A method and device for estimating left ventricular pressure

Abstract

An embodiment of the present invention provides a method and device for estimating left ventricular pressure, which relates to the technical field of medical devices. The above method includes: obtaining target parameter data during the operation of a left ventricular catheter pump in a patient's body, where the target parameter data includes: the physiological data of the patient and / or the operation data of the left ventricular catheter pump; extracting the data features of the target parameter data; based on a preset data interval of a target parameter item corresponding to the target parameter data, mapping the data features of the target parameter data to obtain a mapping feature, where the preset data interval is an interval formed by continuous parameter data representing the same degree among the parameter data included in the target parameter item; estimating the left ventricular pressure of the patient based on the mapping feature. When the scheme provided by this embodiment is used to estimate the left ventricular pressure, the left ventricular pressure of the patient can be accurately estimated.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and particularly to a method and device for estimating left ventricular pressure. Background Art

[0002] A left ventricular catheter pump is a miniaturized axial flow pump in the blood vessel used to support the patient's blood circulation system. The left ventricular catheter pump is implanted into the left ventricle of the patient. When the left ventricular catheter pump is in a normal operating state, the left ventricular catheter pump can transport blood from the inlet area located in the left ventricle to the ascending aorta outlet through a catheter. The left ventricular catheter pump can assist in increasing cardiac output, raising aortic pressure and coronary perfusion pressure, and improving mean arterial pressure and coronary blood flow.

[0003] During the process of assisting the patient with the left ventricular catheter pump, since the left ventricular pressure can indicate the patient's current ventricular function, the operation of the ventricular catheter pump can be adjusted based on the left ventricular pressure. Therefore, there is an urgent need for a scheme for estimating left ventricular pressure to accurately detect the left ventricular pressure of the patient. Summary of the Invention

[0004] The purpose of the embodiments of the present invention is to provide a method and device for estimating left ventricular pressure to accurately detect the left ventricular pressure of the patient. The specific technical solutions are as follows:

[0005] In a first aspect, the embodiments of the present invention provide a method for estimating left ventricular pressure, the method comprising:

[0006] During the operation of the left ventricular catheter pump in the patient's body, obtaining target parameter data, where the target parameter data includes: the physiological data of the patient and / or the operation data of the left ventricular catheter pump;

[0007] Extracting the data features of the target parameter data;

[0008] Based on the preset data interval of the target parameter item corresponding to the target parameter data, mapping the data features of the target parameter data to obtain a mapping feature, where the preset data interval is: an interval formed by continuous parameter data representing the same degree in the parameter data included in the target parameter item;

[0009] Estimating the left ventricular pressure of the patient based on the mapping feature.

[0010] In an embodiment of the present invention, the above-mentioned mapping the data features of the target parameter data based on the preset data interval of the target parameter item corresponding to the target parameter data to obtain a mapping feature includes:

[0011] According to the preset mapping relationship corresponding to each preset data interval of the target parameter item corresponding to the target parameter data, determine the target membership degree corresponding to the data characteristics of the target parameter data, and determine the target membership degree as the mapping feature, where the preset mapping relationship corresponding to the preset data interval is: the mapping relationship between the preset data characteristics of the target parameter item and the membership degree of the preset data characteristics belonging to the preset data interval.

[0012] In one embodiment of the present invention, the above-mentioned estimating the left ventricular pressure of the patient based on the mapping feature includes:

[0013] According to the preset set correspondence relationship, determine the target left ventricular pressure corresponding to the target membership degree set, where the set correspondence relationship is: the correspondence relationship between the membership degree set formed by the preset membership degree combinations corresponding to each preset data interval of the target parameter item and the left ventricular pressure, and the target membership degree set is: the membership degree set formed by the target membership degree combinations corresponding to each preset data interval of each target parameter item;

[0014] Based on the target left ventricular pressure, determine the left ventricular pressure of the patient.

[0015] In one embodiment of the present invention, in the case where there are multiple target left ventricular pressures, the above-mentioned determining the left ventricular pressure of the patient based on the target left ventricular pressure includes:

[0016] For each target left ventricular pressure, calculate the confidence degree of the target left ventricular pressure based on the target membership degree set corresponding to the target left ventricular pressure;

[0017] Based on the calculated confidence degree, determine the left ventricular pressure of the patient from the target left ventricular pressures.

