A central lumen management system

Abstract

The application discloses a kind of central lumen management systems for intra-aortic balloon pump, which includes: regulating device group, multichannel data acquisition module and master module;Wherein: the multichannel data acquisition module is used to collect the monitoring data corresponding to the multiple positions of intra-aortic balloon pump;The master module is used to obtain abnormal data based on monitoring data, and control the regulating device group based on abnormal data to execute corresponding action to intra-aortic balloon pump, to realize the management of the central lumen of intra-aortic balloon pump.The application obtains the monitoring data corresponding to the multiple positions of intra-aortic balloon pump by multichannel data acquisition module, so as to identify the abnormal data of each position of intra-aortic balloon pump by multidimensional monitoring data, identify the abnormal state of the central lumen of intra-aortic balloon pump in all directions, and improve the comprehensiveness of central lumen management.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical equipment, and in particular to a central lumen management system. BACKGROUND

[0002] Intra-Aortic Balloon Pump (IABP) is a mechanical circulatory assist device, which is used to temporarily enhance the function of the heart, and is widely used in acute cardiac dysfunction, cardiogenic shock, and some high-risk cardiac surgery to improve myocardial perfusion and reduce cardiac load. The core of IABP is a catheter with an inflatable balloon, which is inserted into the femoral artery, sent to the lower segment of the thoracic aorta, and close to the left subclavian artery opening. The balloon is driven by a controller synchronized with electrocardiogram (ECG) for synchronous inflation and deflation, thereby realizing the counterpulsation effect.

[0003] The existing central lumen saline channel management of intra-aortic balloon pump relies on manual nursing, and needs manual operation of the flushing device for cleaning, and relies on manual bubble detection and blood return detection, which is easy to miss due to fatigue or environmental factors, resulting in low efficiency of the central lumen saline channel management of intra-aortic balloon pump. SUMMARY

[0004] The present application provides a central lumen management system to improve the efficiency and comprehensiveness of the central lumen management of intra-aortic balloon pump.

[0005] In order to solve the above technical problems, the present application provides a central lumen management system for intra-aortic balloon pump, which comprises a control device group, a multi-channel data acquisition module and a master control module; wherein:

[0006] The multi-channel data acquisition module is used to acquire monitoring data corresponding to multiple positions of the intra-aortic balloon pump;

[0007] The master control module is used to acquire 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 realize the management of the central lumen of the intra-aortic balloon pump.

[0008] The application obtains monitoring data corresponding to multiple positions of an intra-aortic balloon pump through a multi-channel data acquisition module, so as to identify abnormal data of 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, so that the central cavity of the intra-aortic balloon pump is responded and controlled in time, without relying on manual monitoring of the central cavity, and the central cavity management efficiency is improved.

[0009] Further, the multi-channel data acquisition module comprises a pressure sensing sub-module arranged at an interface of a pressure gauge of the intra-aortic balloon pump, for obtaining pressure data of the intra-aortic balloon pump in a braking state as monitoring data.

[0010] The application accurately monitors the pressure data at the interface of the pressure gauge by arranging the pressure sensing sub-module at the interface of the pressure gauge of the intra-aortic balloon pump, so as to realize timely response to the abnormality of the intra-aortic balloon pump.

[0011] 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 realize management of the central cavity of the intra-aortic balloon pump, comprising:

[0012] The main control module is used to determine that the pressure data lower than a preset first pressure threshold or higher than a preset second pressure threshold is abnormal data;

[0013] The control device group is controlled based on the abnormal data to perform corresponding actions on the intra-aortic balloon pump, so as to realize management of the central cavity of the intra-aortic balloon pump.

[0014] The application determines that the pressure data exceeding the threshold is abnormal through the main control module, and controls the control device group to perform corresponding actions on the intra-aortic balloon pump for regulation, so as to realize automatic identification and regulation of the abnormality, improve the response speed of abnormal processing, and improve the central cavity management efficiency without manual monitoring.

[0015] Further, the control device group comprises a booster pump and a pressure relief valve, 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 realize management of the central cavity of the intra-aortic balloon pump, comprising:

[0016] when the pressure data is lower than a preset first pressure threshold, controlling the booster pump to boost the intra-aortic balloon pump until the pressure data reaches a preset first target pressure;

[0017] when the pressure data is higher than a preset second pressure threshold, controlling the pressure relief valve to depressurize the intra-aortic balloon pump until the pressure data reaches a preset second target pressure.

[0018] The application automatically boosts when the pressure data is low and automatically depressurizes when the pressure data is high by setting a booster pump and a pressure relief valve, accurately realizes pressure regulation without manual operation, and realizes automatic management of the central cavity.

[0019] Further, the control device group includes a flushing device, and the master control module is further used 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 based on the normal data to realize management of the central cavity of the intra-aortic balloon pump; wherein:

[0020] If the monitoring data is pressure data and the pressure data is determined to be between a preset first pressure threshold and a preset second pressure threshold, the pressure data is determined to be normal data;

[0021] The flushing device is controlled based on the normal data to flush the central cavity saline channel of the intra-aortic balloon pump to realize management of the central cavity of the intra-aortic balloon pump.

[0022] When the pressure data is normal data, the flushing device is used to flush the central cavity saline channel of the intra-aortic balloon pump to realize automatic flushing of the central cavity saline channel without manual operation, thereby improving the flushing efficiency.

[0023] Further, the multi-channel data acquisition module includes an infrared sensing sub-module, which is arranged at a blood return observation position of the intra-aortic balloon pump and is used to obtain infrared light data of the intra-aortic balloon pump in a braking state as monitoring data.

[0024] The infrared sensing sub-module is arranged at the blood return observation position of the intra-aortic balloon pump to introduce optical detection, which can objectively evaluate whether the central cavity liquid returns blood, avoids manual visual inspection, and improves the accuracy of the subsequent blood return detection module.

[0025] Further, the master 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 to realize management of the central cavity of the intra-aortic balloon pump, including:

[0026] The master module is used for calculating blood concentration based on the infrared light data, and when the blood concentration is greater than or equal to a preset concentration threshold, the blood concentration is abnormal data;

[0027] The control device group is controlled based on the abnormal data to perform corresponding actions on the intra-aortic balloon pump, so as to realize management of the central cavity of the intra-aortic balloon pump.

[0028] The application calculates the blood concentration based on the infrared light data, determines the abnormality when the concentration exceeds the threshold, quantifies the blood concentration in the central cavity, identifies the abnormal data in time, and improves the reliability of the central cavity management.

[0029] Further, the control device group further includes an alarm device, and the master module is used for controlling the control device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to realize management of the central cavity of the intra-aortic balloon pump, including:

[0030] The alarm device is controlled based on the abnormal data to perform blood return detection alarm, so as to realize management of the central cavity of the intra-aortic balloon pump.

[0031] When the infrared light data detects abnormal data, the application timely performs blood return detection alarm, avoids blood invasion into the central cavity pipeline, and affects the use effect of the intra-aortic balloon pump.

