Method, device and equipment for calculating left ventricular end-diastolic pressure and storage medium

Abstract

The application provides a left ventricular end-diastolic pressure calculation method, device, computer equipment and storage medium, comprising: collecting the current and outlet pressure value of a catheter pump, obtaining a heart beat cycle, an inlet pressure value, an aortic valve opening time and an aortic valve closing time; determining a heart diastolic time according to the heart beat cycle, the aortic valve opening time and the aortic valve closing time; determining a current diastolic pressure value according to the outlet pressure value; determining a left ventricular pressure minimum value according to the inlet pressure value; determining an isovolumic relaxation time constant according to the inlet pressure value and the aortic valve closing time; determining an isovolumic contraction efficiency according to the inlet pressure value and the aortic valve opening time; and calculating the left ventricular end-diastolic pressure based on the heart diastolic time, the current diastolic pressure value, the left ventricular pressure minimum value, the isovolumic relaxation time constant and the isovolumic contraction efficiency. The above method can safely and accurately predict the left ventricular end-diastolic pressure.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, and in particular to a method, apparatus, computer device, and computer-readable storage medium for calculating left ventricular end-diastolic pressure. Background Technology

[0002] Left ventricular end-diastolic pressure (LVEDP) reflects the pressure level of the left ventricle at the end of diastole and is an important indicator for assessing cardiac function. An excessively high LVEDP value may indicate left ventricular diastolic dysfunction, such as heart failure or myocardial ischemia.

[0003] Traditional methods for measuring left ventricular end-diastolic pressure (LVEDP) can be divided into invasive and non-invasive methods. Invasive measurement involves inserting a pressure sensor catheter directly into the left ventricle and then using an electrocardiogram (ECG) to determine the end-diastolic pressure of the left ventricle based on the QRS complex endpoint. Non-invasive measurement, on the other hand, achieves indirect estimation through echocardiography. However, invasive measurement may cause harm to the human body and carries a higher safety risk, while estimation using echocardiography is difficult to guarantee in terms of accuracy. Summary of the Invention

[0004] This invention provides a method, apparatus, computer device, and storage medium for calculating left ventricular end-diastolic pressure, in order to solve the technical problem that existing technologies cannot safely and accurately measure left ventricular end-diastolic pressure.

[0005] This invention provides a method for calculating left ventricular end-diastolic pressure, comprising:

[0006] The current and outlet pressure of the catheter pump were collected to obtain the cardiac cycle, inlet pressure, aortic valve opening time, and aortic valve closing time.

[0007] The diastolic time is determined based on the cardiac pulsation cycle, the aortic valve opening time, and the aortic valve closing time.

[0008] Determine the current diastolic pressure value based on the outlet pressure value;

[0009] The minimum left ventricular pressure is determined based on the inlet pressure value.

[0010] The isovolumetric relaxation time constant is determined based on the inlet pressure value and the aortic valve closure time.

[0011] The isovolumetric contraction efficiency is determined based on the inlet pressure value and the aortic valve opening time.

[0012] The left ventricular end-diastolic pressure is calculated based on the cardiac diastolic time, the current diastolic pressure value, the minimum left ventricular pressure, the isovolumetric relaxation time constant, and the isovolumetric contraction efficiency.

[0013] In one embodiment, the step of acquiring the current and outlet pressure values ​​of the catheter pump to obtain the cardiac cycle, inlet pressure value, aortic valve opening time, and aortic valve closing time includes the following steps:

[0014] Collect the outlet pressure value of the catheter pump, obtain the current heart rate, and determine the cardiac cycle based on the current heart rate;

[0015] The current of the duct pump is collected, and the pressure difference is determined based on the relationship between the pressure difference between the outlet and inlet ends of the duct pump and the current of the duct pump. The inlet pressure value is then determined based on the pressure difference.

[0016] The aortic valve opening time and aortic valve closing time are determined by the pressure values ​​at the outlet and inlet ends.

[0017] In one embodiment, determining the diastolic time of the heart based on the cardiac cycle, the aortic valve opening time, and the aortic valve closing time includes the following steps:

[0018] The systolic ejection period is determined based on the aortic valve opening time and the aortic valve closing time.

[0019] The diastolic time of the heart is determined based on the cardiac pulsation cycle and the period of systolic ejection.

[0020] In one embodiment, determining the current diastolic pressure value based on the outlet pressure value includes:

[0021] Multiple outlet pressure values ​​are acquired within one cardiac cycle;

[0022] The minimum value among the plurality of outlet pressure values ​​is determined as the current diastolic pressure value.

[0023] In one embodiment, determining the minimum left ventricular pressure based on the inlet pressure value includes:

[0024] Acquire multiple inlet pressure values ​​within one cardiac cycle;

[0025] The minimum value among the multiple inlet pressure values ​​is determined as the minimum left ventricular pressure.

[0026] In one embodiment, determining the isovolumetric relaxation time constant based on the inlet pressure value and the aortic valve closure time includes the following steps:

[0027] After the aortic valve closure time, the inlet pressure data during the first time period is acquired;

[0028] The acquired inlet pressure data is fitted using a single exponential decay function to obtain the isochoric relaxation time constant.

[0029] The inlet pressure data includes the inlet pressure value and the corresponding time. The first time period is dynamically adjusted according to the heartbeat cycle and is completely in the isovolumetric contraction period.

