Central cavity management system

Abstract

The invention discloses a central cavity management system, which is used for an in-aorta balloon counterpulsation pump, and comprises a regulation and control device group, a multi-channel data acquisition module and a main control module, wherein the multi-channel data acquisition module is used for acquiring monitoring data corresponding to a plurality of positions of a balloon counterpulsation pump in the aorta; and the main control module is used for acquiring abnormal data based on the monitoring data and controlling the regulation and control device group to execute corresponding actions on the balloon counterpulsation pump in the aorta based on the abnormal data so as to realize management of a central cavity of the balloon counterpulsation pump in the aorta. The monitoring data corresponding to the multiple positions of the balloon counterpulsation pump in the aorta are acquired through the multi-channel data acquisition module, so that the abnormal data of the positions of the balloon counterpulsation pump in the aorta are recognized through the multi-dimensional monitoring data, the abnormal state of the central cavity of the balloon counterpulsation pump in the aorta is recognized in an all-around mode, and the comprehensiveness of central cavity management is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and particularly to a central cavity management system. Background Art

[0002] An Intra-Aortic Balloon Pump (IABP) is a mechanical circulatory assist device used to temporarily enhance cardiac function and is widely used in acute heart failure, cardiogenic shock, and certain high-risk cardiac surgeries to improve myocardial perfusion and reduce cardiac load. The core of the IABP is a catheter with an inflatable balloon. This catheter is inserted into the femoral artery and advanced along the aorta to the lower segment of the thoracic aorta, near the opening of the left subclavian artery. The balloon is driven by a controller synchronized with the electrocardiogram (ECG) to inflate and deflate synchronously, thereby achieving the counterpulsation effect.

[0003] The management of the central cavity saline channel of the existing Intra-Aortic Balloon Pump relies on manual nursing. It requires manual operation of the flushing device to clean it, and relies on manual bubble detection and blood return detection, which is prone to missed detection due to fatigue or environmental factors, resulting in low efficiency in the management of the central cavity saline channel of the Intra-Aortic Balloon Pump. Summary of the Invention

[0004] The present invention provides a central cavity management system to improve the management efficiency and comprehensiveness of the central cavity of the Intra-Aortic Balloon Pump.

[0005] To solve the above technical problems, the present invention provides a central cavity management system for an Intra-Aortic Balloon Pump. The central cavity management system includes: a regulation device group, a multi-channel data acquisition module, and a main control module; wherein: The multi-channel data acquisition module is used to acquire monitoring data corresponding to multiple positions of the Intra-Aortic Balloon Pump. The main control module is used to obtain abnormal data based on the monitoring data, and control the regulation device group to perform corresponding actions on the Intra-Aortic Balloon Pump based on the abnormal data, so as to achieve the management of the central cavity of the Intra-Aortic Balloon Pump.

[0006] The present invention obtains the monitoring data corresponding to multiple positions of the Intra-Aortic Balloon Pump through the multi-channel data acquisition module, thereby identifying the abnormal data at each position of the Intra-Aortic Balloon Pump through multi-dimensional monitoring data, comprehensively identifying the abnormal state of the central cavity of the Intra-Aortic Balloon Pump, and improving the comprehensiveness of the central cavity management; and when obtaining abnormal data, immediately automatically controls the regulation device group to perform corresponding actions on the Intra-Aortic Balloon Pump according to the abnormal data, and timely responds to and controls the abnormality of the central cavity of the Intra-Aortic Balloon Pump, without relying on manual monitoring of the central cavity, and improving the central cavity management efficiency.

[0007] Further, the multi-channel data acquisition module includes a pressure sensing sub-module, which is disposed at the interface of the pressure gauge of the intra-aortic balloon pump for obtaining the pressure data of the intra-aortic balloon pump in the braking state as monitoring data.

[0008] By setting a pressure sensing sub-module at the interface of the pressure gauge of the intra-aortic balloon pump, the present invention can accurately monitor the pressure data at the interface of the pressure gauge, and can realize the timely response to the abnormality of the intra-aortic balloon pump.

[0009] Further, the main control module is used to obtain abnormal data based on the monitoring data, and control the regulation device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to realize the management of the central cavity of the intra-aortic balloon pump, including: The main control module is used to determine that the pressure data is lower than the preset first pressure threshold or higher than the preset second pressure threshold as abnormal data; Based on the abnormal data, control the regulation device group to perform corresponding actions on the intra-aortic balloon pump, so as to realize the management of the central cavity of the intra-aortic balloon pump.

[0010] The present invention determines that the pressure data exceeds the threshold as abnormal through the main control module, and controls the regulation device group to perform corresponding actions on the intra-aortic balloon pump for regulation, realizes automatic identification and adjustment of abnormalities, improves the response speed of abnormality handling, and does not require manual monitoring, thus improving the management efficiency of the central cavity.

[0011] Further, the regulation device group includes a booster pump and a pressure relief valve. The main control module is used to control the regulation device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to realize the management of the central cavity of the intra-aortic balloon pump, including: When the pressure data is lower than the preset first pressure threshold, control the booster pump to pressurize the intra-aortic balloon pump until the pressure data reaches the preset first target pressure; When the pressure data is higher than the preset second pressure threshold, control the pressure relief valve to decompress the intra-aortic balloon pump until the pressure data reaches the preset second target pressure.

[0012] By setting a booster pump and a pressure relief valve, the present invention automatically pressurizes when the pressure data is low and automatically relieves pressure when the pressure data is high, accurately realizes pressure regulation, does not require manual operation, and realizes automatic management of the central cavity.

[0013] Further, the control device group includes a flushing device, and the main control module is further configured to obtain normal data based on the monitoring data, and control the control device group to perform corresponding actions on the intra-aortic balloon pump to manage the central cavity of the intra-aortic balloon pump; wherein: If the monitoring data is pressure data and it is determined that the pressure data is between a preset first pressure threshold and a preset second pressure threshold, then the pressure data is determined as normal data; Based on the normal data, control the flushing device to flush the saline channel of the central cavity of the intra-aortic balloon pump to manage the central cavity of the intra-aortic balloon pump.

[0014] When the pressure data is normal data, the present invention flushes the saline channel of the central cavity of the intra-aortic balloon pump by controlling the flushing device, realizing automatic flushing of the saline channel of the central cavity without manual operation, and improving the flushing efficiency.

[0015] Further, the multi-channel data acquisition module includes an infrared sensing sub-module, and the infrared sensing sub-module is arranged at the blood return observation position of the intra-aortic balloon pump for obtaining infrared light data of the intra-aortic balloon pump in the braking state as monitoring data.

[0016] The present invention introduces optical detection by arranging an infrared sensing sub-module at the blood return observation position of the intra-aortic balloon pump, and can objectively evaluate whether the central cavity liquid returns blood with objective data, avoiding relying on manual visual inspection and improving the accuracy of the subsequent blood return detection module.

[0017] Further, the main control module is configured to obtain abnormal data based on the monitoring data, and control the control device group to perform corresponding actions on the intra-aortic balloon pump to manage the central cavity of the intra-aortic balloon pump, including: The main control module is configured to calculate the blood concentration based on the infrared light data. When the blood concentration is greater than or equal to a preset concentration threshold, the blood concentration is abnormal data; Based on the abnormal data, control the control device group to perform corresponding actions on the intra-aortic balloon pump to manage the central cavity of the intra-aortic balloon pump.