[0032] Further, 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 for acquiring ultrasonic wave data of the intra-aortic balloon pump in the braking state as monitoring data.

[0033] The application acquires ultrasonic wave signals by arranging the ultrasonic sensing sub-module below the flow clamp, so that the central cavity pipeline can be managed in all directions according to the ultrasonic wave signals by collecting different signals at different positions.

[0034] Further, the master module is used for acquiring abnormal data based on the monitoring data, and controlling the control device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to realize management of the central cavity of the intra-aortic balloon pump, including:

[0035] The master module is used for calculating signal loss amplitude based on the ultrasonic wave data, and when the signal difference amplitude is greater than or equal to a preset amplitude threshold for a preset time period, the ultrasonic wave data is abnormal data;

[0036] Control the regulating device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data to achieve management of the central cavity of the intra-aortic balloon pump.

[0037] The application calculates the signal loss amplitude by the master module, and if it continuously exceeds the set period, the preset amplitude threshold determines the abnormality, combines time and amplitude, improves the accuracy of abnormality identification, and avoids misjudgment.

[0038] Further, the regulating device group also includes an alarm device, and the master module is used to control the regulating device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data to achieve management of the central cavity of the intra-aortic balloon pump, including:

[0039] Control the alarm device to perform bubble detection alarm based on the abnormal data to achieve management of the central cavity of the intra-aortic balloon pump.

[0040] The application detects abnormal data through ultrasonic data, and timely performs bubble detection alarm to avoid bubbles in the central cavity pipeline and affect the use effect of the intra-aortic balloon pump.

[0041] Further, the master module is used to obtain abnormal data based on the monitoring data, and control the regulating device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data to achieve management of the central cavity of the intra-aortic balloon pump, including:

[0042] The master module is used to obtain the monitoring data, and detect the monitoring data based on the abnormal detection model to obtain abnormal data;

[0043] Control the regulating device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data to achieve management of the central cavity of the intra-aortic balloon pump.

[0044] The application monitors the monitoring model by the abnormal detection model to automatically identify abnormal data, so as to subsequently control the regulating device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data to achieve management of the central cavity of the intra-aortic balloon pump.

[0045] Further, the monitoring data includes pressure data, infrared light data and ultrasonic data; the master module is used to obtain the monitoring data, and detect the monitoring data based on the abnormal detection model to obtain abnormal data, including:

[0046] 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;

[0047] correlation coefficients between any two of the pressure feature, the infrared feature and the ultrasonic feature, and constructing a geometric triangular structure of the pressure feature, the infrared feature and the ultrasonic feature based on the correlation coefficients;

[0048] adjusting 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;

[0049] inputting the fusion feature into a CAE-LSTM model for reconstruction to obtain Z scores and isolated forest scores of each feature;

[0050] determining abnormal data based on the Z scores and the isolated forest scores.

[0051] The present application avoids data feature loss by first extracting the features of the pressure data, the infrared light data and the ultrasonic data separately, and improves the recognition ability in complex situations by fusing each feature, for example, in IABP use, balloon rupture or catheter folding may only show slight changes in pressure waveform, and multi-modal data can cross verify different abnormal situations.

[0052] Further, the calculation of the correlation coefficients between any two of the pressure feature, the infrared feature and the ultrasonic feature, and the construction of the geometric triangular structure of the pressure feature, the infrared feature and the ultrasonic feature based on the correlation coefficients, comprises:

[0053] calculating a first correlation coefficient between the pressure feature and the infrared feature based on the R correlation coefficient method;

[0054] calculating a second correlation coefficient between the pressure feature and the ultrasonic feature based on the R correlation coefficient method;

[0055] calculating a third correlation coefficient between the infrared feature and the ultrasonic feature based on the M correlation coefficient method;

[0056] mapping the first correlation coefficient, the second correlation coefficient and the third correlation coefficient to 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 length.

[0057] In the present embodiment, the correlation coefficients between different features are constructed based on the R / M correlation coefficient method, so as to construct a geometric triangular structure with the correlation coefficients as the side length, quantify the correlation strength between different data features, and thus couple different data features to avoid system misjudgment caused by failure of a single sensor.

[0058] Further, the fusion weight of the pressure feature, the infrared feature and the ultrasonic feature is adjusted based on the geometric triangle structure, and the pressure feature, the infrared feature and the ultrasonic feature are fused based on the fusion weight to obtain a fusion feature, comprising:

[0059] The triangular area of the geometric triangle structure is calculated.

[0060] When the triangular area minus the preset area threshold is greater than or equal to a first area threshold, the fusion weight is a preset reference weight.

[0061] When the triangular area minus the preset area threshold is less than the first area threshold, the proportion value of each side of the geometric triangle structure to the triangular area is calculated, and the fusion weight of the pressure feature, the infrared feature and the ultrasonic feature is adjusted based on the proportion value.

[0062] The pressure feature, the infrared feature and the ultrasonic feature are fused based on the fusion weight to obtain a fusion feature.

[0063] The present application measures the stability between different data sources by the area of the geometric triangle structure. When the triangular structure area is larger, it represents that the coupling between features is weak, the information complementarity is strong, and the reference weight can maximize information retention. When the area is smaller, it represents that some data is abnormal or interfered, and then the weight of each feature is dynamically adjusted by the proportion value of each side of the triangular structure to the triangular area to avoid noise amplification. BRIEF DESCRIPTION OF DRAWINGS

[0064] Figure 1 It is a structural schematic diagram of a center lumen management system for an intra-aortic balloon pump provided in an embodiment of the present application.

[0065] Figure 2 It is a process schematic diagram of center lumen saline flushing provided in an embodiment of the present application.

[0066] Figure 3 It is a process schematic diagram of blood return monitoring provided in an embodiment of the present application.

[0067] Figure 4 It is a process schematic diagram of bubble detection provided in an embodiment of the present application. DETAILED DESCRIPTION

[0068] The specific embodiments of the present application are described in detail below in conjunction with the drawings and embodiments. The following embodiments are used to illustrate the present application, but are not used to limit the scope of the present application.

[0069] The terms "first" and "second" and the like in the description and in the claims of the present application and in the appended drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. Moreover, the terms "including" and "having" and any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to the listed steps or elements, but can include additional steps or elements not expressly listed or inherent to such process, method, system, article, or apparatus.

[0070] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment is included in at least one embodiment of the application. The appearances of the phrase "in an embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive of one another. It is expressly understood that any of the embodiments described herein can be combined with any of the other embodiments unless specifically noted otherwise.

[0071] Embodiment 1

[0072] Reference is made to Figure 1 , Figure 1 A structural schematic diagram of a center lumen management system for an intra-aortic balloon pump is provided in an embodiment of the application. The application provides a center lumen management system for an intra-aortic balloon pump, which comprises: a regulating device group 103, a multi-channel data acquisition module 101, and a master control module 102; wherein:

[0073] The multi-channel data acquisition module is configured to acquire monitoring data corresponding to multiple positions of the intra-aortic balloon pump;

[0074] The master control module is configured to acquire abnormal data based on the monitoring data, and control the regulating device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so as to manage the center lumen of the intra-aortic balloon pump.