[0030] In one embodiment, determining the isovolumetric contraction efficiency based on the inlet pressure value and the aortic valve opening time includes the following steps:

[0031] Before the aortic valve opening time, the inlet pressure data during the second time period is acquired;

[0032] The rate of change of inlet pressure is calculated based on the inlet pressure data to obtain the isochoric shrinkage efficiency;

[0033] The inlet pressure data includes the inlet pressure value and the corresponding time. The second time period is dynamically adjusted according to the heart's pulsation cycle and is completely in the isovolumetric contraction period.

[0034] In one embodiment, the cardiac diastolic time, the current diastolic pressure value, the minimum left ventricular pressure, the isovolumetric relaxation time constant, and the isovolumetric contraction efficiency are input into a machine learning model to calculate the left ventricular end-diastolic pressure.

[0035] And / or, a fitting equation is constructed based on the cardiac diastolic time, the current diastolic pressure value, the minimum left ventricular pressure, the isovolumetric relaxation time constant, and the isovolumetric contraction efficiency to calculate the left ventricular end-diastolic pressure.

[0036] In one embodiment, the machine learning model includes a first sub-model and a second sub-model that operate in parallel.

[0037] The first sub-model is pre-trained on the first dataset, and the second sub-model is pre-trained on the second dataset. The accuracy of the pre-trained first and second sub-models is verified using bin data.

[0038] The parameters of the first dataset, the second dataset, and the bin data all include at least one of the following: cardiac diastolic time, current diastolic pressure value, minimum left ventricular pressure, isovolumetric relaxation time constant, and isovolumetric contraction efficiency.

[0039] In one embodiment, the method further includes:

[0040] When the difference between the left ventricular end-diastolic pressure output by the first sub-model and the second sub-model exceeds a preset threshold, the left ventricular end-diastolic pressure is determined to be an invalid value.

[0041] In one embodiment, the method further includes:

[0042] Acquire inlet pressure data during a preset time period prior to the aortic valve opening time;

[0043] The acquired inlet pressure data is input into the hemodynamic model to obtain the effective range of left ventricular end-diastolic pressure.

[0044] When the left ventricular end-diastolic pressure is not within the effective value range, the left ventricular end-diastolic pressure is determined to be an invalid value.

[0045] In one embodiment, the method further includes:

[0046] Obtain a reasonable pressure value; when the left ventricular end-diastolic pressure does not reach the reasonable pressure value, calculate the difference between the left ventricular end-diastolic pressure and the reasonable pressure value.

[0047] The recommended rotational speed of the duct pump is determined based on the difference.

[0048] In one embodiment, the method further includes:

[0049] The left ventricular end-diastolic pressure and recommended rotational speed that have not reached the reasonable pressure value are displayed on the interactive interface, and an abnormal prompt is also displayed on the interactive interface.

[0050] In one embodiment, the method further includes:

[0051] The speed of the catheter pump is adjusted according to the recommended speed in preset steps to adjust the left ventricular end-diastolic pressure to the reasonable pressure value.

[0052] Furthermore, this application also provides a device for calculating left ventricular end-diastolic pressure, comprising:

[0053] The data acquisition module is used to acquire the current and outlet pressure values ​​of the catheter pump, and to obtain the cardiac cycle, inlet pressure value, aortic valve opening time, and aortic valve closing time.

[0054] The diastolic time module is used to determine the cardiac diastolic time based on the cardiac pulsation cycle, the aortic valve opening time, and the aortic valve closing time.

[0055] A diastolic pressure module is used to determine the current diastolic pressure value based on the outlet pressure value.

[0056] A minimum pressure module is used to determine the minimum left ventricular pressure based on the inlet pressure value.

[0057] The relaxation time module is used to determine the isovolumetric relaxation time constant based on the inlet pressure value and the aortic valve closure time.

[0058] The contraction efficiency module is used to determine the isovolumetric contraction efficiency based on the inlet pressure value and the aortic valve opening time.

[0059] The pressure calculation module is used to calculate the left ventricular end-diastolic pressure based on the cardiac diastolic time, the current diastolic pressure value, the minimum left ventricular pressure, the isovolumetric relaxation time constant, and the isovolumetric contraction efficiency.

[0060] Furthermore, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method for calculating left ventricular end-diastolic pressure as described in any of the preceding claims.

[0061] Furthermore, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the method for calculating left ventricular end-diastolic pressure as described in any of the preceding claims.

[0062] Compared with the prior art, the technical solution of the embodiments of the present invention has the following beneficial effects:

[0063] The method, apparatus, computer equipment, and storage medium for calculating left ventricular end-diastolic pressure provided in this invention comprehensively consider the main influencing factors on left ventricular end-diastolic pressure during calculation. The influence of heart rate is determined by diastolic time, the influence of myocardial compliance and ejection resistance is determined by the current diastolic pressure value and isovolumetric contraction efficiency, and the influence of myocardial active relaxation ability is determined by the minimum left ventricular pressure and isovolumetric relaxation time constant. Thus, the calculation of left ventricular end-diastolic pressure is achieved safely and accurately. Attached Figure Description

[0064] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention, but not all embodiments. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0065] Figure 1 This is a flowchart illustrating a method for calculating left ventricular end-diastolic pressure provided in an embodiment of this application.

