CN116370815B

CN116370815B - IABP balloon inflation time prediction method and device

Info

Publication number: CN116370815B
Application number: CN202310660869.8A
Authority: CN
Inventors: 王平; 解尧; 周波; 陈宏凯; 李剑; 黄继然; 杨秋实; 刘伟; 汪卫
Original assignee: Anhui Tongling Bionic Technology Co Ltd
Current assignee: Anhui Tongling Bionic Technology Co Ltd
Priority date: 2023-06-06
Filing date: 2023-06-06
Publication date: 2023-08-11
Anticipated expiration: 2043-06-06
Also published as: CN116370815A

Abstract

The embodiment of the invention provides a method and a device for predicting inflation time of an IABP balloon, and relates to the technical field of medical instruments, wherein the method comprises the following steps: for each historical cardiac cycle, acquiring a first pressure characteristic representing the variation trend of the aortic pressure in the historical cardiac cycle, predicting the first duration of a target duration item of the historical cardiac cycle based on the first pressure characteristic, and predicting the second duration of the target duration item of the historical cardiac cycle based on the time interval of the historical cardiac cycle; predicting a third duration of a target duration item of the current cardiac cycle based on the predicted first duration and second duration corresponding to each historical cardiac cycle; and extracting a second pressure characteristic representing the variation trend of the aortic pressure in the current cardiac cycle, and predicting the balloon inflation moment of the current cardiac cycle based on the second pressure characteristic and the third duration. By applying the scheme provided by the embodiment, the accuracy of balloon inflation time prediction can be improved.

Description

IABP balloon inflation time prediction method and device

Technical Field

The invention relates to the technical field of medical equipment, in particular to a method and a device for predicting inflation time of an IABP balloon.

Background

The IABP (Intra-aortic balloon counterpulsation) technique is an auxiliary support method for supporting cardiac function and improving hemodynamics. The IABP controller needs to rapidly inflate and deflate the IABP balloon at a specific time in the cardiac cycle. How to accurately predict the inflation time of an IABP balloon is a need to be addressed.

Disclosure of Invention

The embodiment of the invention aims to provide a method and a device for predicting the inflation time of an IABP balloon, so as to accurately predict the inflation time of the IABP balloon. The specific technical scheme is as follows:

in a first aspect, an embodiment of the present invention provides a method for predicting inflation time of an IABP balloon, where the method includes:

for each historical cardiac cycle, acquiring a first pressure characteristic representing the variation trend of the aortic pressure in the historical cardiac cycle, predicting the first duration of a target duration item of the historical cardiac cycle based on the first pressure characteristic, and predicting the second duration of the target duration item of the historical cardiac cycle based on the time interval of the historical cardiac cycle; wherein the historical cardiac cycle is: adjacent continuous preset number of cardiac cycles before the current cardiac cycle, wherein the target duration item represents a time interval parameter item between a heart contraction peak time and a heart relaxation starting time in the cardiac cycle;

Predicting a third duration of a target duration item of the current cardiac cycle based on the predicted first duration and second duration corresponding to each historical cardiac cycle;

and extracting a second pressure characteristic representing the variation trend of the aortic pressure in the current cardiac cycle, and predicting the balloon inflation moment of the current cardiac cycle based on the second pressure characteristic and the third duration.

In one embodiment of the present invention, predicting the third duration of the target duration item of the current cardiac cycle based on the predicted first duration and the predicted second duration corresponding to each historical cardiac cycle includes:

acquiring a first time length characteristic representing a change trend of a second time length corresponding to each historical cardiac cycle, and adjusting the first time length corresponding to each historical cardiac cycle based on the determined first time length characteristic;

based on the adjusted first time length of each historical cardiac cycle, a third time length of a target time length item of the current cardiac cycle is predicted.

In one embodiment of the present invention, before the predicting the third duration of the target duration item of the current cardiac cycle based on the adjusted first duration of each historical cardiac cycle, the method includes:

acquiring a second time length feature representing the change trend of the first time length corresponding to each historical cardiac cycle, and adjusting the second time length corresponding to each historical cardiac cycle based on the determined second time length feature;

The predicting the third duration of the target duration item of the current cardiac cycle based on the first duration adjusted by each historical cardiac cycle includes:

and predicting a third duration of the target duration item of the current cardiac cycle based on the adjusted first duration and second duration of each historical cardiac cycle.

In one embodiment of the present invention, after the acquiring, for each historical cardiac cycle, a first pressure characteristic that characterizes a trend of aortic pressure variation in the historical cardiac cycle, predicting a first duration of a target duration item of the historical cardiac cycle based on the first pressure characteristic, and predicting a second duration of the target duration item of the historical cardiac cycle based on a time interval of the historical cardiac cycle, the method further includes:

calculating the correlation degree between the first time length and the second time length corresponding to each historical cardiac cycle, and determining a target cardiac cycle, wherein the correlation degree corresponding to the historical cardiac cycle is greater than a preset correlation degree threshold value;

the predicting the third duration of the target duration item of the current cardiac cycle based on the predicted first duration and the predicted second duration corresponding to each historical cardiac cycle includes:

and predicting a third duration of the target duration item of the current cardiac cycle based on the determined first duration and second duration corresponding to the target cardiac cycle.

In one embodiment of the present invention, predicting the balloon inflation time of the current cardiac cycle based on the second pressure characteristic and the third duration includes:

determining a time of a heart contraction peak value in the current cardiac cycle, which is characterized by the second pressure characteristic, as a starting time, and acquiring a time range of the starting time extending backwards for a third duration; determining a target moment which characterizes the beginning of the diastole of the heart in the current cardiac cycle in the second pressure characteristic, and judging whether the target moment which characterizes the beginning of the diastole of the heart in the current cardiac cycle exists in the acquired time range or not based on the second pressure characteristic;

if the balloon inflation time exists, determining the target time as the balloon inflation time;

if not, the balloon inflation time of the current cardiac cycle is predicted based on the acquired time range.

In one embodiment of the present invention, predicting the second duration of the target duration item of the historical cardiac cycle based on the time interval of the historical cardiac cycle includes:

predicting a second duration for each historical cardiac cycle as follows:

calculating the heart rate of the target object corresponding to the historical cardiac cycle based on the time interval of the historical cardiac cycle;

Based on the calculated heart rate, a second duration of the target duration item of the historical cardiac cycle is predicted.

