System and method for determining myocardial contractility based on signals from mechanical circulatory support devices

Abstract

A method and apparatus are provided for estimating a measure of myocardial contractility based on a set of features determined from a set of signals associated with a mechanical circulatory assist device. The method includes using a computer processor to determine a set of features based at least in part on a set of signals, providing the set of features as input to a machine learning model trained to output a measure of myocardial contractility, and performing an action based at least in part on the measure of myocardial contractility output by the machine learning model.

Description

Technical Field

[0001] The present disclosure relates to a technique for determining cardiac contractility based on signals from a mechanical circulatory assist device.

Background Art

[0002] Cardiovascular diseases are a major cause of morbidity, mortality, and burden in global healthcare. A variety of treatment modalities, ranging from pharmaceuticals to mechanical devices and transplantation, have been developed for heart health. Mechanical heart assist devices, such as heart pump systems, provide hemodynamic assistance and promote heart recovery. Some heart pump systems can be percutaneously inserted into the heart and operate in parallel with the native heart to complement cardiac output. Examples of such devices include the Impella® family of devices (Abiomed, Inc., Danvers, MA). Such heart pump systems can have sensors that detect blood pressure (or assess differential pressure across a membrane), monitor motor current, and, in particular, can be useful in identifying pump positioning using sensor data and motor current readings.

[0003] Such a pump can be positioned, for example, within a ventricle of the heart, such as the left ventricle, and can assist the heart. In this case, the pump can be inserted via the femoral artery using a hollow catheter, advanced to the left ventricle of the patient's heart, and introduced therein. From this position, the pump inlet can draw in blood and the pump outlet can pump blood into the aorta. Thus, the function of the heart can be replaced or at least assisted by the operation of the pump.

[0004] The cardiac pump is typically connected to a separate cardiac pump controller that controls the pump, such as motor speed, and collects and displays operational data about the blood pump, including cardiac signal levels, battery temperature, blood flow rate, and piping integrity. An exemplary cardiac pump controller is available from ABIOMED, ​​Inc. under the trademark name Automated Impella Controller®. In some cases, the controller may sound an alarm when operational data values ​​fall outside a predetermined value or range, for example, when leakage, aspiration, and / or pump malfunction are detected. The controller may include a video display screen that shows a graphical user interface configured to display operational data and / or alarms. [Overview of the project] [Means for solving the problem]

[0005] Mechanical cardiac assist devices, such as cardiac pump systems, provide hemodynamic assistance and facilitate the recovery of innate cardiac function (e.g., the innate contractility of the heart). Therefore, having a measurement of a patient's current myocardial contractility can be useful in facilitating clinical decisions regarding the patient's treatment while using such a device. For example, once a patient's innate myocardial contractility is restored, the patient may be weaned off the cardiac pump system. The inventors recognize and understand that the cardiac pump of a cardiac pump system is positioned within a patient's heart in a way that provides a unique set of signals that can be used to more accurately estimate myocardial contractility for a patient compared to existing techniques for estimating myocardial contractility without considering such signals. For this purpose, some embodiments of the present disclosure relate to improved techniques for estimating myocardial contractility using a machine learning model trained to output a measurement of myocardial contractility based on a set of features determined at least partially based on signals associated with a cardiac pump system.

[0006] In one aspect, a computer implementation method is provided. The computer implementation method includes receiving a set of signals from a mechanical circulatory assist device, determining a set of features based at least in part on the set of signals using a computer processor, providing the set of features as input to a machine learning model trained to output cardiac contractility measurements, and performing an action based at least in part on the cardiac contractility measurements output by the machine learning model.

[0007] In another aspect, the set of signals includes at least one pressure signal and / or at least one pump function signal. In another aspect, determining a set of features includes determining at least one feature using a combination of a first pressure signal of at least one pressure signal and a first pump function signal of at least one pump function signal. In another aspect, the at least one feature using a combination of a first pressure signal of at least one pressure signal and a first pump function signal of at least one pump function signal comprises the maximum rate of rise in left ventricular pressure during systole. In another aspect, determining a set of features includes determining one or more per-beat features based at least in part on the set of signals. In another aspect, determining one or more per-beat features includes determining one or more of the mean pump flow rate, mean aortic pressure, left ventricular pressure at end-diastole, maximum rate of rise in left ventricular pressure during systole, or mean motor current. In some embodiments, the per-pulse features may further include the maximum rate of increase of a transient signal during contraction, and the transient signal may include, but is not limited to, an aortic pressure signal, a motor current signal, or a combination or deviation of one or more of the aforementioned signals. In another aspect, the measure of myocardial contractility is an estimate of the preload mobilizable stroke work index. In another aspect, the machine learning model comprises a feedforward dense neural network.

[0008] In another aspect, taking action based at least partially on the myocardial contractility measurements output by the machine learning model includes displaying an indication of the myocardial contractility measurements on a user interface associated with the mechanical circulatory support device. In another aspect, the indication of the myocardial contractility measurements is a trend of myocardial contractility over a specific time range. In another aspect, taking action based at least partially on the myocardial contractility measurements output by the machine learning model includes determining a stability score for a patient with an implanted mechanical circulatory support device, the stability score being at least partially based on the myocardial contractility measurements, and displaying the stability score on a user interface associated with the mechanical circulatory support device. In another aspect, taking action based at least partially on the myocardial contractility measurements output by the machine learning model includes providing treatment recommendations for a patient with an implanted mechanical circulatory support device, the treatment recommendations being determined at least partially based on the myocardial contractility measurements. In another aspect, taking action based at least partially on the myocardial contractility measurements output by the machine learning model includes adjusting the operating conditions of the mechanical circulatory support device. In another respect, adjusting the operating conditions of a mechanical circulation assist device includes adjusting the pump speed of the mechanical circulation assist device.

[0009] In another aspect, performing an action based at least in part on a measure of myocardial contractility output by a machine learning model includes determining the contractile reserve based at least in part on a measure of myocardial contractility. In another aspect, the measure of myocardial contractility includes a first myocardial contractility output by a machine learning model based on a signal from a mechanical circulatory support device at a first time, and a second myocardial contractility output by a machine learning model based on a signal from a mechanical circulatory support device at a second time after the first time, and determining the contractile reserve includes determining the contractile reserve based on the first and second myocardial contractility. In another aspect, determining the contractile reserve based on the first and second myocardial contractility includes determining the contractile reserve based on the difference between the first and second myocardial contractility.

[0010] In one aspect, a controller for a mechanical circulatory assistance device is provided. The controller includes at least one hardware processor, which is configured to determine a set of features at least in part on a set of signals received from the mechanical circulatory assistance device, to provide the set of features as input to a machine learning model trained to output cardiac contractility measurements, and to perform an action at least in part on the cardiac contractility measurements output by the machine learning model.

[0011] In another aspect, the set of signals includes at least one pressure signal and / or at least one pump function signal. In another aspect, determining the set of features includes determining at least one feature using a combination of a first pressure signal of at least one pressure signal and a first pump function signal of at least one pump function signal. In another aspect, the at least one feature using a combination of a first pressure signal of at least one pressure signal and a first pump function signal of at least one pump function signal comprises the maximum rate of rise in left ventricular pressure during systole. In another aspect, at least one hardware processor is further configured to determine the set of features by determining one or more per-beat features based at least partially on the set of signals. In another aspect, determining one or more per-beat features includes determining one or more of the mean pump flow rate, mean aortic pressure, left ventricular pressure at end-diastole, maximum rate of rise in left ventricular pressure during systole, or mean motor current. In another aspect, the measure of myocardial contractility is an estimate of the preload-mobilizable stroke work index. On another level, machine learning models feature feedforward dense neural networks.

[0012] In another aspect, at least one hardware processor is configured to take action based at least partially on myocardial contractility measurements output by a machine learning model by displaying an indication of myocardial contractility measurements on a user interface associated with a mechanical circulatory support device. In another aspect, the indication of myocardial contractility measurements is a trend of myocardial contractility over a specific time range. In another aspect, at least one hardware processor is configured to take action based at least partially on myocardial contractility measurements output by a machine learning model by determining a stability score for a patient with an implanted mechanical circulatory support device, the stability score being at least partially based on myocardial contractility measurements, and by displaying the stability score on a user interface associated with the mechanical circulatory support device. In another aspect, at least one hardware processor is configured to take action based at least partially on myocardial contractility measurements output by a machine learning model by providing treatment recommendations for a patient with an implanted mechanical circulatory support device, the treatment recommendations being determined at least partially based on myocardial contractility measurements. In another aspect, taking action based at least partially on the cardiac contractility measurements output by the machine learning model includes adjusting the operating conditions of the mechanical circulatory support device based on the cardiac contractility measurements. In another aspect, adjusting the operating conditions of the mechanical circulatory support device includes adjusting the pump speed of the mechanical circulatory support device.