[0066] Figure 2 A flowchart illustrating step S110 in a method for calculating left ventricular end-diastolic pressure provided in an embodiment of this application;

[0067] Figure 3 A flowchart illustrating step S120 in a method for calculating left ventricular end-diastolic pressure provided in an embodiment of this application;

[0068] Figure 4 A flowchart illustrating step S130 in a method for calculating left ventricular end-diastolic pressure provided in an embodiment of this application;

[0069] Figure 5 A flowchart illustrating step S140 in a method for calculating left ventricular end-diastolic pressure provided in an embodiment of this application;

[0070] Figure 6 A flowchart illustrating step S150 in a method for calculating left ventricular end-diastolic pressure provided in an embodiment of this application;

[0071] Figure 7 A flowchart illustrating step S160 in a method for calculating left ventricular end-diastolic pressure provided in an embodiment of this application;

[0072] Figure 8 A flowchart illustrating a method for calculating left ventricular end-diastolic pressure, provided for another embodiment of this application;

[0073] Figure 9 A flowchart illustrating a method for calculating left ventricular end-diastolic pressure, provided for another embodiment of this application;

[0074] Figure 10 A schematic diagram of a module for calculating left ventricular end-diastolic pressure provided in an embodiment of this application;

[0075] Figure 11 A schematic diagram of a module for calculating left ventricular end-diastolic pressure provided in an embodiment of this application;

[0076] Figure 12 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0077] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0078] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0079] When used herein, the singular forms of “a,” “an,” and “the” may also include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising / including” or “having,” etc., specify the presence of the stated features, wholes, steps, operations, components, parts, or combinations thereof, but do not preclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts, or combinations thereof. Meanwhile, the term “and / or” as used in this specification includes any and all combinations of the associated listed items.

[0080] The technical solution of the present invention will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0081] In view of the problems existing in the prior art, the present invention provides a method for calculating left ventricular end-diastolic pressure, a device for calculating left ventricular end-diastolic pressure, a computer and equipment, and a computer-readable storage medium.

[0082] Figure 1 This is a flowchart illustrating a method for calculating left ventricular end-diastolic pressure according to an embodiment of the present invention. Figure 1 As shown, this embodiment of the invention provides a method for calculating left ventricular end-diastolic pressure, including:

[0083] Step S110: Collect the current and outlet pressure values ​​of the catheter pump to obtain the cardiac pulsation cycle, inlet pressure value, aortic valve opening time, and aortic valve closing time.

[0084] Specifically, this embodiment calculates left ventricular end-diastolic pressure (LVEDP) based on a left ventricular catheter pump. First, it is necessary to obtain the relevant data required for the calculation, such as the current data of the catheter pump and the pressure signal of the target area (aorta) at the outlet of the catheter pump. This allows us to determine the time of a single heartbeat cycle, the pressure at the inlet of the catheter pump (left ventricle), and information such as the aortic valve opening time and aortic valve closing time.

[0085] Furthermore, Figure 11 A schematic diagram of a module for calculating left ventricular end-diastolic pressure provided in an embodiment of this application is shown below. Figure 11 As shown, the left ventricular end-diastolic pressure calculation system can communicate with the catheter pump to acquire data and control the pump. The data is acquired through the data acquisition and preprocessing module of the left ventricular end-diastolic pressure calculation system. Firstly, based on the catheter pump current data and the pressure signal at the outlet target region (aorta), the duration of a single cardiac cycle, the inlet pressure (left ventricle), and the aortic valve opening and closing times can be estimated.

[0086] Step S120: Determine the diastolic time of the heart based on the heartbeat cycle, aortic valve opening time, and aortic valve closing time.

[0087] Step S130: Determine the current diastolic pressure value based on the outlet pressure value.

[0088] Step S140: Determine the minimum left ventricular pressure based on the inlet pressure value.

[0089] Step S150: Determine the isovolumetric relaxation time constant based on the inlet pressure value and aortic valve closure time.

[0090] Step S160: Determine the isovolumetric contraction efficiency based on the inlet pressure value and the aortic valve opening time.

[0091] Specifically, theoretically, after determining the pressure value at the inlet (left ventricle), the LVEDP value can be estimated through curve characteristics, falling within the atrial systole (AS) and isovolumetric contraction (IVCP) phases. However, in practical applications, using existing acquisition frequencies and catheter pump current accuracy, there is a high probability that the LVEDP value cannot be estimated. In the corresponding region, it will appear as an upward curve, failing to capture subtle fluctuations, especially at high heart rates, where estimation becomes even more difficult. Therefore, a comprehensive consideration of factors affecting LVEDP is necessary for accurate calculation.

[0092] LVEDP is mainly influenced by three factors: myocardial active relaxation capacity, myocardial compliance and ejection resistance, and heart rate. Among these, the isovolumetric relaxation time constant is used. and minimum left ventricular pressure (LV) min The active relaxation capacity of the myocardium is characterized by isovolumetric contraction efficiency and current diastolic pressure (DP) to represent myocardial compliance and ejection resistance, and diastolic time to represent heart rate. The catheter pump can acquire signals of pressure and current; pressure is obtained from a fiber optic pressure sensor, and current is obtained from the pump's motor. Therefore, the active relaxation capacity of the myocardium, myocardial compliance, ejection resistance, and heart rate are indirectly assessed through the pressure and current of the catheter pump, thereby predicting LVEDP.

[0093] Furthermore, the above-mentioned influencing factors can be calculated using the data acquisition and preprocessing module and the cardiac output calculation module of the left ventricular end-diastolic pressure calculation system. The diastolic time is confirmed by the time of a single heartbeat cycle and the opening and closing time of the aortic valve. The current diastolic pressure is confirmed by the pressure signal of the target area (aorta). The minimum left ventricular pressure is confirmed by the pressure at the inlet end (left ventricle). The isovolumetric relaxation time constant is confirmed by the pressure at the inlet end (left ventricle) and the aortic valve closing time. The isovolumetric contraction efficiency is confirmed by the pressure at the inlet end (left ventricle) and the aortic valve opening time.