[0018] In one embodiment of the present invention, estimate the left ventricular pressure of the patient in the following manner:

[0019] Input the target parameter data into a pre-trained system identification model, and obtain the left ventricular pressure output by the system identification model as the left ventricular pressure of the patient, where the system identification model is: a model for estimating the left ventricular pressure of an object obtained by training an initial neural network model using a fuzzy logic algorithm with the parameter data of a sample object as the training sample and the left ventricular pressure of the sample object as the training benchmark.

[0020] In a second aspect, an embodiment of the present invention provides an apparatus for estimating left ventricular pressure, and the apparatus includes:

[0021] A data acquisition module, configured to acquire target parameter data during the operation of a left ventricular catheter pump in a patient, where the target parameter data includes: physiological data of the patient and / or operation data of the left ventricular catheter pump;

[0022] A feature extraction module, configured to extract data features of the target parameter data;

[0023] A feature mapping module, configured to map the data features of the target parameter data based on a preset data interval corresponding to a target parameter item of the target parameter data to obtain mapped features, where the preset data interval is: an interval formed by continuous parameter data representing the same degree among the parameter data included in the target parameter item;

[0024] A pressure estimation module, configured to estimate the left ventricular pressure of the patient based on the mapped features.

[0025] In an embodiment of the present invention, the above feature mapping module is specifically configured to determine a target membership degree corresponding to the data features of the target parameter data according to a preset mapping relationship corresponding to each preset data interval of the target parameter item corresponding to the target parameter data, and determine the target membership degree as the mapped feature, where the preset mapping relationship corresponding to the preset data interval is: a mapping relationship between the preset data features of the target parameter item and the membership degree of the preset data features belonging to the preset data interval.

[0026] In an embodiment of the present invention, the above pressure estimation module includes:

[0027] A first pressure determination sub-module, configured to determine a target left ventricular pressure corresponding to a target membership degree set according to a preset set correspondence relationship, where the set correspondence relationship is: a correspondence relationship between a membership degree set formed by a preset membership degree combination corresponding to each preset data interval of a target parameter item and the left ventricular pressure, and the target membership degree set is: a membership degree set formed by a target membership degree combination corresponding to each preset data interval of each target parameter item;

[0028] A second pressure determination sub-module, configured to determine the left ventricular pressure of the patient based on the target left ventricular pressure.

[0029] In an embodiment of the present invention, in the case of multiple target left ventricular pressures, the second pressure determination sub-module is specifically configured to, for each target left ventricular pressure, calculate the confidence degree of the target left ventricular pressure based on the target membership degree set corresponding to the target left ventricular pressure; and determine the left ventricular pressure of the patient from the target left ventricular pressures based on the calculated confidence degree.

[0030] In one embodiment of the present invention, the above-mentioned pressure prediction module is specifically configured to input the target parameter data into a pre-trained system identification model, and obtain the left ventricular pressure output by the system identification model as the left ventricular pressure of the patient. The system identification model is a model obtained by training an initial neural network model with the parameter data of a sample object as the training sample and the left ventricular pressure of the sample object as the training benchmark, and using a fuzzy logic algorithm to estimate the left ventricular pressure of the object.

[0031] In a third aspect, an embodiment of the present invention provides an electronic device, which includes a processor, a communication interface, a memory, and a communication bus. The processor, the communication interface, and the memory communicate with each other through the communication bus.

[0032] The memory is used to store a computer program.

[0033] The processor is configured to implement the method steps described in the first aspect above when executing the program stored in the memory.

[0034] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, in which a computer program is stored, and the computer program implements the method steps described in the first aspect above when executed by a processor.

[0035] As can be seen from the above, when applying the solution provided by the embodiment of the present invention, since the above mapping feature is obtained by mapping the data features of the target parameter data based on the preset data interval of the target parameter item, and since the preset data interval is an interval formed by continuous parameter data representing the same degree, that is to say, the data degree represented by each preset data interval is different. Then, the mapping feature can reflect the data degree represented by the target parameter data, that is to say, the mapping feature reflects the data meaning represented by the target parameter data from a deeper level. Therefore, based on the above mapping feature, the left ventricular pressure of the patient can be predicted more accurately.

[0036] Of course, when implementing any product or method of the present invention, it is not necessarily required to achieve all the above-mentioned advantages at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application, and those of ordinary skill in the art can also obtain other embodiments based on these drawings.

