Disclosure of Invention
The embodiment of the application aims to provide a residual heart contractility estimation method and a residual heart contractility estimation system based on left ventricular assist equipment, so as to accurately detect the residual heart contractility of the heart supported by the left ventricular assist equipment. The specific technical scheme is as follows:
in a first aspect, an embodiment of the present application provides a method for estimating a residual contractility of a left ventricle auxiliary device, the method including:
determining left ventricular pressure time sequence data of a preset number of continuous cardiac cycles, and generating a left ventricular pressure curve;
Determining a first curve and a second curve in the left ventricular pressure curve based on curve characteristics of the left ventricular pressure curve, wherein the first curve is used for representing a left ventricular contraction phase and the second curve is used for representing a left ventricular diastole phase;
Based on time sequence relations in the first curve and the second curve, respectively carrying out pressure characteristic analysis on the first curve and the second curve to obtain a first pressure characteristic and a second pressure characteristic;
based on the first pressure characteristic, the second pressure characteristic, a remaining systole force is estimated.
In one embodiment of the present application, estimating the remaining systole force based on the first pressure characteristic and the second pressure characteristic includes:
Fitting the first pressure characteristic and the second pressure characteristic by adopting a preset fitting coefficient to obtain fitting characteristics, wherein the preset fitting coefficient is used for reflecting the degree of association between the first pressure characteristic and the second pressure characteristic;
based on the fitted features, the remaining systole force is estimated.
In one embodiment of the present application, estimating the remaining systole force based on the fitting features includes:
And inputting the fitting characteristics into a pre-trained heart contraction force estimation model to obtain heart contraction force output by the heart contraction force estimation model, wherein the heart contraction force estimation model adopts sample fitting characteristics as a training sample, takes actual heart contraction force as a training reference, trains an initial neural network model and is used for estimating heart contraction force.
In one embodiment of the present application, the determining the left ventricular pressure timing data of the preset number of consecutive cardiac cycles includes:
the left ventricular pressure timing data for each preset number of consecutive cardiac cycles is determined as follows:
Acquiring target blood pressure at an outlet of the left ventricular assist device in a current cardiac cycle, and acquiring the blood flow pumped by the left ventricular assist device at each target moment as target flow;
Calculating a delay time corresponding to each target time based on the target time and a preset delay time length, wherein the preset delay time length is used for representing the delay degree of the left ventricular assist device in response to the heart activity change;
Acquiring the current rotating speed of the left ventricular assist device in the current cardiac cycle, and calculating a target pressure difference at each target moment based on the blood flow corresponding to the delay moment of the target moment and the current rotating speed, wherein the target pressure difference represents the pressure difference between the pressure at the outlet and the pressure at the inlet of the left ventricular assist device;
Based on the target blood pressure and the target pressure difference at each target time, the blood pressure at the inlet of each target time is calculated as left ventricular pressure time series data.
In a second aspect, an embodiment of the present application provides a residual systole force estimation system based on a left ventricular assist device, the system including a left ventricular catheter pump including an inlet and an outlet, the inlet being located in a left ventricle after the left ventricular catheter pump is implanted in a heart of a patient, the outlet being located in an aorta, and a controller integrating a residual systole force estimation device, the residual systole force estimation device including:
the curve generation module is used for determining left ventricular pressure time sequence data of a preset number of continuous cardiac cycles and generating a left ventricular pressure curve;
The curve determining module is used for determining a first curve and a second curve in the left ventricular pressure curve based on curve characteristics of the left ventricular pressure curve, wherein the first curve is used for representing a left ventricular contraction phase, and the second curve is used for representing a left ventricular diastole phase;
The characteristic analysis module is used for respectively carrying out pressure characteristic analysis on the first curve and the second curve based on the time sequence relation in the first curve and the second curve to obtain a first pressure characteristic and a second pressure characteristic;
and the contraction force estimation module is used for estimating residual heart contraction force based on the first pressure characteristic and the second pressure characteristic.
