Suction detection method and device for ventricular assist device

Abstract

The invention provides a suction detection method and device for a ventricular assist device, and the method comprises the steps: obtaining a target pumping flow curve which is a pumping flow curve of the ventricular assist device in a first operation period; extracting a target feature set of the target pumping flow curve; inputting the target feature set into a target classification tree model to obtain a classification result; and when the classification result is suction, calculating the suction degree of the ventricular assist device. According to the method, the classification tree model is used for carrying out suction judgment on the pumping flow curve of the ventricular assist device, whether suction happens to the current ventricular assist device or not can be rapidly detected, the suction detection accuracy is improved, the suction degree is further judged when suction exists, medical staff can be reminded to take corresponding solutions in time, and the success rate of the medical staff is improved. The safety of the patient is improved.

Description

Technical Field

[0001] The present application relates to the field of medical device technology, and in particular to a method and device for detecting suction of a ventricular assist device. Background Art

[0002] At present, ventricular assist device (VAD) has become an important means of treating end-stage heart failure. It is an artificial mechanical device that draws fluid from the venous system or heart directly into the arterial system, partially or completely replacing the work of the ventricles, and can solve the problem of shortage of heart donors. In order to meet the circulation needs of patients, developing a suitable pump control system to regulate the pumping flow through the ventricular assist device by controlling the speed of the pump is an important challenge faced by the increased use of these devices. However, when the speed of the ventricular assist device exceeds the user's requirements, it may cause suction problems in the ventricular assist device and damage the patient's heart. Summary of the invention

[0003] The embodiments of the present application provide a method and device for detecting aspiration of a ventricular assist device, which can timely and accurately detect whether aspiration exists in the ventricular assist device and the degree of aspiration.

[0004] In a first aspect, an embodiment of the present application provides a method for detecting aspiration of a ventricular assist device, the method comprising: Acquire a target pumping flow curve, where the target pumping flow curve is a pumping flow curve of the first cycle of the ventricular assist device; extracting a target feature set of the target pumping flow rate curve; Inputting the target feature set into a target classification tree model to obtain a classification result; When the classification result is pumping, the pumping degree of the ventricular assist device is calculated.

[0005] In a second aspect, an embodiment of the present application provides a control unit of a ventricular assist device, the control unit comprising one or more processors, the one or more processors being used to: Acquire a target pumping flow curve, where the target pumping flow curve is a pumping flow curve of the first cycle of the ventricular assist device; extracting a target feature set of the target pumping flow rate curve; Inputting the target feature set into a target classification tree model to obtain a classification result; When the classification result is pumping, the pumping degree of the ventricular assist device is calculated.

[0006] In a third aspect, an embodiment of the present application provides a ventricular assist device, the ventricular assist device comprising: case; an impeller disposed in the housing; A motor driving the impeller to rotate in suspension; A control unit connected to the motor, the control unit is used to execute instructions of the steps in the method described in the first aspect above.

[0007] In a fourth aspect, an embodiment of the present application provides a medical device, comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing some or all of the steps described in the method described in the first aspect above.

[0008] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute some or all of the steps described in the method described in the first aspect above.

[0009] In a sixth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the method described in the first aspect of the embodiment of the present application. The computer program product may be a software installation package.

[0010] The technical solution provided by the present application obtains a target pumping flow curve, which is a pumping flow curve of the first cycle of the ventricular assist device; extracts a target feature set of the target pumping flow curve; inputs the target feature set into a target classification tree model to obtain a classification result; and when the classification result is suction, calculates the degree of suction of the ventricular assist device. The present application uses a classification tree model to perform suction judgment on the pumping flow curve of the ventricular assist device, which can quickly detect whether suction occurs in the current ventricular assist device, improve the accuracy of suction detection, and further judge the degree of suction when suction exists, which can promptly remind medical staff to take corresponding solutions and improve the safety of patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0012] Figure 1 is a schematic diagram of a ventricular assist system provided in an embodiment of the present application; Figure 2is a schematic structural diagram of a ventricular assist device provided in an embodiment of the present application; Figure 3 is a schematic diagram of a classification tree model provided in Example 1 of the present application; Figure 4 It is a flow chart of a method for detecting aspiration of a ventricular assist device provided in Embodiment 2 of the present application; Figure 5 It is a partial schematic diagram of a classification tree model provided in Example 2 of the present application; Figure 6 It is a structural schematic diagram of a medical device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0013] In order to help those skilled in the art better understand the technical solutions of the present application, the following is a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the description of the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0014] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, software, product, or device that includes a series of steps or units is not limited to the listed steps or units, but also includes steps or units that are not listed, or also includes other steps or units inherent to these processes, methods, products, or devices.

[0015] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0016] The medical device involved in the present application may be a ventricular assist device, such as an implantable ventricular assist device. The ventricular assist device may be used for the left heart, the right heart, or both hearts. The ventricular assist device may include at least one blood pump, which may be a magnetic levitation pump.

[0017] "Speed" as used herein refers to the rotational speed of a motor or electric machine, which is associated with the rotational speed of the rotor or impeller of a ventricular assist device, and may be defined as revolutions per minute. "Flow", "fluid flow", "pumping flow" refers to the volume of fluid delivered through the ventricular assist device per unit of time, which may be measured in liters per minute.