[0038] Figure 1 It is a schematic flow chart of a method for estimating left ventricular pressure provided by an embodiment of the present invention.

[0039] Figure 2 Shows the schematic diagram of the fuzzy function of each preset data interval of the aortic pressure parameter item;

[0040] Figure 3 Schematic diagram of the structure of an estimation device for left ventricular pressure provided by an embodiment of the present invention;

[0041] Figure 4 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0042] Next, in combination with the accompanying drawings in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art based on this application belong to the scope of protection of the present invention.

[0043] First, before specifically describing the solution provided by the embodiment of the present invention, the application scenario and the execution subject of the embodiment of the present invention are introduced.

[0044] The application scenario of the embodiment of the present invention is: the application scenario where a left ventricular catheter pump operates in a patient's body.

[0045] The execution subject of the embodiment of the present invention is: the control device of the left ventricular catheter pump. The above control device is used to monitor and control the left ventricular catheter pump.

[0046] The following specifically describes the method for estimating left ventricular pressure provided by the embodiment of the present invention.

[0047] See Figure 1 , Figure 1 Schematic diagram of the flow of a method for estimating left ventricular pressure provided by an embodiment of the present invention. The above method includes the following steps S101 - S104.

[0048] Step S101: Obtain target parameter data during the operation of the left ventricular catheter pump in the patient's body.

[0049] Among them, the above target parameter data includes: the operation data of the left ventricular catheter pump and / or the physiological data of the patient.

[0050] In one implementation manner, the physiological data of the patient is the aortic pressure of the patient; the operation data of the left ventricular catheter pump is the motor current and motor speed of the left ventricular catheter pump.

[0051] The above aortic pressure can be collected by the fiber optic sensor set in the ventricular catheter pump, and the above motor current and motor speed can be collected by the signal collector set in the control device.

[0052] After the above target parameter data is collected by the parameter collection device, the target parameter data can be stored in the control device or in the cloud server. When estimating the left ventricular pressure, the above target parameter data can be read from the information stored locally or in the cloud server.

[0053] Step S102: Extract the data features of the target parameter data.

[0054] The above data features are used to reflect the deep information of the target parameter data. When extracting the above data features, in one implementation, a feature extraction algorithm can be used to extract features from the target parameter data to obtain data features. The above feature extraction algorithm can be principal component analysis, linear discriminant analysis, etc.

[0055] Step S103: Map the data features of the target parameter data based on the preset data interval of the target parameter item corresponding to the target parameter data to obtain the mapped features.

[0056] Since the parameter value of the target parameter item is the target parameter data, each target parameter data has a corresponding target parameter item. For example: when the target parameter data is the aortic pressure, the target parameter item corresponding to the aortic pressure is the aortic pressure parameter item; when the target parameter data is the motor current, the target parameter item corresponding to the motor current is the motor current parameter item; when the target parameter data is the motor speed, the target parameter item corresponding to the motor speed is the motor speed parameter item.

[0057] The above preset data interval is: an interval formed by continuous parameter data representing the same degree among the parameter data included in the target parameter item. Taking the aortic pressure parameter item as an example, the parameter data included in the aortic pressure parameter item are all the parameter data between 60 - 200 mmHg. Among these parameter data, there are parameter data with different values that represent the same degree. For example, the parameter data in the range of 60 - 90 mmHg represent a smaller aortic pressure, the parameter data in the range of 90 - 140 mmHg represent a normal aortic pressure, and the parameter data in the range of 140 - 200 mmHg represent a larger aortic pressure. Based on this, [60 mmHg, 90 mmHg], [90 mmHg, 140 mmHg], and [140 mmHg, 2000 mmHg] are respectively the preset data intervals of the aortic pressure parameter item.

[0058] Since the above mapping features are obtained by mapping the data features of the target parameter data based on the preset data intervals of the target parameter items, and since the preset data intervals are intervals formed by continuous parameter data representing the same degree, that is to say, the data degrees represented by each preset data interval are different. Then, the mapping features can reflect the data degree represented by the target parameter data.

[0059] When mapping the data features of the target parameter data, in one implementation, the target data interval containing the target parameter data can be determined from the preset data intervals of the target parameter items, the first distance between the data features of the target parameter data and the data features of the minimum value of the target data interval can be calculated, and the second distance between the data features of the parameter data and the data features of the maximum value of the target data interval can be calculated. The feature distance with the minimum distance is selected from the first distance and the second distance as the mapping feature.