[0075] In the embodiment, a multi-channel data acquisition module is arranged on the intra-aortic balloon pump, so as to acquire multi-dimensional monitoring data of the intra-aortic balloon pump, and identify whether the monitoring data is abnormal according to a preset rule. When the monitoring data is abnormal, the regulating device group is controlled to perform corresponding actions on the intra-aortic balloon pump based on the data type of the abnormal data, so as to manage the center lumen of the intra-aortic balloon pump.

[0076] In the embodiment, the monitoring data corresponding to the multiple positions of the intra-aortic balloon pump is acquired by the multi-channel data acquisition module, so that the abnormal data of each position of the intra-aortic balloon pump is identified through multi-dimensional monitoring data, the abnormal state of the central cavity of the intra-aortic balloon pump is comprehensively identified, and the comprehensiveness of the central cavity management is improved; and when the abnormal data is acquired, the control device group is automatically controlled according to the abnormal data to perform corresponding actions on the intra-aortic balloon pump, so that the central cavity of the intra-aortic balloon pump is responded and controlled in time, without relying on manual monitoring of the central cavity, and the central cavity management efficiency is improved.

[0077] In the embodiment, the multi-channel data acquisition module includes a pressure sensing sub-module, an infrared sensing sub-module, and an ultrasonic sensing sub-module, which are arranged at different positions outside the intra-aortic balloon pump to monitor the data of the central cavity pipeline of the intra-aortic balloon pump.

[0078] In the embodiment, the multi-channel data acquisition module includes a pressure sensing sub-module, which is arranged at the interface of the pressure gauge of the intra-aortic balloon pump to acquire the pressure data of the intra-aortic balloon pump in the braking state as the monitoring data.

[0079] In the embodiment, the pressure sensing sub-module includes an infrared sensor, specifically a MEMS piezoresistive sensor (range 0-500 mmHg, accuracy ±1%), which is arranged at the interface of the pressure bag and the pressure gauge.

[0080] In the embodiment, the pressure sensing sub-module starts to monitor the pressure data of the pressure bag of the intra-aortic balloon pump when the intra-aortic balloon pump is braked.

[0081] In the embodiment, the pressure sensing sub-module is arranged at the interface of the pressure gauge of the intra-aortic balloon pump, so that the pressure data at the interface of the pressure gauge is accurately monitored, and timely response to the abnormality of the intra-aortic balloon pump can be realized.

[0082] In the embodiment, the main control module is used to acquire 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:

[0083] The main control module is used to determine that the pressure data lower than a preset first pressure threshold or higher than a preset second pressure threshold is abnormal data;

[0084] The main control module is used to determine that the pressure data lower than a preset first pressure threshold or higher than a preset second pressure threshold is abnormal data;

[0085] In the embodiment, the pressure data is monitored in real time, and when the pressure data is abnormal data at a preset first pressure threshold or higher than a preset second pressure threshold, the control device group is controlled to perform corresponding actions on the intra-aortic balloon pump according to a control strategy.

[0086] In the embodiment, if abnormal pressure data is identified during the saline flushing process, the saline flushing is stopped, and if abnormal pressure data is identified during the non-saline flushing process, the control device group is controlled to perform corresponding actions on the intra-aortic balloon pump based on the target pressure, so as to adjust the pressure of the pressure bag.

[0087] In the embodiment, the pressure data exceeding the threshold is determined as abnormal by the master control module, and the control device group is controlled to perform corresponding actions on the intra-aortic balloon pump for regulation, so as to realize automatic identification and adjustment of abnormalities, improve the response speed of abnormal handling, and improve the central lumen management efficiency without human monitoring.

[0088] In the embodiment, the control device group includes a booster pump and a pressure relief valve, and the master 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 lumen of the intra-aortic balloon pump, including:

[0089] When the pressure data is lower than a preset first pressure threshold, the booster pump is controlled to boost the intra-aortic balloon pump until the pressure data reaches a preset first target pressure.

[0090] When the pressure data is higher than a preset second pressure threshold, the pressure relief valve is controlled to depressurize the intra-aortic balloon pump until the pressure data reaches a preset second target pressure.

[0091] In the embodiment, by setting the booster pump and the pressure relief valve, the pressure is automatically boosted when the pressure data is low and the pressure is automatically released when the pressure data is high, so as to accurately regulate the pressure without human operation and realize automatic management of the central lumen.

[0092] In the embodiment, when it is determined that the current pressure data has 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.

[0093] In the embodiment, when pressure abnormalities are detected, the pressure of the pressure bag is automatically adjusted based on the control strategy without human intervention, so as to ensure continuous and stable pipeline pressure and further reduce the risk of channel occlusion or poor blood return caused by pressure abnormalities.

[0094] In this embodiment, the pressure sensor adopts a MEMS piezoresistive sensor with a range of 0-500 mmHg and an accuracy of ±1%.

[0095] In this embodiment, the pressure sensor is arranged at the pressure gauge interface.

[0096] In this embodiment, if the pressure is <280 mmHg or >320 mmHg, the current pressure data is in an abnormal state. When the pressure is <280 mmHg, the booster pump is controlled to boost the pressure; when the pressure is >320 mmHg, the pressure relief valve is controlled to reduce the pressure.

[0097] In this embodiment, the pressure relief valve is triggered to reduce the pressure when the pressure is too high, and the booster pump is triggered to increase the pressure when the pressure is too low. Different adjustment strategies are adopted for different abnormal scenarios based on the control strategy, which can more finely maintain the system within the safe pressure range, improve the system stability, and ensure the continuous and reliable operation of the balloon counterpulsation pump.

[0098] In this embodiment, the control device group includes a booster pump and a pressure relief valve, and the main control module is configured to control the control device group to perform corresponding actions on the intra-aortic balloon counterpulsation pump based on the abnormal data, so as to manage the central cavity of the intra-aortic balloon counterpulsation pump. The system further comprises:

[0099] When adjusting the pressure value of the pressure bag based on the pressure control 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 not, pressure data abnormal information is generated, and an alarm is given based on the pressure data abnormal information.

[0100] In this embodiment, a preset pressure control time is set. If the pressure does not return to normal after a period of time, an alarm information is generated.

[0101] In this embodiment, when the abnormal state is that the pressure data is higher than the 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. If the real-time pressure data does not reach the second target pressure within a period of time, an alarm is given.

[0102] In this embodiment, when the abnormal state is that the pressure data is lower than the preset first pressure threshold, a pressure boosting control instruction is generated, and the booster pump is controlled to boost the pressure based on the pressure boosting control instruction. If the real-time pressure data does not reach the first target pressure within a period of time, an alarm is given.

