Blood pressure feature position extraction method and system, and storage medium

Abstract

A blood pressure feature position extraction method and system, and a storage medium, wherein the blood pressure feature position extraction method comprises: acquiring a current electrocardiogram signal and a current blood pressure signal (S602); performing parameter parsing on the current electrocardiogram signal and the current blood pressure signal to obtain a target parameter group (S604); performing blood pressure feature position extraction on the current blood pressure signal to obtain initial blood pressure feature positions (S606); and screening the initial blood pressure feature positions on the basis of the target parameter group to obtain a target blood pressure feature position (S608). The method can improve the accuracy of blood pressure feature position extraction.

Description

Blood pressure feature position extraction method, system and storage medium

[0001] Related applications

[0002] The present application claims priority to the Chinese patent application No. 202410628891.9, filed on May 20, 2024, entitled "Blood pressure feature position extraction method, system and storage medium", the contents of which are hereby incorporated by reference in its entirety. TECHNICAL FIELD

[0003] The present application relates to the field of intelligent medical technology, in particular to a blood pressure feature position extraction method, system and storage medium. BACKGROUND

[0004] Intra-aortic balloon counterpulsation is to place a strip-shaped intra-balloon in the descending aorta 2-3 cm below the left clavicular artery through the femoral artery, and the balloon catheter is connected with an extracorporeal pressure pump. Its working principle is that the balloon is rapidly inflated at the beginning of ventricular diastole to increase coronary perfusion, and the balloon is rapidly deflated at the end of ventricular diastole to reduce the left ventricular afterload, thereby achieving the effect of assisting the heart, reducing the pressure load of the heart, increasing the cardiac output, improving the coronary perfusion pressure and myocardial oxygen supply, and reducing myocardial oxygen consumption, thereby improving the perfusion of peripheral organs and tissues. Intra-aortic balloon counterpulsation is an effective temporary mechanical assist device for maintaining the pressure of the body circulation aorta and ensuring the perfusion of important organs and tissues such as heart and brain. For patients with obvious low aortic pressure and coronary artery stenosis, intra-aortic balloon counterpulsation can increase the blood flow in the coronary artery and improve the myocardial oxygen supply in pathological conditions. The balloon is rapidly deflated before the aortic valve opens in the systolic phase, which produces a pumping effect, reduces the afterload of the heart, and reduces the work of the heart, thereby reducing the demand for oxygen by the myocardium. Effective intra-aortic balloon counterpulsation therapy can reduce left ventricular end-diastolic pressure, left ventricular systolic pressure and ejection resistance, reduce left ventricular afterload, and increase cardiac output.

[0005] In the traditional three-dimensional aortic balloon system, a RR interval (RR interval refers to a parameter on an electrocardiogram, which is the distance between R waves in two QRS complexes, that is, the interval time, and the RR interval generally represents the ventricular beat frequency) prediction method is usually used for general patients: inflate the auxiliary pump at the end of left ventricular pumping to increase the ejection volume; deflate the balloon to create a negative pressure difference between the artery and the left ventricle at a certain time before the next left ventricular pumping, thereby reducing the left ventricular pumping load.

[0006] However, in the case of atrial fibrillation, due to the electrical physiology of the heart, the electrocardiogram will be extremely chaotic, which brings great difficulty to the feature position extraction of the signal processing algorithm structure.

[0007] SUMMARY

[0008] Therefore, it is necessary to provide a blood pressure feature position extraction method, system and storage medium capable of improving blood pressure feature position extraction accuracy in view of the above technical problems.

[0009] In a first aspect, the application provides a blood pressure feature position extraction method, which comprises:

[0010] obtaining a current electrocardiogram signal and a current blood pressure signal;

[0011] performing parameter analysis on the current electrocardiogram signal and the current blood pressure signal to obtain a target parameter group;

[0012] extracting a blood pressure feature position from the current blood pressure signal to obtain an initial blood pressure feature position;

[0013] screening the initial blood pressure feature position according to the target parameter group to obtain a target blood pressure feature position.

[0014] In one embodiment, the current electrocardiogram signal and the current blood pressure signal are obtained by:

[0015] obtaining an electrocardiogram signal collected by an electrocardiogram device as a current electrocardiogram signal;

[0016] obtaining a measured blood pressure signal collected by a sensor, converting the measured blood pressure signal based on local atmospheric pressure to obtain a first blood pressure signal;

[0017] converting the measured blood pressure signal based on the last measured blood pressure signal collected by the sensor to obtain a second blood pressure signal;

[0018] the first blood pressure signal and the second blood pressure signal are used as the first current blood pressure signal, and the second blood pressure signal is used as the second current blood pressure signal, wherein the current blood pressure signal comprises the first current blood pressure signal and the second current blood pressure signal.

[0019] In one embodiment, the blood pressure feature position is extracted from the current blood pressure signal to obtain an initial blood pressure feature position, which comprises:

[0020] extracting a first cycle segmentation result based on the current electrocardiogram signal, and extracting a second cycle segmentation result based on the current blood pressure signal;

[0021] obtaining a target cycle segmentation result according to the first cycle segmentation result and the second cycle segmentation result;

[0022] extracting a feature position from the current blood pressure signal based on the target cycle segmentation result to obtain an initial blood pressure feature position.

