External counterpulsation self-adaptive parameter adjustment method

Abstract

The invention relates to the technical field of external counterpulsation, in particular to an external counterpulsation adaptive parameter adjustment method, which comprises a signal acquisition module, a feature extraction module, a decision optimization module and a control execution module. Through real-time acquisition and analysis of multi-modal physiological signals, in combination with time-frequency domain feature extraction and a nonlinear prediction model, a relationship between treatment parameters and physiological indexes is dynamically mapped, and adaptive parameter adjustment is realized by using a particle swarm optimization algorithm. The problems that in the prior art, signal collection is insufficient, parameter adjustment lags behind, and individualized treatment accuracy is low can be solved, the matching degree of the hemodynamic effect and patient characteristics is improved, and efficient and accurate in-vitro counterpulsation treatment is achieved.

Description

Technical Field

[0001] The invention belongs to the technical field of external counterpulsation adaptive parameter adjustment, and in particular relates to an external counterpulsation adaptive parameter adjustment method. Background Art

[0002] As an important circulatory support therapy, EECP applies external pressure to the patient's limbs during diastole to promote blood return, thereby improving blood supply to vital organs such as the heart and brain. However, existing EECP devices still have deficiencies in parameter adjustment and control, particularly the lack of adaptive adjustment capabilities to individual patients' real-time physiological changes, which affects the accuracy and safety of treatment.

[0003] An extracorporeal counterpulsation and pressurization system with publication number CN112206142B proposes a method based on gradient pressure control, which can gradually adjust the airbag pressure to the set value according to the patient's physical condition and tolerance differences, thereby optimizing the treatment experience and compliance. However, the pressure regulation process of this technical solution relies on preset step-by-step rules, and does not fully consider the monitoring and feedback of the patient's real-time dynamic physiological signals (such as arterial blood pressure waveform, heart rate variability, etc.), resulting in parameter adjustment being out of sync with physiological state changes, limiting the realization of individualized treatment. In addition, its control logic is relatively fixed, and it is difficult to flexibly adjust according to the hemodynamic characteristics of different patients, which affects the application effect in complex clinical scenarios.

[0004] The external counterpulsation collaborative control system and method with publication number CN113018135B determines the pressurization time point, frequency and intensity by analyzing the pulse wave signal, and outputs a control signal to achieve collaborative work with the heart rate. However, the pulse wave analysis in this technical solution is mainly based on static functions, and does not fully consider the dynamic physiological changes that may occur during the treatment process (such as heart rate fluctuations, blood flow volume changes, etc.), resulting in a certain delay in the generation of control signals, which may affect the real-time optimization of hemodynamic effects. At the same time, the system does not introduce intelligent algorithms to conduct comprehensive analysis and prediction of multimodal physiological signals, which limits its adaptability to complex physiological states and fails to fully meet the needs of individualized treatment.

[0005] The above issues indicate that existing EECP technology still has room for improvement in terms of real-time acquisition and analysis of dynamic physiological signals, intelligent adaptive parameter adjustment, and the precision of individualized treatment. Therefore, the present invention provides an EECP adaptive parameter adjustment method. This method aims to address the existing issues of parameter adjustment lagging behind physiological changes and insufficient individual adaptability by integrating multimodal physiological signal sensors and intelligent control models to construct a dynamic optimization system consisting of a feature extraction layer and an adaptive decision-making layer. This method achieves dynamic matching of the hemodynamic effects during EECP treatment with the individual patient characteristics, effectively improving the precision and safety of treatment. Summary of the Invention

[0006] The purpose of the present invention is to provide a method and system for adaptive parameter adjustment of external counterpulsation to solve the problems in the prior art of insufficient dynamic physiological signal acquisition and analysis, parameter adjustment lagging behind physiological changes, and low accuracy of individualized treatment.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] In one aspect, the present invention provides an adaptive parameter adjustment system for external counterpulsation, comprising the following components:

[0009] A signal acquisition module is used to obtain the patient's multimodal physiological signals in real time, including arterial blood pressure waveform, heart rate variability signal and limb blood flow volume signal;

[0010] Feature extraction module, used to perform time-frequency domain analysis on the collected multimodal physiological signals and extract key features of the hemodynamic response;

[0011] A decision optimization module is used to establish a nonlinear prediction model based on the extracted features, generate a dynamic mapping relationship between treatment parameters and physiological indicators, and optimize the working parameters of the counterpulsation device through an adaptive algorithm;

[0012] The control execution module is used to output instructions based on the optimized parameters to adjust the inflation timing, pressure amplitude and inflation and deflation duration of the counterpulsation device.