[0018] The present invention calculates the blood concentration based on the infrared light data, determines abnormality when exceeding the concentration threshold, quantifies the blood concentration in the central cavity, timely identifies abnormal data, and improves the reliability of central cavity management.

[0019] Further, the control device group further includes an alarm device, and the main control module is used to control the control device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to manage the central cavity of the intra-aortic balloon pump, including: Based on the abnormal data, controlling the alarm device to perform a blood return detection alarm to manage the central cavity of the intra-aortic balloon pump.

[0020] When the present invention detects abnormal data through infrared light data, it timely performs a blood return detection alarm to avoid blood invading the central cavity pipeline and affecting the use effect of the intra-aortic balloon pump.

[0021] Further, the multi-channel data acquisition module includes an ultrasonic sensing sub-module, and the ultrasonic sensing sub-module is arranged below the flow clamp of the intra-aortic balloon pump for acquiring ultrasonic data of the intra-aortic balloon pump in the braking state as monitoring data.

[0022] In the present invention, the ultrasonic sensing sub-module is placed below the flow clamp to obtain ultrasonic signals, so that according to the ultrasonic signals, by collecting different signals at different positions, the all-round management of the central cavity pipeline can be realized.

[0023] Further, the main control module is used to obtain abnormal data based on the monitoring data, and control the control device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to manage the central cavity of the intra-aortic balloon pump, including: The main control module is used to calculate the signal loss amplitude based on the ultrasonic data. When the signal difference amplitude continuously is greater than or equal to a preset amplitude threshold within a preset time period, the ultrasonic data is abnormal data; Based on the abnormal data, controlling the control device group to perform corresponding actions on the intra-aortic balloon pump to manage the central cavity of the intra-aortic balloon pump.

[0024] In the present invention, the main control module calculates the signal loss amplitude. If it continuously exceeds the preset amplitude threshold within the set time period, it is determined as abnormal, combining time and amplitude to improve the accuracy of abnormal recognition and avoid misjudgment.

[0025] Further, the control device group further includes an alarm device, and the main control module is used to control the control device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to manage the central cavity of the intra-aortic balloon pump, including: Based on the abnormal data, controlling the alarm device to perform a bubble detection alarm to manage the central cavity of the intra-aortic balloon pump.

[0026] When the present invention detects abnormal data through ultrasonic data, it promptly performs bubble detection and alarm to avoid the generation of bubbles in the central cavity pipeline, which affects the use effect of the intra-aortic balloon pump.

[0027] Further, the main control module is used to obtain abnormal data based on the monitoring data, and control the regulation device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to realize the management of the central cavity of the intra-aortic balloon pump, including: The main control module is used to obtain the monitoring data, and detect the monitoring data based on the abnormal detection model to obtain abnormal data; Based on the abnormal data, control the regulation device group to perform corresponding actions on the intra-aortic balloon pump, so as to realize the management of the central cavity of the intra-aortic balloon pump.

[0028] The present invention monitors the monitoring model through the abnormal detection model, thereby automatically identifying abnormal data, so as to subsequently control the regulation device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to realize the management of the central cavity of the intra-aortic balloon pump.

[0029] Further, the monitoring data includes pressure data, infrared light data, and ultrasonic data; the main control module is used to obtain the monitoring data, and detect the monitoring data based on the abnormal detection model to obtain abnormal data, including: Obtain the monitoring data, respectively extract features of the pressure data, the infrared light data, and the ultrasonic data to obtain pressure features, infrared features, and ultrasonic features; Calculate the correlation coefficients of any two of the pressure features, infrared features, and ultrasonic features, and construct a geometric triangle structure of the pressure features, infrared features, and ultrasonic features based on the correlation coefficients; Adjust the fusion weights of the pressure features, infrared features, and ultrasonic features based on the geometric triangle structure, and fuse the pressure features, infrared features, and ultrasonic features based on the fusion weights to obtain fusion features; Input the fusion features into the CAE-LSTM model for reconstruction to obtain the Z-score and isolation forest score of each feature; Determine abnormal data based on the Z-score and isolation forest score.

[0030] The present invention first separately extracts the features of the pressure data, the infrared light data, and the ultrasonic data to avoid the loss of data features, and then fuses each feature to improve the recognition ability in complex situations. For example, in the use of IABP, balloon rupture or catheter kinking may only show a slight change in the pressure waveform, while multi-modal data can cross-verify different abnormal situations.

[0031] Further, calculating the correlation coefficients of any two of the pressure feature, the infrared feature, and the ultrasonic feature, and constructing the geometric triangular structure based on the correlation coefficients includes: Calculating the first correlation coefficient between the pressure feature and the infrared feature based on the R correlation coefficient method; Calculating the second correlation coefficient between the pressure feature and the ultrasonic feature based on the R correlation coefficient method; Calculating the third correlation coefficient between the infrared feature and the ultrasonic feature based on the M correlation coefficient method; Mapping the first correlation coefficient, the second correlation coefficient, and the third correlation coefficient into a two-dimensional plane, and constructing a geometric triangular structure with the first correlation coefficient, the second correlation coefficient, and the third correlation coefficient as the side lengths.

[0032] In this embodiment, the correlation coefficients between different features are respectively constructed based on the R / M correlation coefficient method, so as to construct a geometric triangular structure with the correlation coefficients as the side lengths, quantify the association strength between different data features, and thus perform data coupling on different data features to avoid system misjudgment caused by the failure of a single sensor.

[0033] Further, adjusting the fusion weights of the pressure feature, the infrared feature, and the ultrasonic feature based on the geometric triangular structure, and fusing the pressure feature, the infrared feature, and the ultrasonic feature based on the fusion weights to obtain a fusion feature includes: Calculating the triangular area of the geometric triangular structure; When the triangular area minus the preset area threshold is greater than or equal to the first area threshold, the fusion weight is the preset reference weight; When the triangular area minus the preset area threshold is less than the first area threshold, calculating the ratio value of each side in the geometric triangular structure to the triangular area; adjusting the fusion weights of the pressure feature, the infrared feature, and the ultrasonic feature based on the ratio value; Fusing the pressure feature, the infrared feature, and the ultrasonic feature based on the fusion weights to obtain a fusion feature.

[0034] The present invention measures the stability between different data sources through the area of the geometric triangular structure. When the area of the triangular structure is larger, it indicates that the coupling between features is weak and the information complementarity is strong. Keeping the reference weight can maximize information retention. When the area is smaller, it indicates that a certain type of data is abnormal or interfered. Furthermore, the weights of each feature are dynamically adjusted through the ratio value of each side in the triangular structure to the triangular area to avoid noise amplification. Description of the Drawings

[0035] Figure 1Schematic structural diagram of a central cavity management system for an intra-aortic balloon pump provided in an embodiment of the present invention; Figure 2 Schematic flow diagram of central cavity saline flushing provided in an embodiment of the present invention; Figure 3 Schematic flow diagram of blood return monitoring provided in an embodiment of the present invention; Figure 4 Schematic flow diagram of bubble detection provided in an embodiment of the present invention. Detailed implementation manners

[0036] The following further describes in detail the specific implementation manners of the present invention in conjunction with the accompanying drawings and embodiments. The following embodiments are used to illustrate the present invention, but are not used to limit the scope of the present invention.

[0037] The terms "first" and "second" in the specification, claims and drawings of this application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally further include steps or units not listed, or may optionally further include other steps or units inherent to these processes, methods, products or devices.