[0023] In one of the embodiments, the blood pressure feature position extraction on the current blood pressure signal obtains initial blood pressure feature positions, including:

[0024] The feature position extraction on the current blood pressure signal obtains a first phase position and a second phase position;

[0025] A predetermined time difference value is obtained;

[0026] The first phase position and the time difference value are used to obtain a third phase position;

[0027] The second phase position and the third phase position are used as the initial blood pressure feature positions.

[0028] In one of the embodiments, the initial blood pressure feature positions are screened according to the target parameter group to obtain target blood pressure feature positions, including:

[0029] A position screening condition set is obtained, and each position screening condition set includes at least one position screening condition;

[0030] When at least one position screening condition in the position screening condition set corresponding to each target parameter in the target parameter group is determined to be satisfied, the initial blood pressure feature position is used as a target blood pressure feature position.

[0031] In one of the embodiments, after the corresponding position screening condition set is obtained, the method further includes:

[0032] A local condition set is obtained, and the local condition set is a subset of the position screening condition set;

[0033] Based on each target parameter in the target parameter group, a score corresponding to each position screening condition in the local condition set is obtained;

[0034] A weight of each position screening condition in the local condition set is obtained, and a weighted value of each position screening condition in the local condition set is obtained based on the score and the weight;

[0035] When the weighted value is greater than a condition threshold value, it is determined that the target parameter corresponding to the local condition set satisfies each position screening condition in the local condition set.

[0036] In one of the embodiments, the target parameter group includes an adaptive window parameter; the method further includes:

[0037] The adaptive window parameter is used for correlation calculation with the current blood pressure signal to obtain a correlation calculation result;

[0038] When the correlation calculation result is greater than or equal to an autocorrelation threshold, it is determined that the position screening condition corresponding to the autocorrelation is met.

[0039] In one of the embodiments, before the correlation calculation of the adaptive window parameter and the current blood pressure signal is performed to obtain a correlation calculation result, the method further comprises:

[0040] determining a current signal channel, counterpulsation information and inflation-deflation information;

[0041] selecting an adaptive window parameter corresponding to the current signal channel, counterpulsation information and inflation-deflation information.

[0042] In one of the embodiments, the target parameter group comprises an adaptive window parameter; and the extraction manner of the adaptive window parameter comprises:

[0043] performing feature point extraction on the current blood pressure signal to obtain initial feature points for signal segmentation;

[0044] performing screening on the initial feature points to obtain target feature points, and performing signal segmentation based on the target feature points;

[0045] obtaining each adaptive window module;

[0046] adjusting each adaptive window module based on the current blood pressure signal after signal segmentation to obtain each initial adaptive window parameter;

[0047] optimizing each initial adaptive window parameter to obtain each adaptive window parameter.

[0048] In one of the embodiments, the initial blood pressure feature position comprises an aortic blood pressure feature point; and the aortic blood pressure feature point comprises at least one of four feature points of a systolic peak, a dicrotic notch, a diastolic peak and a diastolic end.

[0049] In one of the embodiments, the first phase position is a systolic peak position, the second phase position is a diastolic end phase position, and the third phase position is a dicrotic notch phase position.

[0050] In one of the embodiments, the optimization of each initial adaptive window parameter comprises normalization and frequency domain adjustment.

[0051] In a second aspect, the application provides a blood pressure feature position extraction device, comprising:

[0052] a signal acquisition module, configured to acquire a current electrocardiogram signal and a current blood pressure signal;

[0053] The parameter group obtaining module is configured to perform parameter analysis on the current electrocardiogram signal and the current blood pressure signal to obtain a target parameter group.

[0054] The feature extraction module is configured to perform blood pressure feature position extraction on the current blood pressure signal to obtain an initial blood pressure feature position.

[0055] The screening module is configured to screen the initial blood pressure feature position according to the target parameter group to obtain a target blood pressure feature position.

[0056] In a third aspect, the present application further provides a counterpulsation device control system, which comprises:

[0057] The electrocardiogram device is configured to collect a current electrocardiogram signal.

[0058] The sensor is configured to collect a measured blood pressure signal.

[0059] The control device is configured to obtain a target blood pressure feature position based on the blood pressure feature position extraction method in any one of the above embodiments, and output an instruction for the counterpulsation device to inflate or deflate at the target blood pressure feature position.

[0060] The counterpulsation device is configured to inflate or deflate based on the instruction.

[0061] In a fourth aspect, the present application further provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the steps of the method in any one of the above embodiments.

[0062] The blood pressure feature position extraction method, system and storage medium described above obtain a current electrocardiogram signal and a current blood pressure signal, extract blood pressure feature positions from the two signals, obtain multi-channel signals, lay a foundation for blood pressure feature position extraction, perform parameter analysis on the current electrocardiogram signal and the current blood pressure signal to obtain a target parameter group, perform blood pressure feature position extraction on the current blood pressure signal to obtain an initial blood pressure feature position, and screen the initial blood pressure feature position according to the target parameter group to obtain a target blood pressure feature position. In this way, a parameter group is designed, the initial blood pressure feature position is screened through the parameter group, and the recognition accuracy is high. BRIEF DESCRIPTION OF DRAWINGS

[0063] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the following will briefly introduce the drawings needed to be used in the embodiment or related art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0064] FIG. 1 is a framework diagram of a blood pressure feature position extraction system in an embodiment of the present application.

[0065] Fig. 2 is a schematic diagram of a control device according to an embodiment of the present application.

[0066] Fig. 3 is a schematic diagram of a blood pressure signal acquisition device according to an embodiment of the present application.