[0103] In the embodiment, during the pressure regulation process, the pressure in the pressure bag is monitored in real time to see whether it meets 300 mmHg, to meet the micro-pressure perfusion, reach balance with the intravascular pressure, and prevent backflow. When the pressure of the saline bag is less than (first pressure threshold) 280 mmHg, the pressure pump is started to increase the pressure to 305 mmHg (first target pressure) and then stopped. If the target pressure is not reached for more than 10 seconds, the device alarms, and if the flow clamp is open at this time, the flow clamp is closed. When the pressure is greater than 320 mmHg (second pressure threshold), the pressure is released to 300 mmHg (second target pressure). If the target pressure is not reached for more than 10 seconds, the device alarms, and if the flow clamp is open at this time, the flow clamp is closed.

[0104] In the embodiment, the pressure is continuously monitored during the pressure regulation process, and it is detected whether it returns to normal within a preset time, otherwise an alarm is given, so as to realize closed-loop verification of the pressure regulation effect, and immediately alarm once continuous regulation is invalid, to prevent potential safety hazards caused by control command failure or device failure.

[0105] In the embodiment, when the pressure regulation is completed and it is determined that the current pressure data is normal, flushing control instructions are generated based on the flushing mode.

[0106] In the embodiment, the regulation device group includes a flushing device, and the master control module is further configured to acquire 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, to realize management of the central lumen of the intra-aortic balloon pump.

[0107] 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, the pressure data is determined as normal data.

[0108] The flushing device is controlled based on the normal data to flush the central lumen saline channel of the intra-aortic balloon pump, to realize management of the central lumen of the intra-aortic balloon pump.

[0109] In the embodiment, when the pressure data is normal, the central lumen saline channel of the intra-aortic balloon pump is flushed by the regulation flushing device, to realize automatic flushing of the central lumen saline channel, without manual operation, and improve the flushing efficiency.

[0110] Please refer to Figure 2 , Figure 2 A flowchart of central lumen saline flushing is provided for the embodiment of the application.

[0111] In the embodiment, when the pressure data is determined to be normal, the flushing device flushes the central lumen saline channel of the intra-aortic balloon pump through different flushing modes including a manual mode and an automatic mode.

[0112] In the embodiment, the flushing control instruction is generated based on a preset flushing mode, and the flushing device flushes the central lumen saline channel based on the flushing control instruction, wherein the flushing mode includes a manual mode and an automatic mode.

[0113] In the embodiment, in the automatic mode, the preset flushing period is once per hour, and the flushing duration can be manually set, and the default is 15 seconds.

[0114] In the embodiment, in the manual mode, long-pressing the flushing button supports continuous flushing, and short-pressing the flushing button supports short-time flushing, and the short-time flushing duration can be manually set, and the default flushing duration is 15 seconds.

[0115] In the embodiment, the manual mode and the automatic mode are supported; the flushing control instruction can be generated according to different pressure modes when the pressure is in the normal range, and the flexibility of the central lumen management is improved.

[0116] In the embodiment, before flushing, a braking device is enabled, the braking device is connected to the data acquisition module, the flushing control module and the flushing control module, and after the braking device is powered on, the pressure can be detected to flush the central lumen saline.

[0117] In the embodiment, the braking device includes a clamping device and a stepper motor driven ball screw, wherein the step angle of the stepper motor is 1.8°, and the clamping force of the clamping device is set to 0.5-2.0N, which can be manually adjusted.

[0118] In the embodiment, when the flushing mode is the automatic mode, the flushing control instruction is generated based on a preset flushing period and a preset flushing duration, and the flushing device flushes the central lumen saline channel based on the flushing control instruction.

[0119] In the embodiment, in the automatic mode, the flushing valve is opened for 15 seconds (error ±1s) per hour for flushing.

[0120] In the embodiment, in the automatic mode, the flushing instruction is automatically generated and executed based on a preset flushing period and duration, the central lumen channel can be maintained and flushed in a timed and quantitative manner, the nursing staff does not need to manually trigger, the working efficiency is significantly improved, and the channel is always kept unobstructed.

[0121] In the embodiment, when the flushing mode is the manual mode, the flushing button state is acquired, the flushing control instruction is generated based on the flushing button state, and the flushing device is controlled to flush the saline channel of the central cavity based on the flushing control instruction.

[0122] In the embodiment, the manual mode supports short pressing (15-second timing) or long pressing (continuous flushing).

[0123] In the embodiment, in the manual mode, the flushing instruction is generated by monitoring the flushing button state, so that the medical staff can initiate cleaning at any time according to clinical needs, and the flexibility of the system is improved.

[0124] In the embodiment, when the flushing mode is the manual mode, the flushing button state is also monitored, and when the flushing button state changes or the flushing duration reaches a preset duration threshold, the flushing is stopped, and the central cavity management is completed.

[0125] In the embodiment, by monitoring the button state or the cleaning duration in the manual mode, the flushing is stopped when the conditions are met, excessive flushing caused by button mis-touch or excessive cleaning is prevented, the safety and reliability are improved, and the controllability of the flushing process is ensured.

[0126] In the embodiment, the multi-channel data acquisition module includes an infrared sensing sub-module, which is arranged at a blood return observation position of the intra-aortic balloon pump, and is used to acquire infrared light data of the intra-aortic balloon pump in the braking state as monitoring data.

[0127] In the embodiment, the infrared sensing sub-module further includes an infrared sensor, which is arranged at the blood return observation position of the intra-aortic balloon pump.

[0128] In the embodiment, the infrared sensor is a U-shaped clamping type infrared sensing unit, which is arranged at the blood return observation position and includes an emitting end (wavelength 940nm LED) and a receiving end (photosensitive diode) clamped on the outer wall of the pipeline. Using the optical sensing principle, whether there is blood return is judged according to the light transmittance. When there is blood return in the pipeline, the characteristics of infrared reflection will change, and the voltage at both ends will increase. The sensor is connected with the voltage acquisition module in a wired manner. The voltage acquisition module converts the continuous analog voltage signal into a discrete digital signal through AD analog-digital conversion. The voltage acquisition module is connected with the main control module in a wired manner, and data is transmitted using a can bus. The main control module judges whether to alarm according to the set threshold.

[0129] Please refer to Figure 3 , Figure 3 A blood return monitoring flowchart is provided for the embodiment of the application.

[0130] In the embodiment, by setting an infrared sensor submodule at the blood return observation position of the intra-aortic balloon pump, optical detection is introduced, so that whether the central cavity liquid returns blood can be evaluated by objective data, manual visual inspection is avoided, and the accuracy of the subsequent blood return detection module is improved.

[0131] In the embodiment, the master control module is configured to acquire 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:

[0132] The master control module is configured to calculate the blood concentration based on the infrared light data, and when the blood concentration is greater than or equal to a preset concentration threshold, the blood concentration is abnormal data.

[0133] The master control module is configured to calculate the blood concentration based on the infrared light data, and when the blood concentration is greater than or equal to a preset concentration threshold, the blood concentration is abnormal data.

[0134] In the embodiment, the infrared light data of the central cavity liquid is acquired, the light transmittance of the central cavity liquid is calculated based on the infrared light data, the blood concentration of the central cavity liquid is calculated based on the light transmittance, and when the blood concentration is greater than or equal to a preset concentration threshold, blood return alarm information is generated, and blood return alarm is performed based on the blood return alarm information.