[0013] Preferably, the signal acquisition module includes multiple sensor units, wherein the arterial blood pressure waveform signal is collected by a piezoelectric sensor, the heart rate variability signal is collected by a photoelectric plethysmography sensor, and the limb blood flow volume signal is collected by an ultrasonic Doppler probe; each sensor unit is connected to the central processing unit via a data transmission bus.

[0014] Preferably, the feature extraction module uses a method combining short-time Fourier transform and wavelet transform to decompose and reconstruct the signal and extract key features; short-time Fourier transform is used to analyze the frequency distribution characteristics of the signal, and wavelet transform is used to capture the instantaneous change characteristics of the signal; the extracted features include waveform peak, rising slope, falling slope and periodic fluctuation amplitude.

[0015] Preferably, the decision optimization module is divided into a two-layer structure: the first layer is the feature mapping layer, which uses the support vector machine algorithm to map the extracted features to the treatment parameter space; the second layer is the adaptive adjustment layer, which dynamically adjusts the mapping results based on the particle swarm optimization algorithm to generate the optimal parameter combination; the adaptive adjustment layer introduces a feedback mechanism to iteratively update the parameters according to the real-time collected signals.

[0016] Preferably, the control execution module drives the solenoid valve through pulse width modulation technology to regulate the inflation and deflation process of the airbag of the counterpulsation device; the control signal of the solenoid valve is generated by the microprocessor, and the microprocessor converts the control signal into an analog voltage signal through a digital-to-analog converter to drive the solenoid valve to operate; the opening and closing state of the solenoid valve is monitored in real time by the pressure detection unit and fed back to the microprocessor.

[0017] In another aspect, the present invention provides a method for adjusting adaptive parameters of external counterpulsation, comprising the following steps:

[0018] Real-time acquisition of multimodal physiological signals from patients, including arterial blood pressure waveforms, heart rate variability signals, and limb blood flow volume signals;

[0019] Perform time-frequency domain analysis on the acquired signals to extract key features of the hemodynamic response;

[0020] A nonlinear prediction model is established based on the extracted features to generate a dynamic mapping relationship between treatment parameters and physiological indicators;

[0021] Adaptive algorithms are used to optimize the operating parameters of the counterpulsation device, including inflation timing, pressure amplitude, and inflation and deflation duration;

[0022] Output optimized parameter instructions to adjust the operating status of the counterpulsation device.

[0023] Preferably, synchronous sampling technology is used in the signal acquisition process to ensure the time consistency of multimodal signals; the synchronous sampling frequency is set to 1000 Hz, and the sampled data is processed by a low-pass filter with a filter cutoff frequency set to 50 Hz to remove high-frequency noise interference.

[0024] Preferably, the time-frequency domain analysis adopts a method combining short-time Fourier transform and wavelet transform, which specifically includes the following steps: first, the signal is segmented, each segment is 1 second long, and adjacent segments overlap by 50%; second, each segment of the signal is short-time Fourier transform to calculate its spectral energy distribution; finally, the instantaneous change characteristics of the signal are extracted using wavelet transform to generate a feature vector.

[0025] Preferably, the nonlinear prediction model is constructed using a support vector machine algorithm, the input feature vector includes waveform peak, rising slope, falling slope and periodic fluctuation amplitude, and the output is the target treatment parameter; the support vector machine kernel function selects the radial basis function, the parameter C is set to 10, and γ is set to 0.1.

[0026] Preferably, the adaptive algorithm adopts a particle swarm optimization algorithm, which specifically includes the following steps: initializing the particle swarm, where each particle represents a set of treatment parameter combinations; calculating the fitness value of each particle, where the fitness function is defined as the sum of squared deviations between the hemodynamic effect and the target value; updating the particle position according to the fitness value until the convergence condition is reached; and finally outputting the optimal parameter combination.

[0027] Preferably, the expressions for the inflation timing, pressure amplitude, and inflation and deflation duration of the counterpulsation device are:

[0028] T=α×(P max -P min )+β×Δf+γ×V,

[0029] Among them, T represents the inflation time sequence, P max and P min represent the maximum and minimum values of the arterial blood pressure waveform, Δf represents the change in heart rate variability, V represents the average value of the limb blood volume signal, and α, β, and γ are weight coefficients.

[0030] The technical effects of the present invention are reflected in the following aspects: by integrating multimodal physiological signal sensors and intelligent control models, real-time acquisition and analysis of dynamic physiological signals are realized; by combining feature extraction and nonlinear prediction models, a dynamic mapping relationship between treatment parameters and physiological indicators is established; by introducing an adaptive algorithm, the problem of parameter adjustment lagging behind physiological changes is solved; by optimizing the working parameters of the counterpulsation device, the matching degree between the hemodynamic effect and the individual characteristics of the patient is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 This is the overall structural block diagram of the external counterpulsation adaptive parameter adjustment system of the present invention.