[0060] Other ways of mapping data features can be seen in the subsequent embodiments and will not be elaborated here.

[0061] Step S104: Estimate the left ventricular pressure of the patient based on the mapping features.

[0062] Since the mapping features can reflect the data degree represented by the target parameter data and can reflect the data meaning represented by the target parameter data at a deeper level, therefore, based on the above mapping features, the left ventricular pressure of the patient can be accurately estimated.

[0063] When estimating the left ventricular pressure, in one implementation, a deep learning algorithm can be combined, and the mapping features are input into a pre-trained pressure estimation model to obtain the pressure value output by the pressure estimation model as the left ventricular pressure of the patient. The above pressure estimation model is: a model obtained by training an initial neural network model using the mapping features corresponding to the parameter data of the sample object as training samples and the left ventricular pressure of the sample object as the training benchmark, and is used to estimate the left ventricular pressure of the sample object.

[0064] The above sample object is: a sample left ventricular catheter pump or a sample test patient, and the sample left ventricular catheter pump operates in the body of the sample test patient.

[0065] The parameter data of the above sample object includes the physiological data of the sample test patient and / or the operation data of the sample left ventricular catheter pump;

[0066] The mapping features corresponding to the parameter data of the above sample object are: features obtained by mapping the data features of the above parameter data based on the data intervals of the parameter items corresponding to the parameter data of the sample object, and the data intervals are: intervals formed by continuous parameter data representing the same degree among the parameter data included in the above parameter items.

[0067] As can be seen from the above, when applying the solution provided in this embodiment, since the above mapping features are obtained by mapping the data features of the target parameter data based on the preset data interval of the target parameter item, and since the preset data interval is an interval formed by continuous parameter data representing the same degree, that is to say, the data degrees represented by each preset data interval are different. Then, the mapping features can reflect the data degree represented by the target parameter data, that is to say, the mapping features reflect the data meaning represented by the target parameter data from a deeper level. Therefore, based on the above mapping features, the left ventricular pressure of the patient can be predicted more accurately.

[0068] In the above Figure 1 In step S103 of the corresponding embodiment, in addition to using the mentioned mapping method to map the data features, the mapping method of the following step A can also be used to map the data features.

[0069] Step A: According to the preset mapping relationship corresponding to each preset data interval of the target parameter item corresponding to the target parameter data, determine the target membership degree corresponding to the data features of the target parameter data, and determine the target membership degree as the mapping feature.

[0070] The preset mapping relationship corresponding to the above preset data interval is: the mapping relationship between the preset data features of the target parameter item and the membership degree of the preset data features belonging to the preset data interval. The above membership degree reflects the degree to which the preset data feature belongs to the preset data interval. The larger the membership degree, the higher the degree to which the preset data feature belongs to the preset data interval, and the smaller the membership degree, the lower the degree to which the preset data feature belongs to the preset data interval.

[0071] The above preset mapping relationship can be represented by a fuzzy function. The form of the fuzzy function can be Gaussian distribution, trapezoidal distribution, ridge distribution, parabolic distribution, and triangular distribution, etc. Specifically, the corresponding fuzzy function can be selected based on the type of the target parameter item.

[0072] The above target membership degree reflects the membership degree of the target parameter data belonging to the preset data interval.

[0073] The number of the above target membership degrees can be multiple. In one case, each target parameter data of each target parameter item corresponds to one target membership degree. In another case, each target parameter data of each target parameter item corresponds to multiple target membership degrees. The following will specifically describe the latter case.

[0074] The preset mapping relationships corresponding to different preset data intervals may record the membership degrees corresponding to the same preset data feature. Then, based on the above preset mapping relationships, the determined target membership degrees can be multiple. Taking Figure 2 as an example, Figure 2The fuzzy functions of each preset data interval of the aortic pressure parameter item are shown, where the abscissa is the preset data feature, the ordinate represents the membership degree, function S is the fuzzy function of preset data interval Ds1, function M is the fuzzy function of preset data interval Ds2, function H is the fuzzy function of preset data interval Ds3, and there are overlapping situations among function S, function M, and function H. Then, there may be multiple corresponding membership degrees for the same preset data feature. Taking data feature X1 as an example, the corresponding membership degrees are: B1, B2.