[0067] Fig. 4 is an enlarged view of a fiber-optic pressure sensor and a balloon portion according to an embodiment of the present application.

[0068] Fig. 5 is a system interaction diagram according to an embodiment of the present application.

[0069] Fig. 6 is a flowchart of a blood pressure feature position extraction method according to an embodiment of the present application.

[0070] Fig. 7 is a schematic diagram of a multi-channel signal according to an embodiment of the present application.

[0071] Fig. 8 is a diagram of an aortic blood pressure waveform during aortic counterpulsation according to an embodiment of the present application.

[0072] Fig. 9 is a flowchart of a screening step according to an embodiment of the present application.

[0073] Fig. 10 is a schematic diagram of an adaptive window according to an embodiment of the present application.

[0074] Fig. 11 is a flowchart of an adaptive window parameter acquisition step according to an embodiment of the present application.

[0075] Fig. 12 is a logic diagram of a blood pressure feature position extraction method according to an embodiment of the present application.

[0076] Fig. 13 is a structural block diagram of a blood pressure feature position extraction apparatus according to an embodiment of the present application.

[0077] Fig. 14 is an internal structure diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0078] To make the objectives, technical solutions, and advantages of the present application clearer, further detailed descriptions will be given below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely intended to explain the present application, and are not intended to limit the present application.

[0079] The blood pressure feature position extraction method provided by the embodiments of the present application can be applied to a system as shown in Fig. 1, which includes a control device, a photoelectric signal acquisition device, and a blood pressure signal acquisition device. The control device is in communication connection with the photoelectric signal acquisition device and the blood pressure signal acquisition device, respectively.

[0080] In one embodiment, in combination with the control device shown in FIG. 2, the control device can be an IABP device, for example, an intra-aortic balloon pump (IABP) device. The IABP device includes a display screen, a fiber pressure interface, and an electrocardio interface. The photoelectric signal acquisition device is connected to the IABP device through a connecting line and the electrocardio interface, and the blood pressure signal acquisition device is connected to the IABP device through an optical fiber and the fiber pressure interface. The IABP device is used to determine whether the blood pressure signal reaches the inflation and deflation requirement, and to complete the inflation and deflation of the balloon by controlling the IABP motor.

[0081] In one embodiment, in combination with FIG. 3, which is a schematic diagram of a blood pressure signal acquisition device, the blood pressure signal acquisition device can be a balloon device, including a fiber connector, a fiber pressure sensor, and a balloon. Specifically, in combination with FIG. 4, which is an enlarged view of the fiber pressure sensor and the balloon part in the embodiment shown in FIG. 3, in this embodiment, the fiber pressure sensor is a pressure monitoring device made by using the Fabry-Perot (hereinafter referred to as F-P) interferometer principle. When the aortic pressure value changes, the F-P cavity length changes, resulting in a significant difference in interference fringes due to the cavity length. The interference fringes are received at the detection end, and the blood pressure electrical signal is finally transmitted to the IABP device through the built-in demodulator of the sensor.

[0082] Specifically, in combination with FIG. 5, which is a system interaction diagram in one embodiment, in this embodiment, the IABP device includes a computer program corresponding to the blood pressure feature position extraction method, which processes and judges the blood pressure electrical signal transmitted once every 0.002s (500Hz) and controls the motor according to the judgment result to achieve indirect control of the inflation and deflation of the balloon. The blood pressure error is derived from the cavity length calculation error and the random error of the demodulation circuit. After calibration (i.e., taking the local atmospheric pressure as a reference), the blood pressure is derived from the difference of the calibrated pressure. The sampling frequency is 500Hz, and each sampling is independent. The single error is derived from the drift of the true value, and the overall does not have cumulative effect. The error between the blood pressure collected at any time and the true blood pressure is within ±1mmHg, and the maximum error is not more than 3mmHg.

[0083] In this application, the blood pressure signal mentioned refers to the aortic blood pressure signal.

[0084] In one exemplary embodiment, as shown in FIG. 6, a blood pressure feature position extraction method is provided, which is applied to the control device in FIG. 1 as an example for illustration, including the following steps S602 to S608. Among them:

[0085] S602: Obtain the current electrocardio signal and the current blood pressure signal.

[0086] The current electrocardiosignal is obtained by an electrocardiosignal acquisition device, and can be obtained by a conventional medical electrocardio electrode.

[0087] The current blood pressure signal is obtained by a blood pressure signal acquisition device. The current blood pressure signal includes a first blood pressure signal and a second blood pressure signal. The first blood pressure signal can be an absolute aortic blood pressure signal, and the second blood pressure signal is a relative aortic blood pressure signal.

[0088] In an optional embodiment, the step of obtaining the current electrocardiosignal and the current blood pressure signal can include: obtaining an electrocardiosignal collected by an electrocardio device as the current electrocardiosignal; obtaining a first measured blood pressure signal collected by a sensor, converting the first measured blood pressure signal based on the local atmospheric pressure to obtain the first blood pressure signal; converting a second measured blood pressure signal based on the obtained last sensor collected second measured blood pressure signal to obtain the second blood pressure signal; taking the first blood pressure signal and the second blood pressure signal as the first current blood pressure signal, and taking the second blood pressure signal as the second current blood pressure signal, wherein the current blood pressure signal includes the first current blood pressure signal and the second current blood pressure signal.