In one embodiment of the present invention, predicting the second duration of the target duration term of the historical cardiac cycle based on the calculated heart rate includes:

calculating the second time period according to the following expression:

；

wherein R represents the heart rate,representing a second duration, +.>、/>、/>、/>、/>、/>、/>、/>Are all preset coefficients.

In a second aspect, an embodiment of the present invention provides an apparatus for predicting inflation time of an IABP balloon, including:

the first time length prediction module is used for acquiring a first pressure characteristic representing the change trend of the aortic pressure in each historical cardiac cycle, predicting the first time length of a target time length item of the historical cardiac cycle based on the first pressure characteristic, and predicting the second time length of the target time length item of the historical cardiac cycle based on the time interval of the historical cardiac cycle; wherein the historical cardiac cycle is: adjacent continuous preset number of cardiac cycles before the current cardiac cycle, wherein the target duration item represents a time interval parameter item between a heart contraction peak time and a heart relaxation starting time in the cardiac cycle;

A second duration prediction module, configured to predict a third duration of the target duration item of the current cardiac cycle based on the predicted first duration and second duration corresponding to each historical cardiac cycle;

and the moment prediction module is used for extracting a second pressure characteristic representing the variation trend of the aortic pressure in the current cardiac cycle and predicting the balloon inflation moment of the current cardiac cycle based on the second pressure characteristic and the third duration.

In one embodiment of the present invention, the second duration prediction module includes:

the first time length adjustment sub-module is used for obtaining first time length characteristics representing the change trend of the second time length corresponding to each historical cardiac cycle and adjusting the first time length corresponding to each historical cardiac cycle based on the determined first time length characteristics;

and the duration prediction sub-module is used for predicting the third duration of the target duration item of the current cardiac cycle based on the first duration after the adjustment of each historical cardiac cycle.

In an embodiment of the present invention, the second duration prediction module further includes:

the second time length adjusting submodule is used for acquiring a second time length characteristic representing the change trend of the first time length corresponding to each historical cardiac cycle after the first time length is adjusted by the first time length adjusting submodule, and adjusting the second time length corresponding to each historical cardiac cycle based on the determined second time length characteristic;

The time length prediction sub-module is specifically configured to predict a third time length of the target time length item of the current cardiac cycle based on the first time length and the second time length after adjustment of each historical cardiac cycle.

In one embodiment of the present invention, the apparatus further includes:

the information determining module is used for calculating the correlation between the first time length and the second time length corresponding to each historical cardiac cycle after the first time length predicting module and determining a target cardiac cycle, wherein the correlation corresponding to the historical cardiac cycle is larger than a preset correlation threshold;

the second duration prediction module is specifically configured to predict a third duration of the target duration item of the current cardiac cycle based on the determined first duration and the second duration corresponding to the target cardiac cycle.

In one embodiment of the present invention, the time prediction module includes:

the time judging sub-module is used for extracting a second pressure characteristic representing the variation trend of the aortic pressure in the current cardiac cycle, determining the time of the heart contraction peak value in the current cardiac cycle in the second pressure characteristic as the starting time, and acquiring the time range of the starting time extending backwards for a third duration; determining a target moment which characterizes the beginning of the diastole of the heart in the current cardiac cycle in the second pressure characteristic, and judging whether the target moment which characterizes the beginning of the diastole of the heart in the current cardiac cycle exists in the acquired time range or not based on the second pressure characteristic; if yes, determining a sub-module at the triggering moment; if not, triggering a time prediction sub-module;

The time determining submodule is used for determining the target time as the balloon inflation time;

the time prediction submodule is used for predicting the balloon inflation time of the current cardiac cycle based on the acquired time range.

In one embodiment of the present invention, the first time length prediction module is specifically configured to calculate, based on a time interval of a historical cardiac cycle, a heart rate of the target object corresponding to the historical cardiac cycle; based on the calculated heart rate, a second duration of the target duration item of the historical cardiac cycle is predicted.

In one embodiment of the present invention, the first duration prediction module is specifically configured to calculate the second duration according to the following expression:

；

In a third aspect, an embodiment of the present invention provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;

a memory for storing a computer program;

and a processor, configured to implement the method steps described in the first aspect when executing the program stored in the memory.

In a fourth aspect, embodiments of the present invention provide a computer-readable storage medium having stored therein a computer program which, when executed by a processor, implements the method steps of the first aspect described above.

From the above, the inflation time prediction is performed by applying the scheme provided by the embodiment of the invention, and is obtained by predicting the third time length based on the pressure characteristic change trend corresponding to the current cardiac cycle and the information comprehensive determination based on the historical cardiac cycle. The third time length is determined by integrating the first time length and the second time length corresponding to the historical cardiac cycle, the first time length is determined based on the aortic pressure change trend in the historical cardiac cycle, and the second time length is determined based on the time interval of each historical cardiac cycle, so that the third time length is determined comprehensively by combining the two dimensions of the historical cardiac cycle, and the third time length is more similar to the real time length of the target time length item; on the basis of the third duration, the pressure characteristic change trend of the historical cardiac cycle information and the current cardiac cycle is combined, that is, when the balloon inflation time is predicted, the historical information is considered, the current information is considered, and meanwhile, the historical information is deeply mined, so that the accuracy of the predicted balloon inflation time is remarkably improved.

Of course, it is not necessary for any one product or method of practicing the application to achieve all of the advantages set forth above at the same time.

Drawings

In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the application, and other embodiments may be obtained according to these drawings to those skilled in the art.

Fig. 1 is a flowchart of a method for predicting inflation time of a first IABP balloon according to an embodiment of the present application;

FIG. 2 is a flowchart of a method for predicting inflation time of a second IABP balloon according to an embodiment of the present application;

FIG. 3 is a flowchart of a third method for predicting inflation time of an IABP balloon according to an embodiment of the application;

FIG. 4 is a flowchart of a fourth method for predicting inflation time of an IABP balloon according to an embodiment of the application;

fig. 5 is a schematic structural diagram of an inflation time prediction apparatus for a first IABP balloon according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of an inflation time prediction apparatus for a second IABP balloon according to an embodiment of the present application;

Fig. 7 is a schematic structural diagram of an inflation time prediction apparatus of a third IABP balloon according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of an inflation time prediction apparatus for a fourth IABP balloon according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by the person skilled in the art based on the present application are included in the scope of protection of the present application.