[0075] When determining the target membership degree, the membership degree corresponding to the data feature of the target parameter data can be determined from the preset mapping relationship as the target membership degree. Since the preset mapping relationship is the mapping relationship between the preset data features of the target parameter item and the membership degree of the preset data features belonging to the preset data interval, based on the above mapping relationship, the target membership degree corresponding to the data feature can be accurately determined, so as to obtain an accurate mapping feature.

[0076] On the basis of the above step A, the Figure 1 corresponding step S104 of the embodiment can also estimate the left ventricular pressure of the patient according to the estimation method of the following step B1-step B2.

[0077] Step B1: Determine the candidate values of the left ventricular pressure corresponding to the target membership degree set according to the preset set correspondence.

[0078] The above set correspondence is: the correspondence between the membership degree set formed by the preset membership degree combinations corresponding to each preset data interval of the target parameter item and the left ventricular pressure. Combining the following Table 1, taking the target parameter item as aortic pressure and the motor current parameter item as an example, the above set correspondence is described.

[0079] Table 1

[0080]

[0081]

[0082] In the above Table 1, P1_1, …… P3_4 represent the membership degrees corresponding to each preset data interval of the aortic pressure parameter item, I1_1, …… I3_4 represent the membership degrees corresponding to each preset data interval of the motor current parameter item, the blank cells represent the left ventricular pressure, and the specific left ventricular pressure values are not reflected in Table 1. Table 1 records the correspondence between the membership degree set formed by the preset membership degree combinations and the left ventricular pressure. In Table 1, each blank cell corresponds to the preset membership degree combination of each preset data interval.

[0083] The above target membership degree set is: the membership degree set formed by the target membership degree combinations corresponding to each target parameter item.

[0084] When determining the candidate value of the left ventricular pressure, in one implementation, the left ventricular pressure value corresponding to the target membership set can be determined from the preset set correspondence as the candidate value of the left ventricular pressure.

[0085] Step B2: Determine the patient's left ventricular pressure based on the target left ventricular pressure.

[0086] Since the set correspondence is the correspondence between the membership degree set and the left ventricular pressure, based on the above set correspondence, the target left ventricular pressure corresponding to the target membership degree set can be accurately determined, and then the patient's left ventricular pressure can be accurately determined.

[0087] Based on the analysis in the foregoing step A, it can be known that the target parameter data of each target parameter item can correspond to one target membership degree or multiple target membership degrees. When the target parameter data of each target parameter item corresponds to one target membership degree, the number of target membership degree sets is 1. In this case, one left ventricular pressure is determined based on one target membership degree set, that is, the number of target left ventricular pressures is 1. Therefore, the target left ventricular pressure can be directly determined as the patient's left ventricular pressure.

[0088] When the target parameter data of each target parameter item corresponds to multiple target membership degrees, the number of target membership degree sets is multiple. In this case, the number of target left ventricular pressures is also multiple. Therefore, it is necessary to determine the patient's left ventricular pressure from multiple target left ventricular pressures. Based on this, in one embodiment of the present invention, for each target left ventricular pressure, the confidence level of the target left ventricular pressure can be calculated based on the target membership degree set corresponding to the target left ventricular pressure; based on the calculated confidence level, the patient's left ventricular pressure can be determined from the target left ventricular pressures.

[0089] The above confidence level represents the credibility that the target left ventricular pressure is the actual left ventricular pressure of the patient. The greater the confidence level, the higher the credibility that the target left ventricular pressure is the actual left ventricular pressure of the patient; the smaller the confidence level, the lower the credibility that the target left ventricular pressure is the actual left ventricular pressure of the patient.

[0090] When calculating the above confidence level, the average value of each target membership degree in the target membership degree set corresponding to the target left ventricular pressure can be calculated, and the average value is used as the above confidence level.

[0091] When determining the patient's left ventricular pressure, in one implementation, the target left ventricular pressure corresponding to the maximum confidence level can be determined as the patient's left ventricular pressure.

[0092] Since the above confidence level represents the credibility of the target left ventricular pressure being the actual left ventricular pressure of the patient, in the case of multiple target left ventricular pressures, based on the confidence level of the target left ventricular pressure, the left ventricular pressure of the patient can be accurately determined from the target left ventricular pressure.

[0093] In an embodiment of the present invention when estimating the left ventricular pressure of a patient, the fuzzy logic algorithm and the deep learning algorithm can also be combined, and the target parameter data is input into a pre-trained system identification model to obtain the left ventricular pressure output by the system identification model as the left ventricular pressure of the patient.