[0135] In the embodiment, the regulation device group further includes an alarm device, and the master 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 realize the management of the central cavity of the intra-aortic balloon pump, including:

[0136] The master 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 realize the management of the central cavity of the intra-aortic balloon pump, including:

[0137] In the embodiment, when abnormal data is detected by infrared light data, blood return detection alarm is performed in time, so as to avoid blood invasion into the central cavity pipeline and affect the use effect of the intra-aortic balloon pump.

[0138] In the embodiment, the infrared light data can quantize the infrared light transmittance of the liquid, so as to calculate the blood concentration, and when the concentration is too high, an alarm is generated, so as to realize automatic and quantitative identification of blood return, early detection of blood return in the pipeline, avoidance of liquid pollution or misplacement, and improvement of patient safety.

[0139] In the embodiment, when the infrared light signal is detected through the infrared light data detection 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 whether the blood concentration is greater than or equal to a preset concentration threshold is judged based on the voltage, if yes, a back blood alarm information is generated, and a back blood alarm is performed based on the back blood alarm information.

[0140] As a specific example of the embodiment, when the voltage collected by the voltage acquisition module exceeds a preset standard voltage threshold (2. V-3.0V), the blood concentration is greater than a preset concentration threshold (0.5%), a back blood alarm information is generated, and a back blood alarm is performed based on the back blood alarm information.

[0141] In the embodiment, the blood concentration is calculated by using the infrared light transmittance, and an alarm is generated when the concentration is too high, so that automatic and quantitative identification of back blood is realized, blood backflow in the pipeline can be detected early, liquid pollution or misdelivery can be avoided, and patient safety is improved.

[0142] Please refer to Figure 4 , Figure 4 A flowchart of a bubble detection process is provided for the embodiment.

[0143] In the embodiment, the multi-channel data acquisition module includes an ultrasonic sensing sub-module, which is arranged below the flow clamp of the intra-aortic balloon pump, and is used to obtain ultrasonic wave data of the intra-aortic balloon pump in the braking state as monitoring data.

[0144] In the embodiment, the ultrasonic sensor is a 1MHz piezoelectric ceramic ultrasonic transducer, and the distance between the transmitting end and the receiving end is 10mm.

[0145] In the embodiment, the ultrasonic sensing sub-module is arranged below the flow clamp to obtain ultrasonic wave signals, so that the central cavity pipeline can be managed in all directions by collecting different signals at different positions according to the ultrasonic wave signals.

[0146] In the 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:

[0147] The main control module is used to calculate the signal loss amplitude based on the ultrasonic wave data, and when the signal difference amplitude is greater than or equal to a preset amplitude threshold for a preset time period, the ultrasonic wave data is abnormal data.

[0148] Control the regulating device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data to achieve management of the central lumen of the intra-aortic balloon pump.

[0149] In this embodiment, the ultrasonic signal strength of the central lumen liquid is obtained, and the ultrasonic signal strength includes the receiving strength and the transmitting strength; the signal loss amplitude can be calculated by the receiving strength and the transmitting strength, specifically: signal loss amplitude = receiving strength / transmitting strength.

[0150] In this embodiment, the signal loss amplitude at this moment can be calculated by the receiving signal strength and the transmitting signal strength, and the signal loss amplitude is less than 20% in the normal state, that is, the receiving signal strength is greater than or equal to 80% of the transmitting 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 lumen liquid, at this time, a bubble alarm information is generated.

[0151] In this embodiment, the ultrasonic wave is used to detect whether there is a bubble in the passing liquid; the ultrasonic bubble monitoring realizes the identification and detection of bubbles or liquids by using the principle that the acoustic impedance of ultrasonic waves in liquid and gas is different. When there is a bubble, due to the large change of acoustic impedance, the ultrasonic wave is reflected back and cannot reach the receiving end, so that the sensor can detect the existence of the bubble. The ultrasonic bubble sensor is based on the attenuation principle of ultrasonic transmission medium. When the pipeline is full of liquid, the propagation impedance of the liquid is small, so the signal received by the receiving end is roughly the same as that of the transmitting end. After amplification and shaping by hardware, it can be judged. When the pipeline is full of bubbles, that is, the propagation impedance of air becomes large, resulting in no signal at the receiving end, that is, when the ultrasonic wave is incident from water to air, almost all the energy is reflected on the boundary surface. According to this transformation, it is judged whether bubbles are generated. The bubbles in the fluid are monitored by detecting the change of ultrasonic signal strength.

[0152] In this embodiment, the bubbles are determined by the receiving strength and the transmitting strength, and an alarm is given when the receiving signal continuously falls below the strength threshold and times out, so that the generation of bubbles in the central lumen can be automatically and continuously monitored and an alarm can be given in time, the risk of air embolism is prevented, and the safety of the patient using the pump is further ensured.

[0153] In this embodiment, the main control module calculates the signal loss amplitude, and if the signal loss amplitude continuously exceeds the preset amplitude threshold within a set period, the abnormality is determined, and the time and amplitude are combined to improve the accuracy of abnormal identification and avoid misjudgment.

[0154] In this embodiment, the regulating device group further includes an alarm device, and the main control module is configured to control the regulating device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data to achieve management of the central lumen of the intra-aortic balloon pump, including:

[0155] control the alarm device to perform bubble detection alarm based on the abnormal data, so as to manage the central cavity of the intra-aortic balloon pump.

[0156] In this embodiment, when abnormal data is detected through ultrasonic data, bubble detection alarm is performed in time to avoid bubbles in the central cavity pipeline and affect the use effect of the intra-aortic balloon pump.

[0157] In this embodiment, the monitoring data corresponding to multiple positions of the intra-aortic balloon pump is obtained through the multi-channel data acquisition module, so that the abnormal data of each position of the intra-aortic balloon pump is identified through multi-dimensional monitoring data, the abnormal state of the central cavity of the intra-aortic balloon pump is identified in all directions, and the comprehensiveness of the central cavity management is improved; and when abnormal data is obtained, the control device group is automatically controlled to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data, so that the central cavity of the intra-aortic balloon pump is responded and controlled in time, without relying on manual monitoring of the central cavity, and the central cavity management efficiency is improved.

[0158] In this embodiment, 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 based on the abnormal data, so as to manage the central cavity of the intra-aortic balloon pump, including:

[0159] The main control module is configured to obtain the monitoring data, and detect the monitoring data based on the abnormal detection model to obtain abnormal data.

[0160] The control device group is controlled 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.

[0161] In this embodiment, the monitoring data is stored to build a historical monitoring database.

[0162] In this embodiment, the monitoring data includes pressure data, infrared light data and ultrasonic data; the main control module is configured to obtain the monitoring data, and detect the monitoring data based on the abnormal detection model to obtain abnormal data, including:

[0163] The monitoring data is obtained, and the pressure data, the infrared light data and the ultrasonic data are respectively subjected to feature extraction to obtain pressure features, infrared features and ultrasonic features.