[0089] In the embodiment, the current blood pressure signal includes two channels of blood pressure signals, i.e., the first blood pressure signal and the second blood pressure signal. The first blood pressure signal is an absolute blood pressure signal, and the second blood pressure signal is a relative blood pressure signal. The two blood pressure signals are processed in parallel. In the embodiment, as shown in FIG. 7, the absolute aortic pressure signal is defined as a numerical result after conversion calculation based on the local atmospheric pressure, and any measurement is referenced to the calibration pressure as a standard. The relative aortic pressure signal is defined as a numerical result after conversion calculation based on the last lumen conversion blood pressure, and each measurement is referenced to the last aortic pressure value as a standard.

[0090] In actual application, the electrocardiosignal is obtained from an electrocardiosignal acquisition device of a control device, and the sampling frequency is 1KHz. The absolute aortic blood pressure signal and the relative aortic blood pressure signal are both obtained from a blood pressure signal acquisition device, so as to obtain accurate and real-time aortic pressure state to the greatest extent.

[0091] In the embodiment, the current electrocardiosignal, the first blood pressure signal, and the second blood pressure signal can be three independent signal channels, but the first blood pressure signal and the second blood pressure signal are obtained based on blood pressure signals collected by a blood pressure signal acquisition device. The three independent signal channels can be processed respectively, for example, processed in parallel by a multi-thread or multi-process manner, so as to provide multi-dimensional judgment of the arrival of the inflation and deflation phase, thereby making the judgment result of the inflation and deflation phase more accurate.

[0092] S604: performing parameter analysis on the current electrocardiosignal and the current blood pressure signal to obtain a target parameter group.

[0093] The target parameter group is obtained based on parameter analysis of the current electrocardiosignal and the current blood pressure signal. The target parameters in the target parameter group are characteristic parameters closely related to blood pressure. The target parameters can include an average RR interval, a QRS wave duration, a T wave duration, a systolic pressure, a diastolic pressure, a mean pressure, a systolic duration, a diastolic duration, a systolic rising duration, a diastolic falling duration, a diastolic inflection point, and a specific adaptive window threshold group. It should be noted that the physiological state of the object in a certain time period can be considered stable, and therefore the target parameter group is also stable.

[0094] S606: Blood pressure feature position extraction is performed on the current blood pressure signal to obtain initial blood pressure feature positions.

[0095] The initial blood pressure feature positions include an aortic blood pressure feature point, and the aortic blood pressure feature point includes at least one of four feature points, i.e., a systolic peak, a dicrotic notch, a diastolic peak, and a diastolic end. In this embodiment, the four feature points in each cardiac cycle are obtained by performing blood pressure feature position extraction on the current blood pressure signal.

[0096] It should be noted that the calculation period of the target parameter group is greater than the calculation period of the initial blood pressure feature positions, that is, the target parameter group is considered unchanged in a certain time period, thereby reducing the calculation amount.

[0097] S608: The initial blood pressure feature positions are screened according to the target parameter group to obtain target blood pressure feature positions.

[0098] The target blood pressure feature positions are the charging and discharging phases. For example, the dicrotic notch feature position corresponds to the charging phase, and the diastolic end corresponds to the discharging phase.

[0099] In this embodiment, the initial blood pressure feature positions are screened by the obtained target parameter group to obtain the target blood pressure feature positions.

[0100] The blood pressure feature position extraction method obtains the current electrocardiosignal and the current blood pressure signal, uses the two signals to extract the blood pressure feature positions, and lays a foundation for the extraction of the blood pressure feature positions through multi-channel signal acquisition. The current electrocardiosignal and the current blood pressure signal are subjected to parameter analysis to obtain a target parameter group. The current blood pressure signal is subjected to blood pressure feature position extraction to obtain initial blood pressure feature positions. The initial blood pressure feature positions are screened according to the target parameter group to obtain target blood pressure feature positions. In the above method, a parameter group is designed, the initial blood pressure feature positions are screened through the parameter group, and the recognition accuracy is high. In addition, multi-channel input information is introduced in the above method embodiment, and multi-dimensional judgment of the target blood pressure feature positions is provided. Through multi-channel comprehensive recognition and comparison and judgment, the reliability is greatly improved, and a multi-thread processor can avoid increasing the delay.

[0101] In an optional embodiment, the step of extracting blood pressure feature positions from the current blood pressure signal to obtain initial blood pressure feature positions can include: extracting a first cycle segmentation result based on the current electrocardiogram signal, extracting a second cycle segmentation result based on the current blood pressure signal; obtaining a target cycle segmentation result according to the first cycle segmentation result and the second cycle segmentation result; and extracting feature positions from the current blood pressure signal based on the target cycle segmentation result to obtain the initial blood pressure feature positions.

[0102] The more accurate the target cycle segmentation result is, the more accurate the initial blood pressure feature positions are identified. In order to improve the accuracy of the target cycle segmentation result, in the embodiment, the electrocardiogram signal and the blood pressure signal are combined to double guarantee the accuracy of the target cycle segmentation result.

[0103] In the embodiment, the current electrocardiogram signal and the current blood pressure signal of each channel are respectively subjected to cycle segmentation, for example, a first cycle segmentation result is extracted based on the current electrocardiogram signal, and a second cycle segmentation result is extracted based on the current blood pressure signal, so that the target cycle segmentation result is obtained according to the first cycle segmentation result and the second cycle segmentation result. Each channel can include a quality evaluation step, so that the first cycle segmentation result and the second cycle segmentation result are respectively evaluated by the quality evaluation step, and the target cycle segmentation result is obtained based on the evaluation result. The evaluation method can be any method, which is not limited here. In the embodiment, the R-wave interval array of the electrocardiogram signal is applied to correspond to the diastolic end time array of the aortic blood pressure signal, combined with a clustering algorithm structure, and set with a medical cognitive threshold, which can basically achieve a comprehensive and accurate cardiac cycle segmentation function, and then more accurately identify each feature point.