[0094] Step S170: Calculate the left ventricular end-diastolic pressure based on cardiac diastolic time, current diastolic pressure value, minimum left ventricular pressure, isovolumetric relaxation time constant, and isovolumetric contraction efficiency.

[0095] Specifically, after determining the main computational parameters affecting LVEDP, left ventricular end-diastolic pressure can be calculated based on these parameters using machine learning models or fitting equations. The LVEDP estimation module of the left ventricular end-diastolic pressure calculation system can include a pre-trained machine learning model. Inputting the aforementioned parameters into this model can predict LVEDP. Alternatively, the LVEDP estimation module can also include other kinetic models, combining machine learning models with kinetic models for LVEDP prediction. Alternatively, the LVEDP estimation module can also construct fitting equations based on the aforementioned parameters to predict LVEDP.

[0096] In summary, the method for calculating left ventricular end-diastolic pressure provided in this embodiment of the invention comprehensively considers the main influencing factors on left ventricular end-diastolic pressure during calculation. It determines the influence of heart rate through diastolic time, determines the influence of myocardial compliance and ejection resistance through the current diastolic pressure value and isovolumetric contraction efficiency, and determines the influence of myocardial active relaxation ability through the minimum left ventricular pressure and isovolumetric relaxation time constant. Thus, it safely and accurately calculates left ventricular end-diastolic pressure.

[0097] Figure 2 A flowchart illustrating step S110 in a method for calculating left ventricular end-diastolic pressure provided in this application embodiment is shown below. Figure 2 As shown, in one embodiment, step S110 may include:

[0098] Step S111: Collect the outlet pressure value of the catheter pump, obtain the current heart rate, and determine the cardiac cycle based on the current heart rate.

[0099] Step S112: Collect the current of the duct pump, determine the pressure difference based on the relationship between the pressure difference between the outlet and inlet ends of the duct pump and the current of the duct pump, and determine the inlet pressure value based on the pressure difference.

[0100] Step S113: Determine the aortic valve opening time and aortic valve closing time using the outlet pressure value and the inlet pressure value.

[0101] Specifically, when acquiring parameters such as the cardiac pulsation cycle, inlet pressure value, aortic valve opening time, and aortic valve closing time, the heart rate can be determined by collecting the pressure value at the outlet end (aorta) of the catheter pump, thereby determining the time of a single cardiac pulsation cycle. Then, the pressure value at the inlet end (left ventricle) can be fitted using the catheter pump current and the outlet end (aorta) pressure value. Finally, the opening and closing times of the aortic valve can be obtained by using the outlet and inlet pressures.

[0102] Figure 3 A flowchart illustrating step S120 in a method for calculating left ventricular end-diastolic pressure provided in this application embodiment is shown below. Figure 3 As shown, in one embodiment, step S120 may include:

[0103] Step S121: Determine the systolic ejection period based on the aortic valve opening time and aortic valve closing time.

[0104] Step S122: Determine the diastolic time of the heart based on the heart's pulsating cycle and the period of systolic ejection.

[0105] Specifically, when determining the diastolic time, the systolic ejection period (SEP) can be determined by using the aortic valve opening time (AVO time) and closing time (AVC time) obtained in step S110. Then, the SEP time is calculated by subtracting the SEP time T from the time T of a single cardiac cycle. SEP Confirm the diastolic time T Dia .

[0106] Figure 4 A flowchart illustrating step S130 in a method for calculating left ventricular end-diastolic pressure provided in this application embodiment is shown below. Figure 4 As shown, in one embodiment, step S130 may include:

[0107] Step S131: Acquire multiple outlet pressure values ​​within one cardiac cycle.

[0108] Step S132: Determine the minimum value among multiple outlet pressure values ​​as the current diastolic pressure value.

[0109] Specifically, when determining the current diastolic pressure value, a series of pressure values ​​at the outlet (aorta) can be collected within the time T of a single cardiac cycle, denoted as AOP1, AOP2…AOP. n Take the minimum value among them (AOP) min , denoted as the current diastolic blood pressure DP.

[0110] Figure 5 A flowchart illustrating step S140 in a method for calculating left ventricular end-diastolic pressure provided in this application embodiment is shown below. Figure 5 As shown, in one embodiment, step S140 may include:

[0111] Step S141: Acquire multiple inlet pressure values ​​within one cardiac cycle.

[0112] Step S142: Determine the minimum value among the multiple inlet pressure values ​​as the minimum left ventricular pressure.

[0113] Specifically, when determining the minimum left ventricular pressure, a series of pressure values ​​at the inlet (left ventricle) can be estimated within the time T of a single cardiac cycle, denoted as LVP1, LVP2…LVP. n Take the minimum value LV. min This is recorded as the minimum left ventricular pressure.

[0114] Figure 6 A flowchart illustrating step S150 in a method for calculating left ventricular end-diastolic pressure provided in this application embodiment is shown below. Figure 6As shown, in one embodiment, step S150 may include:

[0115] Step S151: After the aortic valve closure time, acquire the inlet pressure data during the first time period.

[0116] Step S152: Fit the obtained inlet pressure data using a single exponential decay function to obtain the isochoric relaxation time constant.