In one embodiment of the present application, the shrinkage force estimation module includes:
the characteristic fitting sub-module is used for fitting the first pressure characteristic and the second pressure characteristic by adopting a preset fitting coefficient to obtain a fitting characteristic, and the preset fitting coefficient is used for reflecting the degree of association between the first pressure characteristic and the second pressure characteristic;
and a contraction force estimation sub-module for estimating a residual heart contraction force based on the fitting features.
In one embodiment of the present application, the above-mentioned contractility estimation submodule is specifically configured to input the fitting feature into a pre-trained heart contractility estimation model to obtain the heart contractility output by the heart contractility estimation model, where the heart contractility estimation model uses a sample fitting feature as a training sample, and uses an actual heart contractility as a training reference, to train an initial neural network model, and is a model for estimating the heart contractility.
In one embodiment of the present application, the curve generating module is specifically configured to determine left ventricular pressure time-series data of each preset number of consecutive cardiac cycles according to the following manner: acquiring target blood pressure at an outlet of the left ventricular assist device in a current cardiac cycle, and acquiring the blood flow pumped by the left ventricular assist device at each target moment as target flow; calculating a delay time corresponding to each target time based on the target time and a preset delay time length, wherein the preset delay time length is used for representing the delay degree of the left ventricular assist device in response to the heart activity change; acquiring the current rotating speed of the left ventricular assist device in the current cardiac cycle, and calculating a target pressure difference at each target moment based on the blood flow corresponding to the delay moment of the target moment and the current rotating speed, wherein the target pressure difference represents the pressure difference between the pressure at the outlet and the pressure at the inlet of the left ventricular assist device; based on the target blood pressure and the target pressure difference at each target time, the blood pressure at the inlet of each target time is calculated as left ventricular pressure time series data.
In a third aspect, an embodiment of the present application provides a control host of a left ventricular assist device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;
a memory for storing a computer program;
And a processor, configured to implement the method steps described in the first aspect when executing the program stored in the memory.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium having stored therein a computer program which, when executed by a processor, implements the method steps of the first aspect described above.
From the above, it can be seen that, by applying the scheme provided by the embodiment of the application, since the systole force is determined based on the first pressure characteristic and the second pressure characteristic, the first pressure characteristic reflects the pressure characteristic of the systole stage, and the second pressure characteristic reflects the pressure characteristic of the diastole stage. The systolic force determined on the basis of the first pressure characteristic, the second pressure characteristic is then related to both the pressure characteristic of the systolic phase and the pressure characteristic of the diastolic phase. The contractile function of the heart is an intrinsic property of the heart, and affects each phase of the cardiac cycle as it progresses through the cardiac cycle. Therefore, the estimated systole ability can accurately reflect the contractile function characteristics of the heart, thereby improving the accuracy of the estimation of the systole ability.
Of course, it is not necessary for any one product or method of practicing the application to achieve all of the advantages set forth above at the same time.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by the person skilled in the art based on the present application are included in the scope of protection of the present application.
First, before describing an embodiment of the present application, a specific description is given of a left ventricular assist device provided in the present application with reference to fig. 1.
As shown in fig. 1, the left ventricular assist device mainly includes a motor 101, an impeller 102, an inlet 104, and an outlet 103.
The motor drives the impeller to rotate at a high speed to generate suction force, so that blood in the left ventricle is sucked into the outlet from the inlet until the aorta, thereby realizing auxiliary pumping and unloading of heart load.
When the left ventricular assist device assists the heart, the pumping function of the left ventricle gradually recovers over time, and when the pumping function of the left ventricle gradually recovers, the operation parameters of the left ventricular assist device, such as reducing the rotating speed, need to be adjusted to reduce the heart load; when the left ventricular pump function is restored, withdrawal of the left ventricular assist device is considered.
The following describes the scheme provided by the application in detail.
Referring to fig. 2, fig. 2 is a flowchart of a first left ventricular assist device-based residual systole estimation method according to the present application, and the method includes the following steps S201-S204.
Step S201: and determining left ventricular pressure time sequence data of a preset number of continuous cardiac cycles, and generating a left ventricular pressure curve.