[0038] Referring to "embodiment" herein means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0039] Embodiment 1 Refer to Figure 1 , Figure 1 Schematic structural diagram of a central cavity management system for an intra-aortic balloon pump provided in an embodiment of the present invention. An embodiment of the present invention provides a central cavity management system for an intra-aortic balloon pump, and the central cavity management system includes: a regulation device group 103, a multi-channel data acquisition module 101, and a main control module 102; wherein: The multi-channel data acquisition module is used to acquire monitoring data corresponding to multiple positions of the intra-aortic balloon pump; The main control module is used to obtain abnormal data based on the monitoring data, and control the regulation device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to realize the management of the central cavity of the intra-aortic balloon pump.

[0040] In this embodiment, by setting a multi-channel data acquisition module on the intra-aortic balloon pump, multi-dimensional monitoring data of the intra-aortic balloon pump is obtained, and whether the monitoring data is abnormal is identified according to a preset rule. When an abnormality occurs, the control device group is controlled based on the data type of the abnormal data to perform corresponding actions on the intra-aortic balloon pump, so as to realize the management of the central cavity of the intra-aortic balloon pump.

[0041] In this embodiment, the monitoring data corresponding to multiple positions of the intra-aortic balloon pump is obtained through a multi-channel data acquisition module, so as to identify the abnormal data at each position of the intra-aortic balloon pump through multi-dimensional monitoring data, comprehensively identify the abnormal state of the central cavity of the intra-aortic balloon pump, and improve the comprehensiveness of central cavity management; and when abnormal data is obtained, the control device group is automatically controlled according to the abnormal data to perform corresponding actions on the intra-aortic balloon pump immediately, and the central cavity of the intra-aortic balloon pump is abnormally responded to and controlled in a timely manner, without relying on manual monitoring of the central cavity, thereby improving the central cavity management efficiency.

[0042] In this embodiment, the multi-channel data acquisition module includes a pressure sensing sub-module, an infrared sensing sub-module, and an ultrasonic sensing sub-module. The multi-channel data acquisition module is arranged at different positions outside the intra-aortic balloon pump and is used to monitor the data of the central cavity pipeline of the intra-aortic balloon pump.

[0043] In this embodiment, the multi-channel data acquisition module includes a pressure sensing sub-module, and the pressure sensing sub-module is arranged at the interface of the pressure gauge of the intra-aortic balloon pump and is used to obtain the pressure data of the intra-aortic balloon pump in the braking state as monitoring data.

[0044] In this embodiment, the pressure sensing sub-module includes an infrared sensor, which is specifically a MEMS piezoresistive sensor (range 0-500 mmHg, accuracy ±1%) and is arranged at the interface between the pressure bag and the pressure gauge.

[0045] In this embodiment, when the intra-aortic balloon pump is braked, the pressure sensing sub-module starts to monitor the pressure data of the pressure bag of the intra-aortic balloon pump.

[0046] In this embodiment, by arranging a pressure sensing sub-module at the interface of the pressure gauge of the intra-aortic balloon pump, the pressure data at the interface of the pressure gauge can be accurately monitored, and timely response to the abnormality of the intra-aortic balloon pump can be realized.

[0047] In this embodiment, the main control module is configured to obtain abnormal data based on the monitoring data, and control the regulation device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to manage the central cavity of the intra-aortic balloon pump, including: The main control module is configured to determine that the pressure data is abnormal data when it is lower than a preset first pressure threshold or higher than a preset second pressure threshold; Based on the abnormal data, control the regulation device group to perform corresponding actions on the intra-aortic balloon pump, so as to manage the central cavity of the intra-aortic balloon pump.

[0048] In this embodiment, the pressure data is monitored in real time. When the pressure data is lower than the preset first pressure threshold or higher than the preset second pressure threshold, it is abnormal data. At this time, the regulation device group can be controlled according to the control strategy to perform corresponding actions on the intra-aortic balloon pump.

[0049] In this embodiment, if abnormal pressure data is recognized during the saline flushing process, the saline flushing is stopped. If abnormal pressure data is recognized during the non-saline flushing process, the regulation device group is controlled based on the target pressure to perform corresponding actions on the intra-aortic balloon pump, so as to adjust the pressure of the pressure bag enough.

[0050] In this embodiment, it is determined by the main control module that the pressure data exceeds the threshold as abnormal, and the regulation device group is controlled to perform corresponding actions on the intra-aortic balloon pump for regulation, realizing automatic abnormal recognition and adjustment, improving the response speed of abnormal handling, eliminating the need for manual monitoring, and improving the management efficiency of the central cavity.

[0051] In this embodiment, the regulation device group includes a booster pump and a pressure relief valve. The main control module is configured to control the regulation device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to manage the central cavity of the intra-aortic balloon pump, including: When the pressure data is lower than the preset first pressure threshold, control the booster pump to increase the pressure of the intra-aortic balloon pump until the pressure data reaches the preset first target pressure; When the pressure data is higher than the preset second pressure threshold, control the pressure relief valve to reduce the pressure of the intra-aortic balloon pump until the pressure data reaches the preset second target pressure.

[0052] In this embodiment, by setting a booster pump and a pressure relief valve, when the pressure data is at a low pressure, it automatically increases the pressure, and when the pressure data is at a high pressure, it automatically relieves the pressure, accurately realizing pressure regulation without manual operation, and realizing automatic management of the central cavity.

[0053] In this embodiment, when it is determined that the current pressure data is in an abnormal state, a pressure regulation instruction is generated based on a preset control strategy and the abnormal state, and the pressure value of the pressure bag is adjusted based on the pressure regulation instruction.

[0054] In this embodiment, when pressure abnormality is detected, the pressure of the pressure bag is automatically adjusted based on the control strategy without manual intervention, ensuring continuous and stable pipeline pressure and further reducing the risk of channel occlusion or poor blood reflux caused by pressure abnormality.

[0055] In this embodiment, the pressure sensor is a MEMS piezoresistive sensor with a measurement range of 0 - 500 mmHg and an accuracy of ±1%.

[0056] In this embodiment, the pressure sensor is arranged at the pressure gauge interface.

[0057] In this embodiment, if the pressure < 280 mmHg or the pressure > 320 mmHg, the current pressure data is in an abnormal state. When the pressure < 280 mmHg, the booster pump is controlled to increase the pressure; when the pressure > 320 mmHg, the pressure relief valve is controlled to reduce the pressure.

[0058] In this embodiment, when the pressure is too high, the pressure relief valve is triggered to reduce the pressure; when the pressure is too low, the booster pump is triggered to increase the pressure. Different adjustment methods are adopted for different abnormal scenarios based on the control strategy, which can more precisely maintain the system running within the safe pressure range, improve the system stability, and ensure the continuous and reliable operation of the intra-aortic balloon pump.

[0059] In this embodiment, the regulation device group includes a booster pump and a pressure relief valve. The main control module is used to control the regulation device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data to manage the central cavity of the intra-aortic balloon pump. It also includes: When adjusting the pressure value of the pressure bag based on the pressure regulation instruction, real-time pressure data is obtained; it is detected whether the real-time pressure data returns to normal within a preset time period; if it does not return to normal, a pressure data abnormality information is generated, and an alarm is made based on the pressure data abnormality information.

[0060] In this embodiment, a preset pressure control duration is set. When the pressure still does not return to the normal state after being regulated for a period of time, an alarm information is generated.

[0061] In this embodiment, when the abnormal state is that the pressure data is higher than a preset second pressure threshold, a pressure relief control instruction is generated, and the pressure relief valve is controlled to reduce the pressure based on the pressure relief control instruction. When the real-time pressure data does not reach the second target pressure within a period of time, an alarm is made.