First, the execution subject of the embodiment of the present application will be described. The execution main body of the embodiment of the application is an IABP controller, and the IABP controller is used for inflating and deflating an IABP balloon.

Referring to fig. 1, fig. 1 is a flowchart of a method for predicting inflation time of a first IABP balloon according to an embodiment of the present application, where the method includes the following steps S101 to S103.

Step S101: for each historical cardiac cycle, a first pressure characteristic representing the variation trend of the aortic pressure in the historical cardiac cycle is obtained, a first duration of a target duration item is predicted based on the first pressure characteristic, and a second duration of the target duration item is predicted based on the time interval of the historical cardiac cycle.

The historical cardiac cycle is: adjacent consecutive preset number of cardiac cycles preceding the current cardiac cycle. The preset number may be 10, 20, etc., and taking the preset number 10 as an example, the historical cardiac cycle may be 10 adjacent consecutive cardiac cycles before the current cardiac cycle.

The target duration term represents a time interval parameter term between a peak systole time and a beginning diastole time in a cardiac cycle. One cardiac cycle comprises systole and diastole, with the aortic valve open, the heart is in systole and the aortic pressure gradually increases, the aortic pressure reaching a maximum at the peak systole, that is to say the moment at which the peak systole characterizes the moment at which the aortic pressure reaches a maximum; the aortic pressure then drops until the aortic valve closes; with the aortic valve closed, the heart is in diastole, and the balloon needs to be inflated rapidly during diastole.

The first pressure characteristic is used to represent the aortic pressure variation trend in the historical cardiac cycle, and the aortic pressure variation trend may include a slope, a peak value, a peak time, a valley value, a valley time, an average value, and the like of each point in the aortic pressure variation waveform. The first pressure characteristic may be a stored pressure characteristic of the historical cardiac cycle, that is, a characteristic extraction of a pressure variation trend of the historical cardiac cycle is performed in advance, and the extracted characteristic is stored. The first pressure characteristic may also be a pressure characteristic that extracts a historical cardiac cycle in real time.

The first time length is the value of a target time length item of each historical cardiac cycle, and the first time length is predicted from the dimension of the variation trend of the aortic pressure. When the first duration is predicted based on the first pressure characteristic, the first pressure characteristic can be input into a pre-trained first duration prediction model to obtain the duration of a target duration item output by the first duration prediction model as the first duration. The first time length prediction model is a pre-trained model for predicting the time length of a target time length item in the cardiac cycle based on pressure characteristics characterizing the pressure trend of the aorta.

In addition to the prediction using the neural network approach, a time value representing the systolic peak of the aortic pressure and a time value representing the diastolic onset may be determined from the first pressure signature, and the difference between the determined time values may be calculated as the first time period.

The second time length is also the value of the target time length item of each historical cardiac cycle, and the second time length is predicted from the time interval dimension of the historical cardiac cycle. When the second time length is predicted based on the time interval of the historical cardiac cycle, the prediction can also be performed in a neural network mode, the time interval of the historical cardiac cycle is input into a pre-trained second time length prediction model, the value of the target time length item output by the second time length prediction model is obtained and used as the second time length, and the second time length prediction model is a pre-trained model for predicting the time length of the target time length item in the cardiac cycle based on the time interval of the cardiac cycle.

In addition to the above-mentioned neural network mode for predicting the second duration, other modes may be used for prediction, and the specific prediction mode is not described in detail in the embodiment following the embodiment corresponding to fig. 4.

After this step is performed, a first duration and a second duration corresponding to each historical cardiac cycle are obtained, for example: the number of historical cardiac cycles comprises 10, the first duration may be [ t ] ₁ 、t ₂ 、t ₃ 、……、t ₉ 、t ₁₀ ]The second time period may be [ T ] ₁ 、T ₂ 、T ₃ 、……、T ₉ 、T ₁₀ ]。

Step S102: and predicting a third duration of the target duration item of the current cardiac cycle based on the predicted first duration and second duration corresponding to each historical cardiac cycle.

The third time length is a value of a target time length item of the current cardiac cycle, and is obtained by prediction based on the first time length and the second time length corresponding to the historical cardiac cycle. Because the third duration is based on the consideration of the information of the adjacent continuous preset number of historical cardiac cycles, and combines the two dimensional information of the aortic pressure change trend and the time interval of each historical cardiac cycle, and because the aortic pressure change trend of the cardiac cycle is influenced by the complex environment, the obtained pressure change trend information contains more noise data, in this case, if the accuracy of the inflation time prediction by only using the aortic pressure of the cardiac cycle is necessarily lower, the embodiment considers not only the aortic pressure change trend, but also the aortic pressure change and the time interval of the cardiac cycle, and predicts based on the consideration of the information of the historical cardiac cycle, thereby improving the accuracy of the predicted inflation time.

When the third time length is predicted, the neural network mode can also be adopted to predict, the first time length and the second time length corresponding to each historical cardiac cycle are input into a pre-trained third time length prediction model, the value of a target time length item output by the third time length prediction model is obtained and used as the third time length, and the third time length prediction model is a pre-trained model for predicting the time length of the target time length item based on different values of the target time length item of the cardiac cycle.

In the above case, the first time length prediction model, the second time length prediction model, and the third time length prediction model may be integrated into one neural network model, and the first, second, and third time length prediction models may be used as sub-models of the integrated neural network model. The first pressure characteristic and the time interval corresponding to each historical cardiac cycle may be input as input data into an integrated model that outputs a third duration corresponding to the current cardiac cycle. The first pressure characteristic is used as the input of a first time length prediction model, the time interval is used as the input of a second time length prediction model, the output of the first time length prediction model and the output of the second time length prediction model are used as the input of a third time length prediction model, and the third time length prediction model outputs a third time length corresponding to the current cardiac cycle.