[0013] In another aspect, at least one hardware processor is configured to perform an action based at least partly on a measure of myocardial contractility output by a machine learning model by determining the contractile reserve based at least partly on the measure of myocardial contractility. In another aspect, the measure of myocardial contractility includes a first myocardial contractility output by the machine learning model based on a signal from a mechanical circulatory support device at a first time, and a second myocardial contractility output by the machine learning model based on a signal from a mechanical circulatory support device at a second time after the first time, and determining the contractile reserve includes determining the contractile reserve based on the first and second myocardial contractility. In one aspect, determining the contractile reserve based on the first and second myocardial contractility includes determining the contractile reserve based on the difference between the first and second myocardial contractility.

[0014] In one aspect, a cardiac pump system is provided. The cardiac pump system includes a cardiac pump including at least one pressure sensor configured to sense pressure within a portion of a patient's heart, and a controller. The controller is configured to determine a set of features, at least in part, based on a set of signals received from the cardiac pump, wherein the set of features is a first feature based on sensed pressure, and to provide the set of features as input to a machine learning model trained to output a measure of myocardial contractility, and to perform an action, at least in part, based on the measure of myocardial contractility output by the machine learning model.

[0015] In another aspect, the set of features further includes a second feature based on a signal corresponding to the operating state of the cardiac pump. In another aspect, the first feature further includes a signal corresponding to the operating state of the cardiac pump. In another aspect, the first feature comprises the maximum percentage increase in left ventricular pressure during systole. In another aspect, the controller is further configured to determine the set of features by determining one or more per-beat features based at least partially on the set of signals. In another aspect, determining one or more per-beat features includes determining one or more of the following: mean pump flow rate, mean aortic pressure, left ventricular pressure at end-diastole, maximum percentage increase in left ventricular pressure during systole, or mean motor current. In another aspect, the measure of myocardial contractility is an estimate of the preload-mobilizable stroke work index. In another aspect, the machine learning model comprises a feedforward dense neural network.

[0016] In another aspect, the cardiac pump system further includes a display configured to show a user interface containing representations of one or more signals associated with the operation of the cardiac pump system, and the controller is configured to perform actions at least in part based on cardiac contractility measurements output by a machine learning model by displaying an indication of cardiac contractility measurements on the user interface. In another aspect, the indication of cardiac contractility measurements is a trend of cardiac contractility over a specific time range.

[0017] In another aspect, the cardiac pump system further includes a display configured to show a user interface that includes a representation of one or more signals associated with the operation of the cardiac pump system, and the controller is configured to perform an action, which is to determine a stability score for a patient in whom the cardiac pump is implanted, the stability score being at least partially based on a measure of myocardial contractility, and to display the stability score on the user interface, based at least partially on a measure of myocardial contractility.

[0018] In another aspect, the cardiac pump system further includes a display configured to show a user interface containing representations of one or more signals associated with the operation of the cardiac pump system, and the controller is configured to perform an action on the user interface, which is to provide treatment recommendations for a patient with the cardiac pump implanted, the treatment recommendations being determined at least in part on the cardiac contractility measurements output by performing an action. In another aspect, the controller is configured to perform an action at least in part on the cardiac contractility measurements output by a machine learning model by adjusting the operating conditions of the cardiac pump based on the cardiac contractility measurements. In another aspect, adjusting the operating conditions of the cardiac pump includes adjusting the pumping speed of the cardiac pump.

[0019] In another aspect, the controller is configured to perform an action based at least partially on the cardiac contractility measurements output by the machine learning model, by determining the contractile reserve based at least partially on the cardiac contractility measurements. In another aspect, the cardiac contractility measurements include a first cardiac contractility output by the machine learning model based on a signal from the cardiac pump at a first time, and a second cardiac contractility output by the machine learning model based on a signal from the cardiac pump at a second time after the first time, and determining the contractile reserve includes determining the contractile reserve based on the first and second cardiac contractility. In another aspect, determining the contractile reserve based on the first and second cardiac contractility includes determining the contractile reserve based on the difference between the first and second cardiac contractility. [Brief explanation of the drawing]

[0020] [Figure 1A] Figure 1A shows an illustrative cardiac assist device that may be used in conjunction with some embodiments of the present disclosure.

[0021] [Figure 1B] Figure 1B shows an exemplary cardiac assist system including the cardiac assist device of Figure 1A.

[0022] [Figure 2A] Figure 2A schematically illustrates various features that can be used to estimate native cardiac contractility, according to some embodiments of the present disclosure.

[0023] [Figure 2B] Figure 2B schematically illustrates a process for estimating a measurement of cardiac contractility using a machine learning model, according to some embodiments of the present disclosure.

[0024] [Figure 3] Figure 3A is a flowchart of a process for estimating a measurement of cardiac contractility, according to some embodiments of the present disclosure. Figure 3B is a flowchart of a process for estimating a measurement of cardiac contractility using a plurality of neural networks, according to some embodiments of the present disclosure.

[0025] [Figure 4] Figure 4 shows an exemplary plot for deriving one or more features used to estimate a measurement of cardiac contractility, according to some embodiments of the present disclosure.

[0026] [Figure 5] Figure 5 shows an exemplary plot comparing different estimated measurements of cardiac contractility, according to some embodiments of the present disclosure.

[0027] [Figure 6A] Figures 6A and 6B respectively illustrate a comparison of estimated measurements of cardiac contractility with respect to load and contractility, according to some embodiments of the present disclosure. [Figure 6B] Figures 6A and 6B respectively illustrate a comparison of estimated measurements of cardiac contractility with respect to load and contractility, according to some embodiments of the present disclosure.

[0028] [Figure 7] Figure 7 is a flowchart of a process for determining an estimate of a cardiac contractility measurement, according to some embodiments of the present disclosure.

[0029] [Figure 8] Figure 8 shows a portion of an exemplary user interface for displaying estimated measurements of myocardial contractility, according to some embodiments of the present disclosure.

[0030] [Figure 9] Figure 9 shows a portion of an exemplary user interface for displaying cardiac information for a patient with an implanted cardiac pump system, according to several embodiments.

[0031] [Figure 10] Figure 10 is a flowchart of a process for determining shrinkage reserve according to some embodiments of the present disclosure. [Modes for carrying out the invention]

[0032] Detailed explanation Contractility is a measure of cardiac function. At the cellular level, contractility can be defined as the amount of force that cardiomyocytes can generate. At the ventricular level (e.g., left ventricle), contractility can be defined as the sum of those cellular forces acting in parallel, which generate wall motion and blood ejection. Contractility as a property of the heart is sometimes also referred to as inotropy, cardiac inotropy, inotropic effect, or inotropic level.

[0033] Because contractility is a force measurement at the cellular level (e.g., measured in Newtons), measuring the true sum of these forces can be difficult. Rather, measurable surrogate indices have been developed and experimentally validated. These measurements include, among others, preload-mobilizable work per stroke (PRSW) and end-systolic pressure-volume relationship (ESPVR). In all cases, measurable surrogate indices can be assumed to fluctuate with changes in contractility and, ideally, be robust (unfluctuating) to changes in other factors such as load state, heart rate, or other non-innotropic effects. Measurements such as PRSW and ESPVR can be difficult to measure as part of clinical practice, and therefore other surrogate indices such as ejection fraction, wall motion / shortening ratio, and strain-based measurements (Doppler, DENSE MRI) may be used instead to estimate contractile function.

[0034] Cardiac load (e.g., preload) is a measure of the degree of stress or "load" applied to the myocardium prior to contraction. Because the myocardium can automatically vary the amount of force generated depending on the myocyte length at the start of contraction, there can be significant overlap between the concepts of contractility, contractility, and preload. To distinguish these concepts, force-length curves (or Frank-Starling curves on a ventricular scale) are used to show that, with respect to a given contractility state (e.g., with respect to a certain level of contractility), there exists a variable level of force generated depending on muscle length. It can be assumed that there exists an "optimal" length at which peak force is generated. Variations along the force-length curve can be considered changes in contraction due to load or "load effects," rather than changes in contractility. Such changes in contraction due to load effects may also be referred to as "length-dependent activation."