[0018] Patients with heart failure can use a ventricular assist device to assist the heart in completing its pumping function. The ventricular assist device can be placed in the patient's left ventricle to pump blood from the patient's left ventricle to the aorta to solve the patient's left heart failure problem; the ventricular assist device can also be placed in the patient's right ventricle to pump blood from the patient's right ventricle to the pulmonary artery to solve the patient's right heart failure problem.

[0019] The ventricular assist system of the present application may include an LVAD (left ventricular assist device), an RVAD (right ventricular assist device) or a BIVAD (biventricular assist device), which includes not only a ventricular assist device implanted in the patient's body during operation, but also typically includes a controller disposed outside the patient's body and connected to the ventricular assist device via a percutaneous line (transmission system). A portion of the transmission system extends outside the patient's body between the controller and the puncture site, while another portion extends into the patient's body between the puncture site and the ventricular assist device. The controller may, for example, include an integrated battery (rechargeable battery) or may be connected to a battery so that the implanted ventricular assist device may be powered by the controller via a percutaneous line. The ventricular assist device typically includes a motor having a stator and a rotor having blades. The motor of the ventricular assist device may typically be driven by power delivered by the controller, for example, generating current in the windings of the stator, which causes the rotor and its blades to rotate in order to deliver the patient's blood.

[0020] See also Figure 1 , Figure 1 A ventricular assist system is provided in an embodiment of the present application. The ventricular assist system includes a ventricular assist device 100, a controller 200, and a percutaneous cable 300 for connecting the ventricular assist device 100 to the controller 200. The proximal end of the percutaneous cable 300 extends through the skin into the ventricular assist device 100 to transmit power, information, and control signals for the operation of the ventricular assist device 100.

[0021] The ventricular assist device 100 can be implanted in the body, for example, it can be attached to the heart via a ventricular connection component (such as a top ring, a ventricular cuff, or a ventricular cuff), and the ventricular connection component can be sutured to the heart and connected to the ventricular assist device 100. The other end of the ventricular assist device 100 can be connected to the ascending aorta or the pulmonary artery via an outlet tube and / or an artificial blood vessel connected to the outlet tube, so that the ventricular assist device 100 can effectively transfer blood from a weakened heart and propel it to the aorta or the pulmonary artery, thereby circulating it to the rest of the patient's vascular system and providing ventricular assist function to the patient.

[0022] The controller 200 is used to monitor the ventricular assist device 100, and can realize functions such as control and data display of the ventricular assist device 100, fault detection, alarm, and data recording. For example, the controller 200 may have a touch screen display for displaying the operating data of the ventricular assist device 100, patient information, information of the ventricular assist device 100, etc. Further, the user can set the operating parameters of the ventricular assist device 100 through the controller 200.

[0023] See also Figure 2 , Figure 2 : is a schematic diagram of the structure of a ventricular assist device 100 proposed in an embodiment of the present application. The ventricular assist device 100 includes a housing assembly having an inlet pipe 50, an impeller 20 for pushing a fluid, and a motor 30 for driving the impeller 20 to rotate in suspension. The housing assembly includes a first housing and a second housing connected to the first housing, the first housing and the second housing together form a chamber 10, and the housing assembly is also provided with a fluid inlet 14 and a fluid outlet 15 connected to the chamber 10, and the fluid inlet 14 is provided on the first housing. The impeller 20 can rotate in suspension in the chamber 10, and the rotation of the impeller 20 can generate a centrifugal force for conveying the fluid, so that the fluid can enter the chamber 10 from the fluid inlet 14 and be output from the fluid outlet 15. Among them, the suspended rotation of the impeller 20 means that the impeller 20 does not contact the cavity wall of the chamber 10 when rotating.

[0024] The second housing includes a first side wall 11, the first housing includes a second side wall 12, and the motor 30 includes a stator 31 and a rotor 32 arranged on both sides of the first side wall 11. The stator 31 is fixed to the outer side of the first side wall 11 relative to the chamber 10, and the corresponding rotor 32 is located in the chamber 10. Further, the rotor 32 is fixedly connected to the impeller 20, and when the stator 31 drives the rotor 32 to rotate in the chamber 10, the impeller 20 also rotates synchronously with the rotor 32 in the chamber 10.

[0025] The ventricular assist device 100 further includes a control unit 33 , which is electrically connected to the stator 31 . The control unit 33 can control the rotation speed and suspension height of the rotor 32 by adjusting the current flowing through the stator 31 .

[0026] Taking left ventricular assist as an example, the inlet tube 50 is fixed at the apex of the heart. During the implantation or operation of the ventricular assist device 100, the tube mouth of the inlet tube 50 may be too close to or adjacent to the heart tissue, resulting in a suction event. A suction event may occur when the fluid inlet 14 interacts with the heart tissue, resulting in partial or complete blockage of the inlet tube 50. Continuous suction may damage the patient's heart, impair the function of the ventricular assist device 100, and cause insufficient perfusion of the patient.