The preset number is a preset number, such as 5, 10, etc.
The left ventricular pressure timing data includes a corresponding left ventricular pressure at each time instant. The left ventricular pressure curve is used to reflect the changes in left ventricular pressure over a preset number of consecutive cardiac cycles.
The inlet of the left ventricular assist device may be integrated with a pressure sensor, and since the inlet of the left ventricular assist device is located in the left ventricle, the pressure acquired by the pressure sensor may be regarded as the left ventricular pressure, based on which the pressure data acquired by the pressure sensor at each time may be acquired as the left ventricular pressure time series data.
Other ways of determining left ventricular pressure timing data may be found in the subsequent embodiments, which are not described in detail herein.
The left ventricular pressure curve is characterized in a curve form and the left ventricular pressure data is arranged in time sequence at each moment.
Step S202: the first curve and the second curve in the left ventricular pressure curve are determined based on curve characteristics of the left ventricular pressure curve.
The first curve is used to characterize the left ventricular contraction phase and the second curve is used to characterize the left ventricular diastole phase.
The above curve features are used to characterize the curve characteristics of the left ventricular pressure curve. The curve features may be left ventricular pressure maximum, minimum, average, curve rate of change, curve morphology, etc.
The curve characteristic of the left ventricular systolic phase and the curve characteristic of the diastolic phase are different in one cardiac cycle, and therefore, based on the curve characteristic of the left ventricular pressure curve, the first curve characterizing the left ventricular systolic phase and the second curve characterizing the left ventricular diastolic phase can be accurately determined.
When the first curve and the second curve are determined, a critical point representing a contraction phase and a relaxation phase of the left ventricle in the left ventricle pressure curve can be determined based on curve characteristics of the left ventricle pressure curve, and the critical point is used as a curve demarcation point to divide the left ventricle pressure curve, so that the first curve and the second curve are obtained.
In this embodiment, the characteristic comparison may be performed between the left ventricular pressure curve and a first preset curve representing the left ventricular contraction phase, and between the left ventricular pressure curve and a second preset curve representing the left ventricular diastole phase, and the critical point may be determined based on the characteristic comparison result.
Step S203: and respectively carrying out pressure characteristic analysis on the first curve and the second curve based on the time sequence relation in the first curve and the second curve to obtain a first pressure characteristic and a second pressure characteristic.
The time sequence relation in the first curve and the second curve is used for reflecting the time sequence information among data points contained in the first curve and the second curve, and the pressure characteristic analysis is carried out on the curve based on the time sequence relation, so that the obtained pressure characteristic reflects the time sequence information of the curve.
When the pressure characteristic analysis is carried out, a pressure characteristic extraction algorithm can be adopted to extract the pressure characteristics of the first curve and the second curve, so as to obtain the pressure characteristics. And the pressure characteristic analysis can be carried out on the first curve and the second curve respectively by adopting a pre-trained characteristic extraction model to obtain a first pressure characteristic and a second pressure characteristic. The characteristic extraction model may be obtained by training a preset neural network model by taking a sample curve and time sequence information of the sample curve as training samples and taking actual pressure characteristics of the sample curve as training references, and is used for determining pressure characteristics reflecting a curve time sequence relation.
Step S204: based on the first pressure characteristic, the second pressure characteristic, a remaining systole force is estimated.
Since the remaining systole is determined based on the first pressure characteristic and the second pressure characteristic, the first pressure characteristic reflects the pressure characteristic of the systole stage, and the second pressure characteristic reflects the pressure characteristic of the diastole stage, then the remaining systole determined based on the first pressure characteristic and the second pressure characteristic is related to both the pressure characteristic of the systole stage and the pressure characteristic of the remaining diastole stage, and the systole function of the heart accompanies the whole process of the cardiac cycle, the estimated remaining systole function accurately reflects the systole function characteristic of the heart, thereby improving the estimation accuracy of the remaining systole function.