[0094] Among them, the above system identification model is: a model for estimating the left ventricular pressure of an object, which is obtained by using the parameter data of a sample object as training samples and the left ventricular pressure of the sample object as the training benchmark, and training an initial neural network model using the fuzzy logic algorithm.

[0095] The system identification model combines the fuzzy logic algorithm and the deep learning algorithm. After obtaining the target parameter data, it first extracts the data features of the target parameter data, secondly calculates the membership degrees of the data features belonging to each preset fuzzy set, then performs fuzzy inference based on the membership degrees, and finally defuzzifies the inference result to output the left ventricular pressure of the patient.

[0096] Since the system identification model is trained using a large number of training samples, the system identification model can learn the law of estimating the left ventricular pressure based on the parameter data, and the left ventricular pressure of the patient can be accurately estimated using the system identification model.

[0097] Corresponding to the above method for estimating the left ventricular pressure, an embodiment of the present invention also provides an apparatus for estimating the left ventricular pressure.

[0098] See Figure 3 , Figure 3 which is a schematic structural diagram of an apparatus for estimating the left ventricular pressure provided by an embodiment of the present invention. The above apparatus includes the following modules 301 - 304.

[0099] The data acquisition module 301 is used to acquire target parameter data during the operation of the left ventricular catheter pump in the patient's body, where the target parameter data includes: the physiological data of the patient and / or the operation data of the left ventricular catheter pump;

[0100] The feature extraction module 302 is used to extract the data features of the target parameter data;

[0101] A feature mapping module 303, configured to map data features of the target parameter data based on a preset data interval of a target parameter item corresponding to the target parameter data, so as to obtain a mapped feature, where the preset data interval is an interval formed by continuous parameter data representing the same degree in the parameter data included in the target parameter item;

[0102] A pressure prediction module 304, configured to predict the left ventricular pressure of the patient based on the mapped feature.

[0103] As can be seen from the above, when applying the solution provided in this embodiment, since the above-mentioned mapped feature is obtained by mapping the data features of the target parameter data based on the preset data interval of the target parameter item, and since the preset data interval is an interval formed by continuous parameter data representing the same degree, that is to say, the data degrees represented by each preset data interval are different. Then, the mapped feature can reflect the data degree represented by the target parameter data, that is to say, the mapped feature reflects the data meaning represented by the target parameter data from a deeper level. Therefore, based on the above-mentioned mapped feature, the left ventricular pressure of the patient can be predicted more accurately.

[0104] In an embodiment of the present invention, the above-mentioned feature mapping module 303 is specifically configured to determine a target membership degree corresponding to the data feature of the target parameter data according to a preset mapping relationship corresponding to each preset data interval of the target parameter item corresponding to the target parameter data, and determine the target membership degree as the mapped feature, where the preset mapping relationship corresponding to the preset data interval is: a mapping relationship between the preset data feature of the target parameter item and the membership degree of the preset data feature belonging to the preset data interval.

[0105] Since the preset mapping relationship is a mapping relationship between the preset data feature of the target parameter item and the membership degree of the preset data feature belonging to the preset data interval, based on the above mapping relationship, the target membership degree corresponding to the data feature can be accurately determined, so as to obtain an accurate mapped feature.

[0106] In an embodiment of the present invention, the above-mentioned pressure prediction module 304 includes:

[0107] A first pressure determination sub-module, configured to determine a target left ventricular pressure corresponding to a target membership degree set according to a preset set correspondence relationship, where the set correspondence relationship is: a correspondence relationship between a membership degree set formed by a preset membership degree combination corresponding to each preset data interval of the target parameter item and the left ventricular pressure, and the target membership degree set is: a membership degree set formed by a target membership degree combination corresponding to each preset data interval of each target parameter item;

[0108] A second pressure determination sub-module, configured to determine the left ventricular pressure of the patient based on the target left ventricular pressure.

[0109] Since the set correspondence is the correspondence between the membership degree set and the left ventricular pressure, based on the above set correspondence, the target left ventricular pressure corresponding to the target membership degree set can be accurately determined, and then the left ventricular pressure of the patient can be accurately determined.