[0164] The correlation coefficients of any two features of the pressure features, the infrared features and the ultrasonic features are calculated, and a geometric triangular structure of the pressure features, the infrared features and the ultrasonic features is built based on the correlation coefficients.

[0165] Adjust fusion weights of the pressure feature, the infrared feature and the ultrasonic feature based on the geometric triangular structure, and fuse the pressure feature, the infrared feature and the ultrasonic feature based on the fusion weights to obtain a fusion feature;

[0166] Input the fusion feature into a CAE-LSTM model for reconstruction to obtain Z scores and isolation forest scores of each feature.

[0167] Determine abnormal data based on the Z scores and the isolation forest scores.

[0168] In this embodiment, the monitoring data is preprocessed and time-synchronized.

[0169] In this embodiment, the monitoring data is aligned based on a preset window length and an overlap rate, thereby generating time series blocks in a fixed format, and normalization is performed in each port to generate standard data including pressure data, infrared light data and ultrasonic wave data. After obtaining the standard data, feature extraction is performed on the pressure data, the infrared light data and the ultrasonic wave data, respectively, to obtain pressure features, infrared features and ultrasonic features, wherein the pressure features, the infrared features and the ultrasonic features each include time domain features (mean, variance, peak value, etc.) and frequency domain features (FFT energy band).

[0170] In this embodiment, by extracting time domain (mean, variance, peak value, etc.) features and frequency domain (FFT energy band) features from each of the pressure, infrared and ultrasonic channels, physical interpretability and signal integrity can be maintained, and information loss can be avoided.

[0171] In this embodiment, the correlation coefficients of any two of the pressure feature, the infrared feature and the ultrasonic feature are calculated, and a geometric triangular structure of the pressure feature, the infrared feature and the ultrasonic feature is constructed based on the correlation coefficients, including:

[0172] A first correlation coefficient between the pressure feature and the infrared feature is calculated based on an R correlation coefficient method.

[0173] A second correlation coefficient between the pressure feature and the ultrasonic feature is calculated based on the R correlation coefficient method.

[0174] A third correlation coefficient between the infrared feature and the ultrasonic feature is calculated based on an M correlation coefficient method.

[0175] The first correlation coefficient, the second correlation coefficient and the third correlation coefficient are mapped to a two-dimensional plane, and a geometric triangular structure is constructed with the first correlation coefficient, the second correlation coefficient and the third correlation coefficient as side lengths.

[0176] In the embodiment, in actual application scenarios, the occurrence of an abnormal condition can cause abnormalities in multi-channel data. Multi-channel sensors are not completely independent, and there is a certain coupling relationship between their observation values under physiological or physical processes. For example, when pressure changes, blood reflux changes, bubbles form, and ultrasound signal attenuation and pressure micro-oscillation often occur simultaneously. Therefore, the correlation coefficient between any two features is calculated, and a combination structure is constructed to reflect the overall coupling balance degree between multi-channel data and quantify the stability of system operation.

[0177] In the embodiment, the first correlation coefficient between the pressure feature and the infrared feature is calculated based on the R correlation coefficient method, including:

[0178] (1)

[0179] wherein, is the mean of pressure data, is the pressure data, is the infrared data, is the mean of infrared data.

[0180] In the embodiment, the second correlation coefficient between the pressure feature and the ultrasound feature is calculated based on the R correlation coefficient method, including:

[0181] (2)

[0182] wherein, is the mean of pressure data, is the pressure data, is the ultrasound data, is the mean of ultrasound data.

[0183] In the embodiment, the third correlation coefficient between the infrared feature and the ultrasound feature is calculated based on the M correlation coefficient method, including:

[0184] The infrared feature and the ultrasound feature are normalized to eliminate dimensional differences. The normalized infrared and ultrasound features are discretized into a joint distribution matrix, the frequency of occurrence of each feature combination is counted, specifically, the gray values in the infrared feature are divided into N intervals, and the echo intensity in the ultrasound feature is divided into M intervals, interval combinations are constructed based on the N intervals and the M intervals, and the joint probability of each interval combination is calculated , and the marginal probability g(ir), g(y) is calculated, and then the third correlation coefficient is calculated through the joint probability and the marginal probability, including:

[0185] (3)

[0186] wherein, is infrared data, is ultrasonic data.

[0187] In the embodiment, the first correlation coefficient, the second correlation coefficient and the third correlation coefficient are mapped into a two-dimensional plane, and a geometric triangular structure is constructed with the first correlation coefficient, the second correlation coefficient and the third correlation coefficient as the side length. Since the first correlation coefficient, the second correlation coefficient and the third correlation coefficient respectively represent the correlation strength between different data characteristics, the data coupling of data from different sources is based on the correlation strength, avoiding system misjudgment caused by failure or fault of a single sensor.

[0188] In the embodiment, in the IABP system, if the first correlation coefficient of pressure-infrared decreases, it may indicate that the balloon position deviates, causing the pressure and temperature response to lose connection. At the same time, the third correlation coefficient of infrared-ultrasound decreases, which may reflect the cross-modal correlation fracture caused by thrombosis. Then, the correlation coefficient is used as the side length to construct a geometric triangular structure, so that the real-time update of the geometric triangular structure can reflect the change of the system state.

[0189] In the embodiment, the fusion weight of the pressure feature, the infrared feature and the ultrasonic feature is adjusted based on the geometric triangular structure, and the pressure feature, the infrared feature and the ultrasonic feature are fused based on the fusion weight to obtain a fusion feature, including:

[0190] The triangular area of the geometric triangular structure is calculated;

[0191] When the triangular area minus the preset area threshold is greater than or equal to a first area threshold, the fusion weight is a preset reference weight;

[0192] When the triangular area minus the preset area threshold is less than the first area threshold, the proportion value of each side of the geometric triangular structure to the triangular area is calculated, and the fusion weight of the pressure feature, the infrared feature and the ultrasonic feature is adjusted based on the proportion value;

[0193] The pressure feature, the infrared feature and the ultrasonic feature are fused based on the fusion weight to obtain a fusion feature.

[0194] In the embodiment, the area of the geometric triangular structure is determined by the correlation coefficients (i.e. the side length) of pressure, infrared and ultrasonic. When the triangular area is significantly greater than the preset threshold, it indicates that the correlation strength between the multi-modal data is high, 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 that the coupling relationship between the sensors is unbalanced, which may be caused by failure of a single sensor or physiological abnormalities (such as thrombosis and bubble embolism).

[0195] In this embodiment, in the IABP operation, if the pressure sensor detects abnormal fluctuations (such as sudden pressure drop caused by balloon leakage), and the correlation of infrared and ultrasound (M correlation coefficient) decreases synchronously, the triangular area will be significantly reduced. At this time, trigger dynamic weight adjustment, reduce the fusion weight of abnormal sensor, preferentially rely on other modal data, and avoid misjudgment.

[0196] In this embodiment, when the triangular area of the geometric triangular structure is below the threshold, the weight is adjusted according to the proportional value of each side (correlation coefficient) of the geometric triangular structure and the area:

[0197] (4)

[0198] wherein, is a small constant to prevent division by zero, S is the triangular area, is the proportional coefficient of each side.