[0117] Specifically, when determining the isovolumetric relaxation time constant, the inlet pressure data is first acquired during the first time interval. This data includes the inlet pressure value and its corresponding time. The first time interval is dynamically adjusted according to the cardiac cycle and is entirely within the isovolumetric contraction phase. At the aortic valve closure time, i.e., T... AVC Subsequently, the pressure value at the inlet (left ventricle) and the corresponding time are captured during the first time period. The capture time is approximately tens of milliseconds and is dynamically adjusted according to the time T of the heartbeat cycle to ensure that it is completely in the isovolumetric relaxation period. Then, the isovolumetric relaxation time constant is determined using a single exponential decay function. .

[0118] Figure 7 A flowchart illustrating step S160 in a method for calculating left ventricular end-diastolic pressure provided in this application embodiment is shown below. Figure 7 As shown, in one embodiment, step S160 may include:

[0119] Step S161: Before the aortic valve opening time, acquire the inlet pressure data during the second time period.

[0120] Step S162: Calculate the rate of change of inlet pressure value based on the inlet pressure value data to obtain the isochoric shrinkage efficiency.

[0121] Specifically, in determining the isovolumetric contraction efficiency, the inlet pressure data for the second time period is first acquired. This data includes the inlet pressure value and its corresponding time. The second time period is dynamically adjusted according to the cardiac cycle and is entirely within the isovolumetric contraction phase. This is done at the aortic valve opening time, i.e., T... AVO Beforehand, the pressure value at the inlet (left ventricle) and the corresponding time are intercepted during the second time period. The interception time is approximately tens of milliseconds and is dynamically adjusted with the time T of the heartbeat cycle to ensure that it is completely in the isovolumetric contraction period. The isovolumetric contraction efficiency Eff is characterized by the characterization function ΔP / Δt.

[0122] In one embodiment, step S170 above may include:

[0123] The heart's diastolic time, current diastolic pressure value, minimum left ventricular pressure, isovolumetric relaxation time constant, and isovolumetric contraction efficiency are input into the machine learning model to calculate the left ventricular end-diastolic pressure.

[0124] Specifically, the aforementioned machine learning model is pre-trained. The machine learning model is established using confirmed parameters and trained using existing data. The training dataset and bin dataset can be obtained from simulation platforms, animal experiments, and clinical data. The dataset must cover the required parameters, including diastolic time, diastolic pressure, minimum left ventricular pressure, isovolumetric relaxation time constant, isovolumetric contraction efficiency, and target parameters (LVEDP).

[0125] During the training process of the aforementioned machine learning model, it is also necessary to set hyperparameters to control the model's behavior and performance, which may include the learning rate, number of iterations, and number of neurons. The dataset size should be kept consistent, with bins used to validate the model's training effectiveness. The machine learning model is considered accurate if the error between its predicted parameters and the target parameters is within a preset error threshold; otherwise, it is considered a prediction error. The accuracy of the prediction results from the trained machine learning model must all exceed the preset accuracy threshold.

[0126] In one embodiment, the machine learning model includes two parallel sub-models: a first sub-model and a second sub-model. The first sub-model is pre-trained on a first dataset, and the second sub-model is pre-trained on a second dataset. The accuracy of the pre-trained first and second sub-models is verified using bin data. The parameters of the first dataset, the second dataset, and the bin data all include at least one of cardiac diastolic time, current diastolic pressure value, minimum left ventricular pressure, isovolumetric relaxation time constant, and isovolumetric contraction efficiency.

[0127] Specifically, two machine learning models are used together for LVEDP prediction. The dataset 1 used to train the first sub-model and the dataset 2 used to train the second sub-model have the same data size. After training, the prediction accuracy of both the first and second sub-models must reach a preset accuracy threshold. Using a dual-model approach allows for mutual validation, effectively improving the reliability of the prediction algorithm.

[0128] In one embodiment, the above method further includes:

[0129] When the difference between the left ventricular end-diastolic pressure output by the first sub-model and the second sub-model exceeds a preset threshold, the left ventricular end-diastolic pressure is determined to be an invalid value.

[0130] Specifically, in practical applications, two sub-models can be used in parallel for LVEDP prediction. If the prediction results of the two sub-models differ by more than a preset threshold, it is considered that the model prediction is incorrect and is judged as invalid to filter out erroneous data. Since the accuracy of both sub-models meets the preset requirements, the probability of both sub-models failing simultaneously is extremely low, meeting the reliability standards.

[0131] In one embodiment, step S170 above may include:

[0132] A fitting equation was constructed based on cardiac diastolic time, current diastolic pressure, minimum left ventricular pressure, isovolumetric relaxation time constant, and isovolumetric contraction efficiency to calculate the left ventricular end-diastolic pressure.

[0133] Specifically, LVEDP can be calculated by creating linear or exponential fitting equations using the aforementioned calculation parameters. When using a linear fitting equation, it can be based on the cardiac diastolic time T. Dia Current diastolic pressure (DP) and minimum left ventricular pressure (LV) min Isochoric relaxation time constant The isochoric shrinkage efficiency Eff is used to construct the following equation:

[0134] .

[0135] Wherein, K1, K2, K3, and C are correction parameters, and the isochoric shrinkage efficiency Eff is characterized by the characterization function ΔP / Δt. The dimension of C is pressure. Based on the above linear fitting equation and the determined calculation parameters, LVEDP is calculated.

[0136] When using an exponential fitting equation, it can be based on the cardiac diastolic time T. Dia Current diastolic pressure (DP), minimum left ventricular pressure (LVmin), and isovolumetric relaxation time constant. The isochoric shrinkage efficiency Eff is used to construct the following equation:

[0137] .

[0138] Where α and β are correction parameters, and the isochoric shrinkage efficiency Eff is characterized by the characterization function ΔP / Δt. Based on the above linear fitting equation and the determined calculation parameters, LVEDP is calculated.