[0035] A change in contractility is a change in the peak force generated by cardiac cells and ventricles with respect to a given initial length. Such a change in contractility is also called "length-independent activation." Using the force-length relationship, a change in contractility can be expressed as a change in the entire force-length curve (scaling it upward or downward), reflecting a new contractile state that can also vary internally depending on the length of the muscle. The inotropic effect is due to calcium ions (Ca) in myocytes. 2+ This can be directly linked to the exchange of Ca. 2+ The exchange of Ca is, for example, Ca into the cell. 2+ Changing the inflow rate, Ca by the sarcoplasmic reticulum 2+ It can be modified by altering the release rate of and / or by altering the sensitivity of troponin-C (which binds to C++ as part of the muscle contraction cycle). At the ventricular level, contractility can also be modified by altering the total number of muscle cells that contribute to the "sum" of cellular contractility. For example, a portion of the total muscle cells may be Ca 2+ Changes in contractility may be observed during disease states in which efficient circulation is impossible.

[0036] The systems, devices, and methods described herein enable the evaluation of one or more aspects of the function of an organ by an assistive device that resides entirely or partially within that organ (e.g., a mechanical circulatory assistive device). In particular, the systems, devices, and methods described herein enable the use of cardiac pump systems, such as percutaneous ventricular assistive devices, to evaluate cardiac function. For example, such a device may be used to estimate a measure of the innate myocardial contractility of a patient's myocardium.

[0037] Monitoring innate myocardial contractility can be useful in patients receiving mechanical circulatory support (MCS) devices because it can provide important information about the recovery of myocardial function. Cardiac recovery refers to the ability of the myocardium to regain its function and strength after a period of injury or disease, and contractility is a key component of cardiac recovery because it refers to the ability of the myocardium to contract and effectively pump blood.

[0038] Under conditions such as heart failure, myocardial infarction, or cardiomyopathy, the heart muscle can become weakened and lose its ability to contract effectively. However, with appropriate treatment and management, the heart may be able to recover its function and improve its contractility. The ability to continuously monitor and track the trend of contractility can enable physicians to make well-informed decisions regarding patient management.

[0039] Some embodiments of the present disclosure relate to a device (e.g., a computing device) configured to determine innate myocardial contractility (also referred to herein simply as “contractility”) using signals from a mechanical circulatory support (MCS) device. In some embodiments, the device may be configured to use only signals from an MCS device. In some embodiments, the device may be configured to continuously determine contractility over multiple points in time so that a trend of contractility over a time scale of interest can be determined. In some embodiments, the amount and / or trend of contractility may be used to determine and / or recommend a treatment strategy for a patient receiving mechanical circulatory device assistance.

[0040] The inventors recognize and understand that existing techniques for measuring contractility typically rely on the simultaneous measurement of left ventricular pressure and volume, and that the complexity and invasiveness of this procedure often hinder its clinical adoption. In addition, existing techniques for measuring contractility do not tend to measure contractility accurately over a long period of time, and therefore, trends in contractility are not usually observable. For this purpose, some embodiments of the present disclosure relate to improved techniques for estimating contractility using signals associated with the pump of an MCS device during its operation.

[0041] The inventors also recognize and understand that, because the pump of the MCS device may be positioned in the left ventricle across the aortic valve, the rate of pressure change (which may reflect innate cardiac systolic function), measured using one or more sensors on the pump, may be measured. In addition, innate cardiac output may cause the pump to deviate from its set performance curve. The amount of deviation may be related to the intensity of innate cardiac function. In some embodiments, the measured rate of pressure change and pump performance parameter measurements may be provided as input to a machine learning model trained to output an estimate of innate cardiac contractility, along with other information derived from the pump signal (e.g., pressure, velocity, motor current).

[0042] Figure 1A shows an illustrative embodiment of a blood pump assembly 100 according to the present disclosure. The blood pump assembly 100 may include a pump 101, a pump housing 103, a proximal end 105, a distal end 107, a cannula 108, an impeller (not shown), a non-traumatic extension 102, a catheter 112, an inlet region 110, an outlet region 106, and a blood drainage opening 117. In some embodiments, the catheter 112 may be connected to the inlet region 110 of the cannula 108. The inlet region 110 may be located near the proximal end 105 of the cannula, and the outlet region 106 may be located toward the distal end 107 of the cannula 108. The inlet region 110 may include a pump housing 103 having a peripheral wall 111 extending about the rotation axis of the impeller blades, the peripheral wall 111 positioned radially outward from the inner surface with respect to the rotation axis of the impeller. The impeller may be rotatably coupled to the pump 101 in the inlet region 110 adjacent to a blood discharge opening 117 formed within the wall 111 of the pump housing 103. The pump housing 103 may be made of metal, according to several implementations. An extension 102, also referred to as a "pigtail," may be connected to the distal end 107 of the cannula 108 and may help stabilize the blood pump assembly 100 and / or position it correctly within the heart. The pigtail 102 may be configured from a straight configuration to a partially curved configuration. The pigtail 102 may be made of a flexible material, at least partially, and may have dual rigidity. It should be understood that some embodiments of the pump assembly may not include the pigtail 102.

[0043] The cannula 108 may have a shape that matches (or resembles) the biostructure of the patient's right ventricle. In the exemplary embodiment shown in Figure 1A, the cannula has a proximal end 105 positioned near the patient's inferior vena cava and a distal end 107 positioned near the pulmonary artery. The cannula 108 may include a first compartment Sl extending from the inflow region to point B between the inlet region 110 and the outlet region 106. The cannula 108 may also include a second compartment S2 extending from point C between the inlet region 110 and the outlet region 106 to the outlet region 106. In some implementations, points B and C may be located in the same place along the cannula 108. The first compartment Sl of the cannula may form an "S" shape in a first plane. In some implementations, the compartment Sl may have a curvature of 30 to 180 degrees. The second compartment S2 of the cannula may form an "S" shape in the second plane. In some implementations, compartment S2 can have a curvature of 30 to 180 degrees (e.g., 40°, 50°, 60°, 70°, 80°, 90°, 100°, 110°, 120°, 130°, 140°, 150°, 160°, or 170°). The second plane may differ from the first plane. In some implementations, the second plane may be parallel to or the same as the first plane.

[0044] While shown with an "S" shape, it should be understood that other implementations of the blood pump assembly may have other shapes (e.g., a "U" shape) or no shape at all when outside the body. In such implementations, the cannula may be formed from a flexible material so that it can bend during insertion and achieve the desired shape when it comes inside the patient's heart.

[0045] In some implementations, the blood pump assembly 100 can be percutaneously inserted into the right ventricle through the internal jugular vein, through the right atrium. When properly positioned, the blood pump assembly 100 can deliver blood from an inlet region 110 located inside the patient's right atrium, through a cannula 108, to a blood discharge opening 117 of the pump housing 103 positioned in the pulmonary artery. Alternatively, in some implementations, the blood pump assembly 100 can be percutaneously inserted into the left ventricle through the femoral artery, delivering blood from the left ventricle into the aorta.

[0046] Figure 1B shows that the blood pump assembly 100 may form part of a cardiac assist system 120. The cardiac assist system 120 may also include a controller 130 (e.g., an Automated Impella Controller®, hereafter referred to as “AIC”, manufactured by ABIOMED, ​​Inc., Danvers, Mass.), a display 140, a purge subsystem 150, a connector cable 160, a plug 170, and a repositioning unit 180. As shown, the controller 130 may include a display 140. The controller 130 may be configured to monitor and control the operation of the blood pump assembly 100. During operation, the purge subsystem 150 may be configured to deliver purge fluid to the blood pump assembly 100 through a catheter 112 to prevent blood from entering the motor of the cardiac pump (not shown). In some implementations, the purge fluid is a glucose solution (e.g., 5% glucose in water with 25 or 50 IU / mL heparin, although the solution does not necessarily have to contain heparin in all embodiments). A connector cable 160 may provide an electrical connection between the blood pump assembly 100 and the controller 130. A plug 170 may connect the catheter 112, the purge subsystem 150, and the connector cable 160. In some implementations, the plug 170 may include a storage device (e.g., memory) configured to store, for example, operating parameters, to facilitate patient transfer to another controller if necessary. A repositioning unit 180 may be used to reposition the blood pump assembly 100 within the patient's heart (e.g., by maintaining the position of the pump assembly relative to the patient).

[0047] As shown in Figure 1B, in some embodiments, the cardiac support system 120 may include a purge subsystem 150 having a container 151, a supply line 152, a purge cassette 153, a purge disc 154, purge tubing 155, a check valve 156, a pressure reservoir 157, an infusion filter 158, and a side arm 159. The container 151 may be, for example, a bag or a bottle. As understood, in other embodiments, the cardiac support system 120 may not include the purge subsystem. In some embodiments, the purge fluid may be stored in the container 151. The supply line 152 may provide a fluid connection between the container 151 and the purge cassette 153. The purge cassette 153 may control the extent to which the purge fluid in the container 151 is delivered to the blood pump assembly 100. For example, the purge cassette 153 may include one or more valves to control the pressure and / or flow rate of the purge fluid. The purge disc 154 may include one or more pressure and / or flow sensors to measure the pressure and / or flow rate of the purge fluid. As shown, the controller 130 may include the purge cassette 153 and the purge disc 154. Purge tubing 155 may provide a fluid connection between the purge disc 154 and the check valve 156. A pressure reservoir 157 may provide additional filling volume during purge fluid exchange. In some implementations, the pressure reservoir 157 may include a flexible rubber diaphragm with an expansion chamber to provide additional filling volume. An infusion filter 158 may help prevent bacterial contamination and air from entering the catheter 112. A side arm 159 may provide a fluid connection between the infusion filter 158 and the plug 170. Although shown to have separate purge tubing and connector cables, it should be understood that in some embodiments, the cardiac support system 120 may include a single connector having both fluid and electrical lines connectable to the controller 130.