[0027] Based on this, the present application proposes a method for detecting suction of a ventricular assist device 100, by inputting the pumping flow curve of the ventricular assist device 100 into a pre-trained classification tree model, and determining whether the current ventricular assist device 100 has suction according to the output classification result, and then further judging the degree of suction when the classification result is suction, so as to promptly and quickly detect whether the ventricular assist device 100 has suction, improve the accuracy of suction detection, and judge the degree of suction, and make corresponding processing according to the degree of suction in time.

[0028] In combination with the above description, the method provided by this application is described below from the model training side and the model application side: The method for training a classification tree model provided in an embodiment of the present application involves the processing of natural language and computer vision, and can be specifically applied to data training, machine learning, deep learning and other data processing methods to perform symbolic and formalized intelligent information modeling, extraction, preprocessing, training, etc. on the training data (such as the pumping flow of the central chamber auxiliary device in the present application), and finally obtain a trained classification tree model.

[0029] It should be noted that the training method of the classification tree model provided in the embodiment of the present application and the method of using the classification tree model to determine whether to inhale are inventions based on the same concept, and can also be understood as two parts in a system, or two stages of an overall process: such as the model training stage and the model application stage.

[0030] Embodiment 1 The present application embodiment describes the structural features of the classification tree model. For example, Figure 3 As shown in the figure, the input of the classification tree model is the first feature P1, the second feature P2, the third feature P3 and the fourth feature P4. The leaf nodes of the tree are the classification results output by the model, which are divided into suction and normal, suction is represented by y=1, and normal is represented by y=0. The nodes of the tree are any one of the first feature P1, the second feature P2, the third feature P3 and the fourth feature P4. Each layer uses the first feature P1, the second feature P2, the third feature P3 and the fourth feature P4 as the segmentation points to construct the classification rules, and the classification rules make the classification results output by the classification tree model close to the true category of the data.

[0031] The first feature P1 is used to measure the degree of symmetry of the data and is a statistic that describes the symmetry of the data distribution. The fourth feature P4 is used to measure the distribution shape of the data. In statistics, the fourth feature can be represented by kurtosis, which is a measure of the degree of peak compared to the normal distribution. If the data is evenly distributed or more dispersed in the center and lacks extreme values, its kurtosis value is low; if the data tends to be concentrated near the mean and has more extreme values ​​at the same time, its kurtosis value is high.

[0032] The first feature P1 can be calculated by the first formula, and the fourth feature P4 can be calculated by the second formula. The first formula is:

[0033] The second formula is:

[0034] in, is the data sampling point, is the average value of n data sampling points, and S is the standard deviation of n data sampling points.

[0035] The second feature P2 is the ratio of the low-frequency energy to the fundamental frequency energy of the data on the spectrum, and the third feature P3 is the ratio of the high-frequency energy to the fundamental frequency energy of the data on the spectrum. In the spectrum data PF(w), the frequency (0, a) is the low-frequency range, the frequency (a, b) is the fundamental frequency range, and the frequency (b, ) is the high frequency range. By summing the spectrum data PF(w) in the fundamental frequency range, low frequency range and high frequency range, low frequency energy, fundamental frequency energy and high frequency energy can be obtained respectively. The low frequency energy is expressed as N1=PF(0)+…+PF(a), the fundamental frequency energy is expressed as N1=PF(a)+…+PF(b), and the high frequency energy is expressed as N1=PF(b)+…+PF( ). Therefore, the second feature P2 = N1 / N2, and the third feature P3 = N3 / N3.

[0036] The extracted first feature P1, second feature P2, third feature P3 and fourth feature P4 are input into the classification tree model, classified layer by layer according to the classification rules, and finally the classification result is output.

[0037] For example, the classification tree model can be a classification regression tree model, a decision tree model, a random forest model, etc.

[0038] The classification and regression tree model consists of multiple nodes, and the number of nodes is positively correlated with the complexity of the model. The nodes include a root node, several intermediate nodes, and multiple leaf nodes (the root node is the starting node of the decision tree, indicating the initial segmentation point of the entire data set. The leaf node is the terminal node of the decision tree, indicating the final classification result, and no further segmentation is performed. The intermediate node is a non-terminal node in the decision tree, responsible for further segmentation of the data set according to the features until the leaf node is finally reached). Each node represents the decision condition of a feature, and each non-leaf node has two child nodes, representing that the data is allocated to two different subsets based on the judgment result of a certain feature value.

[0039] At each node, a feature and a threshold value of the feature are selected to divide the data set into two subsets. The basis for selecting the feature and the threshold value of the feature is to measure the quality of each segmentation by evaluating the Gini index. This criterion is used to evaluate whether the subsets after segmentation are more "pure", that is, the more concentrated the category distribution of the samples in the subset is, the more conducive it is to improve the classification accuracy.

[0040] The calculation formula of the Gini coefficient is: , where pi is the proportion of samples belonging to the i-th category in the data set, and c is the number of categories. The smaller the Gini index, the higher the purity of the data set. An intermediate node will be divided into two branches, and the Gini coefficients of the left and right branches will be calculated respectively. Then, the weighted average of the two Gini coefficients will be calculated as the Gini coefficient of the intermediate node. The final selection of the feature and a certain threshold of the feature as the intermediate node is based on the minimum Gini coefficient calculated by them.