[0062] In this embodiment, when the abnormal state is that the pressure data is lower than the preset first pressure threshold, a boost control instruction is generated, and the boost pump is controlled to boost based on the boost control instruction. When the real-time pressure data does not reach the first target pressure within a period of time, an alarm is given.

[0063] In this embodiment, during the pressure adjustment process, it is continuously monitored whether the pressure in the pressure bag meets 300 mmHg to meet the micro-pressure perfusion, balance with the intravascular pressure, and prevent blood backflow. When the pressure of the saline bag is less than (the first pressure threshold) 280 mmHg, the boost pump is started to boost until the pressure reaches 305 mmHg (the first target pressure), and then the pressure pump is stopped. If the target pressure is not reached after more than 10 s, the device alarms. If the flow clamp is open at this time, the flow clamp is closed; when it is greater than 320 mmHg (the second pressure threshold), the pressure is relieved to 300 mmHg (the second target pressure). If the target pressure is not reached within 10 s, the device alarms. If the flow clamp is open at this time, the flow clamp is closed.

[0064] In this embodiment, during the pressure regulation process, the pressure is continuously monitored, and it is detected whether it returns to normal within the preset time. Otherwise, an alarm is given, so as to realize the closed-loop verification of the pressure regulation effect. Once the continuous adjustment is ineffective, an alarm is given immediately to prevent potential safety hazards caused by the failure of the control command or device failure.

[0065] In this embodiment, when the pressure adjustment is completed and it is determined that the current pressure data is normal, a flushing control instruction is generated based on the flushing mode.

[0066] In this embodiment, the regulation device group includes a flushing device. The main control module is further configured to obtain normal data based on the monitoring data, and control the regulation device group to perform corresponding actions on the intra-aortic balloon pump based on the normal data, so as to realize the management of the central cavity of the intra-aortic balloon pump; wherein: If the monitoring data is pressure data and it is determined that the pressure data is between the preset first pressure threshold and the preset second pressure threshold, then the pressure data is determined as normal data; Based on the normal data, control the flushing device to flush the central cavity saline channel of the intra-aortic balloon pump, so as to realize the management of the central cavity of the intra-aortic balloon pump.

[0067] In this embodiment, when the pressure data is normal data, the central cavity saline channel of the intra-aortic balloon pump is flushed by controlling the flushing device, realizing the automatic flushing of the central cavity saline channel without manual operation, and improving the flushing efficiency.

[0068] Please refer to Figure 2 , Figure 2 which is a schematic flow diagram of central cavity saline flushing provided by the embodiment of the present invention.

[0069] In this embodiment, when it is determined that the pressure data is normal, the flushing device is controlled through different flushing modes including manual mode and automatic mode to flush the saline channel of the central cavity of the intra-aortic balloon pump.

[0070] In this embodiment, a flushing control instruction is generated based on a preset flushing mode, and the flushing device is controlled based on the flushing control instruction to flush the saline channel of the central cavity, where the flushing mode includes manual mode and automatic mode.

[0071] In this embodiment, in the automatic mode, the preset flushing period is to flush once per hour, and the flushing duration can be set manually, with a default of 15 seconds.

[0072] In this embodiment, in the manual mode, long pressing the flushing button is supported for continuous flushing, and short pressing the flushing button is supported for short-time flushing. The short-time flushing duration can be set manually, and the default flushing duration is set to 15 seconds.

[0073] In this embodiment, two flushing methods of manual mode and automatic mode are supported; within the normal pressure range, flushing control instructions can be generated according to different pressure modes, improving the flexibility of central cavity management.

[0074] In this embodiment, before flushing, the braking device is enabled. The braking device is connected to the data acquisition module, the flushing control module, and the flushing control module. After the braking device is powered on, the pressure can be detected for central cavity saline flushing.

[0075] In this embodiment, the braking device includes a clamping device and a stepping motor driving a ball screw. Among them, the stepping angle of the stepping motor is 1.8°, and the clamping force of the clamping device is set to 0.5 - 2.0 N, which can be adjusted manually.

[0076] In this embodiment, when the flushing mode is the automatic mode, a flushing control instruction is generated based on the preset flushing period and the preset flushing duration, and the flushing device is controlled based on the flushing control instruction to flush the saline channel of the central cavity.

[0077] In this embodiment, in the automatic mode, the flushing valve is opened for 15 seconds per hour for flushing (error ±1 s).

[0078] In this embodiment, in the automatic mode, a flushing instruction is automatically generated and executed based on the preset flushing period and duration, and the central cavity channel can be maintained and flushed regularly and quantitatively without manual triggering by nursing staff, significantly improving work efficiency and ensuring that the channel is always unobstructed.

[0079] In this embodiment, when the flushing mode is the manual mode, the state of the flushing button is acquired, a flushing control instruction is generated based on the state of the flushing button, and the flushing device is controlled based on the flushing control instruction to flush the saline channel of the central cavity.

[0080] In this embodiment, the manual mode supports short pressing (15 - second timing) or long pressing (continuous flushing).

[0081] In this embodiment, in the manual mode, a flushing instruction is generated by monitoring the state of the flushing button, enabling medical staff to initiate cleaning at any time according to clinical needs, thereby improving the flexibility of the system.

[0082] In this embodiment, when the flushing mode is the manual mode, it further includes monitoring the state of the flushing button. When the state of the flushing button changes or the flushing duration reaches a preset duration threshold, the flushing is stopped to complete the management of the central cavity.

[0083] In this embodiment, by also monitoring the button state or the flushing duration in the manual mode and stopping the flushing when the conditions are met, it prevents excessive flushing caused by accidental button touch or over - flushing, improves safety and reliability, and at the same time ensures the controllability of the flushing process.

[0084] In this embodiment, the multi - channel data acquisition module includes an infrared sensing sub - module. The infrared sensing sub - module is arranged at the blood return observation point of the intra - aortic balloon pump, and is used to acquire the infrared light data of the intra - aortic balloon pump in the braking state as monitoring data.

[0085] In this embodiment, the infrared sensing sub - module further includes an infrared sensor, which is arranged at the blood return observation point of the intra - aortic balloon pump.

[0086] In this embodiment, the infrared sensor is a U - type clamping infrared sensing unit, which is arranged at the blood return observation point and includes a transmitting end (940nm wavelength LED) and a receiving end (photodiode), clamped on the outer wall of the pipeline. Using the principle of optical induction, it judges whether there is blood return according to the light transmittance. When there is blood return in the pipeline, it will cause a change in the characteristics of infrared reflection, and the voltage at both ends will increase. The sensor is wired to the voltage acquisition module, and the voltage acquisition module converts the continuous analog voltage signal into a discrete digital signal through AD analog - to - digital conversion. The voltage acquisition module is wired to the main control module and uses the CAN bus to transmit data. The main control module judges whether to alarm according to the set threshold.

[0087] Please refer to Figure 3 , Figure 3 which is a schematic flow diagram of blood return monitoring provided by the embodiment of the present invention.

[0088] In this embodiment, by setting an infrared sensing sub-module at the blood return observation point of the intra-aortic balloon pump, optical detection is introduced, enabling the assessment of whether the central cavity liquid returns blood with objective data, avoiding relying on manual visual inspection, and improving the accuracy of the subsequent blood return detection module.