[0048] During operation, the controller 130 may be configured to receive measurements from one or more pressure sensors (not shown) included as part of the blood pump assembly 100 and purge disk 154. The controller 130 may also be configured to control the operation of the motors (not shown) of the blood pump assembly 100 and purge cassette 153. In some embodiments, the controller 130 may be configured to control and measure the pressure and / or flow rate of the purge fluid via the purge cassette 153 and purge disk 154. During operation, after exiting the purge subsystem 150 through the side arm 159, the purge fluid may be guided through a purge lumen (not shown) in the catheter 112 and plug 170. The catheter 112, connector cable 160, and sensor cable (not shown) in the plug 170 may provide electrical connections between components of the blood pump assembly 100 (e.g., one or more pressure sensors) and the controller 130. A catheter 112, a connector cable 160, and a motor cable (not shown) within a plug 170 may provide an electrical connection between the motor of the blood pump assembly 100 and the controller 130. During operation, the controller 130 may be configured to receive measurements from one or more pressure sensors of the blood pump assembly 100 through a sensor cable (e.g., optical fiber) and to control the power delivered to the motor of the blood pump assembly 100 through the motor cable. By controlling the power delivered to the motor of the blood pump assembly 100, the controller 130 may be operable to control the speed of the motor.

[0049] Various modifications can be made to the cardiac assist system 120 and one or more of its components. For example, one or more additional sensors may be added to the blood pump assembly 100. In another embodiment, a signal generator may be added to the blood pump assembly 100 to generate a signal indicating the rotational speed of the motor of the blood pump assembly 100. In yet another embodiment, one or more components of the cardiac assist system 120 may be isolated. For example, the display 140 may be incorporated into another device that communicates with the controller 130 (e.g., wirelessly or through one or more electrical cables).

[0050] As described herein, signals from an MCS device (e.g., a blood pump assembly 100) may be used to estimate innate myocardial contractility. In particular, the controller of the MCS device may determine a pressure signal (e.g., left ventricular pressure) that is used at least partially to estimate or approximate one or more measures of myocardial contractility, according to some embodiments of the present disclosure. Figure 2A schematically illustrates various features 200 that may be used to estimate innate myocardial contractility 220, according to some embodiments of the present disclosure. As described herein, since contractility may not be directly measurable, features 200 may include one or more contractility surrogate index features (examples of which are described herein), such as wall displacement 202, ejection fraction 204, end-systolic pressure-volume relationship (ESPVR), and preload-mobilizable stroke work (PRSW). Some contractility surrogate features (e.g., ESPVR and PRSW) have been shown to better represent innate myocardial contractility as measured, for example, in animal studies, compared to other contractility surrogate features (e.g., ejection fraction). As shown in Figure 2A, feature 200 may also include information determined based on a signal (e.g., a pressure signal) associated with the operation of the cardiac pump. For example, one or more features may be derived from an LV pressure signal, including, but not limited to, the maximum slope of the signal during contraction (dP / dt max206) or the slope of the signal during contraction normalized to pressure. In some embodiments, feature 200 may include a normalized feature. For example, feature 200 may include dP / dt normalized to mean pressure, dP / dt normalized to end-diastolic pressure prior to the onset of contraction, or dP / dt normalized to the integral of pressure during the systolic cycle up to the maximum dP / dt point. Feature 200 can be used alone or in any preferred combination to estimate innate cardiac contractility, and examples thereof are described herein.

[0051] The inventors recognize and understand that some features (e.g., feature 200) do not provide a best estimate of intrinsic myocardial contractility when considered in isolation. Accordingly, some embodiments of the present disclosure relate to using a machine learning approach to process MCS device signals and / or features derived from MCS device signals to experimentally arrive at improved estimated measurements of myocardial contractility. Figure 2B schematically illustrates how a machine learning model may be used to estimate myocardial contractility according to some embodiments of the present disclosure. As shown in Figure 2B, one or more pump features 230 (its embodiments include, but are not limited to, features determined from pump signals (e.g., motor current, pressure, pump flow rate) 222, features determined from pressure waveform signals (e.g., dP / dt max) 224, and correlation features (e.g., systolic region) 226) may be provided as input to a machine learning (ML) model 240 trained to output estimated measurements of myocardial contractility 250 based on signals associated with the pumps of the MCS device. In the example shown in Figure 2B, the estimated cardiac contractility value of 250 is the pump preload mobilizable stroke work index (pump PRSWi).

[0052] Figure 3A is a flowchart of process 300 for determining an estimated measure of myocardial contractility (e.g., pump PRSWi) using a machine learning model, according to several embodiments. While pump PRSWi is described herein as an estimated measure of myocardial contractility, it should be understood that the machine learning model may be trained as alternative to output estimates of other surrogate indices of myocardial contractility, such as ESPVR. In act 302, one or more MCS device signals (e.g., pressure signal, motor current, blood flow rate) are received. Process 300 may then proceed to act 304, in which one or more per-beat features are estimated based at least in part on the received MCS device signals. Non-limiting embodiments of per-beat features that may be estimated in act 304 include the mean pump flow rate over two consecutive beats, the mean aortic pressure over two consecutive beats, left ventricular (LV) pressure at end-diastolic (LVED), dP / dt max defined as the maximum rate of increase in LV pressure during LV systole, and the mean pump motor current over two consecutive beats. Process 300 may then proceed to action 306, in which one or more of the per-pulse features estimated in action 304 are provided as input to the trained machine learning model. In exemplary process 300, the trained machine learning model may be a feedforward dense neural network. Process 300 may then proceed to action 308, in which the estimated measure of myocardial contractility is output from the trained machine learning model. In exemplary process 300, the output of the trained machine learning model is the pump PRSWi.

[0053] It should be understood that any suitable model architecture may be used for a trained machine learning model according to some embodiments of this disclosure. An exemplary architecture of ML model 350, which may be used according to some embodiments of this disclosure, is shown in Figure 3B. In the embodiment shown in Figure 3B, ML model 350 is implemented using a deep neural network (DNN) architecture, but it should be understood that other ML network architectures may be used as alternatives. In addition, ML model 350 is illustrated in Figure 3B to include three DNNs (DNNs 320, 322, and 324). The use of three DNNs is merely illustrative and not limiting, but it should be understood that any number of DNNs, including a single DNN or more than three DNNs, may be used as alternatives according to embodiments of this disclosure.

[0054] As shown in Figure 3B, the ML model 350 receives AoP-based features 310, pump function features 312, and correlation features 314 as inputs. The AoP-based features 310 may include features associated with pressure signals measured by or derived from pressure sensors located on the pump of the MCS device. For example, the AoP-based features 310 may include systolic pressure measurements, diastolic pressure measurements, time-based pressure measurements (e.g., dP / dt max), or any other suitable pressure measurements associated with a pressure signal (e.g., LV pressure signal). The pump function features 312 may include features associated with the operation of the pump itself, and its embodiments may include, but are not limited to, motor current, pump speed, and pump flow rate. The correlation features 314 may include features that depend at least partially on the AoP-based features 310 and the pump function features 312. For example, Figure 4 shows a plot of LV pressure (y-axis) versus motor current (x-axis). The feature values ​​derived from such relationships (including the systolic region as shown in Figure 4 in some embodiments) may be contained within the correlation feature 314. Each of the AoP-based feature 310, the pump function feature 312, and the correlation feature 314 may be provided as input to an ML model 350, which, when trained (e.g., using preclinical data), can be configured to output a value 326 for PRSWi as an estimated measure of myocardial contractility.

[0055] While Figure 3B shows that the ML model 350 receives three different types of inputs (i.e., AoP-based features 310, pump function features 312, and correlation features 314), it should be understood that some embodiments may include fewer (e.g., one or two) or additional (e.g., more than three) types of features as inputs to the ML model 350, and embodiments of the present disclosure are not limited in this respect. In addition, within each of the different types of features provided as inputs, any preferred number of features may be used. For example, in one embodiment, seven AoP-based features 310, three pump function features 312, and nine correlation features 314 may be used. In another embodiment, five AoP-based features 310, six pump function features 312, and seven correlation features 314 may be used.