[0139] Figure 8 A flowchart illustrating a method for calculating left ventricular end-diastolic pressure, as provided in another embodiment of this application, is shown below. Figure 8 As shown, in one embodiment, the method for calculating the left ventricular end-diastolic pressure may further include:

[0140] Step S181: Obtain inlet pressure data within a preset time period before the aortic valve opening time.

[0141] Step S182: Input the acquired inlet pressure data into the hemodynamic model to obtain the effective range of left ventricular end-diastolic pressure.

[0142] Step S183: When the left ventricular end-diastolic pressure is not within the valid range, the left ventricular end-diastolic pressure is determined to be an invalid value.

[0143] Specifically, the LVEDP estimation module of the left ventricular end-diastolic pressure calculation system also includes a hemodynamic model. This model allows for the validation of the machine learning model's predictions, further enhancing the overall reliability of the module. The hemodynamic model is optional; it is based on inlet (left ventricle) pressure data, capturing pressure data from a period before aortic valve opening to assess the effective range of LVEDP. If the machine learning model's prediction falls outside this effective range, the prediction is considered unreliable and thus invalid.

[0144] Figure 9 A flowchart illustrating a method for calculating left ventricular end-diastolic pressure, as provided in another embodiment of this application, is shown below. Figure 9 As shown, in one embodiment, the method for calculating the left ventricular end-diastolic pressure may further include:

[0145] Step S191: Obtain a reasonable pressure value. When the left ventricular end-diastolic pressure does not reach the reasonable pressure value, calculate the difference between the left ventricular end-diastolic pressure and the reasonable pressure value.

[0146] Step S192: Determine the recommended speed of the duct pump based on the difference.

[0147] Specifically, optimizing the pump rate of the left ventricular catheter pump is a key factor affecting LVEDP (Left Ventricular Effusion Diagnosis). Both excessively high and low pump rates can impair hemodynamics. If the pump speed is too low, insufficient flow will result in inadequate left ventricular unloading, preventing effective reduction of LVEDP and potentially exacerbating blood stasis and thrombosis risks. Conversely, excessively high pump speed can lead to over-pumping, causing left ventricular collapse and arrhythmias, thus increasing the risk of LVEDP fluctuations. Therefore, by analyzing the predicted LVEDP value, a recommended pump rate can be calculated, allowing for fine-tuning of the pump rate to bring the LVEDP value within a reasonable range.

[0148] In one embodiment, after step S192, the above method may further include:

[0149] Step S193: Display the left ventricular end-diastolic pressure and suggested rotation speed that have not reached a reasonable pressure value on the interactive interface, and output an abnormal prompt on the interactive interface.

[0150] Specifically, after determining the recommended rotational speed of the catheter pump, this speed can be provided on the interactive interface, allowing medical staff to choose whether to adjust it to the recommended speed. The left ventricular end-diastolic pressure calculation system includes an interactive interface that displays the recommended rotational speed and adjustment method. Users can choose to adjust manually, selecting the appropriate speed level based on the actual patient's condition. When the algorithm predicts an excessively high LVEDP value, the corresponding data will be turned red and an anomaly warning will be displayed. Users can then manually adjust to the recommended speed or take other external measures. Retaining manual speed adjustment allows users (medical staff) to retain the right to make decisions, combining the system's output data with monitoring results from external systems to choose a more appropriate treatment plan.

[0151] In one embodiment, after step S192, the above method may further include:

[0152] Step S194: Adjust the speed of the catheter pump according to the recommended speed and the preset step size to adjust the left ventricular end-diastolic pressure to a reasonable pressure value.

[0153] Specifically, in addition to displaying a suggested rotational speed for manual adjustment, the system can also automatically adjust the catheter pump speed based on the suggested speed. When automatic adjustment is selected, the user cannot select the rotational speed level; the calculation of left ventricular end-diastolic pressure (LVEDP) will adjust the catheter pump speed based on the predicted LVEDP value until the LVEDP value reaches a reasonable range. The LVEDP calculation system includes a catheter pump drive module that controls the catheter pump motor. Specifically, it dynamically and steadily adjusts the catheter pump speed using a preset step size, which can be determined according to actual adjustment needs; for example, a preset step size of 50 RPM can be selected.

[0154] This application also provides a device for calculating left ventricular end-diastolic pressure. Figure 10 This is a schematic diagram of a module for calculating left ventricular end-diastolic pressure, provided as an embodiment of this application. Figure 10As shown, the left ventricular end-diastolic pressure calculation device 200 includes: an acquisition module 210 for acquiring the current and outlet pressure value of the catheter pump, and acquiring the cardiac pulsation cycle, inlet pressure value, aortic valve opening time, and aortic valve closing time; a diastolic time module 220 for determining the cardiac diastolic time based on the cardiac pulsation cycle, aortic valve opening time, and aortic valve closing time; a diastolic pressure module 230 for determining the current diastolic pressure value based on the outlet pressure value; a minimum pressure module 240 for determining the minimum left ventricular pressure based on the inlet pressure value; a relaxation time module 250 for determining the isovolumetric relaxation time constant based on the inlet pressure value and aortic valve closing time; a systolic efficiency module 260 for determining the isovolumetric contraction efficiency based on the inlet pressure value and aortic valve opening time; and a pressure calculation module 270 for calculating the left ventricular end-diastolic pressure based on the cardiac diastolic time, the current diastolic pressure value, the minimum left ventricular pressure, the isovolumetric relaxation time constant, and the isovolumetric contraction efficiency.