In estimating the remaining systole force, in one embodiment, a correspondence relationship between the pressure characteristic of the systole stage and the pressure characteristic of the diastole stage and the systole force may be previously constructed, and based on this, the systole force corresponding to the first pressure characteristic and the second pressure characteristic may be determined as the remaining systole force according to the correspondence relationship.
Other ways of estimating the residual systole force can be found in the corresponding embodiment of fig. 3 which follows and will not be described in detail here.
From the above, it can be seen that, by applying the solution provided by the present embodiment, since the systole force is determined based on the first pressure characteristic and the second pressure characteristic, the first pressure characteristic reflects the pressure characteristic of the systole phase, and the second pressure characteristic reflects the pressure characteristic of the diastole phase. The systolic force determined on the basis of the first pressure characteristic, the second pressure characteristic is then related to both the pressure characteristic of the systolic phase and the pressure characteristic of the diastolic phase. The contractile function of the heart is an intrinsic property of the heart, and affects each phase of the cardiac cycle as it progresses through the cardiac cycle. Therefore, the estimated systole ability can accurately reflect the contractile function characteristics of the heart, thereby improving the accuracy of the estimation of the systole ability.
The estimation of the residual systole force referred to in the aforementioned step S204 in fig. 2 may be carried out according to the following steps S304-S305, in addition to the estimation in the mentioned manner. Based on this, referring to fig. 3, fig. 3 is a flowchart of a second method for estimating a heart contractility based on a left ventricular assist device according to an embodiment of the present application, where the method includes the following steps S301 to S305.
Step S301: and determining left ventricular pressure time sequence data of a preset number of continuous cardiac cycles, and generating a left ventricular pressure curve.
Step S302: the first curve and the second curve in the left ventricular pressure curve are determined based on curve characteristics of the left ventricular pressure curve.
The first curve is used to characterize the left ventricular contraction phase and the second curve is used to characterize the left ventricular diastole phase.
Step S303: and respectively carrying out pressure characteristic analysis on the first curve and the second curve based on the time sequence relation in the first curve and the second curve to obtain a first pressure characteristic and a second pressure characteristic.
The steps S301 to S303 are the same as the steps S201 to S203, and are not described herein.
Step S304: and fitting the first pressure characteristic and the second pressure characteristic by adopting a preset fitting coefficient to obtain fitting characteristics.
The preset fitting coefficient is used for reflecting the degree of correlation between the first pressure characteristic and the second pressure characteristic. Since the first pressure characteristic reflects the pressure characteristic of the systolic phase and the second pressure characteristic reflects the pressure characteristic of the diastolic phase, the preset fitting coefficient can reflect the correlation between the pressure characteristic of the systolic phase and the pressure characteristic of the diastolic phase.
The fitting characteristic is obtained by fitting the first pressure characteristic and the second pressure characteristic by adopting a preset fitting coefficient, and can accurately reflect the correlation characteristic between the pressure characteristic of the systole stage and the pressure characteristic of the diastole stage.
When fitting is performed, a preset fitting feature calculation formula can be adopted, the fitting feature calculation formula reflects a functional relation among fitting features, pressure features and fitting coefficients, the first pressure features and the second pressure features are used as parameter values of corresponding parameter items in the functional relation, and the calculated features are determined to be the fitting features.
Step S305: based on the fitted features, the remaining systole force is estimated.
In one embodiment, a correspondence between the fitting feature and the heart contractility may be constructed in advance, and the remaining heart contractility corresponding to the fitting feature may be determined based on the correspondence.
In another embodiment, the fitting features may be input into a pre-trained heart contractility estimation model to obtain the remaining heart contractility output by the heart contractility estimation model.
The heart contractility estimation model is a model which is obtained by training an initial neural network model by taking the sample fitting characteristics as training samples and taking the actual residual heart contractility as a training reference and is used for estimating the residual heart contractility. The residual heart contractility is estimated by using the heart contractility estimation model, and the heart contractility model is obtained by training a large number of training samples, so that the characteristics between the fitting characteristics and the residual heart contractility are learned, and the residual heart contractility can be accurately estimated based on the heart contractility estimation model.