[0056] In some embodiments, the features provided as input to the ML model 350 may be categorized and provided to separate network components (e.g., separate DNNs) prior to being combined to determine an estimated measure of myocardial contractility (e.g., pump PRSWi). Such an approach may facilitate the use of simpler and / or more compact ML models that can be implemented on processors with limited processing resources (e.g., on the controller of a cardiac pump system). In some embodiments, it may not be necessary to categorize the features prior to processing them using the ML model. For example, a set of features determined from an MCS device signal (e.g., per-beat features) may be provided as input to a training neural network without categorization, and the network may learn over time how to weight different features and determine the best estimated measure of myocardial contractility.

[0057] In some embodiments, the ML model 350 may be trained using a skip-cross-validation training process. For example, multiple ML models may be defined, each using the same architecture and hyperparameters. Each of the multiple ML models may be trained on a separate dataset of features, and the final ML model may be defined and trained based on one or more of the multiple ML models.

[0058] In some embodiments, estimated measurements of innate myocardial contractility, such as those determined based on the output of an ML model, can be visualized, trended, and / or tracked longitudinally. For example, estimated contractility values ​​can be displayed on one or more displays associated with the MCS device. Figure 5 shows an exemplary plot 500 of estimated measurements of myocardial contractility (pump PRSWi) 514 determined using a trained machine learning model as described herein. The pump PRSWi values ​​514 are trended over time relative to time and compared with measured (e.g., ground truth) PRSWi values ​​510 (e.g., when a stress test is performed) and measured dP / dt max values ​​512 determined based on the LV pressure signal of the cardiac pump system. As can be observed in Figure 5, the pump PRSWi values ​​514 track the measured PRSWi values ​​510 more closely than the dP / dt max measurements 512 alone, illustrating the effectiveness of using ML-based techniques to reliably estimate myocardial contractility. For example, when an increase in contractility is induced around the 10:50 mark in plot 500, a good correspondence exists between the pump PRSWi measurement 514 and other PRSW measurements. Furthermore, plot 500 shows that, following the initial induction of contractility (e.g., after the 11:00 mark in plot 500), the pump PRSWi measurement 514 tracks the ground truth PRSWi measurement 510 more closely than the dP / dt max measurement 512. Such comparisons demonstrate the ability of a trained ML model to accurately predict innate cardiac contractility based on the pump-associated signals of the MCS device.

[0059] Figures 6A and 6B further illustrate a comparison of pump PRSWi values ​​determined as the output of a trained ML model using the technique described herein, compared to alternative index measurements conventionally used to estimate contractility. Ideally, an accurate estimated measure of cardiac contractility would be sensitive to changes in contractility and insensitive to changes in load. Plots 600 in Figure 6A and 610 in Figure 6B show that the pump measurement performance (pump PRSWi) determined using the technique described herein lies between the reference value (PRSWi) and the input to the model (dP / dt max) in terms of sensitivity to both load and contractility, demonstrating that the pump-signal-based technique described herein for determining contractility performs as well as existing techniques for determining contractility.

[0060] Figure 7 illustrates a process 700 for estimating a measure of myocardial contractility using signals from a mechanical circulatory assistance (MCS) device and a trained, machined, and learned model, according to some embodiments of the present disclosure. Process 700 may begin with act 710, in which a set of features during the operation of the MCS device is determined. For example, as described herein, one or more signals associated with the operation of the MCS device (e.g., pressure signal, flux signal, motor current signal, etc.) may be processed and one or more features (e.g., one or more per-pulse features) that may be included in the set of features may be extracted. Process 700 may then proceed to act 712, in which the set of features is provided as input to a machine learning (ML) model trained to output a measure of myocardial contractility. For example, as described herein, the ML model may be trained (e.g., using preclinical data) to estimate PRSWi based on features extracted from pump signal data.

[0061] Process 700 may then proceed to action 714, in which an action is performed based at least in part on the myocardial contractility measurement output from the ML model. In some embodiments, the action may be to display the value and / or trend of the myocardial contractility measurement on a user interface associated with the MCS device. In some embodiments, the myocardial contractility measurement may be measured over time as an absolute or relative (e.g., percentage) change in contractility compared to a baseline measurement at a previous point in time or from a baseline measurement. In such embodiments, an indication of the change in contractility relative to the baseline measurement may be displayed. In some embodiments, the action may be to provide a Clinical Decision Assistance (CDS) to a user (e.g., a physician or other healthcare professional) associated with the MCS device. For example, when the myocardial contractility measurement is above (or below) a threshold, an alert or other indication may be provided to the user, which may indicate to the user that the patient's cardiac function is improving (or declining), and the user may take appropriate action to improve patient management based on the alert / indication. In some embodiments, the action may involve using the myocardial contractility measurement to modify one or more other measurements that may be used to facilitate patient management. In some embodiments, the action may involve adjusting the operating conditions of the MCS device (with or without user assistance). For example, the pump speed of the MCS device may be adjusted based at least in part on the myocardial contractility measurement. Thus, the myocardial contractility measurement may be used as feedback to adjust the assistance provided by the MCS device according to the patient's needs and to further promote the recovery of the patient's innate cardiac function.

[0062] In some embodiments, once the MCS device is deployed, the cardiac contractility measurement (e.g., PRSWi) parameter may become continuously available for use and trend display via either user-initiated or automated system-initiated deployment. The contractility measurement may be used for a wider range of clinical decision aid (CDS) algorithms for patient management on the MCS device, such as device output enhancement, device detachment, device-assisted titration, secondary device titration, ventilator titration / extubation, or pharmacological titration of vasoactive or inotropic therapeutic agents.

[0063] Systolic measurements can be visualized, trend-represented, and longitudinally tracked on a daily / weekly basis as a measure of innate cardiac recovery. These measurements may have significant short-term and / or long-term predictive power regarding patient outcomes.

[0064] Figure 8 shows some embodiments of a user interface 800 in which estimated measurements of myocardial contractility may be displayed, according to several embodiments. As shown in Figure 8, estimated measurements of myocardial contractility may be shown over time as numerical values ​​810 and / or trends 820. In some embodiments, the user interface 800 may include a time window selector 830 configured to allow the user to interact with the user interface and display trends (e.g., trends 820) over different time scales.

[0065] As described herein, in some embodiments, estimated cardiac contractility measurements may be used to correct one or more other measurements determined based on signals associated with the MCS device and to provide improved patient management. For some patients with implanted MCS devices, it may be desirable to wean the patient from the device (and potentially, eventually, remove the device) once the patient's innate cardiac function has recovered. Recovery of innate cardiac function may, in some cases, be characterized as a recovery of cardiac contractility. Therefore, in some embodiments, estimated contractility measurements may be used, at least in part, to provide clinicians with guidance on the extent and / or timing of weaning a patient from the MCS device. Figure 9 shows some embodiments of a user interface 900 for a weaning aid clinical decision aid tool according to some embodiments of this disclosure. In the exemplary user interface 900 shown in Figure 9, the weaning aid tool includes a stability score 910, which may indicate the patient's relative stability, such as that determined by several variables or measurements associated with the MCS device. In some embodiments, at least one of the measurements used to determine the stability score 910 may be an estimated cardiac contractility measurement (e.g., pump PRSWi). Based on the patient's stability score 910, the healthcare provider may decide to modify the amount of assistance provided to the patient by the MCS device with the goal of weaning the patient off the device or providing additional assistance if necessary.

[0066] The concept of contractile reserve can be defined as the “excess volume” or “reserve” that the heart has available to increase contraction in response to changes in its physiological state. For example, following an acute event (e.g., acute myocardial infarction (AMI)), there may be a decrease in contractility. In response, the heart may partially increase contractility in the remaining available muscle cells, preserving afterload / cardiac output / peripheral organ perfusion. Similarly, in events such as bleeding / blood loss, a decrease in mean blood pressure may induce the heart to respond to the event by partially increasing contractility and preserving perfusion. In addition to complexity, these changes often overlap with other response mechanisms, including changes in load, changes in heart rate (chronotropy), and / or changes in vascular properties (compliance and resistance), all of which tend to alter the hemodynamic state in parallel with the true changes in inotropy.

