotension

[0229] Treatment process: The patient was admitted to the hospital with acute aortic dissection, accompanied by severe hypotension and visceral ischemia, and IABP treatment was immediately initiated. The device collected the patient's dynamic blood pressure data, ECG, and PPG signals in real time, generated a personalized physiological model, and simulated the velocity, pressure, and resistance of aortic blood flow through computational fluid dynamics (CFD). The load prediction module analyzed fluctuations in cardiac load and adjusted the inflation time and pressure of the airbag in real time to reduce the burden on the heart and avoid the risk of excessive counterpulsation. Precise counterpulsation-assisted adjustment was achieved through the intelligent adjustment control unit, ensuring that the airbag inflation was highly synchronized with changes in aortic pressure.

[0230] Treatment Effect: After IABP treatment, the patient's blood pressure gradually returned to normal, and the symptoms of acute visceral ischemia were alleviated. Through real-time monitoring and intelligent adjustment, the IABP's inflation time and pressure were consistently synchronized with the patient's cardiac load, effectively controlling cardiac load fluctuations during treatment. The patient successfully survived the acute aortic dissection crisis and remained in stable condition postoperatively, with no major complications.

[0231] Clinical Case 5: Intra-aortic Balloon Counterpulsation in a Patient with Advanced Cardiomyopathy

[0232] Patient Background:

[0233] Gender: Female, 70 years old

[0234] Diagnosis: Advanced dilated cardiomyopathy, functional congestive heart failure

[0235] Clinical manifestations: edema, dyspnea, fatigue

[0236] Treatment Process: The patient was hospitalized for severe heart failure caused by advanced cardiomyopathy. His heart's pumping function was severely impaired, and he urgently needed IABP treatment. The device collected real-time PPG, ECG, and ambulatory blood pressure signals, and combined them with a biomechanical modeling module to assess the response characteristics of the patient's heart and blood vessels. The load prediction module predicted instantaneous changes in cardiac load based on this real-time data and adjusted the IABP inflation pressure and timing in real time, precisely controlling the counterpulsation process and avoiding excessive counterpulsation. The adaptive control module adjusted the IABP assistance range to ensure accurate support for the cardiac load during treatment.

[0237] Treatment Effect: During treatment, the patient's dyspnea and edema symptoms were significantly alleviated, and the heart's pumping function was effectively supported. The IABP assist adjustment device ensured optimal cardiac load regulation through precisely synchronized inflation and deflation, and neither inadequate nor excessive counterpulsation was observed during treatment. The patient successfully passed the critical period within four days of treatment, achieving stable hemodynamics and significantly improved heart failure symptoms.

[0238] The above five clinical cases demonstrate how the device optimizes the IABP-assisted treatment effect through real-time monitoring and intelligent adjustment in patients with different causes and stages of the disease, ensuring that cardiac load regulation during treatment reaches the optimal state, improving patient treatment outcomes and reducing potential risks.

[0239] Specifically, the method for improving the auxiliary adjustment range of intra-aortic balloon counterpulsation by the present device includes:

[0240] S1. Real-time collection of patient physiological signals

[0241] First, the device needs to collect the patient's physiological signals in real time to provide raw data for subsequent analysis and control. These physiological signals include pulse wave (PPG), electrocardiogram (ECG), heart rate variability (HRV), blood pressure and other physiological data.

[0242] Specific steps:

[0243] Pulse wave (PPG) acquisition: Pulse wave information is collected using existing photoelectric sensors (such as fingertip or earlobe PPG sensors). PPG sensors monitor minute optical changes caused by blood flow, reflecting blood flow fluctuations in real time. PPG data is transmitted to the system for real-time transmission and processing via wireless technology.

[0244] Electrocardiogram (ECG) acquisition: Use existing 12-lead ECG equipment or portable ECG devices to collect real-time information about the heart's electrical activity. These devices transmit ECG signals via Bluetooth or USB interface to the control system for subsequent analysis.

[0245] Blood pressure collection: Use existing automated blood pressure monitoring devices (such as wrist or upper arm automated blood pressure monitors) to collect patients' ambulatory blood pressure data in real time. This data is transmitted to the system via an interface for integrated analysis with other physiological signals.

[0246] Data fusion and synchronization: Various physiological signals are transmitted to the control system in real time and fused and processed through data interfaces. These signals will provide basic data for subsequent individual characteristic modeling and load forecasting.