[0199] For the weight of any feature, the proportional coefficients of the two connected sides are calculated, and the weight increment is calculated according to the sum of the proportional coefficients.

[0200] For example, the weight increment of the infrared feature is:

[0201] (5)

[0202] (6)

[0203] wherein, , is the proportional coefficient of the infrared feature and, is the infrared-ultrasound side length, is the infrared-pressure side length, is a small constant.

[0204] Therefore, the fusion weight of the infrared feature is:

[0205] (7)

[0206] wherein, is the fusion weight of the infrared feature, , is the reference weight of the infrared feature, is the weight increment.

[0207] In this embodiment, the fusion weights of the pressure feature and the ultrasound feature can also be calculated as described above, and after obtaining the fusion weights of the pressure feature, the infrared feature and the ultrasound feature (Wp, Wi, Wu), , , normalization is performed, and then the pressure feature, the infrared feature and the ultrasound feature are fused:

[0208] (8)

[0209] wherein, is a pressure feature, is an infrared feature, is an ultrasonic feature.

[0210] 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.

[0211] In this embodiment, when the coupling of a certain channel is extremely weak (corresponding to a shorter edge length), resulting in a significant decrease in the triangular area, the channel has a low proportion in the calculation of delta, so the fusion weight is automatically reduced to reduce the influence of noise or fault signals.

[0212] In this embodiment, the stability between different data sources is measured by the area of the geometric triangular structure. The larger the triangular structure area, the weaker the coupling between features and the stronger the information complementarity, which maximizes information retention by maintaining the reference weight. When the area is smaller, it represents that a certain type of data is abnormal or disturbed, and then the weight of each feature is dynamically adjusted by the proportion of each edge in the triangular area to avoid noise amplification.

[0213] In this embodiment, the fusion feature is input into the CAE-LSTM model.

[0214] In this embodiment, the CAE-LSTM model includes an Encoder module, an LSTM module, and a Decoder module. The Encoder module includes two 1D convolution layers (kernel size 3), a ReLU activation layer, a pooling dimension reduction layer; the LSTM module includes a bidirectional LSTM (hidden unit number 64) for capturing temporal dependencies; the Decoder module includes a mirror deconvolution layer and an up-sampling layer for restoring the original fusion feature dimension.

[0215] In this embodiment, the fusion feature in each sliding window is input into the convolutional autoencoder (CAE) + bidirectional LSTM architecture to obtain the reconstruction vector F^ and calculate the reconstruction error vector.

[0216] (9)

[0217] wherein, is an error vector, is a reconstruction vector.

[0218] In this embodiment, the reconstruction error set Calculate the mean and standard deviation of the error of each feature dimension, and calculate the Z-score of the error of the dth dimension in the current window:

[0219] (10)

[0220] wherein, , is the mean and standard deviation of the error.

[0221] In this embodiment, a Z threshold is set, and all dimensions whose Z scores exceed the Z threshold are marked as reconstruction-type abnormal dimensions. The Z scores of all dimensions are sorted, and the maximum Z score is determined as the dominant abnormal dimension.

[0222] Table 1

[0223]

[0224] In this embodiment, since each dimension of the fusion feature corresponds to a time-frequency description of different physical quantities such as pressure, infrared, ultrasound, etc., a dimension-channel- abnormal type mapping table is constructed in advance, as shown in Table 1.

[0225] In this embodiment, if the reconstruction-type abnormal dimension falls in the “pressure” dimension set, it is determined to be a pressure anomaly, and the low or high pressure can be determined based on the sign of the Z score; if it falls in the “infrared” dimension set, it is determined to be a blood reflux concentration anomaly; if it falls in the “ultrasound” dimension set, it is determined to be a bubble / flow anomaly.

[0226] In this embodiment, in the model initialization stage, K random isolation trees are trained using the fusion features collected during the “normal” operation, and the model parameters (tree structure, split threshold, etc.) are saved.

[0227] In this embodiment, the fusion feature of the current window is input into each isolation tree of the model. For the tth tree, the path length is obtained by counting the split nodes from the root node to the leaf node along the tree.

[0228] In this embodiment, the average path length of all trees is calculated:

[0229] (11)

[0230] In this embodiment, the average path length is normalized based on the expected path length to obtain the final isolation forest score:

[0231] (12)

[0232] wherein, is the expected path length constant, which can be calculated based on the number of samples during training of the isolation forest model.

[0233] In the embodiment, a threshold value of the isolation forest score is set, if both , the cluster type or gradual anomaly is determined, and is classified as a "complex / mixed anomaly". If both the Z-score and the isolation forest score exceed the threshold value, the strong anomaly is determined, and is marked as a "multi-channel linkage fault".

[0234] In the embodiment, when it is determined that there is an anomaly, the alarm device is controlled to alarm based on the anomaly data and the anomaly type, so as to realize the management of the central cavity of the intra-aortic balloon pump.

[0235] In the embodiment, the isolation forest is good at detecting group, slow drift or complex mode anomalies, and makes up for the lag of the Z-score on the point anomaly, and the isolation forest has no assumption on the data distribution, and is suitable for the multi-peak, non-Gaussian distribution scene of the IABP central cavity fusion features.

[0236] In the embodiment, the features of the pressure data, the infrared light data and the ultrasonic wave data are extracted separately, so as to avoid the loss of data features, and the fusion of the features is performed, so as to improve the identification ability in complex situations, for example, in the use of the IABP, the balloon rupture or the catheter folding may only show slight changes in the pressure waveform, and the multi-modal data can cross verify different abnormal situations.

[0237] In the embodiment of the application, a terminal is also provided, which includes a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, and the processor implements the central cavity management method described above when executing the computer program.

[0238] In the embodiment of the application, a computer readable storage medium is also provided, which includes a stored computer program, and when the computer program runs, the device where the computer readable storage medium is located executes the central cavity management method described above.

[0239] For example, the computer program can be divided into one or more modules, the one or more modules are stored in the memory and executed by the processor to complete the application. The one or more modules can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program in the terminal.

[0240] The terminal can be a desktop computer, a notebook computer, a palm computer, a cloud server, and the like. The terminal can 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 merely examples of the terminal and do not constitute a limitation on the terminal, and the terminal can include more or fewer components, or combine certain components, or different components, for example, the terminal can also include an input / output device, a network access device, a bus, and the like.

[0241] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor and the like. The processor is a control center of the terminal and connects all parts of the terminal through various interfaces and lines.

[0242] The memory can be used to store computer programs and / or modules, and the processor can realize various functions of the terminal by running or executing the computer programs and / or modules stored in the memory and calling data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store operating systems, at least one application program required by a function (such as a sound playing function, a text conversion function, and the like), and the like; and the data storage area can store data created according to the use of the terminal (such as audio data, text message data, and the like), and the like. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, for example, a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state memory devices.

[0243] If the module based on the center cavity management is implemented in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and 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. The computer program includes computer program code, which can be in the form of source code, object code, an executable file, or some intermediate form. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a U disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. Those of ordinary skill in the art can understand and implement it without creative labor.