[0067] To isolate and measure contractile reserve, a "cardiac stress test" is performed to induce an inotropic change, typically using either exercise or pharmacological agents. In a typical stress test, the heart is subjected to (physical or pharmacological) stress, and cellular Ca2+ is increased. 2+ Changes in handling induce changes in inotropy. The heart, under repeated load, can push itself to a “maximal” inotropic state, which may represent the highest possible contractility (zero remaining reserve). Total contractility reserve can then be measured by subtracting peak contractility from baseline contractility, with the difference being “contractility reserve.” Contractility reserve can be normalized to the baseline state or other factors. Alternatively, the ratio of peak contractility measurements to baseline values ​​can be used to quantify contractility reserve on a normalized basis. Some typical clinical measures of contractility reserve include changes in ejection fraction or “wall motion score index” (WMSI). Other measures of contractility reserve may also use imaging-based changes in left ventricular (LV) dimensions or overall LV distortion (e.g., circumferential or longitudinal).

[0068] Measures of systolic reserve have shown a strong correlation with clinical outcomes, particularly long-term recovery following acute events. The concept of “innate cardiac recovery” can essentially be linked to the recovery of systolic reserve. Therefore, quantifying systolic reserve may be important in patients where the recovery of innate cardiac function is the treatment goal during hospitalization. In some cases, knowledge of systolic reserve can be used as an indicator in decisions to wean / remove assistive devices (e.g., mechanical circulatory assistive devices), reduce pharmacological support, and / or discharge the patient from the hospital. Similarly, measures of systolic reserve can be a useful indicator of a patient’s quality of life in dealing with future stress situations (e.g., climbing stairs) that may not be easily assessable while the patient is at rest in a hospital bed.

[0069] Contractile reserve has been shown to be a valuable prognostic indicator of short-term and long-term outcomes for several different cardiac diseases. Therefore, we recognize and understand that measuring, estimating, and / or predicting contractile reserve can be a valuable tool for patient management in patients receiving mechanical circulatory support. We further recognize and understand that existing solutions for determining contractile reserve typically do not accurately measure contractility. Thus, estimates of contractile reserve based on such inaccurate contractility measurements are likely to have compound errors, which may limit the clinical utility of such measurements. In addition, existing techniques typically require interventions (e.g., stress tests) to induce changes in the patient's cardiac state and measure differences in contractility when the patient has different cardiac states. Limitations of such techniques may include the fact that they cannot be performed continuously, and in some cases, cannot be performed at all (e.g., when the patient cannot withstand the stress event and / or when there are time / resource limitations). Furthermore, existing techniques may not utilize signals such as LV pressure or LV volume, which can be most closely associated with true changes in cellular contractility.

[0070] The inventors recognize and understand that the techniques described herein for estimating innate myocardial contractility using signals from mechanical circulatory system devices may also be useful in estimating contractile reserve. For example, myocardial contractility may be measured at multiple time points (or windows) using the techniques described herein. Multiple measurements may then be used to estimate the contractile reserve for a patient. For example, the difference in contractility measured at two different time points may be used to estimate the patient's contractile reserve. In some embodiments, rather than having the patient undergo a conventional cardiac stress test (e.g., induced by exercise or medication), the operation of the cardiac pump itself may be used to apply different stresses to the patient's heart and measure cardiac reserve. For example, a change in pump function may induce a change in contractility as a “minor stress test”. In some embodiments, the pump may be configured to operate continuously, and predictions of cardiac reserve may be evaluated or trended over time using one or more of the techniques described herein.

[0071] In some embodiments, the tendency of contractility may be determined during a typical clinical stress test. For example, the device may store or remember a first contractility value determined before the stress test (e.g., using techniques described herein), perform the stress test (e.g., using a pharmaceutical such as dobutamine, or using exercise), and store a second contractility value measured at the peak stress during the stress test. The first and second contractility values ​​may be used to determine the patient's contractility reserve. For example, contractility reserve may be determined based on the ratio of the first and second contractility values, the difference between the first and second contractility values, the percentage difference between the first and second contractility values, or a regression fit / prediction of the peak stress when multiple stress points are collected.

[0072] In some embodiments, small changes in contractility can be induced within a patient such that the degree of change correlates with the patient's true (or near-true) contractile reserve, according to known transformations. Changes in the pump speed of a mechanical circulatory support device over short cycles (e.g., about 1 minute time cycles) can induce changes in coronary perfusion pressure, leading to changes in coronary flow, and transient changes in contractility that induce reserve action (to some extent) and restore homeostasis, with the degree of change correlating with peak reserve. Coronary perfusion pressure may represent the difference between aortic pressure and left ventricular pressure. Different pump flow rates can alter coronary flow / perfusion, which can mimic or otherwise approximate a Dipyridamole stress test. Operating times at high force and low flow rates may be longer to allow the heart to respond to changes in coronary flow, and changes in systolic and diastolic function can be mapped to contractile reserve. In some embodiments, pressure measurements from the cardiac pump (e.g., reflecting coronary perfusion pressure) may be used to estimate contractile reserve as the heart transitions from a first "unstressed" state to a "stressed" state.

[0073] In some embodiments, contractile reserve may be determined at least in part based on electrocardiogram (ECG) information combined with information from left ventricular (LV) pressure waveforms. For example, ECG-based lead signals may be used to measure excitation-contractile coupling (EC-Coupling) components, such as the delay between the onset of electrical contraction and mechanical rise, which may reflect calcium channel overcapacity. One or more extracted features of the ECG waveform (e.g., QRS interval, PR interval, T-wave amplitude, morphology of electrical depolarization and repolarization phases) may be combined with information associated with the LV pressure profile measured from a mechanical circulatory support device pump to predict contractile reserve for the patient.

[0074] In some embodiments, contractile reserve may be determined at least in part on a known end-systolic pressure volume (LV ESV) combined with information from the LV pressure waveform (e.g., LV SP / LV ESV). In addition to or as an alternative to using ECG information, information from other sources containing information about the turbulence / initial contraction range (e.g., first and second heart sounds) may be used. When combined with one or more features of the LV pressure signal, the relationship between heart sounds and pressure generation may indicate the expected "hidden reserve." For example, the LV pressure waveform may reflect the contraction (force) range, and heart sounds may reflect the range of motion (strain / shortening / valve action).

[0075] In some embodiments, contractile reserve may be determined at least in part on morphological signals in available waveforms, including, but not limited to, the LV diastolic filling curve, current contractility value, heart rate, cardiac output, and / or cardiac output (CPO). In such embodiments, the focus may be on the range of lucitropy / relaxation during early diastole and the true passive period during diastole (fast lucitropy / short relaxation time), which may correlate with a larger contractile reserve volume. When the heart is operating at or near its capacity (lower reserve), it is more likely that relaxation time will be insufficient / absent and true passive periods will be minimal.

[0076] In some embodiments, contractile reserve can be determined using at least partially a system (e.g., all available signals) that implements a lumped-parameter model of the circulation and heart. In this embodiment, a stress test may then be simulated using the model, and contractile reserve may be estimated from the simulation. Contractile reserve may be determined based on a change in true contractility (e.g., PRSW) or through another simulated alternative index. For example, an estimate of cardiac contractility (e.g., pump PRSWi) using the techniques described herein may be determined at multiple points in time, and contractile reserve for a patient may be determined based on multiple determinations of cardiac contractility.

[0077] In some embodiments, contractile reserve can be determined, at least in part, by combining information from imaging (e.g., ultrasound) and the relationship between wall strain / wall motion and the resulting LV pressure, as determined from mechanical circulatory support devices. In such embodiments, knowledge of the strain rate, wall motion, or LV pressure waveform morphology coupled to end-systolic pressure volume can be used to determine a patient's contractile reserve.

[0078] It should be understood that one or more of the aforementioned concepts can be combined in any preferred manner to determine the contractile reserve of a patient. For example, in some embodiments, the contractile reserve may be determined at least in part based on information from cardiac sound information, imaging information, and LV pressure waveforms.

[0079] Figure 10 illustrates a process 1000 for determining contractility reserve according to some embodiments of the present disclosure. Process 1000 may begin with act 1010, in which a first cardiac contractility is determined based on signals recorded at a first time. For example, a set of features may be determined from signals recorded at a first time (e.g., a single time point or time window) from a mechanical circulatory assistance device, the set of features may be provided as input to a trained machine learning model, and the output of the trained machine learning model shall be the first cardiac contractility. Process 1000 may then proceed to act 1012, in which a second cardiac contractility is determined based on signals recorded at a second time. For example, a set of features may be determined from signals recorded at a second time (e.g., a single time point or time window) from a mechanical circulatory assistance device, the second time being after the first time. The set of features may be provided as input to a trained machine learning model, and the output of the trained machine learning model shall be the second cardiac contractility. Process 1000 may then proceed to act 1014, in which contractility reserve is determined based on the first and second myocardial contractility. For example, contractility reserve may be determined based on the ratio of the first and second myocardial contractility values, the difference between the first and second myocardial contractility values, the percentage difference between the first and second myocardial contractility values, or the regression fit / prediction of peak stress when multiple stress points are collected.