[0104] In the above embodiment, the target cycle segmentation result is obtained by combining the signals of multiple channels, thereby guaranteeing the accuracy of the target cycle segmentation result and laying a foundation for the accuracy of the initial blood pressure feature positions.

[0105] In an optional embodiment, the step of extracting blood pressure feature positions from the current blood pressure signal to obtain initial blood pressure feature positions can include: extracting a first phase position and a second phase position from the current blood pressure signal; obtaining a predetermined time difference value; obtaining a third phase position based on the first phase position and the time difference value; and taking the second phase position and the third phase position as the initial blood pressure feature positions.

[0106] In the embodiment, the first phase position is a systolic peak position, the second phase position is a diastolic end phase position, and the third phase position is a incisura jugularis position.

[0107] The inflation phase is consistent with the dicrotic notch phase of the aortic blood pressure signal, and the deflation phase is consistent with the end diastolic phase. However, due to the difficulty in identifying the dicrotic notch itself, the technical requirements for the signal feature point extraction algorithm structure are extremely harsh, and there is a technical contradiction between time delay and accuracy. Specifically, in combination with FIG. 8, which is an aortic blood pressure waveform graph in counterpulsation, the position of the dicrotic notch in the counterpulsation theory is determined in combination with the position of the systolic peak in the present embodiment. The theoretical basis is that after the appearance of the systolic peak, the dicrotic notch must follow in physiology, and the time difference is relatively fixed. Moreover, the systolic peak waveform is obvious and easy to identify, and can be used as a pre-work for identifying the dicrotic notch phase. By combining the systolic peak phase identification method with the dicrotic notch phase identification technology, that is, by determining the position of the systolic peak, based on the position of the systolic peak and the time difference between the position of the systolic peak and the position of the dicrotic notch, the position of the dicrotic notch is obtained. Not only is the identification accuracy greatly improved, but also because the systolic peak phase naturally precedes the dicrotic notch phase, it can compensate for the time delay of the algorithm structure itself (about 60 ms on average), giving the algorithm structure relatively generous computing power time, and the stability is obviously improved.

[0108] In an optional embodiment, the step of obtaining the target blood pressure feature position according to the target parameter group can include: obtaining a position screening condition set, the position screening condition set including at least one position screening condition; and determining that the initial blood pressure feature position is the target blood pressure feature position when at least one position screening condition in the corresponding position screening condition set is satisfied based on each target parameter in the target parameter group.

[0109] The position screening condition set can include multiple position screening condition sets, and each position screening condition set includes at least one position screening condition. In the present embodiment, in combination with FIG. 9, which is a flowchart of the screening step in an embodiment, after starting the counterpulsation function and setting the mode to the blood pressure trigger mode, the initial blood pressure feature position is waited for, the corresponding first position screening condition set is obtained, and the inflation point is judged. The next initial blood pressure feature position is waited for, the corresponding second position screening condition set is obtained, and the deflation point is judged. The corresponding third position screening condition set is obtained, and the inflation point is judged. The next initial blood pressure feature position is waited for, the corresponding fourth position screening condition set is obtained, and the deflation point is judged.

[0110] The first position screening condition set can include whether the systolic pressure is within the systolic pressure threshold, whether there is a peak point in the absolute blood pressure within 100 milliseconds, whether there is a relative blood pressure zero point, whether the systolic pressure appears within the first 100 milliseconds, whether the double-channel correlation (i.e., the correlation calculation result below) reaches the threshold, and whether the heart rhythm state changes.

[0111] The second position screening condition set can include whether the diastolic pressure is within a diastolic pressure threshold, whether there is a minimum point in the absolute blood pressure within 200 milliseconds, whether there is a relative blood pressure zero point, whether the relative blood pressure is generally decreased within the first 100 milliseconds, whether the dual-channel correlation (i.e., the correlation calculation result below) reaches a threshold, whether the inflation point has occurred, and whether the heart rhythm state has changed.

[0112] The third position screening condition set can include whether the systolic pressure is within a systolic pressure threshold, whether there is a peak point in the absolute blood pressure within 100 milliseconds, whether it includes a fourth zero point in the action cycle in the relative blood pressure, whether a second peak has occurred in the relative blood pressure, whether there is a relative blood pressure zero point, whether it appears at the end of the cardiac cycle (x%), whether the dual-channel correlation (i.e., the correlation calculation result below) reaches a threshold, whether the previous action is deflation, whether the time difference from the last inflation point is greater than 60% of the cardiac cycle value, whether the heart rhythm state has changed, and whether the counterpulsation is stopped.