[0089] In this embodiment, the main control module is used to obtain abnormal data based on the monitoring data, and control the regulation device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to manage the central cavity of the intra-aortic balloon pump, including: The main control module is used to calculate the blood concentration based on the infrared light data. When the blood concentration is greater than or equal to the preset concentration threshold, the blood concentration is abnormal data; Based on the abnormal data, control the regulation device group to perform corresponding actions on the intra-aortic balloon pump, so as to manage the central cavity of the intra-aortic balloon pump.

[0090] In this embodiment, obtain the infrared light data of the central cavity liquid, calculate the light transmittance of the central cavity liquid based on the infrared light data; calculate the blood concentration of the central cavity liquid based on the light transmittance; when the blood concentration is greater than or equal to the preset concentration threshold, generate a blood return alarm message, and perform a blood return alarm based on the blood return alarm message.

[0091] In this embodiment, the regulation device group further includes an alarm device. The main control module is used to control the regulation device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to manage the central cavity of the intra-aortic balloon pump, including: Based on the abnormal data, control the alarm device to perform a blood return detection alarm, so as to manage the central cavity of the intra-aortic balloon pump.

[0092] In this embodiment, when abnormal data is detected through the infrared light data, a blood return detection alarm is carried out in a timely manner to avoid blood invading the central cavity pipeline and affecting the use effect of the intra-aortic balloon pump.

[0093] In this embodiment, the infrared light transmittance of the liquid can be quantified through the infrared light data, so as to calculate the blood concentration. If the concentration is too high, an alarm is given, realizing automatic and quantitative identification of blood return, early detection of blood reflux in the pipeline, avoiding liquid contamination or mis-infusion, and improving patient safety.

[0094] In this embodiment, when an infrared light signal is detected through the infrared light data of the central cavity liquid, the signal is transmitted to the voltage acquisition module. The voltage acquisition module judges the light transmittance of the central cavity liquid through the obtained voltage, and judges whether the blood concentration is greater than or equal to the preset concentration threshold based on the voltage. If so, a blood return alarm message is generated, and a blood return alarm is performed based on the blood return alarm message.

[0095] As a specific example of an embodiment of the present invention, when the voltage collected by the voltage acquisition module exceeds the preset standard voltage threshold (2.0V - 3.0V), at this time, the blood concentration is greater than the preset concentration threshold (0.5%), a blood return alarm message is generated, and a blood return alarm is performed based on the blood return alarm message.

[0096] In this embodiment, by calculating the blood concentration using the infrared transmittance and alarming when the concentration is too high, automatic and quantitative identification of blood return can be achieved, early detection of blood reflux in the pipeline can be realized, liquid contamination or misinfusion can be avoided, and patient safety can be improved.

[0097] Please refer to Figure 4 , Figure 4 which is a schematic flowchart of a bubble detection provided by an embodiment of the present invention.

[0098] In this embodiment, the multi-channel data acquisition module includes an ultrasonic sensing sub-module, and the ultrasonic sensing sub-module is disposed below the flow clamp of the intra-aortic balloon pump for obtaining ultrasonic data of the intra-aortic balloon pump in the braking state as monitoring data.

[0099] In this embodiment, the ultrasonic sensor is a 1MHz piezoelectric ceramic ultrasonic transducer, and the distance between the transmitting end and the receiving end is 10mm.

[0100] In this embodiment, by placing the ultrasonic sensing sub-module below the flow clamp to obtain ultrasonic signals, and thus, according to the ultrasonic signals, by collecting different signals at different positions, all-round management of the central cavity pipeline can be realized.

[0101] In this embodiment, the main control module is used to obtain abnormal data based on the monitoring data, and based on the abnormal data, control the regulation device group to perform corresponding actions on the intra-aortic balloon pump to realize the management of the central cavity of the intra-aortic balloon pump, including: The main control module is used to calculate the signal loss amplitude based on the ultrasonic data. When the signal difference amplitude continuously is greater than or equal to the preset amplitude threshold within a preset time period, the ultrasonic data is abnormal data; Based on the abnormal data, control the regulation device group to perform corresponding actions on the intra-aortic balloon pump to realize the management of the central cavity of the intra-aortic balloon pump.

[0102] In this embodiment, the ultrasonic signal intensity of the central cavity liquid is obtained, and the ultrasonic signal intensity includes the receiving intensity and the transmitting intensity; the signal loss amplitude can be calculated through the receiving intensity and the transmitting intensity. Specifically: signal loss amplitude = receiving intensity / transmitting intensity.

[0103] In this embodiment, the signal loss amplitude at this moment can be calculated through the received signal strength and the transmitted signal strength. Under normal conditions, the signal loss amplitude is less than 20%, that is, the received signal strength ≥ 80% of the transmitted strength. When the signal loss amplitude continuously exceeds the preset amplitude threshold, the ultrasonic data is abnormal data, and effective bubbles appear in the central cavity liquid. At this time, a bubble alarm message is generated.

[0104] In this embodiment, ultrasonic waves are used to detect whether there are bubbles in the passing liquid; ultrasonic bubble monitoring utilizes the principle that the acoustic impedance of ultrasonic waves in liquid and gas is different to achieve the identification and detection of bubbles or liquid. When there are bubbles, due to the large change in acoustic impedance, the ultrasonic waves will be reflected back and will not reach the receiving end, so that the sensor can detect the presence of bubbles. The ultrasonic bubble sensor is based on the principle of ultrasonic transmission medium attenuation. When the pipeline is full of liquid, since the propagation impedance of the liquid is small, the signal received by the receiving end is roughly the same as that of the transmitting end. After being amplified and shaped by the hardware, a judgment will be made. When the pipeline contains bubbles, that is, the propagation blockage of air becomes larger, resulting in no signal at the receiving end. That is to say, when ultrasonic waves are incident from water into air, almost all the energy is reflected on the boundary surface. Based on this change, it is judged whether bubbles are generated. The bubbles in the fluid are monitored by detecting the change in the ultrasonic signal strength.

[0105] In this embodiment, bubbles are determined by the received intensity and the transmitted intensity. When the received signal continuously drops below the intensity threshold and times out, an alarm is issued, which can automatically and continuously monitor the generation of bubbles in the central cavity and give an alarm in time to prevent the risk of air embolism and further ensure the safety of the patient using the pump.

[0106] In this embodiment, the main control module calculates the signal loss amplitude. If it continuously exceeds the preset amplitude threshold within the set time period, it is determined as abnormal. Combining time and amplitude improves the accuracy of abnormal identification and avoids misjudgment.

[0107] In this embodiment, the control device group further includes an alarm device. The main control module is used to control the control device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data to realize the management of the central cavity of the intra-aortic balloon pump, including: Based on the abnormal data, control the alarm device to perform bubble detection and alarm to realize the management of the central cavity of the intra-aortic balloon pump.

[0108] In this embodiment, when abnormal data is detected through ultrasonic data, bubble detection and alarm are carried out in time to avoid the generation of bubbles in the central cavity pipeline and affect the use effect of the intra-aortic balloon pump.

[0109] In this embodiment, the multi-channel data acquisition module is used to obtain the monitoring data corresponding to multiple positions of the intra-aortic balloon pump, so as to identify the abnormal data at each position of the intra-aortic balloon pump through the multi-dimensional monitoring data, comprehensively identify the abnormal state of the central cavity of the intra-aortic balloon pump, and improve the comprehensiveness of the central cavity management; and when obtaining the abnormal data, the control device group is immediately automatically controlled according to the abnormal data to perform corresponding actions on the intra-aortic balloon pump, and the central cavity of the intra-aortic balloon pump is abnormally responded to and controlled in a timely manner, without relying on manual monitoring of the central cavity, thereby improving the management efficiency of the central cavity.