[0080] In some embodiments, the contractile reserve determined in act 1014 may be used to perform further acts, including, but not limited to, other preferred acts described herein relating to providing clinical decision assistance to healthcare providers, determining a patient's withdrawal status or stability score, or determining a measure of myocardial contractility.

[0081] While some aspects and embodiments of the technology described herein have been described above, it should be understood that various variations, modifications, and improvements will be readily conceivable to those skilled in the art. Such variations, modifications, and improvements are intended to be within the spirit and scope of the technology described herein. For example, those skilled in the art will readily conceivable various other means and / or structures for carrying out the functions described herein and / or obtaining one or more of the results and / or benefits, and each of such variations and / or modifications will be considered within the scope of the embodiments described herein. Those skilled in the art will be able to recognize equivalents to many of the specific embodiments described herein, or to verify them by using only routine experimentation. Therefore, it should be understood that the embodiments described herein are presented only as examples, and that embodiments of the invention may be practiced in ways other than those specifically described. In addition, any combination of two or more features, systems, articles, materials, kits, and / or methods described herein is included within the scope of this disclosure, provided that such features, systems, articles, materials, kits, and / or methods are not mutually inconsistent.

[0082] The embodiments described above can be implemented in any of a number of ways. One or more aspects and embodiments of the Disclosure involving the implementation of a process or method may utilize program instructions executable by a device (e.g., a computer, processor, or other device) to implement or control the implementation of the process or method. In this regard, various concepts of the Invention may be embodied as a computer-readable storage medium (or more computer-readable storage mediums) encoded with one or more programs (e.g., computer memory, one or more floppy disks, compact disks, optical disks, magnetic tape, flash memory, field-programmable gate arrays, or circuit configurations in other semiconductor devices, or other tangible computer storage mediums), which, when executed on one or more computers or other processors, implements a method of implementing one or more of the various embodiments described above. The (one or more) computer-readable mediums may be transportable, and the (one or more) programs stored thereon may be loaded onto one or more different computers or other processors to implement various aspects of the aspects described above. In some embodiments, the computer-readable medium may be a non-transient medium.

[0083] The embodiments of this technology described above can be implemented in any of a number of ways. For example, the embodiments may be implemented using hardware, software, or a combination thereof. When implemented in software, the software code can run on any suitable processor or set of processors, whether provided on a single computer or distributed across multiple computers. It should be understood that any component or set of components that performs the functions described above can generally be considered a controller that controls the functions described above. The controller can be implemented in a number of ways, such as using dedicated hardware or using general-purpose hardware (e.g., one or more processors) programmed with microcode or software to perform the functions listed above, and when the controller corresponds to multiple components of a system, it may be implemented in a combination of ways.

[0084] Furthermore, it should be understood that, in non-limiting embodiments, computers can be embodied in any of several forms, such as rack-mount computers, desktop computers, laptop computers, or tablet computers. In addition, computers can be embedded in devices that are not generally considered computers but possess suitable processing capabilities, including personal digital assistants (PDAs), smartphones, or any other suitable portable or fixed electronic devices.

[0085] Furthermore, a computer may have one or more input and output devices. These devices can, among other things, be used to present a user interface. Embodiments of output devices that can be used to provide a user interface include a printer or display screen for visual presentation of output and a speaker or other sound-generating device for audible presentation of output. Embodiments of input devices that can be used for a user interface include a keyboard and pointing devices such as a mouse, touchpad, and digitized tablet. In another embodiment, a computer may receive input information through speech recognition or in other audible formats.

[0086] Such computers may be interconnected by one or more networks in any preferred form, including local area networks or wide area networks such as enterprise networks, and intelligent networks (INs) or the Internet. Such networks may be based on any preferred technology, operate according to any preferred protocol, and may include wireless networks, wired networks, or fiber optic networks.

[0087] Furthermore, as will be explained, several aspects may be embodied in one or more ways. The actions performed as part of the method may be ordered in any preferred way. Thus, embodiments may be constructed in which the actions are performed in a different order than those illustrated, and may include performing several actions simultaneously, even if they are shown as sequential actions in the illustrative embodiments.

[0088] It should be understood that all definitions defined and used herein take precedence over dictionary definitions, definitions in literature incorporated by reference, and / or the ordinary meaning of the defined term.

[0089] The indefinite articles "a" and "an" as used herein should be understood to mean "at least one" unless explicitly indicated otherwise.

[0090] The phrase "and / or" as used herein should be understood to mean "either one or both" of the elements thus combined, that is, elements that exist conjugately in some cases and disjunctly in others. Multiple elements listed using "and / or" should be interpreted in the same manner, that is, "one or more" of the elements thus combined. Other elements other than those specifically identified by the "and / or" clause may exist, whether related to or unrelated to those specifically identified elements. Therefore, in non-restrictive embodiments, a reference to "A and / or B," when used in conjunction with non-restrictive terms such as "comprising," may refer in one embodiment to A only (optionally including elements other than B), in another embodiment to B only (optionally including elements other than A), and in yet another embodiment to both A and B (optionally including other elements), and so on.

[0091] As used herein, the phrase “at least one” referring to a list of one or more elements means at least one element selected from any one or more of the elements in the list of elements, but it should be understood that it does not necessarily include at least one of every element specifically enumerated in the list of elements, nor does it exclude any combination of elements in the list of elements. This definition also allows for the optional presence of elements other than those specifically identified in the list of elements to which the phrase “at least one” refers, whether related to or unrelated to those specifically identified elements. Therefore, in non-limiting embodiments, “at least one of A and B” (or equivalently “at least one of A or B” or equivalently “at least one of A and / or B”) may refer to, in one embodiment, at least one A (and optionally including elements other than B) which may not include any B; in another embodiment, at least one B (and optionally including elements other than A) which may not include any A; and in yet another embodiment, at least one A which may include one or more, and at least one B (and optionally including other elements), and so on.

[0092] Furthermore, the terminology and grammar used herein are for illustrative purposes only and should not be considered limiting. The use of “including,” “comprising,” “having,” “containing,” “involving,” and their variations herein means that they encompass the items listed below and their equivalents, as well as any additional items.

Claims

1. A computer implementation method, wherein the computer implementation method is Receiving a set of signals from a mechanical circulatory support device, Using a computer processor, determine a set of features based at least partially on the set of signals, To provide the aforementioned set of features as input to a machine learning model trained to output measurements of cardiac contractility, The action is to be performed at least partially based on the measured values ​​of cardiac contractility output by the machine learning model. Computer implementation methods, including those mentioned above.

2. The computer implementation method according to claim 1, wherein the set of signals includes at least one pressure signal and / or at least one pump function signal.

3. The computer implementation method according to claim 2, wherein determining the set of features includes determining at least one feature using a combination of a first pressure signal of the at least one pressure signal and a first pump function signal of the at least one pump function signal.

4. The computer implementation method according to claim 3, wherein the at least one feature using a combination of a first pressure signal of the at least one pressure signal and a first pump function signal of the at least one pump function signal has a maximum rate of increase of left ventricular pressure during systole.

5. The computer implementation method according to claim 1, wherein determining a set of features includes determining one or more per-pulse features based at least partially on the set of signals.

6. The computer implementation method according to claim 5, wherein determining one or more of the above-mentioned per-pulse characteristics includes determining one or more of the following: mean pump flow rate, mean aortic pressure, left ventricular pressure at end diastole, maximum rate of increase of left ventricular pressure during systole, and mean motor current.

7. The computer implementation method according to claim 1, wherein the measured value of cardiac contractility is an estimate of the preload mobilizable stroke work index.

8. The computer implementation method according to claim 1, wherein the machine learning model comprises a feedforward dense neural network.

9. The computer implementation method according to claim 1, wherein performing an action based at least in part on the measured cardiac contractility output by the machine learning model includes displaying an indication of the measured cardiac contractility on a user interface associated with the mechanical circulatory support device.

10. The computer implementation method according to claim 9, wherein the indication of the measured value of myocardial contractility is the trend of myocardial contractility over a specific time range.

11. Performing an action based at least partially on the cardiac contractility measurement output by the machine learning model is Determining a stability score for a patient in whom the mechanical circulatory support device is implanted, wherein the stability score is at least partially based on the measured value of myocardial contractility. Display the stability score on the user interface associated with the mechanical circulation assist device. The computer implementation method according to claim 1, including the method described in claim 1.

12. Performing an action based at least partially on the cardiac contractility measurement output by the machine learning model is The computer implementation method according to claim 1, comprising providing a treatment recommendation for a patient having the mechanical circulatory support device implanted, wherein the treatment recommendation is determined at least in part on the measurement of myocardial contractility.