In addition to the prediction using the neural network model described above, the prediction may be performed using the embodiment corresponding to fig. 2 described below, which is not described in detail herein.

Step S103: and extracting a second pressure characteristic representing the variation trend of the aortic pressure in the current cardiac cycle, and predicting the balloon inflation moment of the current cardiac cycle based on the second pressure characteristic and the third duration.

Because the balloon inflation time of the current cardiac cycle is predicted, and the balloon inflation time is generally far from the starting time of the cardiac cycle, the aortic pressure of the current cardiac cycle just started, such as the aortic pressure within a preset time period after the starting time of the current cardiac cycle, is obtained, the obtained aortic pressure is subjected to feature extraction, and a second pressure feature representing the variation trend of the aortic pressure is obtained, wherein the preset time period can be an average time period between the starting time of the cardiac cycle and the peak time of the systole, and the preset time period can be 0.25s, 0.3s, 0.35s and the like. The second pressure characteristic can be extracted by the existing characteristic extraction algorithm.

In predicting the balloon inflation time based on the second pressure characteristic and the third time period, in one embodiment, a fourth time period of the target time period item of the current cardiac cycle may be predicted based on the second pressure characteristic; and acquiring a heart contraction peak time representing the current cardiac cycle from the second pressure characteristic, determining a time range extending backwards for a third time length and a time range extending backwards for a fourth time length by taking the heart contraction peak time as a starting point, determining a target time range based on the determined two time ranges, and determining the balloon inflation time of the current cardiac cycle based on the second pressure characteristic from the target time range.

The prediction method of the fourth duration may refer to the prediction method of the first duration in step S101, which is not described herein.

In determining the target time range, the minimum range, the maximum range, or the average value of the two time ranges may be taken as the target time range. Since the target time range is determined based on the two determined time ranges, the range of time length for predicting the balloon inflation timing is further narrowed, and the accuracy is improved.

In predicting the balloon inflation time, in one embodiment, the time when the aortic pressure in the second pressure characteristic in the cardiac cycle reaches the peak value for the second time may be determined, the duration between the determined time and the time of the peak systole is calculated, and if the calculated duration is less than the duration in the target time range, the determined time when the aortic pressure reaches the peak value for the second time is determined as the balloon inflation time; and if the calculated duration is greater than the duration of the target time range, determining the end point moment of the duration of the target time range as the balloon inflation moment.

Other ways of predicting the balloon inflation moment can be seen in the following corresponding embodiment of fig. 4, which is not described in detail here.

From the above, the inflation time prediction is performed by applying the scheme provided by the embodiment, and is obtained by predicting the third duration based on the pressure characteristic change trend corresponding to the current cardiac cycle and the information comprehensive determination based on the historical cardiac cycle. The third time length is determined by integrating the first time length and the second time length corresponding to the historical cardiac cycle, the first time length is determined based on the aortic pressure change trend in the historical cardiac cycle, and the second time length is determined based on the time interval of each historical cardiac cycle, so that the third time length is determined comprehensively by combining the two dimensions of the historical cardiac cycle, and the third time length is more similar to the real time length of the target time length item; on the basis of the third duration, the pressure characteristic change trend of the historical cardiac cycle information and the current cardiac cycle is combined, that is, when the balloon inflation time is predicted, the historical information is considered, the current information is considered, and meanwhile, the historical information is deeply mined, so that the accuracy of the predicted balloon inflation time is remarkably improved.

In the foregoing corresponding embodiment of fig. 1, the third duration may be implemented according to steps S202-S203 of the corresponding embodiment of fig. 2 described below, in addition to the prediction according to the above-mentioned manner. Referring to fig. 2, fig. 2 is a flowchart of a method for predicting inflation time of a second IABP balloon according to an embodiment of the present invention, where the method includes the following steps S201 to S204.

Step S201: for each historical cardiac cycle, a first pressure characteristic representing the variation trend of the aortic pressure in the historical cardiac cycle is obtained, a first duration of a target duration item of the historical cardiac cycle is predicted based on the first pressure characteristic, and a second duration of the target duration item of the historical cardiac cycle is predicted based on the time interval of the historical cardiac cycle.

The historical cardiac cycle is: an adjacent consecutive preset number of cardiac cycles preceding the current cardiac cycle, the target duration term characterizing a time interval between a peak systole instant and a beginning diastole instant in the cardiac cycle.

The step S201 is the same as the step S101 of the corresponding embodiment of fig. 1, and will not be described here again.

Step S202: and acquiring a first time length characteristic representing the change trend of the second time length corresponding to each historical cardiac cycle, and adjusting the first time length corresponding to each historical cardiac cycle based on the determined first time length characteristic.

The aforementioned step S201 obtains the second duration of each historical cardiac cycle, that is, a preset number of second durations. The first time length features are used for reflecting the change trend of the time length change formed by the preset number of second time lengths, and the change trend can comprise the slope, the statistical analysis value, the wave crest, the wave trough and the like of the waveform formed by the second time lengths.

The first time length feature may be obtained by extracting features of a trend of a second time length corresponding to the historical cardiac cycle in advance, in which case the extracted features need to be stored, and the first time length feature is obtained from the stored data when the step is executed; the first time length feature may also be obtained by extracting features of the variation trend of the second time length in real time. Any feature extraction method in the prior art can be adopted.

When the first time length is adjusted based on the first time length feature, time length data in the first time length feature can be extracted as a reference time length, and the first time length is adjusted. Extracting a peak value, a valley value or a statistical analysis value in the first time length characteristic as a reference time length; the adjustment mode may include calculating a difference/sum value between each first time length and the reference time length, and taking a result obtained by calculation as an adjusted first time length; the difference between the first time length and the reference time length can also be calculated, and only the first time length with the difference smaller than the preset threshold value is reserved and used as the adjusted first time length.

Taking the latter adjustment as an example, the obtained first time length comprises [ t ] ₁ 、t ₂ 、t ₃ 、……、t ₉ 、t ₁₀ ]The reference time length is b1, and the preset threshold value is 0.05s. Wherein, the first time length meeting the difference value smaller than the preset threshold value is t ₁ 、t ₃ 、t ₆ 、t ₁₀ Only the first time length is reserved, namely the adjusted first time length is [ t ] ₁ 、t ₃ 、t ₆ 、t ₁₀ ]。

Step S203: based on the adjusted first time length of each historical cardiac cycle, a third time length of a target time length item of the current cardiac cycle is predicted.