[0041] For example, assuming that the first feature P1>0.234, the left branch includes 60 feature arrays, of which 40 are normal and 20 are pumped; the right branch includes 80 feature arrays, of which 50 are normal and 30 are pumped. Then the Gini coefficient of the left branch is equal to 1-(40 / 60)^2-(20 / 60)^2=0.44444; the Gini coefficient of the right branch is equal to 1-(50 / 80)^2-(30 / 80)^2=0.46875; the Gini coefficient of the middle node is the weighted average of the two: 0.44444 (60 / 140)+0.46875 (60 / 140)=0.39136.

[0042] To select the best split point, the model calculates the Gini index for all possible split points for each feature and selects the feature and threshold that maximizes purity.

[0043] Once the features and thresholds are selected, all samples are assigned to two branches according to the conditions. The process continues recursively until a leaf node is reached. The leaf node will output a class label. In classification tasks, the class label of a leaf node is the majority class of the samples in the leaf node. That is, among all the samples that reach the leaf node, the class label with the most occurrences will be used as the prediction result.

[0044] Embodiment 2 See also Figure 4 , Figure 4 A schematic flow chart of a method for detecting aspiration of a ventricular assist device provided in an embodiment of the present application is applied to Figure 1-Figure 2 The ventricular assist device 100 is shown. Figure 4 As shown, the method includes the following steps.

[0045] S410. Obtain a target pumping flow curve, where the target pumping flow curve is a pumping flow curve of the first cycle of operation of the ventricular assist device.

[0046] During the operation of the ventricular assist device 100 in the user's body, the pumping flow through the ventricular assist device 100 depends on the work that the ventricular assist device 100 needs to overcome resistance to pump blood from the left ventricle to the aorta. The amount of work done by the ventricular assist device 100 can be quantified as the amount of current that needs to be provided to the motor 30 (more specifically, the stator 31), that is, the motor current corresponds to the amount of current delivered to the motor 30 of the ventricular assist device 100 when the ventricular assist device 100 is operating in the user. During different phases of the cardiac cycle of the user's heart, the load on the motor 30 will change. When the pressure difference in the user's heart changes, the motor current will also change to keep the rotor 32 speed constant. For example, when the flow rate of blood entering the aorta increases (such as during cardiac systole), the current required by the motor 30 will increase. Therefore, changes in the motor current can help characterize cardiac performance. That is, during the operation of ventricular assist device 100 , ventricular assist device 100 has a current-flow characteristic curve, wherein the greater the current, the more work ventricular assist device 100 does, that is, the greater the pumping flow of ventricular assist device 100 .

[0047] The current of the ventricular assist device 100 can be measured by a phase current detection circuit or any other suitable means (such as a current sensor). The current-flow characteristic curve can be pre-stored in the control unit 33. Before the ventricular assist device 100 leaves the factory, it can be placed in a test system to test the relationship curve between the pumping flow rate and the current change of the ventricular assist device 100 at different speeds, and then the current-flow characteristic curve is stored in the control unit 33. The control unit 33 can store the detected current in real time.

[0048] When the ventricular assist device 100 is running at the target rotation speed, after the control unit 33 obtains the current curve, it estimates the flow curve corresponding to the current curve using the pre-stored current-flow characteristic curve to obtain the target pumping flow curve.

[0049] The first cycle is a multiple of the patient's cardiac cycle, such as 3 times, 5 times, 10 times, 30 times, etc.

[0050] S420: Extract a target feature set of the target pumping flow rate curve.

[0051] Among them, the target feature set includes the first feature, the second feature, the third feature and the fourth feature. The first feature is used to measure the symmetry of the target pumping flow curve, the second feature is the ratio of the low frequency to the fundamental frequency of the target pumping flow curve in the frequency domain, the third feature is the ratio of the high frequency to the fundamental frequency of the target pumping flow curve in the frequency domain, and the fourth feature is used to measure the distribution shape of the target pumping flow curve.

[0052] In order to determine whether the ventricular assist device 100 is pumping, the control unit 33 can determine based on the characteristics represented by the target pumping flow curve. When the ventricular assist device 100 is operating normally, the waveform of its pumping flow curve is generally a sine wave waveform. When the ventricular assist device 100 is pumping, the waveform of the pumping flow curve of the ventricular assist device 100 will change. For example, if the pumping occurs during the systolic period of the cardiac cycle, the pumping flow during the systolic period of the cardiac cycle will decrease sharply or even decrease to 0. If the pumping occurs during the diastolic period of the cardiac cycle, the pumping flow during the systolic period of the cardiac cycle will continue to remain at a low value or suddenly decrease to a smaller pumping flow or even decrease to 0. Therefore, when the ventricular assist device 100 is pumping, its pumping flow curve will change in the time domain and frequency domain. Then, by extracting the characteristics of the pumping flow curve in the time domain and frequency domain, it can be determined whether the pumping flow curve is abnormal based on the characteristics, thereby determining whether the ventricular assist device 100 is pumping.

[0053] Optionally, the extraction of the target feature set of the target pumping flow curve includes: obtaining n pumping flow sampling points from the target pumping flow curve, where n is a positive integer; calculating the standard deviation and the average flow of the n pumping flow sampling points; substituting the standard deviation, the average flow and the n pumping flow sampling points into a first formula to calculate the first feature; substituting the average flow and the n pumping flow sampling points into a second formula to calculate the fourth feature; performing a Fourier transform on the target pumping flow to obtain fundamental frequency energy, low-frequency energy and high-frequency energy; calculating the ratio of the low-frequency energy to the fundamental frequency energy to obtain the second feature; calculating the ratio of the high-frequency energy to the fundamental frequency energy to obtain the third feature.