[0110] In this embodiment, the main control module is used to obtain abnormal data based on the monitoring data, and control the control device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to manage the central cavity of the intra-aortic balloon pump, including: The main control module is used to obtain the monitoring data and detect the monitoring data based on the anomaly detection model to obtain abnormal data; Based on the abnormal data, the control device group is controlled to perform corresponding actions on the intra-aortic balloon pump, so as to manage the central cavity of the intra-aortic balloon pump.

[0111] In this embodiment, the monitoring data is stored to construct a historical monitoring database.

[0112] In this embodiment, the monitoring data includes pressure data, infrared light data, and ultrasonic data; the main control module is used to obtain the monitoring data and detect the monitoring data based on the anomaly detection model to obtain abnormal data, including: Obtain the monitoring data, and respectively extract features from the pressure data, the infrared light data, and the ultrasonic data to obtain pressure features, infrared features, and ultrasonic features; Calculate the correlation coefficients of any two of the pressure features, infrared features, and ultrasonic features, and construct a geometric triangle structure of the pressure features, infrared features, and ultrasonic features based on the correlation coefficients; Adjust the fusion weights of the pressure features, infrared features, and ultrasonic features based on the geometric triangle structure, and fuse the pressure features, infrared features, and ultrasonic features based on the fusion weights to obtain fusion features; Input the fusion features into the CAE-LSTM model for reconstruction to obtain the Z-score and isolation forest score of each feature; Determine the abnormal data based on the Z-score and isolation forest score.

[0113] In this embodiment, the monitoring data is preprocessed and time-synchronized and aligned.

[0114] In this embodiment, the monitoring data is aligned based on a preset window length and overlap rate to generate a time series block in a fixed format, and normalization processing is performed in each window to generate standard data, which includes pressure data, infrared light data, and ultrasonic data. After obtaining the standard data, feature extraction is respectively performed on the pressure data, infrared light data, and ultrasonic data to obtain pressure features, infrared features, and ultrasonic features, where the pressure features, infrared features, and ultrasonic features all include time-frequency features and frequency-domain features.

[0115] In this embodiment, by extracting time-domain (mean, variance, peak, etc.) features and frequency-domain (FFT energy band) features through the three channels of pressure, infrared, and ultrasound respectively, physical interpretability and signal integrity can be maintained, and information loss can be avoided.

[0116] In this embodiment, calculating the correlation coefficients between any two of the pressure features, infrared features, and ultrasonic features, and constructing a geometric triangle structure based on the correlation coefficients includes: Calculating a first correlation coefficient between the pressure feature and the infrared feature based on the R correlation coefficient method; Calculating a second correlation coefficient between the pressure feature and the ultrasonic feature based on the R correlation coefficient method; Calculating a third correlation coefficient between the infrared feature and the ultrasonic feature based on the M correlation coefficient method; Mapping the first correlation coefficient, the second correlation coefficient, and the third correlation coefficient into a two-dimensional plane, and constructing a geometric triangle structure with the first correlation coefficient, the second correlation coefficient, and the third correlation coefficient as the side lengths.

[0117] In this embodiment, in an actual application scenario, the occurrence of an abnormal condition may cause abnormalities in multi-channel data, and the multi-channel sensors are not completely independent. There will be a certain coupling relationship between their observed values in the physiological or physical process. For example, when the pressure changes, it is often accompanied by changes in blood reflux, bubble formation, and at the same time, ultrasonic signal attenuation and micro-amplitude pressure oscillation. Therefore, by calculating the correlation coefficients between any two features and constructing a combined structure, the overall coupling balance degree between multi-channel data can be reflected, and the stability of the system operation can be quantified.

[0118] In this embodiment, calculating the first correlation coefficient between the pressure feature and the infrared feature based on the R correlation coefficient method includes: (1) where is the mean value of the pressure data, is the pressure data, is the infrared data, is the mean value of the infrared data.

[0119] In this embodiment, calculating the second correlation coefficient between the pressure feature and the ultrasonic feature based on the R correlation coefficient method includes: (2) Wherein, is the mean value of the pressure data, is the pressure data, is the ultrasonic data, is the mean value of the ultrasonic data.

[0120] In this embodiment, calculating the third correlation coefficient between the infrared feature and the ultrasonic feature based on the M correlation coefficient method includes: Normalize the infrared feature and the ultrasonic feature to eliminate the dimension difference. Discretize the normalized infrared and ultrasonic features into a joint distribution matrix, and count the occurrence frequency of each feature combination. Specifically, divide the gray value in the infrared feature into N intervals, and divide the echo intensity in the ultrasonic feature into M intervals. Construct interval combinations based on the N intervals and the M intervals, and calculate the joint probability of each interval combination , and the marginal probabilities g(ir), g(y), and then calculate the third correlation coefficient through the joint probability and the marginal probability. The third correlation coefficient includes: (3) Wherein, is the infrared data, is the ultrasonic data.

[0121] In this embodiment, by mapping the first correlation coefficient, the second correlation coefficient, and the third correlation coefficient into a two-dimensional plane, and constructing a geometric triangle structure with the first correlation coefficient, the second correlation coefficient, and the third correlation coefficient as the side lengths. Since the first correlation coefficient, the second correlation coefficient, and the third correlation coefficient respectively represent the association strength between different data features, data coupling is performed on data from different sources based on this association strength to avoid system misjudgment caused by the failure or malfunction of a single sensor.

[0122] In this embodiment, in the IABP system, if the first correlation coefficient of pressure-infrared decreases, it may indicate that the balloon position has shifted, resulting in the loss of connection between pressure and temperature responses; at the same time, the decrease in the third correlation coefficient of infrared-ultrasonic may reflect the cross-modal association break caused by thrombus formation. Furthermore, a geometric triangle structure is constructed with the correlation coefficient as the side length, so that the real-time update of the geometric triangle structure can reflect the change of the system state.

[0123] In this embodiment, adjusting the fusion weights of the pressure feature, infrared feature, and ultrasonic feature based on the geometric triangular structure, and fusing the pressure feature, infrared feature, and ultrasonic feature based on the fusion weights to obtain a fusion feature, includes: Calculating the triangular area of the geometric triangular structure; When the triangular area minus the preset area threshold is greater than or equal to the first area threshold, the fusion weight is the preset reference weight; When the triangular area minus the preset area threshold is less than the first area threshold, calculating the ratio value of each side in the geometric triangular structure to the triangular area; adjusting the fusion weights of the pressure feature, infrared feature, and ultrasonic feature based on the ratio value; Fusing the pressure feature, infrared feature, and ultrasonic feature based on the fusion weights to obtain a fusion feature.

[0124] In this embodiment, the area of the geometric triangular structure is determined by the correlation coefficients (i.e., side lengths) of pressure, infrared, and ultrasonic. When the triangular area is significantly greater than the preset threshold, it indicates a high correlation strength among multi-modal data and the system is in a stable state. At this time, the preset reference weight is used for fusion (such as equal weight or fixed weight based on prior knowledge). When the area is close to or lower than the threshold, it indicates an imbalance in the coupling relationship between sensors, which may be caused by the failure of a single sensor or physiological abnormalities (such as thrombus formation, air embolism).