When predicting the third time period based on the adjusted first time period, statistical analysis may be performed on the first time period, for example, calculating an average value, a maximum value, a minimum value, a median value, or the like, and a result of the statistical analysis may be determined as the third time period.

Step S204: and extracting a second pressure characteristic representing the variation trend of the aortic pressure in the current cardiac cycle, and predicting the balloon inflation moment of the current cardiac cycle based on the second pressure characteristic and the third duration.

The step S204 is the same as the step S103 of the corresponding embodiment of fig. 1, and will not be described here again.

From the above, the third time length is obtained by prediction of the adjusted first time length, and the first time length is adjusted based on the time length characteristics of the variation trend of the second time length corresponding to the historical cardiac cycle, so that the adjusted first time length is more accurate compared with the time interval of the historical cardiac cycle before adjustment, and the third time length is more close to the real time length of the target time length item of the current cardiac cycle, that is, the accuracy of predicting the third time length is improved.

Before step S203 of the foregoing corresponding embodiment of fig. 2, step S303 of the corresponding embodiment of fig. 3 described below may be further included in an embodiment of the present invention, and step S203 of the foregoing corresponding embodiment of fig. 2 may be implemented according to step S304 of the corresponding embodiment of fig. 3 described below. Referring to fig. 3, fig. 3 is a flowchart of a third method for predicting inflation time of an IABP balloon according to an embodiment of the present invention, where the method includes the following steps S301 to S305.

Step S301: for each historical cardiac cycle, a first pressure characteristic representing the variation trend of the aortic pressure in the historical cardiac cycle is obtained, a first duration of a target duration item of the historical cardiac cycle is predicted based on the first pressure characteristic, and a second duration of the target duration item of the historical cardiac cycle is predicted based on the time interval of the historical cardiac cycle.

Step S302: and acquiring a first time length characteristic representing the change trend of the second time length corresponding to each historical cardiac cycle, and adjusting the first time length corresponding to each historical cardiac cycle based on the determined first time length characteristic.

The steps S301 to S302 are the same as the steps S201 to S202 in the corresponding embodiment of fig. 2, and are not described herein.

Step S303: and acquiring a second time length feature representing the change trend of the first time length corresponding to each historical cardiac cycle, and adjusting the second time length corresponding to each historical cardiac cycle based on the determined second time length feature.

The second time length feature may be obtained by extracting features of a trend of the first time length corresponding to the historical cardiac cycle in advance, in which case the extracted features need to be stored, and the second time length feature is obtained from the stored data when the step is executed; the second duration feature may also be obtained by extracting features of the variation trend of the first duration in real time. Any feature extraction method in the prior art can be adopted.

When the second time length is adjusted based on the second time length feature, time length data in the second time length feature can be extracted as a reference time length, and the second time length is adjusted. Extracting a peak value, a valley value or a statistical analysis value in the second time length characteristic as a reference time length; the adjustment mode may include calculating a difference/sum value between each second time length and the reference time length, and taking the calculated result as an adjusted second time length; and calculating the difference between the second time length and the reference time length, and only reserving the second time length with the difference smaller than a preset threshold value as the adjusted second time length.

Taking the latter adjustment as an example, the obtained second time length comprises [ T ] ₁ 、T ₂ 、T ₃ 、……、T ₉ 、T ₁₀ ]The reference time length is b2, the preset threshold value is 0.05s, wherein the second time length meeting the difference value smaller than the preset threshold value is T ₁ 、T ₃ 、T ₆ 、T ₁₀ Only the second time length is reserved, namely the adjusted second time length is [ T ] ₁ 、T ₃ 、T ₆ 、T ₁₀ ]。

Step S304: and predicting a third duration of the target duration item of the current cardiac cycle based on the adjusted first duration and second duration of each historical cardiac cycle.

When predicting the third time length based on the adjusted first time length and second time length, the adjusted first time length and second time length of each historical cardiac cycle may be fused for each historical cardiac cycle, and the fusion manner may include statistical analysis, determining an intersection time length/a union time length, and the like, and then performing statistical analysis on the fused time length of each historical cardiac cycle to determine a statistical analysis value as the third time length.

Step S305: and extracting a second pressure characteristic representing the variation trend of the aortic pressure in the current cardiac cycle, and predicting the balloon inflation moment of the current cardiac cycle based on the second pressure characteristic and the third duration.

The step S305 is the same as the step S204 of the corresponding embodiment of fig. 2, and will not be described here again.

From the above, the third time length is obtained by predicting the adjusted first time length and the second time length, and because the first time length is adjusted based on the time length characteristics of the variation trend of the second time length corresponding to the historical cardiac cycle, the adjusted first time length is more accurate compared with the time interval information of the historical cardiac cycle before adjustment, and the second time length is adjusted based on the time length characteristics of the variation trend of the first time length corresponding to the historical cardiac cycle, so that the adjusted second time length is more accurate compared with the time length characteristics of the variation trend of the aorta pressure corresponding to the historical cardiac cycle before adjustment. In this way, the two aspects are combined, so that the third duration further approaches to the real duration of the target duration item of the current cardiac cycle, that is, the accuracy of predicting the third duration is improved.

Before the third duration is predicted, a target cardiac cycle may be selected from the historical cardiac cycles, and the third duration may be predicted based on information corresponding to the target cardiac cycle. Based on this, in one embodiment of the present invention, after the foregoing step S101/S201/S301, the correlation between the first duration and the second duration corresponding to each historical cardiac cycle may be further calculated, and a target cardiac cycle in which the correlation corresponding to the historical cardiac cycle is greater than the preset correlation threshold may be determined.

The degree of correlation between the first time period and the second time period is represented by the degree of correlation, and the higher the degree of correlation is, the more the first time period and the second time period are represented by the degree of correlation; the lower the correlation, the less correlated the first duration and the second duration.

Specifically, for each historical cardiac cycle, a difference between the first duration and the second duration may be calculated, normalization processing may be performed on the difference, and a difference between 1 and the normalized data may be calculated as a correlation.