As can be seen from the above, in the present embodiment, since the residual systole force is estimated based on the fitting feature, the fitting feature reflects the correlation between the first pressure feature and the second pressure feature, and the self-contraction feature of the heart extends through the systole and diastole phases, and the systole and diastole phases affect the systole function of the heart, the residual systole force estimated by using the fitting feature can more accurately reflect the systole function feature of the heart, thereby improving the estimation accuracy of the systole force.
In the foregoing embodiment corresponding to fig. 2, in addition to determining the left ventricular pressure timing data in the manner mentioned above, the following steps A1-A4 may be employed to determine the left ventricular pressure timing data for each cardiac cycle.
Step A1: and acquiring target blood pressure at the outlet of the left ventricular assist device in the current cardiac cycle, and acquiring the blood flow pumped by the left ventricular assist device at each target moment as target flow.
The outlet of the left ventricular assist device may be configured with a pressure sensor that may periodically collect the pressure in the region in which the outlet is located, based on which the blood pressure collected by the pressure sensor at each target instant in the current cardiac cycle may be obtained.
The target flow may be monitored using a flow meter, based on which the flow of blood pumped by the left ventricular assist device may be obtained at each target instant monitored by the flow meter.
Step A2: and calculating the delay time corresponding to each target time based on the target time and the preset delay time.
The predetermined delay period is used to characterize the degree of delay of the left ventricular assist device in response to changes in heart activity. The above-mentioned degree of delay may be understood as a delay in the operation of the left ventricular assist device in relation to a change in the environment of the heart, e.g. a delay in the response of the blood flow pumped by the left ventricular assist device in relation to a change in the heart pressure.
In calculating the delay time, in one embodiment, a time at which the target time extends backward by a preset delay time period may be calculated as the delay time corresponding to the target time. For example: when the preset delay time is 0.8s, the currently targeted target time is t=2s, and the time when t=2s extends backwards for 0.8s is calculated as the delay time, namely t=2.8s.
Step A3: the method comprises the steps of obtaining the current rotating speed of left ventricular assist equipment in the current cardiac cycle, and calculating target pressure difference at each target moment based on the blood flow corresponding to the delay moment of the target moment and the current rotating speed.
The target pressure differential characterizes a pressure difference between a pressure at an outlet and a pressure at an inlet of the left ventricular assist device.
When calculating the target pressure difference, in one embodiment, a corresponding relationship between the pump blood flow corresponding to the current rotation speed and the pressure difference can be determined; and determining a target pressure difference corresponding to the blood flow corresponding to the delay time based on the acquired corresponding relation.
The left ventricular assist device is divided into a plurality of rotational speeds, and the healthcare worker can select an appropriate rotational speed at which the left ventricular assist device operates. In this case, the rotational speed of the currently selected left ventricular assist device may be obtained.
At different rotational speeds, the operation states of the left ventricular assist device are different, and the correspondence between the pump blood flow of the left ventricular assist device and the change in the pressure difference of the heart is different. Based on this, the correspondence between the pump blood flow rate and the differential pressure at each rotation speed may be constructed in advance.
In calculating the target differential pressure, in another embodiment, a rotation speed variation characteristic representing a current rotation speed variation condition may be determined, and a first coefficient is calculated based on the rotation speed variation characteristic and the current rotation speed; determining a second coefficient based on the current rotational speed; determining the first coefficient and the second coefficient as target flow coefficients; for each target moment, calculating the target pressure difference at the target moment according to the reference flow corresponding to the target flow coefficient and the target moment.
Specifically, the current rotation speed can be processed, for example, the change rate of the current rotation speed is calculated and used as the rotation speed change characteristic for representing the change condition of the current rotation speed, and when the first coefficient is calculated, the rotation speed change characteristic can be substituted into the formula according to a preset first coefficient calculation formula to obtain the first coefficient; similarly, when calculating the second coefficient, the current rotation speed may be substituted into the formula according to a preset second coefficient calculation formula to obtain the second coefficient.
Specifically, the first coefficient calculation formula may be:
；
wherein,A first coefficient is represented by a first coefficient,、、The predetermined constant is indicated to be a predetermined constant,Indicating the current rotational speed.