[0244] The above-described specific embodiments further illustrate the purposes, technical solutions, and beneficial effects of the present application. It should be understood that the above-described specific embodiments are merely examples of the present application and are not intended to limit the protection scope of the present application. It is particularly pointed out that any modification, equivalent replacement, improvement, etc. made by those skilled in the art within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A central lumen management system, characterized by, The center cavity management system for an intra-aortic balloon pump comprises a regulating device group, a multi-channel data acquisition module and a master control module, wherein: The multi-channel data acquisition module is used for collecting monitoring data corresponding to multiple positions of the intra-aortic balloon pump; the monitoring data comprises pressure data, infrared light data and ultrasonic wave data; The master control module is used for acquiring abnormal data based on the monitoring data, comprising: respectively extracting features from the pressure data, the infrared light data and the ultrasonic wave data to obtain pressure features, infrared features and ultrasonic features; calculating correlation coefficients of any two features among the pressure features, the infrared features and the ultrasonic features, and constructing a geometric triangular structure of the pressure features, the infrared features and the ultrasonic features based on the correlation coefficients; adjusting fusion weights of the pressure features, the infrared features and the ultrasonic features based on the geometric triangular structure, and fusing the pressure features, the infrared features and the ultrasonic features based on the fusion weights to obtain fusion features, and determining abnormal data based on the fusion features; Based on the abnormal data, the regulating device group is controlled to perform corresponding actions on the intra-aortic balloon pump to realize the management of the center cavity of the intra-aortic balloon pump.

2. A central lumen management system as in claim 1, wherein, The multi-channel data acquisition module comprises a pressure sensor sub-module arranged at an interface of a pressure gauge of the intra-aortic balloon pump, which is used for acquiring pressure data of the intra-aortic balloon pump in a braking state as monitoring data.

3. A central lumen management system as in claim 2, wherein, The master control module is used for acquiring abnormal data based on the monitoring data, and controlling the regulating device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data to realize the management of the center cavity of the intra-aortic balloon pump, comprising: The master control module is used for determining that the pressure data being lower than a preset first pressure threshold or being higher than a preset second pressure threshold is abnormal data; Based on the abnormal data, the regulating device group is controlled to perform corresponding actions on the intra-aortic balloon pump to realize the management of the center cavity of the intra-aortic balloon pump.

4. A central lumen management system as in claim 3, wherein, The regulating device group comprises a booster pump and a pressure relief valve, and the master control module is used for controlling the regulating device group to perform corresponding actions on the intra-aortic balloon pump based on the abnormal data to realize the management of the center cavity of the intra-aortic balloon pump, comprising: When the pressure data is lower than the preset first pressure threshold, the booster pump is controlled to boost the intra-aortic balloon pump until the pressure data reaches a preset first target pressure; When the pressure data is higher than the preset second pressure threshold, the pressure relief valve is controlled to depressurize the intra-aortic balloon pump until the pressure data reaches a preset second target pressure.

5. A central lumen management system as in claim 2, wherein, The regulating device group comprises a flushing device, and the master control module is further used for acquiring normal data based on the monitoring data, and controlling the regulating device group to perform corresponding actions on the intra-aortic balloon pump based on the normal data to realize the management of the center 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, the pressure data is determined as normal data; Based on the normal data, the control device controls the flushing device to flush the central lumen saline channel of the intra-aortic balloon pump, so as to realize the management of the central lumen of the intra-aortic balloon pump.

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

7. A central lumen management system as in claim 6, wherein, The main control module is used to acquire 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 lumen of the intra-aortic balloon pump, including: The main control module is used to calculate the blood concentration based on the infrared light data, and 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, the control device controls the flushing device to flush the central lumen saline channel of the intra-aortic balloon pump, so as to realize the management of the central lumen of the intra-aortic balloon pump.

8. A central lumen management system as in claim 7, wherein, The regulation device group further includes an alarm device, and 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 lumen of the intra-aortic balloon pump, including: Based on the abnormal data, the alarm device is controlled to perform blood return detection alarm, so as to realize the management of the central lumen of the intra-aortic balloon pump.

9. A central lumen management system as in claim 1, wherein, The multi-channel data acquisition module includes an ultrasonic sensing sub-module, which is arranged below a flow clamp of the intra-aortic balloon pump, and is used to acquire ultrasonic wave data of the intra-aortic balloon pump in the braking state as monitoring data.

10. A central lumen management system as defined in claim 9, wherein, The main control module is used to acquire 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 lumen of the intra-aortic balloon pump, including: The main control module is used to calculate the signal loss amplitude based on the ultrasonic wave data, and when the signal difference amplitude is greater than or equal to a preset amplitude threshold within a preset time period, the ultrasonic wave data is abnormal data; Based on the abnormal data, the control device controls the flushing device to flush the central lumen saline channel of the intra-aortic balloon pump, so as to realize the management of the central lumen of the intra-aortic balloon pump.

11. A central lumen management system as in claim 10, wherein, The regulation device group further includes an alarm device, and 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 lumen of the intra-aortic balloon pump, including: Based on the abnormal data, the alarm device is controlled to perform bubble detection alarm, so as to realize the management of the central lumen of the intra-aortic balloon pump.

12. A central lumen management system as in claim 1, wherein, The master module is configured to acquire abnormal data based on the monitoring data, and control the regulating 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 master module is configured to acquire the monitoring data, and detect the monitoring data based on the anomaly detection model to acquire abnormal data; The master module is configured to control the regulating 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.

13. A central lumen management system as in claim 12, wherein, The monitoring data includes pressure data, infrared light data and ultrasonic data; the master module is configured to determine abnormal data based on the fusion features, including: Inputting the fusion features into a CAE-LSTM model for reconstruction to acquire Z scores and isolated forest scores of each feature; Determining abnormal data based on the Z scores and isolated forest scores.

14. A central lumen management system as in claim 13, wherein, The master module is configured to calculate the correlation coefficient 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 coefficient, including: Calculating a first correlation coefficient between the pressure features and the infrared features based on an R correlation coefficient method; Calculating a second correlation coefficient between the pressure features and the ultrasonic features based on the R correlation coefficient method; Calculating a third correlation coefficient between the infrared features and the ultrasonic features based on an M correlation coefficient method; Mapping the first correlation coefficient, the second correlation coefficient and the third correlation coefficient to 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 length.

15. A central lumen management system as in claim 14, wherein, The master module is configured to adjust the fusion weight 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 weight to acquire fusion features, including: Calculating the area of the geometric triangle structure; When the area of the geometric triangle structure minus the preset area threshold is greater than or equal to a first area threshold, the fusion weight is a preset reference weight; When the area of the geometric triangle structure minus the preset area threshold is less than the first area threshold, calculating the proportion of each side of the geometric triangle structure to the area of the geometric triangle structure; adjusting the fusion weight of the pressure features, infrared features and ultrasonic features based on the proportion; Fusing the pressure features, infrared features and ultrasonic features based on the fusion weight to acquire fusion features.

Images