CN-119587868-B - Control method and system of intra-aortic balloon counterpulsation system

CN119587868BCN 119587868 BCN119587868 BCN 119587868BCN-119587868-B

Abstract

The invention provides a control method and a control system of an intra-aortic balloon counterpulsation system, and relates to the technical field of medical system control. According to the method provided by the invention, under the condition that arrhythmia or poor electrocardiosignal quality of a target user occurs in a pre-trained neural network model, the target cardiac cycle of the target user can be rapidly and accurately determined according to the historical electrocardio monitoring data of the target user, and further the inflation and deflation control of the air bag of the IABP system can be realized according to the target cardiac cycle.

Inventors

JIANG XUEJUN
LI JUN
ZHENG XIAOXIN
FENG GAOKE

Assignees

武汉大学人民医院（湖北省人民医院）

Dates

Publication Date: 20260505
Application Date: 20241128

Claims (4)

1. An intra-aortic balloon counterpulsation system is characterized by comprising a gas cylinder, a voltage stabilizer, an electromagnetic valve, a processor, a motor, a gas cylinder, an air bag and an electrocardio monitoring module; the gas cylinder, the gas cylinder and the gas bag are connected through a gas circuit, the electromagnetic valve is used for controlling gas in the gas cylinder to enter the gas bag and the gas cylinder, the voltage stabilizer is arranged between the gas cylinder and the electromagnetic valve and is used for controlling the gas pressure output by the gas cylinder within a preset gas pressure threshold range; The electrocardio monitoring module is used for: acquiring an electrocardiosignal of a target user, and sending the electrocardiosignal of the target user to the processor; The processor is configured to: acquiring historical electrocardiograph monitoring data of a target user under the condition that the amplitude of the electrocardiograph signal of the target user is smaller than a preset amplitude or the waveform quality coefficient corresponding to the electrocardiograph signal of the target user is smaller than the preset waveform quality coefficient, wherein the historical electrocardiograph monitoring data comprise electrocardiograph signals corresponding to a plurality of cardiac cycles of the target user in a target time period; The neural network model comprises a classifier, a first cyclic neural network and a second cyclic neural network, wherein the classifier is respectively connected with the first cyclic neural network and the second cyclic neural network, the classifier is used for determining the category corresponding to the historical electrocardio monitoring data, the category comprises heart rhythm normal or abnormal heart rhythm, the historical electrocardio monitoring data with the category of heart rhythm normal is sent to the first cyclic neural network, the historical electrocardio monitoring data with the category of heart rhythm abnormal is also sent to the second cyclic neural network, the first cyclic neural network is used for outputting a corresponding target cardiac cycle according to the input historical electrocardio monitoring data with the category of heart rhythm normal, and the second cyclic neural network is used for outputting a corresponding target cardiac cycle according to the input historical electrocardio monitoring data with the category of heart rhythm abnormal.
2. The system of claim 1, wherein before the processor is configured to input the historical electrocardiographic monitoring data into a pre-trained neural network model, the processor is configured to: acquiring training data, wherein the training data comprises electrocardiosignals corresponding to a plurality of cardiac cycles of each user in a plurality of users and categories corresponding to each user; Sampling the training data to obtain a plurality of training samples and categories corresponding to each training sample, wherein each training sample comprises characteristic data and label data, the characteristic data is an electrocardiosignal of the first n-1 cardiac cycles in the electrocardiosignals of the continuous n cardiac cycles of any user, and the label data is an electrocardiosignal of the nth cardiac cycle in the electrocardiosignals of the continuous n cardiac cycles; training the classifier based on a plurality of training samples and the category corresponding to each training sample to obtain a trained classifier; the processor trains the second cyclic neural network based on the training sample with abnormal heart rate, and the second cyclic neural network with the trained is obtained, wherein the loss functions of the first cyclic neural network and the second cyclic neural network are root mean square error functions.
3. The system of claim 2, wherein the intra-aortic balloon counterpulsation system further comprises a blood pressure monitoring module and a display module, the blood pressure monitoring module being electrically connected to the processor, the display module being electrically connected to the processor; After the processor is used for controlling the motor to run according to the control instruction so as to adjust the internal pressure of the air cylinder and complete the contraction and expansion operation of the air bag, the blood pressure monitoring module is used for acquiring the arterial blood pressure value of the target user and sending the arterial blood pressure value of the target user to the processor; the processor is further used for generating first alarm information when the arterial blood pressure value of the target user is not in the preset blood pressure threshold value range; The display module is used for displaying the first alarm information, and the first alarm information is used for prompting the abnormality of the arterial blood pressure value of the target user.
4. The system of claim 3, wherein the intra-aortic balloon counterpulsation system further comprises an electronic pressure relief valve and a plurality of pressure sensors disposed on the air path between the cylinder and the balloon, the electronic pressure relief valve and the plurality of pressure sensors being electrically connected to the processor; The pressure sensor is used for acquiring the pressure value inside the air bag and sending the pressure value inside the air bag to the processor; the processor is further configured to: Controlling the electronic pressure relief valve to be opened under the condition that the pressure value in the air bag is larger than a preset pressure threshold value; Generating second alarm information when the difference value between the pressure values between the cylinder and the air bag acquired by the sensors exceeds a preset pressure difference value; The display module is also used for displaying the second alarm information, wherein the second alarm information is used for prompting the abnormality of the pressure sensor; The intra-aortic balloon counterpulsation system further comprises a mechanical pressure relief valve, wherein the mechanical pressure relief valve is arranged on a gas path between the cylinder and the air bag and is used for being opened under the condition that the pressure value inside the air bag is larger than a preset pressure threshold value.