[0155] In summary, the embodiments of the present invention provide a device for calculating left ventricular end-diastolic pressure.

[0156] It is understood that the left ventricular end-diastolic pressure calculation device of this embodiment can also be used to implement the left ventricular end-diastolic pressure calculation method in any of the above embodiments, and has corresponding functional modules.

[0157] Furthermore, this application also provides a computer device, Figure 12 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of this application. Figure 12 As shown, the computer device includes at least one processor and a memory communicatively connected to the at least one processor. The memory stores a computer program, and when the processor executes the computer program, it implements the steps of the method for calculating left ventricular end-diastolic pressure in any of the above embodiments.

[0158] In one embodiment of this application, when the processor executes the computer program, it can: acquire the current and outlet pressure value of the catheter pump; obtain the cardiac pulsation cycle, inlet pressure value, aortic valve opening time, and aortic valve closing time; determine the cardiac diastolic time based on the cardiac pulsation cycle, aortic valve opening time, and aortic valve closing time; determine the current diastolic pressure value based on the outlet pressure value; determine the minimum left ventricular pressure based on the inlet pressure value; determine the isovolumetric relaxation time constant based on the inlet pressure value and aortic valve closing time; determine the isovolumetric contraction efficiency based on the inlet pressure value and aortic valve opening time; and calculate the left ventricular end-diastolic pressure based on the cardiac diastolic time, current diastolic pressure value, minimum left ventricular pressure, isovolumetric relaxation time constant, and isovolumetric contraction efficiency.

[0159] Furthermore, this application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method for calculating left ventricular end-diastolic pressure in any of the above embodiments.

[0160] In one embodiment of this application, when the above-mentioned computer program is executed by a processor, it can: acquire the current and outlet pressure value of the catheter pump; obtain the cardiac pulsation cycle, inlet pressure value, aortic valve opening time, and aortic valve closing time; determine the cardiac diastolic time based on the cardiac pulsation cycle, aortic valve opening time, and aortic valve closing time; determine the current diastolic pressure value based on the outlet pressure value; determine the minimum left ventricular pressure based on the inlet pressure value; determine the isovolumetric relaxation time constant based on the inlet pressure value and aortic valve closing time; determine the isovolumetric contraction efficiency based on the inlet pressure value and aortic valve opening time; and calculate the left ventricular end-diastolic pressure based on the cardiac diastolic time, current diastolic pressure value, minimum left ventricular pressure, isovolumetric relaxation time constant, and isovolumetric contraction efficiency.

[0161] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and medium embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the description of the method embodiments.

[0162] The foregoing has described specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0163] The devices and media provided in this application are one-to-one with the methods. Therefore, the devices and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0164] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0165] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0166] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0167] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0168] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0169] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0170] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0171] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0172] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0173] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these modifications and improvements all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for calculating left ventricular end-diastolic pressure, characterized in that, Includes the following steps: The current and outlet pressure of the catheter pump were collected to obtain the cardiac cycle, inlet pressure, aortic valve opening time, and aortic valve closing time. The diastolic time is determined based on the cardiac pulsation cycle, the aortic valve opening time, and the aortic valve closing time. Determine the current diastolic pressure value based on the outlet pressure value; The minimum left ventricular pressure is determined based on the inlet pressure value. The isovolumetric relaxation time constant is determined based on the inlet pressure value and the aortic valve closure time. Determining the isovolumetric contraction efficiency based on the inlet pressure value and the aortic valve opening time includes the following steps: acquiring inlet pressure value data during a second time period before the aortic valve opening time; calculating the inlet pressure value change rate based on the inlet pressure value data to obtain the isovolumetric contraction efficiency; wherein, the inlet pressure value data includes the inlet pressure value and the corresponding time, and the second time period is dynamically adjusted according to the cardiac cycle and is completely in the isovolumetric contraction period; The left ventricular end-diastolic pressure is calculated based on the cardiac diastolic time, the current diastolic pressure value, the minimum left ventricular pressure, the isovolumetric relaxation time constant, and the isovolumetric contraction efficiency.

2. The method for calculating left ventricular end-diastolic pressure as described in claim 1, characterized in that, The process of acquiring the current and outlet pressure values ​​of the catheter pump to obtain the cardiac cycle, inlet pressure value, aortic valve opening time, and aortic valve closing time includes the following steps: Collect the outlet pressure value of the catheter pump, obtain the current heart rate, and determine the cardiac cycle based on the current heart rate; The current of the duct pump is collected, and the pressure difference is determined based on the relationship between the pressure difference between the outlet and inlet ends of the duct pump and the current of the duct pump. The inlet pressure value is then determined based on the pressure difference. The aortic valve opening time and aortic valve closing time are determined by the pressure values ​​at the outlet and inlet ends.

3. The method for calculating left ventricular end-diastolic pressure as described in claim 1, characterized in that, Determining the diastolic time of the heart based on the cardiac cycle, the aortic valve opening time, and the aortic valve closing time includes the following steps: The systolic ejection period is determined based on the aortic valve opening time and the aortic valve closing time. The diastolic time of the heart is determined based on the cardiac pulsation cycle and the period of systolic ejection.

4. The method for calculating left ventricular end-diastolic pressure as described in claim 1, characterized in that, Determining the current diastolic pressure value based on the outlet pressure value includes: Multiple outlet pressure values ​​are acquired within one cardiac cycle; The minimum value among the plurality of outlet pressure values ​​is determined as the current diastolic pressure value.