The target cardiac cycle refers to a historical cardiac cycle with a correlation greater than a preset correlation threshold. The correlation degree being greater than the preset correlation degree threshold value indicates that the degree of correlation between the first time length and the second time length corresponding to the cardiac cycle is higher, and in this case, the reliability of the first time length and the second time length corresponding to the cardiac cycle is better, that is, the reliability of the first time length and the second time length corresponding to the target cardiac cycle is high, and noise data is less.

On this basis, in the aforementioned step S102/steps S202-S203/steps S302-S304, the historical cardiac cycle may be updated to the target cardiac cycle. Taking step S102 as an example, a third duration of the target duration item of the current cardiac cycle may be predicted based on the determined first duration and second duration corresponding to the target cardiac cycle.

Because the reliability of the first time length and the second time length corresponding to the target cardiac cycle is high and the noise data is less, the third time length can be predicted more accurately based on the two types of time length data corresponding to the target cardiac cycle.

In addition to the prediction of the balloon inflation time in the manner mentioned in step S103, the present invention may be implemented in steps S403 to S405 of the embodiment corresponding to fig. 4 described below. Referring to fig. 4, fig. 4 is a flowchart of a method for predicting inflation time of a fourth IABP balloon according to an embodiment of the present invention. The above method includes the following steps S401 to S405.

It should be noted that this embodiment is based on any of the foregoing embodiments, and in order to avoid a large number of duplicate matters, only fig. 4 based on fig. 1 is provided, and the embodiment based on fig. 2/3 is omitted.

Step S401: for each historical cardiac cycle, a first pressure characteristic representing the variation trend of the aortic pressure in the historical cardiac cycle is obtained, a first duration of a target duration item of the historical cardiac cycle is predicted based on the first pressure characteristic, and a second duration of the target duration item of the historical cardiac cycle is predicted based on the time interval of the historical cardiac cycle.

Step S402: and predicting a third duration of the target duration item of the current cardiac cycle based on the predicted first duration and second duration corresponding to each historical cardiac cycle.

The steps S401 to S402 are the same as the steps S101 to S102 in the corresponding embodiment of fig. 1, and are not described herein.

Step S403: extracting a second pressure characteristic representing the variation trend of the aortic pressure in the current cardiac cycle, determining the time of a heart contraction peak value in the current cardiac cycle in the second pressure characteristic as the starting time, and acquiring a time range of which the starting time extends backwards for a third time length; based on the second pressure characteristic, it is determined whether a target moment in the acquired time frame is present that characterizes a beginning diastole of the heart in the current cardiac cycle. If so, step S404 is performed, and if not, step S405 is performed.

The second pressure characteristic is used to reflect the aortic pressure variation trend in the current cardiac cycle, and the aortic pressure variation trend reflected by the second pressure characteristic includes determining the systolic/diastolic starting time, the systolic/diastolic ending time, etc., for example, the slope of each point in the aortic pressure variation waveform may be based on the slope, when the slope is from positive to negative, the pressure point time is the systolic peak time, and when the slope is from negative to positive, the pressure point time at which the slope is located is the time at which the diastole starts. Thus, a peak moment of systole in the second pressure characteristic can be determined which characterizes the current cardiac cycle.

And taking the heart contraction peak time as the starting time, acquiring a time range formed by extending the starting time backwards for a third time length, and predicting the balloon inflation time from the time range. The third time length is obtained through prediction of the first time length and the second time length corresponding to the historical cardiac cycle, and is closer to the real time length of the target time length item, so that the balloon inflation time can be more accurately determined based on the time range with the third time length.

In determining whether there is a target time within the acquired time range, in one embodiment, a target time in the second pressure characteristic that characterizes the diastole of the heart in the current cardiac cycle may be determined, if the target time is within the acquired time range, step S404 is performed, that is, the target time is determined as the balloon inflation time, and if the target time is not within the acquired time range, step S405 is performed, that is, the balloon inflation time is determined directly based on the acquired time range.

Step S404: the target time is determined as the balloon inflation time.

Because the target time is located in the acquired time range, on one hand, the acquired time range is a third time, the third time is close to the real time of the target time item of the current cardiac cycle, on the other hand, the target time is the time for representing the beginning of diastole of the cardiac cycle, and the two results are combined, the target time is directly determined as the balloon inflation time, so that the accuracy of the determined balloon inflation time is high.

Step S405: based on the acquired time range, the balloon inflation moment of the current cardiac cycle is predicted.

Since the above-mentioned target time is not located within the acquired time range, the possibility that the target time is interference noise data is high, and the third time period is a real time period close to the target time period item of the current cardiac cycle, in this case, the interference noise data can be eliminated, and the balloon inflation time can be predicted based only on the acquired time range in which the time period is the third time period.

When the balloon inflation time is predicted based on the acquired time range, a time may be selected from each time included in the acquired time range as the balloon inflation time of the current cardiac cycle, such as the end time, the middle time, and the like of the acquired time range.

As is clear from the above, in the present embodiment, on the one hand, in the case where the target time is located within the acquired time range in which the time length is the third time length, the target time is directly determined as the balloon inflation time, and since the target time is the time that characterizes the diastole start of the cardiac cycle, the third time length is close to the real time length of the target time length item of the current cardiac cycle, on the other hand, when the target time is located within the acquired time range, the possibility that the balloon inflation time is the target time is high, and therefore, the target time is directly determined as the balloon inflation time, so that the accuracy of the determined balloon inflation time is high. On the other hand, in the case where the target time is not within the acquired time range, the possibility that the target time is the interference noise data is high, and the third time is the real time close to the target time item of the current cardiac cycle, in this case, the interference noise data is eliminated, and the balloon inflation time is predicted based on only the acquired time range in which the time is the third time, so that the determined balloon inflation time avoids the interference of the noise data, and the prediction accuracy is improved.

On the basis of each of the foregoing embodiments, in addition to the prediction that may be performed in the aforementioned prediction manner, the present invention provides an embodiment in which the heart rate of the target object corresponding to the historical cardiac cycle may be calculated based on the time interval of the historical cardiac cycle; based on the calculated heart rate, a second duration of the target duration item of the historical cardiac cycle is predicted.