Description

Control method and system of intra-aortic balloon counterpulsation system Technical Field The invention relates to the technical field of medical system control, in particular to a control method and a control system of an intra-aortic balloon counterpulsation system. Background An Intra-aortic balloon counterpulsation (Intra-Aortic Balloon Pump, IABP) system is a critical component for use in interventional therapy of cardiovascular disease. The IABP system assists in heart operation by controlling the inflation and deflation of the balloon, thereby controlling blood flow through the user's aorta, through counterpulsation. Currently, an IABP system assists in cardiac work by way of an electrocardiographic trigger, which may be understood as synchronizing the inflation and deflation process of the balloon based on the electrophysiological activity of the user's heart. A series of electrocardiographic signals are generated during each cardiac cycle of the heart. The IABP system can accurately identify the systolic phase and the diastolic phase of the heart by monitoring the electrocardiosignal, and accordingly, the air bag of the IABP system is controlled to be inflated and deflated. However, the electrocardiograph triggering mode has certain defects and shortages, and under the condition that arrhythmia or poor electrocardiograph signal quality occurs to a user, the electrocardiograph triggering mode can not accurately identify the cardiac cycle of the user, so that the air bag inflating and deflating process is not synchronous with the cardiac working process of the user. In addition, because the electrocardiosignal is possibly influenced by factors such as electromagnetic interference, signal distortion or false triggering are caused, so that the control of the IABP system is invalid, and the IABP system has the problem of poor safety and effectiveness. Therefore, there is a need for an inflation control method and system for an aortic airbag counterpulsation airbag, which can rapidly and accurately determine the cardiac cycle of a user under the condition that the arrhythmia or poor quality of electrocardiosignals occur to the user, further control the airbag of an IABP system to inflate and deflate based on the cardiac cycle, and improve the safety and effectiveness of the IABP system. Disclosure of Invention The embodiment of the invention provides an inflation control method and an inflation control system for an aortic balloon counterpulsation balloon, which can rapidly and accurately determine the cardiac cycle of a user under the condition that the arrhythmia or poor quality of electrocardiosignals occurs to the user, further control the balloon of an IABP system to inflate and deflate based on the cardiac cycle, and improve the safety and the effectiveness of the IABP system. In order to achieve the above purpose, the embodiment of the present invention adopts the following technical scheme: The method comprises the steps that the electrocardio monitoring module obtains electrocardiosignals of a target user, sends the electrocardiosignals of the target user to the processor, obtains historical electrocardio monitoring data of the target user under the condition that the amplitude of the electrocardiosignals of the target user is smaller than a preset amplitude or the waveform quality coefficient corresponding to the electrocardiosignals of the target user is smaller than the preset waveform quality coefficient, the historical electrocardiosignal monitoring data comprise electrocardiosignals corresponding to a plurality of cardiac cycles of the target user in a target time period, the processor inputs the electrocardiosignal monitoring data to the motor in advance, and the processor controls the electrocardiosignal monitoring data to complete a network operation of the target user according to the training instruction of the target user, so that the target user can complete the operation of the target user, and the expansion cycle is controlled by the control network. In one possible implementation manner of the first aspect, the neural network model includes a classifier, a first recurrent neural network and a second recurrent neural network, the classifier is respectively connected with the first recurrent neural network and the second recurrent neural network, the classifier is used for determining a category corresponding to the historical electrocardiograph monitoring data, the category includes heart rate normal or heart rate abnormal, the historical electrocardiograph monitoring data with the category of heart rate normal is sent to the first recurrent neural network, the historical electrocardiograph monitoring data with the category of heart rate abnormal is also sent to the second recurrent neural network, the first recurrent neural network is used for outputting a corresponding target cardiac cycle according to the input historical electrocardiograph monitoring data with the category of