5. The method for calculating left ventricular end-diastolic pressure as described in claim 1, characterized in that, Determining the minimum left ventricular pressure based on the inlet pressure value includes: Acquire multiple inlet pressure values ​​within one cardiac cycle; The minimum value among the multiple inlet pressure values ​​is determined as the minimum left ventricular pressure.

6. The method for calculating left ventricular end-diastolic pressure as described in claim 1, characterized in that, The step of determining the isovolumetric relaxation time constant based on the inlet pressure value and the aortic valve closure time includes the following steps: After the aortic valve closure time, the inlet pressure data during the first time period is acquired; The acquired inlet pressure data is fitted using a single exponential decay function to obtain the isochoric relaxation time constant. The inlet pressure data includes the inlet pressure value and the corresponding time. The first time period is dynamically adjusted according to the heartbeat cycle and is completely in the isovolumetric contraction period.

7. The method for calculating left ventricular end-diastolic pressure as described in claim 1, characterized in that, The calculation of left ventricular end-diastolic pressure based on the cardiac diastolic time, the current diastolic pressure value, the minimum left ventricular pressure, the isovolumetric relaxation time constant, and the isovolumetric contraction efficiency includes: The cardiac diastolic time, the current diastolic pressure value, the minimum left ventricular pressure, the isovolumetric relaxation time constant, and the isovolumetric contraction efficiency are input into a machine learning model to calculate the left ventricular end-diastolic pressure. And / or, a fitting equation is constructed based on the cardiac diastolic time, the current diastolic pressure value, the minimum left ventricular pressure, the isovolumetric relaxation time constant, and the isovolumetric contraction efficiency to calculate the left ventricular end-diastolic pressure.

8. The method for calculating left ventricular end-diastolic pressure as described in claim 7, characterized in that, The machine learning model includes two parallel sub-models: a first sub-model and a second sub-model. The first sub-model is pre-trained on a first dataset, and the second sub-model is pre-trained on a second dataset. The accuracy of the pre-trained first and second sub-models is verified using bin data. The parameters of the first dataset, the second dataset, and the bin data all include at least one of the following: cardiac diastolic time, current diastolic pressure value, minimum left ventricular pressure, isovolumetric relaxation time constant, and isovolumetric contraction efficiency.

9. The method for calculating left ventricular end-diastolic pressure as described in claim 8, characterized in that, The method further includes: When the difference between the left ventricular end-diastolic pressure output by the first sub-model and the second sub-model exceeds a preset threshold, the left ventricular end-diastolic pressure is determined to be an invalid value.

10. The method for calculating left ventricular end-diastolic pressure as described in claim 1, characterized in that, The method further includes: Acquire inlet pressure data during a preset time period prior to the aortic valve opening time; The acquired inlet pressure data is input into the hemodynamic model to obtain the effective range of left ventricular end-diastolic pressure. When the left ventricular end-diastolic pressure is not within the effective value range, the left ventricular end-diastolic pressure is determined to be an invalid value.

11. The method for calculating left ventricular end-diastolic pressure as described in claim 1, characterized in that, The method further includes: Obtain a reasonable pressure value; when the left ventricular end-diastolic pressure does not reach the reasonable pressure value, calculate the difference between the left ventricular end-diastolic pressure and the reasonable pressure value. The recommended rotational speed of the duct pump is determined based on the difference.

12. The method for calculating left ventricular end-diastolic pressure as described in claim 11, characterized in that, The method further includes: The left ventricular end-diastolic pressure and recommended rotational speed that have not reached the reasonable pressure value are displayed on the interactive interface, and an abnormal prompt is also displayed on the interactive interface.

13. The method for calculating left ventricular end-diastolic pressure as described in claim 11, characterized in that, The method further includes: The speed of the catheter pump is adjusted according to the recommended speed in preset steps to adjust the left ventricular end-diastolic pressure to the reasonable pressure value.

14. A device for calculating left ventricular end-diastolic pressure, characterized in that, include: The data acquisition module is used to acquire the current and outlet pressure values ​​of the catheter pump, and to obtain the cardiac cycle, inlet pressure value, aortic valve opening time, and aortic valve closing time. The diastolic time module is used to determine the cardiac diastolic time based on the cardiac pulsation cycle, the aortic valve opening time, and the aortic valve closing time. A diastolic pressure module is used to determine the current diastolic pressure value based on the outlet pressure value. A minimum pressure module is used to determine the minimum left ventricular pressure based on the inlet pressure value. The relaxation time module is used to determine the isovolumetric relaxation time constant based on the inlet pressure value and the aortic valve closure time. The contraction efficiency module is used to determine the isovolumetric contraction efficiency based on the inlet pressure value and the aortic valve opening time; wherein, before the aortic valve opening time, the inlet pressure value data is acquired during a second time period; the inlet pressure value change rate is calculated based on the inlet pressure value data to obtain the isovolumetric contraction efficiency; wherein, the inlet pressure value data includes the inlet pressure value and the corresponding time, and the second time period is dynamically adjusted according to the cardiac cycle and is completely in the isovolumetric contraction period; The pressure calculation module is used to calculate the left ventricular end-diastolic pressure based on the cardiac diastolic time, the current diastolic pressure value, the minimum left ventricular pressure, the isovolumetric relaxation time constant, and the isovolumetric contraction efficiency.

15. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method for calculating left ventricular end-diastolic pressure as described in any one of claims 1 to 13.

16. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for calculating left ventricular end-diastolic pressure as described in any one of claims 1 to 13.

Images