[0113] The fourth position screening condition set can include whether the diastolic pressure is within a diastolic pressure threshold, whether there is a minimum point in the absolute blood pressure within 200 milliseconds, whether it includes a third zero point in the action cycle in the relative blood pressure, whether a first peak has occurred in the relative blood pressure, whether a second zero point has occurred in the relative blood pressure, whether there is a relative blood pressure zero point, whether the relative blood pressure is generally decreased within the first 100 milliseconds, whether the dual-channel correlation (i.e., the correlation calculation result below) reaches a threshold, whether it is in the tail of the action cycle (y%), whether the previous action is inflation, whether the time difference from the last deflation point is greater than 60% of the cardiac cycle value, whether the heart rhythm state has changed, and whether the counterpulsation is stopped. The above position screening condition sets are only illustrative, and a person skilled in the art can set conditions as needed, which are not specifically limited here.

[0114] In the embodiment, when at least one position screening condition in the corresponding position screening condition set is satisfied based on the determination of each target parameter in the target parameter group, the initial blood pressure feature position is the target blood pressure feature position.

[0115] In actual processing, it can be that only any one of the position screening conditions in the position screening condition set is satisfied, or that any part of the position screening conditions in the position screening condition set is satisfied, and the number of the part of the position screening conditions can include 2, 3, 4, etc., which is not specifically limited in number. Or when all the position screening conditions in the position screening condition set are satisfied at the initial blood pressure feature position, it is determined that the initial blood pressure feature position is the target blood pressure feature position, that is, the corresponding inflation point or deflation point.

[0116] In an optional embodiment, after the corresponding set of position screening conditions is obtained, the above method further comprises: obtaining a local condition set, the local condition set being a subset of the set of position screening conditions; obtaining a score corresponding to each position screening condition in the local condition set based on each target parameter in the target parameter group; obtaining a weight of each position screening condition in the local condition set, and obtaining a weighted value of each position screening condition in the local condition set based on the score and the weight; when the weighted value is greater than a condition threshold, determining that the target parameters corresponding to the local condition set satisfy each position screening condition in the local condition set.

[0117] In the present embodiment, a fusion parameter weighting algorithm is introduced. A part of the position screening conditions in the set of position screening conditions is obtained to form a local condition set. Each position screening condition in the local condition set corresponds to a score. For example, the score can be any value from 1 to 10. In other embodiments, the score can also be other values. A person skilled in the art can pre-set the score of each position screening condition in the local condition set. If the position screening condition is satisfied, the result of the position screening condition is the score. Otherwise, the result of the position screening condition is a preset value, for example, zero.

[0118] In addition, each position screening condition also corresponds to a weight. Optionally, the weights of the position screening conditions in the local condition set can be the same or different. In this way, the weighted value of the weight value of each position screening condition in the local condition set can be calculated based on the score and the weight. Then, the weighted value is compared with a condition threshold. If the weighted value is greater than the condition threshold, it is determined that the target parameters corresponding to the local condition set satisfy each position screening condition in the local condition set, without the need for each position screening condition in the local condition set to be satisfied.

[0119] For the convenience of understanding, the second to fourth position screening conditions in the third set of position screening conditions are taken as an example for description. The corresponding scores of the second to fourth position screening conditions in the third set of position screening conditions are assigned and determined to obtain corresponding determined scores. Then, the weights are obtained to obtain weighted values. For example, the sum of the weighted values is added and divided by the number of items. If the weighted value is greater than the condition threshold, for example, six (in other embodiments, it can be other values), it is considered that each target parameter in the target parameter group corresponding to the local condition set satisfies each position screening condition in the local condition set. In combination with the results of other position screening conditions in the third set of position screening conditions, it is determined whether the initial blood pressure feature position corresponding to the local condition set can be used as the target blood pressure feature position.

[0120] In an optional embodiment, the target parameter group includes an adaptive window parameter. The above method further comprises: performing a correlation calculation on the adaptive window parameter and the current blood pressure signal to obtain a correlation calculation result; and when the correlation calculation result is greater than or equal to an autocorrelation threshold, determining that a position screening condition corresponding to the autocorrelation is satisfied.

[0121] The adaptive window parameter is obtained based on the current electrocardiosignal and the current blood pressure signal when the target parameter group is calculated, and the update period of the adaptive window parameter is greater than the calculation period of the initial blood pressure feature position, that is, the adaptive window parameter is considered to be constant within a certain time.

[0122] The correlation calculation is to calculate the correlation of the data of two channels, that is, the correlation of the target parameter in the target parameter group calculated by the parameter group calculation channel and the current blood pressure signal. The current blood pressure signal includes the first blood pressure signal and the second blood pressure signal, which are calculated separately to obtain the correlation calculation result of the target parameter in the target parameter group and the first blood pressure signal, and the correlation calculation result of the target parameter in the target parameter group and the second blood pressure signal, wherein the target parameter is an adaptive window function wave, and the specific calculation formula is the same, and is as follows:

[0123] wherein, is the correlation calculation result, t is the current time, |x(n)| is the first blood pressure signal or the second blood pressure signal, |φ(n)| is the corresponding adaptive window function wave, and the adaptive window function wave is referred to as the adaptive window parameter below, which is obtained by parameter analysis on the current electrocardiosignal and the current blood pressure signal, and details can be referred to below.

[0124] wherein, R xx represents a self-correlation threshold value with patient characteristics. If the result of R is greater than or equal to 80% of the self-correlation threshold value with patient characteristics, that is, it is considered that the current time has met the adaptive window filtering standard. The self-correlation threshold value can be a parameter in the target parameter group, which is obtained by parameter analysis on the current electrocardiosignal and the current blood pressure signal. The position screening condition corresponding to the self-correlation is the condition related to the correlation in the set of position screening conditions, for example, whether the double-channel correlation in the above meets the threshold value.