The second coefficient calculation formula may be:
；
wherein,A second coefficient is represented by a second coefficient,、The predetermined constant is indicated to be a predetermined constant,Indicating the current rotational speed.
It can be seen that the first coefficient is calculated from the rotation speed change characteristic angle, the second coefficient is calculated from the current rotation speed angle, and the first coefficient and the second coefficient can comprehensively reflect the information of the current rotation speed.
Step A4: based on the target blood pressure and the target pressure difference at each target time, the inlet blood pressure at each target time is calculated and used as left ventricular pressure time series data.
Since the target pressure difference represents the pressure difference between the outlet blood pressure and the inlet blood pressure, and the target blood pressure is the current blood pressure at the outlet of the left ventricular assist device, the blood pressure at the inlet can be calculated by the target pressure difference and the target blood pressure, and the inlet is positioned in the left ventricle after the left ventricular assist device is implanted in the heart of the patient, so that the calculated inlet blood pressure can represent the left ventricular pressure. Based on this, in calculating the left ventricular pressure, a difference between the target blood pressure at each target time and the target pressure difference at the corresponding time may be calculated, and the calculated difference may be determined as the left ventricular pressure.
From the above, since the target differential pressure at the target time is calculated based on the blood flow corresponding to the delay time and the current rotational speed, and since the delay time is determined based on the delay degree of the left ventricular catheter pump in response to the heart activity change, the delay degree of the left ventricular catheter pump in response to the heart activity change is considered by the blood flow corresponding to the delay time, so that the blood flow can more accurately reflect the pump blood flow which should be achieved by the left ventricular catheter pump at the current target time, the differential pressure condition of the heart at the target time can be accurately determined based on the blood flow, and the left ventricular pressure can be accurately estimated based on the target differential pressure and the target blood pressure.
In the foregoing step A2, the preset delay period is preset and is constructed in advance in the test environment, and the specific construction manner may be referred to in the following steps B1 to B4.
Step B1: and acquiring a pressure difference time sequence signal and a flow time sequence signal of the pump blood flow under the test environment.
The pressure differential timing signal characterizes a timing signal of a pressure difference between an outlet pressure and an inlet pressure of the left ventricular assist device.
The test environment may be an environment in which simulation is performed using test data, and under the test environment, the differential pressure timing signal may be a differential pressure timing signal generated based on a differential pressure at each time by detecting the outlet pressure and the inlet pressure respectively by a dedicated pressure sensor and calculating a differential pressure therebetween.
The flow timing signal may be a flow timing signal generated by a dedicated flow meter that calculates the pump blood flow of the left ventricular assist device based on the pump blood flow at each instant.
Step B2: and delaying the time sequence corresponding to each pump blood flow data in the flow time sequence signal based on the delay time length parameter item to obtain a time sequence delay signal of the pump blood flow as a flow delay signal.
In the step, the delay time length parameter item is used as a variable, an objective function is introduced, and the parameter value of the delay time length parameter item is obtained through calculation by solving the objective function.
The above-described determination of the flow delay signal is described as an example. Assume that the delay duration parameter term isThe flow time sequence signal isThen the flow delay signal is expressed as。
Step B3: based on the pressure difference time sequence signal and the flow delay signal, a preset correlation analysis function is adopted to construct an objective function representing the relation between the signal correlation degree and the hysteresis time length parameter item.
The signal correlation represents the correlation between the differential pressure time sequence signal and the flow delay signal.
When the objective function is constructed, the pressure difference time sequence signal and the flow delay signal can be substituted into a preset correlation analysis function to serve as the objective function.
The objective function may be the following expression:
；
wherein,Representing an objective function between the signal correlation and the lag time duration parameter term,Represents a hysteresis time length parameter item, N represents the total number of data points contained in the signal, t represents the serial number of the data points contained in the signal,Representing a pressure differential timing signal,Representing the flow delay signal.
Step B4: and calculating an optimal solution of the objective function, and determining a parameter value of a delay time length parameter item in the optimal solution as a preset delay time length.