[0110] In one embodiment of the present invention, in the case of multiple target left ventricular pressures, the second pressure determination sub-module is specifically configured to, for each target left ventricular pressure, calculate the confidence degree of the target left ventricular pressure based on the target membership degree set corresponding to the target left ventricular pressure; and determine the left ventricular pressure of the patient from the target left ventricular pressures based on the calculated confidence degree.

[0111] Since the above confidence degree represents the credibility that the target left ventricular pressure is the actual left ventricular pressure of the patient, in the case of multiple target left ventricular pressures, based on the confidence degree of the target left ventricular pressure, the left ventricular pressure of the patient can be accurately determined from the target left ventricular pressures.

[0112] In one embodiment of the present invention, the above pressure prediction module 304 is specifically configured to input the target parameter data into a pre-trained system identification model, and obtain the left ventricular pressure output by the system identification model as the left ventricular pressure of the patient, where the system identification model is: a model for estimating the left ventricular pressure of an object, which is obtained by training an initial neural network model with the parameter data of a sample object as the training sample and the left ventricular pressure of the sample object as the training benchmark, using a fuzzy logic algorithm.

[0113] Since the system identification model is trained with a large number of training samples, the system identification model can learn the law of predicting the left ventricular pressure based on the parameter data, and the left ventricular pressure of the patient can be accurately predicted by using the system identification model.

[0114] Corresponding to the above method for estimating the left ventricular pressure, an embodiment of the present invention further provides an electronic device.

[0115] See Figure 4 , Figure 4 which is a schematic structural diagram of an electronic device provided by an embodiment of the present invention, including a processor 401, a communication interface 402, a memory 403, and a communication bus 404, where the processor 401, the communication interface 402, and the memory 403 communicate with each other through the communication bus 404.

[0116] The memory 403 is used to store a computer program.

[0117] The processor 401 is configured to implement the method for estimating the left ventricular pressure provided by the embodiment of the present invention when executing the program stored in the memory 403.

[0118] The communication bus mentioned in the above electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of easy representation, only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0119] The communication interface is used for communication between the above electronic device and other devices.

[0120] The memory may include a Random Access Memory (RAM), and may also include a Non-Volatile Memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located far from the aforementioned processor.

[0121] The above-mentioned processor may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be 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.

[0122] In another embodiment provided by the present invention, a computer-readable storage medium is also provided. A computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the method for estimating the left ventricular pressure provided by the embodiments of the present invention is implemented.

[0123] In another embodiment provided by the present invention, a computer program product containing instructions is also provided. When it runs on a computer, it causes the computer to implement the method for estimating the left ventricular pressure provided by the embodiments of the present invention when executed.

[0124] As can be seen from the above, when applying the solution provided in this embodiment, since the above mapping feature is obtained by mapping the data feature of the target parameter data based on the preset data interval of the target parameter item, and since the preset data interval is an interval formed by continuous parameter data representing the same degree, that is to say, the data degree represented by each preset data interval is different. Then, the mapping feature can reflect the data degree represented by the target parameter data, that is to say, the mapping feature reflects the data meaning represented by the target parameter data from a deeper level. Therefore, based on the above mapping feature, the left ventricular pressure of the patient can be estimated more accurately.

[0125] In the above embodiment, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that a computer can access, or a data storage device such as a server or data center that includes one or more integrated available media. The available medium may be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)).

[0126] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "including a..." does not exclude the presence of additional identical elements in the process, method, article or device including the element.

[0127] Each embodiment in this specification is described in a related manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the device, electronic device, and computer-readable storage medium, since they are basically similar to the method embodiments, the description is relatively simple, and reference can be made to the corresponding parts of the method embodiments for the relevant content.

[0128] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are all included in the protection scope of the present invention.