[0054] When the ventricular assist device 100 is operating normally, its pumping flow curve is roughly symmetrically distributed. However, when the ventricular assist device 100 is pumping, its pumping flow rate will drop suddenly, causing its pumping flow curve to be symmetrical within the cardiac cycle. When the ventricular assist device 100 is operating normally, the pumping flow curve is roughly symmetrically distributed, and the first feature P1 is approximately equal to 0; when the ventricular assist device 100 is pumping, the pumping flow curve is asymmetric, and the first feature P1 is less than 0. When the ventricular assist device 100 is operating normally, its pumping flow curve is relatively evenly distributed, and the value of its feature four is small; when the ventricular assist device 100 is pumping, more extremely low values ​​will appear due to the pumping, making the value of feature four larger.

[0055] Aortic valve regurgitation, abnormal position of the ventricular assist device 100, abnormal patient heart rate, suction of the ventricular assist device 100, abnormal rotation speed of the ventricular assist device 100 (too high or too low), etc. may all cause abnormal pumping flow of the ventricular assist device 100 in the time domain. There is a large error in judging whether there is suction of the ventricular assist device 100 only by the abnormality of the pumping flow curve in the time domain. Therefore, the present application performs Fourier transformation on the pumping flow curve to obtain its spectrum data PF (w). By performing spectrum analysis on the spectrum data, it can be judged whether there is suction in the frequency domain according to the analysis results.

[0056] When the ventricular assist device 100 operates normally, its pumping flow curve is mainly the fundamental frequency in the frequency domain, and its low-frequency energy is much lower than the fundamental frequency energy, and its high-frequency energy is also much lower than the fundamental frequency energy. The change of the pumping flow during suction will appear as abnormal frequency noise in the frequency domain, and the abnormal frequency noise may be low frequency or high frequency. Therefore, when the ventricular assist device 100 is suctioning, the low-frequency energy or high-frequency energy will increase, so that the second feature P2 or the third feature P3 will increase.

[0057] The control unit 33 can extract the first feature P1, the second feature P2, the third feature P3 and the fourth feature P4 from the target pumping flow curve. Specifically, the control unit 33 collects n pumping flow sampling points from the pumping flow curve according to the acquisition frequency, and then substitutes the n pumping flow sampling points into the first formula to calculate the first feature P1 of the target pumping flow curve, and substitutes the n pumping flow sampling points into the second formula to calculate the fourth feature P4 of the target pumping flow curve. At the same time, the target pumping flow curve is subjected to Fourier transformation to obtain the spectrum data of the target pumping flow curve, and the third feature P3 and the fourth feature P4 are calculated based on the spectrum data.

[0058] S430: Input the target feature set into a target classification tree model to obtain a classification result.

[0059] The control unit 33 inputs the first feature P1, the second feature P2, the third feature P3 and the fourth feature P4 extracted from the target pumping flow rate curve into the target classification tree model to obtain the classification result of the target pumping flow rate curve, and the classification result includes suction and normal. If the classification result output by the target classification tree model is 1, it means that the current ventricular assist device 100 has suction; if the classification result output by the target classification tree model is 0, it means that the current ventricular assist device 100 is operating normally.

[0060] In order to better illustrate the classification process of the classification tree model, a small part of the classification tree is taken as an example. Figure 5 As shown, at the root node of the classification tree, if the first feature P1 is less than 0.14173, it enters the left branch; if the first feature P1 is greater than or equal to 0.14173, it enters the right branch. At the child node 1 of the left branch, if the fourth feature P4 is less than 1.74075, its classification result is y=0; if the fourth feature P4 is greater than or equal to 1.74075, it enters the child node 2. If the second feature P2 is less than 0.426645, its classification result is y=1; the second feature P2 is greater than or equal to 0.426645, and its classification result is y=0. At the child node 1 of the right branch, if the third feature P3 is less than 0.148827, its classification result is y=0; if the third feature P3 is greater than or equal to 0.148827, its classification result is y=1. Assuming that the first feature P1, the second feature P2, the third feature P3 and the fourth feature P4 of the target pumping flow curve are 0.13877, 0.41452, 0.14523 and 1.80124 respectively, the classification result is y=1, indicating that the ventricular assist device is currently pumping.

[0061] S440: When the classification result is suction, calculate the suction degree of the ventricular assist device.

[0062] After determining that ventricular assist device 100 has suctioned, control unit 33 may also determine the degree of suction of ventricular assist device 100 in order to facilitate medical personnel to propose solutions in a timely manner.

[0063] Optionally, when the classification result is suction, the pumping degree of the ventricular assist device is calculated, including: obtaining a target average flow rate, wherein the target average flow rate is an average pumping flow rate in a second cycle of operation of the ventricular assist device, the second cycle being earlier than the first cycle; obtaining a minimum pumping flow rate and a maximum pumping flow rate of the target pumping flow curve; calculating a discrimination threshold value based on the target average flow rate, the minimum pumping flow rate and the maximum pumping flow rate; and determining the pumping degree of the ventricular assist device based on the discrimination threshold value.