[0125] In this embodiment, during the operation of IABP, if the pressure sensor detects abnormal fluctuations (such as a sudden drop in pressure caused by balloon leakage), and the correlation (M correlation coefficient) between infrared and ultrasonic synchronously decreases, the triangular area will significantly shrink. At this time, dynamic weight adjustment is triggered to reduce the fusion weight of the abnormal sensor and give priority to relying on other modal data to avoid misjudgment.

[0126] In this embodiment, when the triangular area of the geometric triangular structure is lower than the threshold, the weights are adjusted according to the ratio values of the sides (correlation coefficients) of the geometric triangular structure to the area: (4) Wherein, is a very small constant to prevent division by zero, S is the triangular area, is the ratio coefficient of each side.

[0127] For the weight of any feature, it is necessary to calculate the ratio coefficients of the two adjacent sides and calculate the weight increment according to the sum of the ratio coefficients.

[0128] For example: the weight increment of the infrared feature is: (5) (6) in, , is the proportionality coefficient of the infrared feature and, is the infrared-ultrasonic side length, is the infrared-pressure side length, is a very small constant.

[0129] Therefore, the fusion weight of infrared features is: (7) in, is the fusion weight of infrared features, , is the reference weight of infrared features, is the weight increment.

[0130] In this embodiment, the fusion weight of the pressure feature and the ultrasonic feature can also be calculated as described above to obtain the fusion weight of the pressure feature, the infrared feature and the ultrasonic feature ( , , ), normalize it, and then fuse the pressure feature, infrared feature and ultrasonic feature: (8) in, is the pressure characteristic, For infrared characteristics, Ultrasonic characteristics.

[0131] In this embodiment, if the pressure-infrared correlation (R correlation coefficient) decreases significantly, the corresponding edge ratio value decreases, and the weight of the pressure feature decreases accordingly.

[0132] In this embodiment, when a certain signal coupling is extremely weak (corresponding to a shorter side length) resulting in a significant reduction in the triangle area, the channel accounts for a low proportion in the δ calculation, so the fusion weight is automatically reduced to reduce the impact of noise or fault signals.

[0133] In this embodiment, the stability between different data sources is measured by the area of a geometric triangle structure. The larger the area of the triangle structure, the weaker the coupling between features and the stronger the information complementarity. Maintaining the baseline weight can maximize information retention. The smaller the area, the more abnormal or disturbed a certain type of data is. The weight of each feature is dynamically adjusted by the ratio of each edge in the triangle structure to the triangle area to avoid noise amplification.

[0134] In this embodiment, the fusion feature Feed it into the CAE-LSTM model.

[0135] In this embodiment, the CAE-LSTM model includes an Encoder module, an LSTM module, and a Decoder module. Among them, the Encoder module includes two 1D convolutional layers (kernel size 3), a ReLU activation layer, and a pooling dimensionality reduction layer; the LSTM module includes a bidirectional LSTM (number of hidden units 64) for capturing temporal dependencies; the Decoder module includes a mirror deconvolution layer and an upsampling layer for restoring the original fused feature dimension.

[0136] In this embodiment, the fused features in each sliding window are input into a convolutional autoencoder (CAE) + bidirectional LSTM architecture to obtain a reconstructed vector F^, and the reconstruction error vector is calculated.

[0137] (9) Among them, is the error vector, is the reconstructed vector.

[0138] In this embodiment, for all windows, a reconstruction error set is obtained. The mean and standard deviation of the errors for each feature dimension are calculated, and the Z-score is calculated for the error of the d-th dimension of the current window: (10) Among them, , are the mean and standard deviation of the errors.

[0139] In this embodiment, a Z-threshold is set, and all dimensions with Z-scores exceeding this Z-threshold are marked as reconstructed abnormal dimensions, and the Z-scores of all dimensions are sorted to determine the maximum Z-score as the dominant abnormal dimension.

[0140] Table 1 In this embodiment, since each dimension of the fused features corresponds to the time-frequency description of different physical quantities such as pressure, infrared, and ultrasound, a dimension-channel-abnormal type mapping table is pre-constructed, as shown in Table 1.

[0141] In this embodiment, if the reconstructed abnormal dimension falls within the "pressure" dimension set, it is judged as a pressure anomaly, and low pressure or high pressure can be determined based on the positive or negative sign of the Z-score; if it is within the "infrared" dimension set, it is judged as a blood reflux concentration anomaly; if it is within the "ultrasound" dimension set, it is judged as a bubble / flow anomaly.

[0142] In this embodiment, during the model initialization phase, K random isolated trees are trained using the fused features collected during the "normal" operation, and the model parameters (tree structure, splitting threshold, etc.) are saved.

[0143] In this embodiment, the fusion features of the current window are input into each isolated tree of the model. For the t-th tree, the split nodes along the tree from the root node to the leaf node are counted to obtain the path length .

[0144] In this embodiment, the average path length of all trees is calculated: (11) In this embodiment, the average path length is normalized based on the expected path length to obtain the final isolated forest score: (12) where is the expected path length constant, which can be calculated based on the number of samples during the training of the isolated forest model.

[0145] In this embodiment, an isolated forest score threshold is set. If both are satisfied but , it is determined as a cluster-type or progressive anomaly and classified as "complex / mixed anomaly". If both the Z-score and the isolated forest score exceed the threshold, it is determined as a strong anomaly and marked as "multi-channel linkage failure".

[0146] In this embodiment, when an anomaly is determined to exist, the alarm device is controlled to alarm based on the anomaly data and anomaly type to implement the management of the central cavity of the intra-aortic balloon pump.

[0147] In this embodiment, the isolated forest is good at detecting anomalies in the form of groups, slow drifts or complex patterns, making up for the lag of the Z-score for sudden point anomalies. Moreover, the isolated forest makes no assumptions about the data distribution and is applicable to the multi-modal and non-Gaussian distribution scenario of the fusion features of the IABP central cavity.

[0148] In this embodiment, by separately extracting the features of the pressure data, the infrared light data and the ultrasonic data first, data feature loss is avoided, and then the features are fused to improve the recognition ability for complex situations. For example, during the use of the IABP, balloon rupture or catheter kinking may only be manifested as slight changes in the pressure waveform, while multi-modal data can cross-verify different anomaly situations.

[0149] In an embodiment of the present invention, a terminal is further provided, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the above-mentioned central cavity management method is implemented.

[0150] In an embodiment of the present invention, a computer-readable storage medium is further provided. The computer-readable storage medium includes a stored computer program, wherein when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the above-mentioned central cavity management method.

[0151] Exemplarily, the computer program can be divided into one or more modules. One or more modules are stored in the memory and executed by the processor to complete the present invention. One or more modules can be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal.

[0152] The terminal can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal may include, but is not limited to, a processor, a memory, and a display. Those skilled in the art can understand that the above components are only examples of the terminal and do not constitute a limitation on the terminal. It may include more or fewer components than those described, or combine some components, or different components. For example, the terminal may further include input / output devices, network access devices, a bus, etc.

[0153] The so-called processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the terminal and connects various parts of the entire terminal through various interfaces and lines.

[0154] The memory can be used to store computer programs and / or modules. By running or executing the computer programs and / or modules stored in the memory, and by invoking the data stored in the memory, the processor can implement various functions of the terminal. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, a text conversion function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, text message data, etc.). In addition, the memory can include high-speed random access memory, and can also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices.

[0155] Among them, if the module based on the management of the central cavity is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. Those of ordinary skill in the art can understand and implement it without creative effort.