The heart rate represents the number of beats of the heart per minute, and therefore, when calculating the heart rate, the ratio between "60" and the time of the historic cardiac cycle can be calculated, and the calculated ratio is determined as the heart rate.

In one embodiment, a fourth time length prediction model may be trained in advance in combination with a deep learning manner, where the fourth time length prediction model is used to predict a heart rate to obtain a time length of a target time length item of a cardiac cycle, and the heart rate obtained by the calculation is input into the fourth time length prediction model to obtain a time length output by the fourth time length prediction model, and is used as the second time length of the target time length item of the historical cardiac cycle.

In another embodiment, the second time period is predicted according to the following expression:

；

Can be [ -0.000001135, -0.000001130]Data in->May be [0.000408,0.0004085 ]]Data in->Can be [ -0.05240, -0.05245]Data in->May be [2.7750,2.7755 ]]Data within; />Can be [ -0.000001325, -0.000001320]Data in->May be [0.000460,0.000465 ]]Data in->Can be [ -0.05610, -0.05605]Data in->May be [2.6230,2.6235 ]]Data within.

Since the second time length is predicted based on the heart rate, the second time length is related to the heart rate, and therefore, the second time length is close to the real time length of the target time length item of the historical heart cycle, so that the accuracy of the second time length is high.

Corresponding to the inflation time prediction method of the IABP balloon, the embodiment of the invention also provides an inflation time prediction device of the IABP balloon.

Referring to fig. 5, fig. 5 is a schematic structural diagram of an apparatus for predicting inflation time of a first IABP balloon according to an embodiment of the present invention, where the apparatus includes a first time length prediction module 501, a second time length prediction module 502, and a time length prediction module 503.

A first time length prediction module 501, configured to obtain, for each historical cardiac cycle, a first pressure characteristic that characterizes a trend of aortic pressure variation in the historical cardiac cycle, predict, based on the first pressure characteristic, a first time length of a target time length item of the historical cardiac cycle, and predict, based on a time interval of the historical cardiac cycle, a second time length of the target time length item of the historical cardiac cycle; wherein the historical cardiac cycle is: adjacent continuous preset number of cardiac cycles before the current cardiac cycle, wherein the target duration item represents a time interval parameter item between a heart contraction peak time and a heart relaxation starting time in the cardiac cycle;

a second duration prediction module 502, configured to predict a third duration of the target duration item of the current cardiac cycle based on the predicted first duration and second duration corresponding to each historical cardiac cycle;

a time prediction module 503, configured to extract a second pressure characteristic that characterizes a variation trend of aortic pressure in the current cardiac cycle, and predict a balloon inflation time of the current cardiac cycle based on the second pressure characteristic and the third duration.

Referring to fig. 6, fig. 6 is a schematic structural diagram of an inflation time prediction apparatus for a second type of IABP balloon according to an embodiment of the present invention, and in the second duration prediction module 502 of the foregoing embodiment corresponding to fig. 5, the first duration adjustment sub-module 602 and the duration prediction sub-module 603 may further be included.

A first time length prediction module 601, configured to obtain, for each historical cardiac cycle, a first pressure characteristic that characterizes a trend of aortic pressure variation in the historical cardiac cycle, predict a first time length of a target time length item of the historical cardiac cycle based on the first pressure characteristic, and predict a second time length of the target time length item of the historical cardiac cycle based on a time interval of the historical cardiac cycle; wherein the historical cardiac cycle is: adjacent continuous preset number of cardiac cycles before the current cardiac cycle, wherein the target duration item represents a time interval between a heart contraction peak time and a heart relaxation starting time in the cardiac cycle;

a first time length adjustment sub-module 602, configured to obtain a first time length feature representing a trend of variation of a second time length corresponding to each historical cardiac cycle, and adjust the first time length corresponding to each historical cardiac cycle based on the determined first time length feature;

A duration prediction submodule 603, configured to predict a third duration of the target duration item of the current cardiac cycle based on the adjusted first duration of each historical cardiac cycle;

the time prediction module 604 is configured to extract a second pressure characteristic that characterizes a variation trend of aortic pressure in the current cardiac cycle, and predict a balloon inflation time of the current cardiac cycle based on the second pressure characteristic and the third duration.

Referring to fig. 7, fig. 7 is a schematic structural diagram of an inflation time prediction apparatus for a third IABP balloon according to an embodiment of the present invention, before the duration prediction submodule 603 in the foregoing corresponding embodiment of fig. 6, a second duration adjustment submodule 703 may be further included, on the basis of which the duration prediction submodule 603 may be updated to the following duration prediction submodule 704.

The device comprises:

a first time length prediction module 701, configured to obtain, for each historical cardiac cycle, a first pressure characteristic that characterizes a trend of aortic pressure variation in the historical cardiac cycle, predict, based on the first pressure characteristic, a first time length of a target time length item of the historical cardiac cycle, and predict, based on a time interval of the historical cardiac cycle, a second time length of the target time length item of the historical cardiac cycle; wherein the historical cardiac cycle is: adjacent continuous preset number of cardiac cycles before the current cardiac cycle, wherein the target duration item represents a time interval between a heart contraction peak time and a heart relaxation starting time in the cardiac cycle;

a first time length adjustment sub-module 702, configured to obtain a first time length feature representing a trend of change of a second time length corresponding to each historical cardiac cycle, and adjust the first time length corresponding to each historical cardiac cycle based on the determined first time length feature;

a second duration adjustment sub-module 703, configured to obtain a second duration feature that characterizes a trend of variation of the first duration corresponding to each historical cardiac cycle, and adjust the second duration corresponding to each historical cardiac cycle based on the determined second duration feature;

A duration prediction sub-module 704, configured to predict a third duration of the target duration item of the current cardiac cycle based on the adjusted first duration and second duration of each historical cardiac cycle;

the time prediction module 705 is configured to extract a second pressure characteristic that characterizes a variation trend of aortic pressure in a current cardiac cycle, and predict a balloon inflation time of the current cardiac cycle based on the second pressure characteristic and the third duration.