[0032] Figure 2 This is a schematic diagram of the signal acquisition module.

[0033] Figure 3 This is the workflow diagram of the feature extraction module.

[0034] Figure 4 Schematic diagram of the two-layer structure of the decision optimization module.

[0035] Figure 5 This is the implementation schematic diagram of the control execution module. DETAILED DESCRIPTION

[0036] In order to better enable relevant personnel in this technical field to fully understand and implement the present invention, the specific implementation principle of the present invention is further supplemented below in combination with a specific application scenario.

[0037] During EECP treatment, individual differences and real-time changes in physiological status can lead to fluctuations in hemodynamic effects. To address this issue, this system integrates multimodal physiological signal sensors and intelligent control models to dynamically optimize the operating parameters of the EECP device, thereby improving the accuracy and safety of treatment.

[0038] First, the signal acquisition module uses a piezoelectric sensor, a photoplethysmography sensor, and an ultrasonic Doppler probe to acquire the patient's arterial blood pressure waveform, heart rate variability signal, and limb blood volume signal, respectively. These sensor units are connected to the central processing unit via a data transmission bus to ensure temporal consistency of the multimodal signals. The synchronous sampling frequency is set to 1000 Hz to ensure high temporal resolution. The acquired signals are processed through a low-pass filter with a cutoff frequency of 50 Hz to remove high-frequency noise interference before being transmitted to the feature extraction module.

[0039] The feature extraction module then performs time-frequency analysis on the received multimodal signal. The short-time Fourier transform (SFT) module segments the signal into one-second segments with a 50% overlap. It then calculates the spectral energy distribution using SFT to analyze the signal's frequency distribution characteristics. Simultaneously, the wavelet transform (WFT) module decomposes the signal, capturing its transient variations and generating feature vectors containing the waveform's peak value, rising and falling slopes, and the amplitude of periodic fluctuations. These key features serve as the basis for subsequent decision optimization.

[0040] Next, the decision optimization module establishes a nonlinear prediction model based on the extracted features and generates a dynamic mapping relationship between treatment parameters and physiological indicators. The feature mapping layer uses the support vector machine algorithm to map feature vectors such as waveform peak, rising slope, falling slope, and periodic fluctuation amplitude to the treatment parameter space. The support vector machine kernel function selects the radial basis function, with the parameter C set to 10 and γ set to 0.1 to ensure the generalization ability of the model. The adaptive adjustment layer dynamically adjusts the mapping results based on the particle swarm optimization algorithm. When the particle swarm is initialized, each particle represents a set of treatment parameter combinations, including inflation timing, pressure amplitude, and inflation and deflation duration. The fitness function is defined as the sum of the squares of the deviations between the hemodynamic effect and the target value. The particle position is iteratively updated until the convergence condition is reached, and the optimal parameter combination is finally output.

[0041] Finally, the control execution module generates instructions based on the optimized parameters to adjust the operating state of the counterpulsation device. The microprocessor uses pulse-width modulation technology to drive the solenoid valve, regulating the inflation and deflation of the airbag. The microprocessor generates a control signal for the solenoid valve, which is converted into an analog voltage signal via a digital-to-analog converter to drive the solenoid valve. The opening and closing state of the solenoid valve is monitored in real time by a pressure detection unit, which transmits feedback signals to the microprocessor, forming a closed-loop control loop. In this way, the system can dynamically adjust the operating parameters of the counterpulsation device based on the patient's real-time physiological state, ensuring that the treatment effect is highly matched to the individual's characteristics.

[0042] In a specific application, suppose a patient's heart rate variability signal Δf suddenly increases, while their limb blood volume signal V fluctuates significantly. The system captures these changes through the feature extraction module and transmits them to the decision optimization module. A support vector machine algorithm maps these features into the treatment parameter space, and a particle swarm optimization algorithm generates a new inflation time sequence T, pressure amplitude P, and inflation and deflation duration D based on the current physiological state. The microprocessor adjusts the solenoid valve action based on these optimized parameters, thereby changing the airbag inflation and deflation process and promptly responding to the patient's physiological changes.

[0043] Through the above steps, the system achieves real-time acquisition and analysis of dynamic physiological signals and establishes a dynamic mapping relationship between treatment parameters and physiological indicators. The introduction of the adaptive algorithm solves the problem of parameter adjustment lagging behind physiological changes in traditional technologies, optimizes the operating parameters of the counterpulsation device, and thus improves the matching degree between hemodynamic effects and individual patient characteristics. This closed-loop control method not only improves the accuracy of treatment, but also enhances the robustness and adaptability of the system, providing reliable technical support for personalized treatment in complex clinical scenarios.