When calculating the optimal solution of the objective function, a peak value of the objective function may be calculated, the peak value corresponding to the maximum correlation between the differential pressure timing signal and the flow delay signal, the peak value being taken as the optimal solution of the objective function. And the parameter value of the lag time length parameter item in the optimal solution is the preset delay time length.
As can be seen from the above, in the present embodiment, in the test environment, the objective function is constructed based on the differential pressure timing signal and the flow delay signal, and the optimal solution of the objective function is calculated to obtain the preset delay time, so that the preset delay time is determined based on the correlation between the differential pressure timing signal and the flow delay signal, and the correlation between the differential pressure timing signal and the flow delay signal reflects the response delay degree of the left ventricular assist device, and based on this, the determined preset delay time can accurately reflect the response delay degree of the left ventricular assist device.
Corresponding to the residual heart contraction force estimation method based on the left ventricular assist device, the embodiment of the application also provides a residual heart contraction force estimation system based on the left ventricular assist device. The system includes a left ventricular catheter pump and a controller. The left ventricular catheter pump comprises an inlet and an outlet, wherein the inlet is positioned in the left ventricle, and the outlet is positioned in the aorta after the left ventricular catheter pump is implanted in the heart of a patient. Referring to fig. 4, fig. 4 is a schematic structural diagram of a residual systole estimation device based on a left ventricular assist device according to an embodiment of the present application, where the device is 401-404 described below.
The curve generating module 401 is configured to determine left ventricular pressure time-series data of a preset number of continuous cardiac cycles, and generate a left ventricular pressure curve;
A curve determination module 402, configured to determine a first curve and a second curve in the left ventricular pressure curve based on curve characteristics of the left ventricular pressure curve, where the first curve is used to characterize a left ventricular contraction phase and the second curve is used to characterize a left ventricular diastole phase;
the feature analysis module 403 is configured to perform pressure feature analysis on the first curve and the second curve based on the time sequence relationships in the first curve and the second curve, so as to obtain a first pressure feature and a second pressure feature;
a contraction force estimation module 404 for estimating a remaining heart contraction force based on the first pressure characteristic and the second pressure characteristic.
From the above, it can be seen that, by applying the solution provided by the present embodiment, since the systole force is determined based on the first pressure characteristic and the second pressure characteristic, the first pressure characteristic reflects the pressure characteristic of the systole phase, and the second pressure characteristic reflects the pressure characteristic of the diastole phase. The systolic force determined on the basis of the first pressure characteristic, the second pressure characteristic is then related to both the pressure characteristic of the systolic phase and the pressure characteristic of the diastolic phase. The contractile function of the heart is an intrinsic property of the heart, and affects each phase of the cardiac cycle as it progresses through the cardiac cycle. Therefore, the estimated systole ability can accurately reflect the contractile function characteristics of the heart, thereby improving the accuracy of the estimation of the systole ability.
In one embodiment of the present application, the contraction force estimation module 404 includes:
the characteristic fitting sub-module is used for fitting the first pressure characteristic and the second pressure characteristic by adopting a preset fitting coefficient to obtain a fitting characteristic, and the preset fitting coefficient is used for reflecting the degree of association between the first pressure characteristic and the second pressure characteristic;
and a contraction force estimation sub-module for estimating a residual heart contraction force based on the fitting features.
As can be seen from the above, in the present embodiment, since the residual systole force is estimated based on the fitting feature, the fitting feature reflects the correlation between the first pressure feature and the second pressure feature, and the self-contraction feature of the heart extends through the systole and diastole phases, and the systole and diastole phases affect the systole function of the heart, the residual systole force estimated by using the fitting feature can more accurately reflect the systole function feature of the heart, thereby improving the estimation accuracy of the systole force.
In one embodiment of the present application, the above-mentioned contractility estimation submodule is specifically configured to input the fitting feature into a pre-trained heart contractility estimation model to obtain the heart contractility output by the heart contractility estimation model, where the heart contractility estimation model uses a sample fitting feature as a training sample, and uses an actual heart contractility as a training reference, to train an initial neural network model, and is a model for estimating the heart contractility.