[0064] In the embodiment of the present application, in order to further determine the pumping degree of the ventricular assist device 100, the control unit 33 can determine the pumping degree of the ventricular assist device 100 based on the sudden drop in the pumping flow of the ventricular assist device 100.

[0065] The control unit 33 obtains the pumping flow curve in the second cycle and calculates the average value of the pumping flow curve in the second cycle. The second cycle is a cycle when the ventricular assist device 100 operates normally, that is, the pumping flow curve in the second cycle is a normal pumping flow curve. When the ventricular assist device 100 is pumping, the minimum value or the maximum and minimum values ​​of its pumping flow will change. By comparing it with the normal average value, the degree of sudden drop in the pumping flow can be evaluated, and then the degree of suction can be determined according to the degree of sudden drop.

[0066] Specifically, the control unit 33 calculates a first difference between the target average flow and the minimum value in the target pumping flow curve, and a second difference between the target average flow and the maximum value in the target pumping flow curve, and then uses the ratio of the first difference to the second difference as a discrimination threshold.

[0067] Wherein, determining the pumping degree of the ventricular assist device 100 according to the discrimination threshold includes: if the discrimination threshold is greater than a first value, determining that the ventricular assist device 100 is severely pumping; if the discrimination threshold is greater than or equal to a second value and less than or equal to the first value, determining that the ventricular assist device 100 is moderately pumping; if the discrimination threshold is greater than a third value and less than the second value, determining that the ventricular assist device 100 is slightly pumping.

[0068] The average pumping flow rate when the ventricular assist device 100 is operating normally is a value with very small fluctuations, so the target average flow rate can be approximated as a fixed value. The more severe the pumping of the ventricular assist device 100, the smaller the minimum value in the target pumping flow rate curve, so that the discrimination threshold is larger. When the calculated discrimination threshold is greater than the first value, the current ventricular assist device 100 is considered to be severely pumping; when the discrimination threshold is less than or equal to the first value and greater than or equal to the second value, the current ventricular assist device 100 is considered to be moderately pumping; when the discrimination threshold is less than the second value and greater than the third value, the current ventricular assist device 100 is considered to be lightly pumping.

[0069] The first value, the second value and the third value may be set according to the suction detection accuracy. For example, the first value, the second value and the third value may be set to 1.4, 1.2 and 1 respectively.

[0070] In the embodiment of the present application, the control unit 33 can quickly detect whether the current ventricular assist device 100 has suction by using a classification tree model, thereby improving the accuracy of suction detection and further determining the degree of suction when suction exists, thereby being able to promptly remind medical staff to take corresponding solutions and improve patient safety.

[0071] Embodiment 3 Embodiment 3 of the present application provides a training method for a classification tree model, and the classification tree model may be the classification tree model in embodiment 1. The training method may train the classification tree model to be trained, so that the trained classification tree model can accurately determine whether the ventricular assist device is pumping according to the pumping flow curve.

[0072] In an embodiment of the present application, before training the classification tree model, the method also includes: acquiring a training data set, the training data set including a plurality of first pumping flow curves, the first pumping flow curve being a pumping flow curve when the ventricular assist device is pumping or operating normally; marking a classification label of each of the first pumping flow curves; and calculating a first ratio and a second ratio based on the classification label, the first ratio being the proportion of the first pumping flow curves with the classification label of pumping in the training data set, and the second ratio being the proportion of the first pumping flow curves with the classification label of normal in the training data set.

[0073] The multiple first pumping flow curves include a pumping flow curve when the ventricular assist device is operating normally and a pumping flow curve when the ventricular assist device is pumping. Each first pumping flow curve is a pumping flow curve in the first cycle of the ventricular assist device 100. After the training data set is acquired, each first pumping flow curve in the training data set is manually labeled with a classification label, and the classification labels are divided into suction and normal to distinguish whether the first pumping flow curve is a normal pumping flow curve or a suction pumping flow curve. After the multiple first pumping flow curves are labeled with classification labels, the proportion of the pumping flow curve when the ventricular assist device 100 is pumping and the proportion of the pumping flow curve when the ventricular assist device 100 is normal in the multiple first pumping flow curves can be calculated respectively.

[0074] The control unit 33 trains the classification tree model to be trained, takes multiple first pumping flow curves as inputs of the classification tree model to be trained, takes the first ratio and the second ratio as the Gini coefficients of the output categories of the classification tree model, continuously optimizes the segmentation points in the classification tree model, and obtains the final target classification tree model.

[0075] Optionally, the target classification tree model is trained, specifically including: extracting a target feature set of the multiple first pumping flow curves; inputting each of the target feature sets into the classification tree model to be trained to obtain a classification result of each of the first pumping flow curves; determining the segmentation points of each layer in the classification tree model to be trained according to the classification results, the first ratio and the second ratio to obtain the target classification tree model.