In one embodiment of the present invention, the apparatus further includes:

Referring to fig. 8, fig. 8 is a schematic structural diagram of an inflation time prediction apparatus for a fourth IABP balloon according to an embodiment of the present invention. The time prediction module may include a time determination sub-module 804 and a time prediction sub-module 805 described below. The device comprises:

it should be noted that this embodiment is based on any of the foregoing embodiments, and in order to avoid a large number of duplicate matters, only fig. 8 based on fig. 5 is provided, and the embodiment based on fig. 6/7 is omitted.

A first time length prediction module 801, configured to obtain, for each historical cardiac cycle, a first pressure characteristic that characterizes a trend of aortic pressure variation in the historical cardiac cycle, predict, based on the first pressure characteristic, a first time length of a target time length item of the historical cardiac cycle, and predict, based on a time interval of the historical cardiac cycle, a second time length of the target time length item of the historical cardiac cycle; wherein the historical cardiac cycle is: adjacent continuous preset number of cardiac cycles before the current cardiac cycle, wherein the target duration item represents a time interval between a heart contraction peak time and a heart relaxation starting time in the cardiac cycle;

a second duration prediction module 802, configured to predict a third duration of the target duration item of the current cardiac cycle based on the predicted first duration and second duration corresponding to each historical cardiac cycle;

the time judging sub-module 803 is configured to extract a second pressure characteristic representing a variation trend of the aortic pressure in the current cardiac cycle, determine a time of a heart contraction peak in the current cardiac cycle in the second pressure characteristic as a starting time, and obtain a time range in which the starting time extends backwards for a third duration; determining a target moment which characterizes the beginning of the diastole of the heart in the current cardiac cycle in the second pressure characteristic, and judging whether the target moment which characterizes the beginning of the diastole of the heart in the current cardiac cycle exists in the acquired time range or not based on the second pressure characteristic; if so, triggering the moment determination sub-module 804; if not, triggering the time prediction sub-module 805;

The time determination submodule 804 is configured to determine a target time as a balloon inflation time;

the time prediction sub-module 805 is configured to predict a balloon inflation time of the current cardiac cycle based on the acquired time range.

；

Corresponding to the inflation time prediction method of the IABP balloon, the embodiment of the invention also provides electronic equipment.

Referring to fig. 9, fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, which includes a processor 901, a communication interface 902, a memory 903 and a communication bus 904, wherein the processor 901, the communication interface 902, and the memory 903 communicate with each other through the communication bus 904,

A memory 903 for storing a computer program;

the processor 901 is configured to implement the method for predicting inflation time of an IABP balloon according to the embodiment of the present invention when executing the program stored in the memory 903.

The communication bus mentioned above for the electronic devices may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, etc. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.

The communication interface is used for communication between the electronic device and other devices.

The Memory may include random access Memory (Random Access Memory, RAM) or may include Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.

The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

In yet another embodiment of the present invention, a computer readable storage medium is provided, where a computer program is stored, where the computer program, when executed by a processor, implements the method for predicting inflation time of an IABP balloon provided by an embodiment of the present invention.

In yet another embodiment of the present invention, a computer program product comprising instructions that when executed on a computer cause the computer to perform the method of predicting inflation time of an IABP balloon provided by an embodiment of the present invention is also provided.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present invention, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), etc.

It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for apparatus, electronic devices, computer readable storage medium embodiments, since they are substantially similar to method embodiments, the description is relatively simple, and relevant references are made to the partial description of method embodiments.

The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A method of predicting inflation time of an IABP balloon, the method comprising:

2. The method of claim 1, wherein predicting a third duration of the target duration item for the current cardiac cycle based on the predicted first duration and second duration for each historical cardiac cycle comprises:

3. The method of claim 2, wherein the step of determining the position of the substrate comprises,

before predicting a third duration of the target duration item of the current cardiac cycle based on the adjusted first duration of each historical cardiac cycle, the method comprises:

4. A method according to any one of claims 1 to 3, wherein,

after the first pressure characteristic representing the aortic pressure variation trend in the historical cardiac cycle is obtained for each historical cardiac cycle, the first duration of the target duration item of the historical cardiac cycle is predicted based on the first pressure characteristic, and the second duration of the target duration item of the historical cardiac cycle is predicted based on the time interval of the historical cardiac cycle, the method further comprises:

5. A method according to any one of claims 1-3, wherein said predicting a balloon inflation instant of a current cardiac cycle based on said second pressure characteristic and said third duration comprises:

6. A method according to any of claims 1-3, wherein predicting a second duration of the target duration item of the historical cardiac cycle based on the time interval of the historical cardiac cycle comprises:

Predicting a second duration for each historical cardiac cycle as follows:

7. The method of claim 6, wherein predicting the second duration of the target duration term for the historical cardiac cycle based on the calculated heart rate comprises:

calculating the second time period according to the following expression:

；

8. An IABP balloon inflation moment prediction apparatus, the apparatus comprising:

the first time length prediction module is used for acquiring a first pressure characteristic representing the change trend of the aortic pressure in each historical cardiac cycle, predicting the first time length of a target time length item of the historical cardiac cycle based on the first pressure characteristic, and predicting the second time length of the target time length item of the historical cardiac cycle based on the time interval of the historical cardiac cycle; wherein the historical cardiac cycle is: adjacent continuous preset number of cardiac cycles before the current cardiac cycle, wherein the target duration item represents a time interval between a heart contraction peak time and a heart relaxation starting time in the cardiac cycle;

9. The apparatus of claim 8, wherein the second duration prediction module comprises:

10. The apparatus of claim 9, wherein the second duration prediction module further comprises:

11. The apparatus according to any one of claims 8-10, wherein the apparatus further comprises:

12. The apparatus according to any one of claims 8-10, wherein the time instant prediction module comprises:

the time prediction submodule is used for predicting the balloon inflation time of the current cardiac cycle in the acquired time range.

13. The apparatus according to any one of claims 8-10, wherein the first time-length prediction module is specifically configured to calculate, based on a time interval of the historical cardiac cycle, a heart rate of the target object corresponding to the historical cardiac cycle; based on the calculated heart rate, a second duration of the target duration item of the historical cardiac cycle is predicted.

14. The apparatus of claim 13, wherein the first duration prediction module is configured to calculate the second duration according to the following expression:

；