[0125] In one embodiment, before the adaptive window parameter is correlated with the current blood pressure signal to obtain the correlation calculation result, the above method further comprises: determining the current signal channel, the counterpulsation information and the inflation and deflation information; and selecting the adaptive window parameter corresponding to the current signal channel, the counterpulsation information and the inflation and deflation information.

[0126] In this embodiment, multiple adaptive window parameters are included, respectively corresponding to two channels of absolute aortic pressure and relative aortic pressure, two categories of before and after counterpulsation, two characteristics of inflation point and deflation point, and eight adaptive windows with parameters are formed per characteristic cycle. Referring to FIG. 10, (r, c) represents (row, column), the first parameter: the absolute aortic pressure signal is denoted as 'aBP', and the relative aortic blood pressure signal is denoted as 'rBP'; the second parameter: the before counterpulsation signal is denoted as 'b', and the after counterpulsation signal is denoted as 'a'; the third parameter: the inflation phase judgment is denoted as 'i', and the deflation phase judgment is denoted as 'd'. (1, 1) is (aBP, b, i), (1, 2) is (aBP, a, i), (2, 1) is (aBP, b, d), (2, 2) is (aBP, a, d), (3, 1) is (rBP, b, i), (3, 2) is (rBP, a, i), (4, 1) is (rBP, b, d), and (4, 2) is (rBP, a, d).

[0127] In an optional embodiment, the target parameter group includes adaptive window parameters. The extraction manner of the adaptive window parameters includes: performing feature point extraction on the current blood pressure signal to obtain initial feature points for signal segmentation; performing screening on the initial feature points according to a preset condition to obtain target feature points, and performing signal segmentation based on the target feature points; obtaining each adaptive window module; based on the current blood pressure signal after signal segmentation, adjusting each adaptive window module to obtain each initial adaptive window parameter; and optimizing each initial adaptive window parameter to obtain each adaptive window parameter.

[0128] Specifically, referring to FIG. 11, which is a flowchart of the adaptive window parameter acquisition step in an embodiment, in this embodiment, the current blood pressure signal is periodically acquired, and the period can be the same as the parameter calculation period of the parameter channel. The current blood pressure signal is preprocessed, and feature points are extracted after preprocessing, which are used as initial feature points for signal segmentation. Then, the initial feature points are screened according to a preset condition to obtain target feature points, for example, points with large errors are removed, and the preset condition for screening the initial feature points is not specifically limited. After obtaining the target feature points, signal segmentation is performed based on the target feature points to obtain a first cycle segmentation result, and each adaptive window module is obtained. The adaptive window template is also multiple, for example, 8 in the above, so that parameter calculation is performed based on the signal segmentation result, and the adaptive window template is adjusted to obtain the initial adaptive window parameter.

[0129] The optimization of the initial adaptive window parameter mainly includes normalization and frequency domain adjustment. The process of normalization is to adjust the initial adaptive window parameter to the target range, and the frequency domain adjustment is to reduce the error, for example, first perform Fourier transform on the initial adaptive window parameter, then perform frequency domain adjustment, then perform inverse Fourier transform, finally obtain a period of adaptive window parameter, and then perform window extension, that is, copy, to obtain the final adaptive window parameter.

[0130] The adaptive window parameter described above is obtained based on the current blood pressure signal of the object, and the parameter accumulation is performed to form a parametric adaptive function window as one of the important criterion sources in real-time judgment. The adaptive window is applied to real-time signal feature judgment, and efficient analysis is performed on whether the inflation and deflation phase comes. The calculation time length is limited by the processor computing speed, algorithm structure formula complexity, and data loading information amount. According to the test measurement, the time length is within 10 ms, which is within the inflation and deflation tolerance delay range of IABP treatment requirements.

[0131] For the convenience of understanding, combined with FIG. 12, FIG. 12 is a logic diagram of a blood pressure feature position extraction method in an embodiment, which mainly includes a parameter calculation process, a real-time signal processing process, and a decision-making process.

[0132] In the parameter calculation process, the current electrocardiogram signal and the current blood pressure signal collected by the hardware are obtained, and signal preprocessing and signal analysis are performed thereon. The signal preprocessing mainly removes invalid signals, and the signal analysis obtains a parameter group. In order to improve the processing efficiency, the current electrocardiogram signal, the first blood pressure signal, and the second blood pressure signal are processed by corresponding threads respectively, and finally the parameters obtained by the multiple threads are fused to obtain a target parameter group, which includes multiple target parameters. Since the physiological state of the object can be regarded as stable within a certain time period, the target parameter group is stable within a certain time period, so the calculation period of the target parameter group in the parameter calculation process can be greater than the processing period of the current blood pressure signal, for example, ten seconds. That is, only the current electrocardiogram signal and the current blood pressure signal collected by the hardware are obtained and stored within ten seconds, and the calculation of the target parameter group is performed when ten seconds elapse, and the target parameter group obtained last time is updated based on the calculation result.

[0133] The real-time signal processing process is used for processing the current blood pressure signal in real time, and the initial blood pressure feature position is obtained by preprocessing and analyzing the current blood pressure signal, and the correlation calculation result is obtained based on the adaptive window obtained by the parameter group calculation process and the current blood pressure signal.

[0134] It should be noted that the parameter calculation flow and the real-time signal processing flow are implemented by parallel processes, and the parameter calculation flow and the real-time signal processing flow are executed in parallel, and then combined with the output to perform the algorithm structure execution flow, and finally issue instructions to control the motor movement to complete the inflation and deflation of the IABP balloon, so as to improve the processing efficiency.