13. The computer implementation method according to claim 1, wherein performing an action based at least in part on the measured values ​​of cardiac contractility output by the machine learning model includes adjusting the operating conditions of the mechanical circulatory support device.

14. The computer implementation method according to claim 13, wherein adjusting the operating conditions of the mechanical circulation assist device includes adjusting the pump speed of the mechanical circulation assist device.

15. The computer implementation method according to claim 1, wherein performing an action based at least in part on the measured cardiac contractility output by the machine learning model includes determining the contractile reserve based at least in part on the measured cardiac contractility.

16. The measured cardiac contractility includes a first cardiac contractility output from the machine learning model based on a signal from the mechanical circulatory support device during a first time period, and a second cardiac contractility output from the machine learning model based on a signal from the mechanical circulatory support device during a second time period following the first time period. Determining the contractile reserve includes determining the contractile reserve based on the first and second cardiac contractility. The computer implementation method according to claim 15.

17. The computer implementation method according to claim 16, wherein determining the contractile reserve based on the first and second myocardial contractility includes determining the contractile reserve based on the difference between the first and second myocardial contractility.

18. A controller for a mechanical circulation assist device, wherein the controller comprises at least one hardware processor, The at least one hardware processor is Determining a set of features based at least partially on a set of signals received from a mechanical circulatory assist device, To provide the aforementioned set of features as input to a machine learning model trained to output measurements of cardiac contractility, The action is to be performed at least partially based on the measured values ​​of cardiac contractility output by the machine learning model. A controller configured to perform the following actions.

19. The controller according to claim 18, wherein the set of signals includes at least one pressure signal and / or at least one pump function signal.

20. The controller according to claim 19, wherein determining the set of features includes determining at least one feature using a combination of a first pressure signal of the at least one pressure signal and a first pump function signal of the at least one pump function signal.

21. The controller according to claim 20, which uses a combination of a first pressure signal of the at least one pressure signal and a first pump function signal of the at least one pump function signal, and which has a maximum rate of increase of left ventricular pressure during systole.

22. The controller according to claim 18, wherein the at least one hardware processor is further configured to determine the set of features by determining one or more per-pulse features based at least partially on the set of signals.

23. The controller according to claim 22, wherein determining one or more per-pulsation characteristics includes determining one or more of the mean pump flow rate, mean aortic pressure, left ventricular pressure at end diastole, maximum rate of increase of left ventricular pressure during systole, or mean motor current.

24. The controller according to claim 18, wherein the measured value of cardiac contractility is an estimate of the preload mobilizable stroke work index.

25. The controller according to claim 18, wherein the machine learning model comprises a feedforward dense neural network.

26. The controller according to claim 18, wherein the at least one hardware processor is configured to perform an action at least in part based on the cardiac contractility measurement output by the machine learning model by displaying an indication of the cardiac contractility measurement on a user interface associated with the mechanical circulatory assistance device.

27. The controller according to claim 26, wherein the indication of the measured value of myocardial contractility is the trend of myocardial contractility over a specific time range.

28. The at least one hardware processor is Determining a stability score for a patient in whom the mechanical circulatory support device is implanted, wherein the stability score is at least partially based on the measured value of myocardial contractility. Display the stability score on the user interface associated with the mechanical circulation assist device. The controller according to claim 18, configured to perform an action based at least in part on the measured value of cardiac contractility output by the machine learning model.

29. The controller according to claim 18, wherein the at least one hardware processor is configured to perform an action based at least partially on the myocardial contractility measurement output by the machine learning model, by providing a treatment recommendation for a patient having the mechanical circulatory support device implanted, the treatment recommendation being determined at least partially on the myocardial contractility measurement.

30. The controller according to claim 18, wherein the at least one hardware processor is configured to perform an action at least in part based on the measured cardiac contractility output by the machine learning model by adjusting the operating conditions of the mechanical circulatory support device based on the measured cardiac contractility.

31. The controller according to claim 30, wherein adjusting the operating conditions of the mechanical circulation assist device includes adjusting the pump speed of the mechanical circulation assist device.

32. The controller according to claim 18, wherein the at least one hardware processor is configured to perform an action at least partially based on the cardiac contractility measurement output by the machine learning model by determining contractile reserve at least partially based on the cardiac contractility measurement.

33. The measured cardiac contractility includes a first cardiac contractility output from the machine learning model based on a signal from the mechanical circulatory support device at a first time, and a second cardiac contractility output from the machine learning model based on a signal from the mechanical circulatory support device at a second time after the first time, Determining the contractile reserve includes determining the contractile reserve based on the first and second cardiac contractility. The controller according to claim 32.

34. The controller according to claim 33, wherein determining the contractile reserve based on the first and second myocardial contractility includes determining the contractile reserve based on the difference between the first and second myocardial contractility.

35. A cardiac pump system, wherein the cardiac pump system is A cardiac pump including at least one pressure sensor configured to sense pressure within a portion of the patient's heart, Controller and Equipped with, The aforementioned controller, Determining a set of features based at least in part on a set of signals received from the heart pump, the set of features, a first feature based on the perceived pressure, To provide the aforementioned set of features as input to a machine learning model trained to output measurements of cardiac contractility, The action is to be performed at least partially based on the measured values ​​of cardiac contractility output by the machine learning model. A cardiac pump system configured to perform the following actions.

36. The cardiac pump system according to claim 35, wherein the set of features further includes a second feature based on a signal corresponding to the operating state of the cardiac pump.

37. The first feature further relates to the heart pump system according to claim 35, based on a signal corresponding to the operating state of the heart pump.

38. The first feature is the cardiac pump system according to claim 37, which has a maximum rate of increase in left ventricular pressure during systole.

39. The cardiac pump system according to claim 36, wherein the controller is further configured to determine a set of features by determining one or more per-beat features based at least in part on the set of signals.

40. The cardiac pump system according to claim 39, wherein determining one or more per-pulsate characteristics includes determining one or more of the mean pump flow rate, mean aortic pressure, left ventricular pressure at end diastole, maximum rate of increase of left ventricular pressure during systole, or mean motor current.

41. The cardiac pump system according to claim 35, wherein the measured value of cardiac contractility is an estimate of the preload mobilizable stroke work index.

42. The cardiac pump system according to claim 35, wherein the machine learning model comprises a feedforward dense neural network.

43. The cardiac pump system further includes a display configured to show a user interface that includes a representation of one or more signals associated with the operation of the cardiac pump system, The cardiac pump system according to claim 35, wherein the controller is configured to perform an action at least partially based on the cardiac contractility measurement output by the machine learning model by displaying an indication of the cardiac contractility measurement on the user interface.

44. The cardiac pump system according to claim 43, wherein the indication of the measured cardiac contractility is the trend of cardiac contractility over a specific time range.

45. The cardiac pump system further includes a display configured to show a user interface that includes a representation of one or more signals associated with the operation of the cardiac pump system, The aforementioned controller, Determining a stability score for a patient in whom the cardiac pump is implanted, wherein the stability score is at least partially based on the measured value of myocardial contractility. Display the stability score on the user interface. The cardiac pump system according to claim 35, configured to perform an action based at least in part on the measured value of cardiac contractility output by performing the action.

46. The cardiac pump system further includes a display configured to show a user interface that includes a representation of one or more signals associated with the operation of the cardiac pump system, The aforementioned controller, The user interface provides treatment recommendations for patients with the implanted cardiac pump, wherein the treatment recommendations are determined at least in part on the measurement of myocardial contractility. The cardiac pump system according to claim 35, configured to perform an action based at least in part on the measured value of cardiac contractility output by performing the action.

47. The cardiac pump system according to claim 35, wherein the controller is configured to perform an action at least in part based on the cardiac contractility measurement output by the machine learning model by adjusting the operating conditions of the cardiac pump based on the cardiac contractility measurement.

48. The heart pump system according to claim 47, wherein adjusting the operating conditions of the heart pump includes adjusting the pump speed of the heart pump.

49. The cardiac pump system according to claim 35, wherein the controller is configured to perform an action based at least partially on the cardiac contractility measurement output by the machine learning model, by determining the contractile reserve based at least partially on the cardiac contractility measurement.

50. The measured cardiac contractility includes a first cardiac contractility output from the machine learning model based on a signal from the cardiac pump at a first time, and a second cardiac contractility output from the machine learning model based on a signal from the cardiac pump at a second time after the first time, Determining the contractile reserve includes determining the contractile reserve based on the first and second cardiac contractility. The cardiac pump system according to claim 49.

51. The cardiac pump system according to claim 50, wherein determining the contractile reserve based on the first and second myocardial contractility includes determining the contractile reserve based on the difference between the first and second myocardial contractility.

Images