[0076] The first feature P1, the second feature P2, the third feature P3 and the fourth feature P4 are extracted from each first pumping flow curve. First, n pumping flow sampling points are sampled from the first pumping flow curve according to the sampling frequency, and then the standard deviation S and the average value of the first pumping flow curve are calculated based on the n pumping flow sampling points. Then the standard deviation S and the mean Substitute into the first formula above to calculate the first feature P1, and take the average value Substitute into the above second formula to calculate the fourth characteristic P4. At the same time, each first pumping flow curve is subjected to Fourier transformation to obtain corresponding spectrum data, and spectrum analysis is performed on the spectrum data to calculate the low-frequency energy N1, the fundamental frequency energy N2 and the high-frequency energy N3 corresponding to the low frequency, fundamental frequency and high frequency in each spectrum data, thereby calculating the second characteristic P2=N1 / N2 and the third characteristic P3=N3 / N2 of each first pumping flow curve.

[0077] Construct a classification tree based on the four features of the first feature P1, the second feature P2, the third feature P3 and the fourth feature P4. Specifically, the data is divided into categories y=1 and y=0, y=1 indicates that the classification result is suction, and y=0 indicates that the classification result is normal. Use these four features as the segmentation points of each layer of the classification tree, traverse these four features, and try all possible segmentation points. Then input the first feature P1, the second feature P2, the third feature P3 and the fourth feature P4 of multiple first pumping flow curves into the classification tree formed by each possible segmentation point respectively, and obtain the classification results of different segmentation points. By calculating the Gini coefficients of the two groups of data of the multiple first pumping flow curve categories y=1 and y=0 obtained after classification at each segmentation point, the features and segmentation points with the smallest calculated Gini coefficients are used as the segmentation conditions of this layer. During the segmentation process, if the Gini coefficients of the two groups of data y=1 and y=0 calculated after segmentation of this layer are significantly different from the first proportion and the second proportion of the multiple first pumping flow curves or the error is greater than the preset error, the child nodes of the node of this layer will continue to be segmented, and the segmentation will be performed layer by layer until the optimal segmentation point that meets the preset error is found layer by layer, thereby constructing the classification rules of the classification tree and obtaining the final classification tree model.

[0078] It should be noted that the training process of the classification tree model in the embodiment of the present application is the process of constructing the classification tree. The segmentation points of each layer in the classification tree are continuously optimized through the training data set, and the classification rules of the classification tree are constructed, so that the error between the classification result after classifying the pumping flow curve according to the classification tree model and the actual result is within the preset error.

[0079] It can be seen that the training method of the classification tree model provided in the embodiment of the present application can improve the accuracy of classification by selecting appropriate features, collecting more data samples, improving data quality, and using cross-validation during the training process.

[0080] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that in order to realize the above functions, the network device includes a hardware structure and / or software module corresponding to each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiment provided in this article, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0081] For example, the present application provides a control unit of a ventricular assist device, the control unit comprising one or more processors, the one or more processors being used to: obtain a target pumping flow curve, the target pumping flow curve being a pumping flow curve of a first cycle of operation of the ventricular assist device; extract a target feature set of the target pumping flow curve; The target feature set is input into a target classification tree model to obtain a classification result; when the classification result is suction, the suction degree of the ventricular assist device is calculated.

[0082] For example, the present application also provides a ventricular assist device, the ventricular assist device comprising: case; an impeller disposed in the housing; A motor driving the impeller to rotate in suspension; A control unit connected to the motor, wherein the control unit is used for some or all of the steps described in the above method.

[0083] As an example, the present application also provides a medical device, which includes the control unit or ventricular assist device described above.

[0084] Among them, the control unit of each of the above schemes has the function of implementing the corresponding steps performed by the medical device in the above method; the functions can be implemented by hardware, or by hardware executing corresponding software.

[0085] In the embodiment of the present application, the control unit may also be a chip or a chip system, for example, a system on chip (SoC).

[0086] See also Figure 6 , Figure 6 It is a structural diagram of a medical device provided in an embodiment of the present application, wherein the medical device comprises: one or more processors, one or more memories, one or more communication interfaces, and one or more programs; the one or more programs are stored in the memories and are configured to be executed by the one or more processors.

[0087] The above program includes instructions for performing the following steps: Acquire a target pumping flow curve, where the target pumping flow curve is a pumping flow curve of the first cycle of the ventricular assist device; extracting a target feature set of the target pumping flow rate curve; Inputting the target feature set into a target classification tree model to obtain a classification result; When the classification result is pumping, the pumping degree of the ventricular assist device is calculated.

[0088] Among them, all relevant contents of each scenario involved in the above method embodiment can be referred to the functional description of the corresponding functional module, which will not be repeated here.

[0089] It should be understood that the above-mentioned memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0090] In the embodiment of the present application, the processor of the above-mentioned device may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) 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.

[0091] It should be understood that the "at least one" involved in the embodiments of the present application refers to one or more, and "plurality" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and subsequent associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0092] Furthermore, unless otherwise specified, ordinal numbers such as "first" and "second" mentioned in the embodiments of the present application are used to distinguish multiple objects, and are not used to limit the order, timing, priority or importance of multiple objects. For example, the first information and the second information are only used to distinguish different information, and do not indicate the difference in content, priority, sending order or importance of the two types of information.

[0093] In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software. The steps of the method disclosed in conjunction with the embodiment of the present application can be directly embodied as a hardware processor for execution, or a combination of hardware and software units in a processor for execution. The software unit can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor executes the instructions in the memory, and completes the steps of the above method in conjunction with its hardware. To avoid repetition, it is not described in detail here.