[0044] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0045] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. An adaptive parameter adjustment system for external counterpulsation, characterized in that: include: A signal acquisition module is used to obtain the patient's multimodal physiological signals in real time, including arterial blood pressure waveform, heart rate variability signal and limb blood flow volume signal; Feature extraction module, used to perform time-frequency domain analysis on the collected multimodal physiological signals and extract key features of the hemodynamic response; A decision optimization module is used to establish a nonlinear prediction model based on the extracted features, generate a dynamic mapping relationship between treatment parameters and physiological indicators, and optimize the working parameters of the counterpulsation device through an adaptive algorithm; The control execution module is used to output instructions based on the optimized parameters to adjust the inflation timing, pressure amplitude and inflation and deflation duration of the counterpulsation device.

2. The adaptive parameter adjustment system for external counterpulsation according to claim 1, characterized in that: The signal acquisition module includes multiple sensor units, among which the arterial blood pressure waveform signal is collected by a piezoelectric sensor, the heart rate variability signal is collected by a photoelectric plethysmography sensor, and the limb blood flow volume signal is collected by an ultrasonic Doppler probe; each sensor unit is connected to the central processing unit through a data transmission bus.

3. The adaptive parameter adjustment system for external counterpulsation according to claim 1, characterized in that: The feature extraction module uses a method combining the short-time Fourier transform module and the wavelet transform module to decompose and reconstruct the signal and extract key features; the extracted features include waveform peak, rising slope, falling slope and periodic fluctuation amplitude.

4. The adaptive parameter adjustment system for external counterpulsation according to claim 1, characterized in that: The decision optimization module is divided into two layers. The first layer is the feature mapping layer, which uses the support vector machine algorithm to map the extracted features to the treatment parameter space. The second layer is the adaptive adjustment layer, which dynamically adjusts the mapping results based on the particle swarm optimization algorithm to generate the optimal parameter combination. The adaptive adjustment layer introduces a feedback mechanism to iteratively update the parameters based on the real-time collected signals.

5. The adaptive parameter adjustment system for external counterpulsation according to claim 1, characterized in that: The control execution module drives the solenoid valve through pulse width modulation technology to regulate the inflation and deflation process of the airbag of the counterpulsation device; the control signal of the solenoid valve is generated by the microprocessor, and the microprocessor converts the control signal into an analog voltage signal through a digital-to-analog converter to drive the solenoid valve to operate; the opening and closing status of the solenoid valve is monitored in real time by the pressure detection unit and fed back to the microprocessor.

6. A method for adjusting adaptive parameters of external counterpulsation, characterized in that: The following steps are involved: Real-time acquisition of multimodal physiological signals from patients, including arterial blood pressure waveforms, heart rate variability signals, and limb blood flow volume signals; Perform time-frequency domain analysis on the acquired signals to extract key features of the hemodynamic response; A nonlinear prediction model is established based on the extracted features to generate a dynamic mapping relationship between treatment parameters and physiological indicators; Adaptive algorithms are used to optimize the operating parameters of the counterpulsation device, including inflation timing, pressure amplitude, and inflation and deflation duration; Output optimized parameter instructions to adjust the operating status of the counterpulsation device.

7. The method for adaptive parameter adjustment of external counterpulsation according to claim 6, characterized in that: Synchronous sampling technology is used in the signal acquisition process to ensure the time consistency of multimodal signals; the synchronous sampling frequency is set to 1000 Hz, and the sampled data is processed by a low-pass filter with a filter cutoff frequency set to 50 Hz.

8. The method for adaptive parameter adjustment of external counterpulsation according to claim 6, characterized in that: The time-frequency domain analysis adopts a method that combines short-time Fourier transform and wavelet transform, which specifically includes the following steps: segmenting the signal, with each segment being 1 second long and adjacent segments overlapping by 50%; performing short-time Fourier transform on each signal segment and calculating its spectral energy distribution; using wavelet transform to extract the instantaneous change characteristics of the signal and generate a feature vector.

9. The method for adaptive parameter adjustment of external counterpulsation according to claim 6, characterized in that: The nonlinear prediction model was constructed using the support vector machine algorithm. The input feature vectors included waveform peak, rising slope, falling slope, and periodic fluctuation amplitude, and the output was the target treatment parameter. The radial basis function was selected as the kernel function of the support vector machine, with the parameters C set to 10 and γ set to 0.

1.

10. The method for adaptive parameter adjustment of external counterpulsation according to claim 6, characterized in that: The adaptive algorithm uses a particle swarm optimization algorithm, which specifically includes the following steps: initializing the particle swarm, where each particle represents a set of treatment parameter combinations; calculating the fitness value of each particle, and the fitness function is defined as the sum of squared deviations between the hemodynamic effect and the target value; updating the particle position according to the fitness value until the convergence condition is reached; and finally outputting the optimal parameter combination.

Images