The heart contractility estimation model is a model which is obtained by training an initial neural network model by taking the sample fitting characteristics as training samples and taking the actual residual heart contractility as a training reference and is used for estimating the residual heart contractility. The residual heart contractility is estimated by using the heart contractility estimation model, and the heart contractility model is obtained by training a large number of training samples, so that the characteristics between the fitting characteristics and the residual heart contractility are learned, and the residual heart contractility can be accurately estimated based on the heart contractility estimation model.
In one embodiment of the present application, the curve generating module 401 is specifically configured to determine left ventricular pressure time-series data of each preset number of consecutive cardiac cycles in the following manner: acquiring target blood pressure at an outlet of the left ventricular assist device in a current cardiac cycle, and acquiring the blood flow pumped by the left ventricular assist device at each target moment as target flow; calculating a delay time corresponding to each target time based on the target time and a preset delay time length, wherein the preset delay time length is used for representing the delay degree of the left ventricular assist device in response to the heart activity change; acquiring the current rotating speed of the left ventricular assist device in the current cardiac cycle, and calculating a target pressure difference at each target moment based on the blood flow corresponding to the delay moment of the target moment and the current rotating speed, wherein the target pressure difference represents the pressure difference between the pressure at the outlet and the pressure at the inlet of the left ventricular assist device; based on the target blood pressure and the target pressure difference at each target time, the blood pressure at the inlet of each target time is calculated as left ventricular pressure time series data.
From the above, since the target differential pressure at the target time is calculated based on the blood flow corresponding to the delay time and the current rotational speed, and since the delay time is determined based on the delay degree of the left ventricular catheter pump in response to the heart activity change, the delay degree of the left ventricular catheter pump in response to the heart activity change is considered by the blood flow corresponding to the delay time, so that the blood flow can more accurately reflect the pump blood flow which should be achieved by the left ventricular catheter pump at the current target time, the differential pressure condition of the heart at the target time can be accurately determined based on the blood flow, and the left ventricular pressure can be accurately estimated based on the target differential pressure and the target blood pressure.
Corresponding to the residual heart contractility estimation method based on the left ventricular assist device, the embodiment of the application also provides a control host of the left ventricular assist device, which comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus; a memory for storing a computer program; and the processor is used for realizing the functions of the functional modules of the system when executing the programs stored in the memory.
The communication bus mentioned by the controller may be a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, etc. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.
The communication interface is used for communication between the controller and other devices.
The Memory may include random access Memory (Random Access Memory, RAM) or may include Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but may also be a digital signal Processor (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components.
In yet another embodiment of the present application, a computer readable storage medium is provided, where a computer program is stored, the computer program, when executed by a processor, implements the method for estimating residual systole force based on the left ventricular assist device provided by the embodiment of the present application.
In yet another embodiment of the present application, a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method for estimating residual systole based on the left ventricular assist device provided by the embodiment of the present application is also provided.
From the above, it can be seen that, with the solution provided by the present embodiment, since the systole force is determined based on the first pressure characteristic and the second pressure characteristic, the first pressure characteristic reflects the pressure characteristic of the systole stage, and the second pressure characteristic reflects the pressure characteristic of the diastole stage. The systolic force determined on the basis of the first pressure characteristic, the second pressure characteristic is then related to both the pressure characteristic of the systolic phase and the pressure characteristic of the diastolic phase. The contractile function of the heart is an intrinsic property of the heart, and affects each phase of the cardiac cycle as it progresses through the cardiac cycle. Therefore, the estimated systole ability can accurately reflect the contractile function characteristics of the heart, thereby improving the accuracy of the estimation of the systole ability.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may 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 loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk Solid STATE DISK (SSD)), etc.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system, control host, computer readable storage medium embodiments, since they are substantially similar to method embodiments, the description is relatively simple, with reference to portions of the method embodiments being relevant.
The foregoing description is only of the preferred embodiments of the present application and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application are included in the protection scope of the present application.