[0094] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any method recorded in the above method embodiments.

[0095] The present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps of any method described in the above method embodiment. The computer program product may be a software installation package.

[0096] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0097] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0098] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0099] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0100] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0101] If the above-mentioned integrated unit 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 memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or TRP, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0102] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing the relevant hardware through a program, and the program may be stored in a computer-readable memory, which may include a flash drive, ROM, RAM, a magnetic disk or an optical disk, etc.

[0103] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for detecting aspiration of a ventricular assist device, characterized in that: The method comprises: Acquire a target pumping flow curve, where the target pumping flow curve is a pumping flow curve of the first cycle of the ventricular assist device; extracting a target feature set of the target pumping flow rate curve; Inputting the target feature set into a target classification tree model to obtain a classification result; When the classification result is pumping, the pumping degree of the ventricular assist device is calculated.

2. The method according to claim 1, characterized in that The target feature set includes a first feature, a second feature, a third feature and a fourth feature. The first feature is used to measure the degree of symmetry of the target pumping flow curve. The second feature is the ratio of the low frequency to the fundamental frequency of the target pumping flow curve in the frequency domain. The third feature is the ratio of the high frequency to the fundamental frequency of the target pumping flow curve in the frequency domain. The fourth feature is used to measure the distribution shape of the target pumping flow curve.

3. The method according to claim 2, characterized in that The step of extracting the target feature set of the target pumping flow rate curve comprises: Obtaining n pumping flow sampling points from the target pumping flow curve, where n is a positive integer; Calculate the standard deviation and average flow rate of the n pumping flow rate sampling points; Substituting the standard deviation, the average flow rate and the n pumping flow rate sampling points into a first formula to calculate the first feature; Substituting the average flow rate and the n pumping flow rate sampling points into the second formula to calculate the fourth characteristic; Performing Fourier transformation on the target pumping flow rate to obtain fundamental frequency energy, low frequency energy and high frequency energy; Calculating the ratio of the low-frequency energy to the fundamental frequency energy to obtain the second feature; The ratio of the high frequency energy to the fundamental frequency energy is calculated to obtain the third feature.

4. The method according to claim 1, characterized in that: The method further comprises: Acquire a training data set, wherein the training data set includes a plurality of first pumping flow curves, wherein the first pumping flow curve is a pumping flow curve when the ventricular assist device is pumping or operating normally; labeling each of the first pumping flow rate curves with a classification label; A first ratio and a second ratio are calculated according to the classification label, wherein the first ratio is the proportion of the first pumping flow curve whose classification label is suction in the training data set, and the second ratio is the proportion of the first pumping flow curve whose classification label is normal in the training data set.

5. The method according to claim 4, characterized in that The method further includes: training the target classification tree model, specifically including: extracting the target feature set of the plurality of first pumping flow rate curves; Inputting each of the target feature sets into a classification tree model to be trained to obtain the classification result of each of the first pumping flow rate curves; The segmentation points of each layer in the classification tree model to be trained are determined according to the classification result, the first ratio and the second ratio to obtain the target classification tree model.

6. The method according to claim 1, characterized in that When the classification result is suction, calculating the suction degree of the ventricular assist device includes: Obtaining a target average flow rate, wherein the target average flow rate is an average pumping flow rate in a second cycle of the ventricular assist device operation, wherein the second cycle is earlier than the first cycle; Obtaining a minimum pumping flow rate and a maximum pumping flow rate of the target pumping flow rate curve; Calculating a discrimination threshold according to the target average flow rate, the minimum pumping flow rate and the maximum pumping flow rate; The pumping degree of the ventricular assist device is determined according to the discrimination threshold.

7. The method according to claim 6, characterized in that Determining the pumping degree of the ventricular assist device according to the discrimination threshold comprises: If the discrimination threshold is greater than a first value, determining that the ventricular assist device is severely pumping; If the discrimination threshold is greater than or equal to a second value and less than or equal to the first value, it is determined that the ventricular assist device is moderately pumping; If the discrimination threshold is greater than a third value and less than the second value, it is determined that the ventricular assist device is slightly pumping.

8. A control unit for a ventricular assist device, characterized in that: The control unit comprises one or more processors, wherein the one or more processors are configured to: Acquire a target pumping flow curve, where the target pumping flow curve is a pumping flow curve of the first cycle of the ventricular assist device; extracting a target feature set of the target pumping flow rate curve; Inputting the target feature set into a target classification tree model to obtain a classification result; When the classification result is pumping, the pumping degree of the ventricular assist device is calculated.

9. A ventricular assist device, characterized in that: The ventricular assist device comprises: case; an impeller disposed in the housing; A motor driving the impeller to rotate in suspension; A control unit connected to the motor, the control unit being used to execute instructions of the steps in the method according to any one of claims 1-7.

10. A medical device, characterized in that: The method comprises a processor, a memory and a communication interface, wherein the memory stores one or more programs, and the one or more programs are executed by the processor, and the one or more programs include instructions for executing the steps in the method according to any one of claims 1 to 7.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the method according to any one of claims 1 to 7.

Images