[0247] S2. Build a personalized physiological model based on the patient’s individual characteristic data

[0248] In order to achieve personalized adjustment based on the patient's heart and vascular structure characteristics, the device needs to collect the patient's individual characteristic data through imaging equipment (CT, MRI, echocardiography, etc.), establish a personalized physiological model, and calculate the patient's heart load and blood flow conditions.

[0249] Specific steps:

[0250] Imaging data acquisition: Using imaging equipment such as CT, MRI, or echocardiography, we can obtain information about the patient's heart and vascular structure. The imaging data will be stored and imported into the system through the medical imaging system (PACS).

[0251] 3D Modeling and Parameter Extraction: Using professional medical image processing software, we create 3D models of the image data and extract the geometric parameters of the heart and blood vessels. These parameters are used in computational fluid dynamics (CFD) simulations to estimate the velocity, pressure, and resistance of blood flow within the aorta.

[0252] CFD and biomechanical simulation: Based on a 3D model of the patient's heart and blood vessels, CFD software performs hemodynamic simulations to estimate parameters such as blood flow velocity, pressure, and resistance within the aorta. This data generates personalized cardiac load predictions. Simultaneously, biomechanical modeling analyzes the mechanical properties of the heart and blood vessels, further refining the load prediction data to ensure consistency between the simulation and actual physiological conditions.

[0253] S3. Process physiological signals and individual characteristic data to generate load prediction data

[0254] The purpose of this step is to generate instantaneous cardiac load change data by combining real-time collected physiological signals with the patient's individual characteristic data. This data will provide prediction and decision-making basis for subsequent intelligent regulation and control.

[0255] Specific steps:

[0256] Physiological signal processing: Synchronously processes real-time pulse wave (PPG), electrocardiogram (ECG), blood pressure and other data to analyze instantaneous changes in cardiac load. By analyzing features such as QRS complexes and ST segment changes in the ECG waveform, the cardiac load condition can be estimated.

[0257] Load Fluctuation Trend Prediction: This system uses machine learning algorithms (such as support vector machines, regression models, or deep learning) to process real-time signals and analyze historical data to predict cardiac load fluctuation trends. This load fluctuation data serves as input to the intelligent control unit, which adjusts the airbag inflation pressure and time in real time.

[0258] Generates load change data: Based on real-time heart rate variability (HRV) data and blood pressure fluctuations, it generates instantaneous cardiac load change data. This data is used to accurately predict cardiac load fluctuation trends and ensure that the counterpulsation process is closely aligned with the heart's needs.

[0259] S4. Adjust the airbag inflation pressure and inflation time

[0260] Based on the generated load prediction data, the control system adjusts the balloon's inflation pressure and duration in real time to achieve the optimal intra-aortic balloon pump effect. This process is accomplished through the feedback control module and adaptive control module within the intelligent regulation control unit.

[0261] Specific steps:

[0262] Real-time load adjustment: The control unit receives load prediction data and begins adjusting the airbag inflation pressure. Using a PID control algorithm, the inflation pressure is adjusted in real time based on changes in cardiac load, ensuring that the airbag inflation and deflation processes are highly synchronized with cardiac load fluctuations.

[0263] Inflation Timing and Pressure Regulation: The control unit identifies the heart's contraction and relaxation phases based on real-time ECG signals and adjusts the timing of the airbag inflation. Inflation occurs during diastole and deflation occurs during systole. This precise control of inflation timing maximizes the efficiency of blood counterpulsation.

[0264] Optimizing counterpulsation: Based on individual patient differences and feedback collected during treatment, the system continuously optimizes inflation pressure and time to meet the needs of different patients. The adaptive control module uses machine learning to optimize the airbag inflation strategy to avoid excessive counterpulsation or insufficient blood flow.

[0265] S5. Achieve intelligent adaptive adjustment to optimize the counterpulsation assistance effect

[0266] During the treatment process, as the patient's physiological state changes, the device will adaptively adjust through real-time feedback and machine learning algorithms to ensure the best treatment effect.

[0267] Specific steps:

[0268] Reinforcement Learning Optimization: Utilizing a reinforcement learning algorithm, the system continuously optimizes the inflation and deflation strategies of the airbag based on feedback from each treatment (e.g., counterpulsation effectiveness, blood flow fluctuations, etc.). Feedback from each treatment serves as learning data, continuously improving the accuracy of the adjustments.