[0156] The above-mentioned specific embodiments have further elaborated in detail the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above-mentioned are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. It is particularly pointed out that for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A central cavity management system, characterized in that, For an intra-aortic balloon pump, the central cavity management system includes: a regulation device group, a multi-channel data acquisition module, and a main control module; wherein: The multi-channel data acquisition module is used to acquire monitoring data corresponding to multiple positions of the intra-aortic balloon pump; The main control module is used to obtain abnormal data based on the monitoring data, and control the regulation device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to realize the management of the central cavity of the intra-aortic balloon pump.

2. The central cavity management system according to claim 1, wherein, The multi-channel data acquisition module includes a pressure sensing sub-module, and the pressure sensing sub-module is arranged at the interface of the pressure gauge of the intra-aortic balloon pump, and is used to obtain the pressure data of the intra-aortic balloon pump in the braking state as the monitoring data.

3. The central cavity management system according to claim 2, characterized in that, The main control module is used to obtain abnormal data based on the monitoring data, and control the regulation device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to realize the management of the central cavity of the intra-aortic balloon pump, including: The main control module is used to determine that the pressure data being lower than a preset first pressure threshold or higher than a preset second pressure threshold is abnormal data; Based on the abnormal data, control the regulation device group to perform corresponding actions on the intra-aortic balloon pump, so as to realize the management of the central cavity of the intra-aortic balloon pump.

4. The central cavity management system according to claim 3, characterized in that, The regulation device group includes a booster pump and a pressure relief valve. The main control module is used to control the regulation device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to realize the management of the central cavity of the intra-aortic balloon pump, including: When the pressure data is lower than the preset first pressure threshold, control the booster pump to pressurize the intra-aortic balloon pump until the pressure data reaches the preset first target pressure; When the pressure data is higher than the preset second pressure threshold, control the pressure relief valve to decompress the intra-aortic balloon pump until the pressure data reaches the preset second target pressure.

5. The central cavity management system according to claim 2, characterized in that The regulation device group includes a flushing device. The main control module is also used to obtain normal data based on the monitoring data, and control the regulation device group to perform corresponding actions on the intra-aortic balloon pump based on the normal data, so as to realize the management of the central cavity of the intra-aortic balloon pump; wherein: If the monitoring data is pressure data, and it is determined that the pressure data is between the preset first pressure threshold and the preset second pressure threshold, then the pressure data is determined as normal data; Based on the normal data, control the flushing device to flush the saline channel of the central cavity of the intra-aortic balloon pump, so as to realize the management of the central cavity of the intra-aortic balloon pump.

6. The central cavity management system according to claim 1, wherein, The multi-channel data acquisition module includes an infrared sensing sub-module, and the infrared sensing sub-module is arranged at the blood return observation point of the intra-aortic balloon pump, and is used to obtain the infrared light data of the intra-aortic balloon pump in the braking state as the monitoring data.

7. The central cavity management system according to claim 6, wherein The main control module is used to obtain abnormal data based on the monitoring data, and control the regulation device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to manage the central cavity of the intra-aortic balloon pump, including: The main control module is used to calculate the blood concentration based on the infrared light data. When the blood concentration is greater than or equal to the preset concentration threshold, the blood concentration is abnormal data; Control the regulation device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to manage the central cavity of the intra-aortic balloon pump.

8. The central cavity management system according to claim 7, characterized in that, The regulation device group further includes an alarm device. The main control module is used to control the regulation device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to manage the central cavity of the intra-aortic balloon pump, including: Control the alarm device to perform a blood return detection alarm based on the abnormal data, so as to manage the central cavity of the intra-aortic balloon pump.

9. The central cavity management system according to claim 1, characterized in that, The multi-channel data acquisition module includes an ultrasonic sensing sub-module. The ultrasonic sensing sub-module is arranged below the flow clamp of the intra-aortic balloon pump and is used to obtain ultrasonic data of the intra-aortic balloon pump in the braking state as monitoring data.

10. A central cavity management system according to claim 9, characterized in that, The main control module is used to obtain abnormal data based on the monitoring data, and control the regulation device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to manage the central cavity of the intra-aortic balloon pump, including: The main control module is used to calculate the signal loss amplitude based on the ultrasonic data. When the signal difference amplitude continuously is greater than or equal to the preset amplitude threshold within a preset time period, the ultrasonic data is abnormal data; Control the regulation device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to manage the central cavity of the intra-aortic balloon pump.

11. A central cavity management system according to claim 10, characterized in that, The regulation device group further includes an alarm device. The main control module is used to control the regulation device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to manage the central cavity of the intra-aortic balloon pump, including: Control the alarm device to perform a bubble detection alarm based on the abnormal data, so as to manage the central cavity of the intra-aortic balloon pump.

12. The central cavity management system according to claim 1, characterized in that, The main control module is used to obtain abnormal data based on the monitoring data, and control the regulation device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to manage the central cavity of the intra-aortic balloon pump, including: The main control module is used to obtain the monitoring data and detect the monitoring data based on the anomaly detection model to obtain abnormal data; Control the regulation device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to manage the central cavity of the intra-aortic balloon pump.

13. A central cavity management system according to claim 12, characterized in that, The monitoring data includes pressure data, infrared light data and ultrasonic data; The main control module is used to obtain the monitoring data and detect the monitoring data based on the anomaly detection model to obtain abnormal data, including: Obtain the monitoring data, respectively perform feature extraction on the pressure data, the infrared light data, and the ultrasonic data to obtain pressure features, infrared features, and ultrasonic features; Calculate the correlation coefficients between any two of the pressure features, infrared features, and ultrasonic features, and construct a geometric triangle structure of the pressure features, infrared features, and ultrasonic features based on the correlation coefficients; Adjust the fusion weights of the pressure features, infrared features, and ultrasonic features based on the geometric triangle structure, and fuse the pressure features, infrared features, and ultrasonic features based on the fusion weights to obtain fusion features; Input the fusion features into the CAE-LSTM model for reconstruction to obtain the Z-score and the Isolation Forest score of each feature; Determine the abnormal data based on the Z-score and the Isolation Forest score.

14. A central cavity management system according to claim 13, characterized in that, The calculating the correlation coefficients between any two of the pressure features, infrared features, and ultrasonic features, and constructing a geometric triangle structure of the pressure features, infrared features, and ultrasonic features based on the correlation coefficients includes: Calculate the first correlation coefficient between the pressure feature and the infrared feature based on the R correlation coefficient method; Calculate the second correlation coefficient between the pressure feature and the ultrasonic feature based on the R correlation coefficient method; Calculate the third correlation coefficient between the infrared feature and the ultrasonic feature based on the M correlation coefficient method; Map the first correlation coefficient, the second correlation coefficient, and the third correlation coefficient into a two-dimensional plane, and construct a geometric triangle structure with the first correlation coefficient, the second correlation coefficient, and the third correlation coefficient as the side lengths.

15. A central cavity management system according to claim 14, characterized in that, The adjusting the fusion weights of the pressure features, infrared features, and ultrasonic features based on the geometric triangle structure, and fusing the pressure features, infrared features, and ultrasonic features based on the fusion weights to obtain fusion features includes: Calculate the triangular area of the geometric triangle structure; When the triangular area minus the preset area threshold is greater than or equal to the first area threshold, the fusion weight is the preset reference weight; When the triangular area minus the preset area threshold is less than the first area threshold, calculate the ratio of each side of the geometric triangle structure to the triangular area; adjust the fusion weights of the pressure features, infrared features, and ultrasonic features based on the ratio values; Fuse the pressure features, infrared features, and ultrasonic features based on the fusion weights to obtain fusion features.

Images