Claims

1. A method for estimating left ventricular pressure, characterized in that, The method includes: During the operation of the left ventricular catheter pump in a patient's body, obtaining target parameter data, where the target parameter data includes: the physiological data of the patient and / or the operation data of the left ventricular catheter pump; Extracting the data features of the target parameter data; Based on the preset data interval of the target parameter item corresponding to the target parameter data, mapping the data features of the target parameter data to obtain a mapping feature, where the preset data interval is: an interval formed by continuous parameter data representing the same degree among the parameter data included in the target parameter item; Based on the mapping feature, estimating the left ventricular pressure of the patient; The mapping of the data features of the target parameter data based on the preset data interval of the target parameter item corresponding to the target parameter data to obtain a mapping feature includes: According to the preset mapping relationship corresponding to each preset data interval of the target parameter item corresponding to the target parameter data, determining the target membership degree corresponding to the data features of the target parameter data, and determining the target membership degree as the mapping feature, where the preset mapping relationship corresponding to the preset data interval is: the mapping relationship between the preset data features of the target parameter item and the membership degree of the preset data features belonging to the preset data interval; 2. The method according to claim 1, wherein The estimating the left ventricular pressure of the patient based on the mapping feature includes: According to the preset set correspondence relationship, determining the target left ventricular pressure corresponding to the target membership degree set, where the set correspondence relationship is: the correspondence relationship between the membership degree set formed by the preset membership degree combinations corresponding to each preset data interval of the target parameter item and the left ventricular pressure, and the target membership degree set is: the membership degree set formed by the target membership degree combinations corresponding to each preset data interval of each target parameter item; Based on the target left ventricular pressure, determining the left ventricular pressure of the patient; 3. The method according to claim 2, wherein In the case of multiple target left ventricular pressures, the determining the left ventricular pressure of the patient based on the target left ventricular pressure includes: For each target left ventricular pressure, calculating the confidence degree of the target left ventricular pressure based on the target membership degree set corresponding to the target left ventricular pressure; Based on the calculated confidence degree, determining the left ventricular pressure of the patient from the target left ventricular pressures; 4. The method according to any one of claims 1 to 3, characterized in that, Estimating the left ventricular pressure of the patient in the following manner: Inputting the target parameter data into a pre-trained system identification model, and obtaining the left ventricular pressure output by the system identification model as the left ventricular pressure of the patient, where the system identification model is: a model obtained by training an initial neural network model with the parameter data of a sample object as the training sample and the left ventricular pressure of the sample object as the training benchmark, and using a fuzzy logic algorithm to estimate the left ventricular pressure of the object; 5. An apparatus for estimating left ventricular pressure, characterized in that The device includes: A data acquisition module, configured to obtain target parameter data during the operation of the left ventricular catheter pump in a patient's body, where the target parameter data includes: the physiological data of the patient and / or the operation data of the left ventricular catheter pump; A feature extraction module, configured to extract the data features of the target parameter data; A feature mapping module, configured to map the data features of the target parameter data based on a preset data interval of a target parameter item corresponding to the target parameter data, so as to obtain a mapped feature, where the preset data interval is an interval formed by consecutive parameter data representing the same degree in the parameter data included in the target parameter item; A pressure prediction module, configured to predict the left ventricular pressure of the patient based on the mapped feature; The feature mapping module is specifically configured to determine a target membership degree corresponding to the data features of the target parameter data according to a preset mapping relationship corresponding to each preset data interval of the target parameter item corresponding to the target parameter data, and determine the target membership degree as the mapped feature, where the preset mapping relationship corresponding to the preset data interval is a mapping relationship between the preset data features of the target parameter item and the membership degree of the preset data features belonging to the preset data interval.

6. The device according to claim 5, characterized in that, The pressure prediction module includes: A first pressure determination sub-module, configured to determine a target left ventricular pressure corresponding to a target membership degree set according to a preset set correspondence, where the set correspondence is a correspondence between a membership degree set formed by a preset membership degree combination corresponding to each preset data interval of a target parameter item and the left ventricular pressure, and the target membership degree set is a membership degree set formed by a target membership degree combination corresponding to each preset data interval of each target parameter item; A second pressure determination sub-module, configured to determine the left ventricular pressure of the patient based on the target left ventricular pressure.

7. The device according to claim 6, wherein In the case where there are multiple target left ventricular pressures, the second pressure determination sub-module is specifically configured to, for each target left ventricular pressure, calculate the confidence degree of the target left ventricular pressure based on the target membership degree set corresponding to the target left ventricular pressure; and determine the left ventricular pressure of the patient from the target left ventricular pressures based on the calculated confidence degree.

8. The device according to any one of claims 5 to 7, characterized in that The pressure prediction module is specifically configured to input the target parameter data into a pre-trained system identification model, and obtain the left ventricular pressure output by the system identification model as the left ventricular pressure of the patient, where the system identification model is a model obtained by training an initial neural network model with the parameter data of a sample object as a training sample and the left ventricular pressure of the sample object as a training benchmark, and using a fuzzy logic algorithm, and is used to estimate the left ventricular pressure of an object.

Images