[0269] Individualized Adjustment: Based on individual patient differences and feedback during treatment, the device automatically adjusts the range of counterpulsation assistance during each treatment. For example, for patients with poor cardiac function, the system can appropriately increase the counterpulsation force, while for patients with lower cardiac load, the counterpulsation force can be appropriately reduced, ensuring the safety and effectiveness of treatment.

[0270] Reduced hysteresis and optimized synchronization: The device monitors changes in physiological signals in real time, predicting cardiac load fluctuations and reducing hysteresis. A synchronization control module ensures that the balloon inflation process is highly synchronized with each phase of the cardiac cycle, maximizing the effectiveness of counterpulsation.

[0271] Through these steps, the device can collect the patient's physiological signals and imaging data in real time, generate personalized cardiac load prediction data, and adjust the balloon inflation pressure and time based on real-time changes. This process not only optimizes the effectiveness of counterpulsation assistance, but also, through machine learning and adaptive adjustment functions, enables the device to adjust to the individual differences of different patients, maximizing treatment effectiveness while ensuring safety and reducing the risk of excessive counterpulsation or insufficient blood supply.

[0272] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A device for improving the assistive regulation range of intra-aortic balloon counterpulsation, used for intra-aortic balloon counterpulsation treatment, characterized in that: The device comprises: High-precision physiological signal acquisition unit, used to collect the patient's pulse wave, electrocardiogram, heart rate variability and / or blood pressure physiological signals in real time; The individual characteristic modeling module establishes a personalized physiological model based on the heart and vascular structure of each patient, generating load prediction data that is adapted to the patient's heart and blood vessels; a load prediction and assessment module, configured to process the physiological signals and individual characteristic data, analyze cardiac load changes in real time and generate load prediction data, thereby assessing instantaneous fluctuations in cardiac load; An intelligent adjustment control unit adjusts the inflation time and inflation pressure of the airbag according to the load prediction data to finely control the auxiliary range of the airbag counterpulsation; The individual feature modeling module includes: Imaging data acquisition module, used to collect CT, MRI or echocardiography data of patients and provide information on the patient's heart and blood vessel structure; Computational fluid dynamics simulation module, used to calculate the velocity, pressure, and resistance parameters of blood flow in the aorta based on the patient's individual characteristic data, and generate instantaneous change data of cardiac load; The biomechanical modeling module analyzes the response characteristics of the patient's heart and vascular system by simulating the mechanical properties of the heart and blood vessels; The load forecasting and assessment module includes: A machine learning module is used to analyze real-time collected physiological signals and historical data, and predict the fluctuation trend of cardiac load through deep learning algorithms. Real-time fluctuations in cardiac load include fluctuations in blood pressure and heart rate. The hemodynamic analysis module calculates the real-time fluctuation of cardiac load by combining computational fluid dynamics and real-time physiological data; The intelligent adjustment control unit includes: The feedback control module automatically adjusts the airbag inflation time and pressure based on real-time load prediction data to ensure that the inflation and deflation processes are highly synchronized with changes in cardiac load; The adaptive control module can learn and adapt to the individual differences of different patients, adjust the counterpulsation assistance adjustment range through machine learning algorithms, and optimize the airbag inflation and deflation strategies.

2. The device according to claim 1, wherein The high-precision physiological signal acquisition unit comprises: Pulse wave sensor, used to monitor aortic blood flow fluctuations in real time and provide blood flow information; Electrocardiogram (ECG) sensors, used to obtain information about the heart's electrical activity and assess changes in heart rhythm; Blood pressure sensor, used to monitor dynamic blood pressure changes and assist in evaluating hemodynamics.

3. The device according to claim 1, wherein The load prediction and assessment module can monitor and analyze cardiac load fluctuations in real time, and immediately send a signal when a sudden and drastic change in cardiac load is detected, triggering the intelligent adjustment control unit to adjust the airbag inflation pressure and inflation time to adapt to rapidly changing load requirements.

4. The device according to claim 1, wherein The device uses a PID control or fuzzy control algorithm through a feedback control module to adjust the response time of the airbag expansion, avoid the hysteresis effect, and ensure that the airbag inflation and deflation process is synchronized with the change of cardiac load.

5. The device according to claim 1, wherein The device uses synchronous control technology to ensure that the inflation and deflation time of the airbag are coordinated with the various stages of the cardiac cycle, optimize the direction and speed of blood flow, and maximize the efficiency of counterpulsation.

6. The device according to claim 1, wherein The device avoids excessive counterpulsation or insufficient blood supply during the automatic adjustment process by comparing the patient's historical data and current physiological signals regularly or in real time.

Images