[0135] The decision flow is used to screen the initial blood pressure feature position based on the target parameter group to obtain the target blood pressure feature position, so as to complete the determination of the inflation and deflation point. In the present application, the systolic aortic pressure peak is selected instead of the counterpulsation notch to complete time compensation, which greatly reduces the inevitable time delay problem caused by algorithm structure execution.

[0136] In the present application, the problems of low counterpulsation efficiency, high error rate, and even easy to cause harm to the patient by reverse auxiliary in the case of serious electrocardiogram abnormalities or arrhythmia are solved. The multi-core multi-thread processor is used. Due to the progress of electronic information technology, the processor computing power has been greatly improved, and the price is getting lower and lower, so compared with the early IABP equipment, the cost does not increase greatly. The multi-core multi-thread processor is suitable for the signal processing work of the multi-channel multi-thread method, and can synchronously perform real-time double aortic pressure channel adaptive window calculation and feature point determination, and efficiently identify the inflation and deflation phase. The aortic pressure waveform selected in the present application is stable, and the accuracy is greatly improved by performing IABP aortic pressure counterpulsation, which can reach 98% on average, not less than 95%. After the improvement of the present application, due to the compensation effect and the calculation time test, the signal counterpulsation calculation time delay of the present application can be reduced to 80ms, and the comprehensive counterpulsation time delay can be reduced to 40ms, and due to the improvement of the accuracy, the treatment effect of the critical patient with poor heart rhythm condition is obviously improved.

[0137] It should be understood that although each step in the flowchart involved in each of the above embodiments is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in the flowchart involved in each of the above embodiments can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or steps or stages in other steps.

[0138] Based on the same inventive concept, the application further provides a blood pressure feature position extraction device for implementing the blood pressure feature position extraction method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more blood pressure feature position extraction device embodiments provided below can refer to the limitations of the blood pressure feature position extraction method described above, which will not be repeated here.

[0139] In an exemplary embodiment, as shown in FIG. 13, a blood pressure feature position extraction device is provided, comprising a signal acquisition module 1301, a parameter group acquisition module 1302, a feature extraction module 1303, and a screening module 1304, wherein:

[0140] The signal acquisition module 1301 is configured to acquire a current electrocardiogram signal and a current blood pressure signal.

[0141] The parameter group acquisition module 1302 is configured to perform parameter analysis on the current electrocardiogram signal and the current blood pressure signal to obtain a target parameter group.

[0142] The feature extraction module 1303 is configured to perform blood pressure feature position extraction on the current blood pressure signal to obtain an initial blood pressure feature position.

[0143] The screening module 1304 is configured to screen the initial blood pressure feature position according to the target parameter group to obtain a target blood pressure feature position.

[0144] In an optional embodiment, the signal acquisition module 1301 is specifically configured to acquire an electrocardiogram signal collected by an electrocardiogram device as a current electrocardiogram signal; acquire a measured blood pressure signal collected by a sensor, convert the first measured blood pressure signal based on the local atmospheric pressure to obtain a first blood pressure signal; convert a second measured blood pressure signal based on the acquired second measured blood pressure signal collected by the sensor to obtain a second blood pressure signal; take the first blood pressure signal and the second blood pressure signal as a first current blood pressure signal, and take the second blood pressure signal as a second current blood pressure signal, wherein the current blood pressure signal includes the first current blood pressure signal and the second current blood pressure signal.

[0145] In an optional embodiment, the feature extraction module 1303 is specifically configured to perform period extraction based on the current electrocardiogram signal to obtain a first period segmentation result, perform period extraction based on the current blood pressure signal to obtain a second period segmentation result; obtain a target period segmentation result according to the first period segmentation result and the second period segmentation result; and perform feature position extraction on the current blood pressure signal based on the target period segmentation result to obtain an initial blood pressure feature position.

[0146] In an optional embodiment, the feature extraction module 1303 is specifically configured to extract a feature position of the current blood pressure signal to obtain a first phase position and a second phase position; obtain a predetermined time difference value; obtain a third phase position based on the first phase position and the time difference value; and take the second phase position and the third phase position as initial blood pressure feature positions.

[0147] In an optional embodiment, the screening module 1304 is specifically configured to obtain a position screening condition set, the position screening condition set including at least one position screening condition; and determine that the initial blood pressure feature position is a target blood pressure feature position when at least one position screening condition in the position screening condition set corresponding to each target parameter in the target parameter group is determined to be satisfied.

[0148] In an optional embodiment, the screening module 1304 is specifically configured to obtain a local condition set, the local condition set being a subset of the position screening condition set; obtain a score corresponding to each position screening condition in the local condition set based on each target parameter in the target parameter group; obtain a weight of each position screening condition in the local condition set, and obtain a weighted value of each position screening condition in the local condition set based on the score and the weight; and determine that each target parameter corresponding to the local condition set satisfies each position screening condition in the local condition set when the weighted value is greater than a condition threshold.

[0149] In an optional embodiment, the target parameter group includes an adaptive window parameter; and the parameter group obtaining module 1302 is specifically configured to perform correlation calculation on the adaptive window parameter and the current blood pressure signal to obtain a correlation calculation result; and determine that a position screening condition corresponding to self-correlation is satisfied when the correlation calculation result is greater than or equal to a self-correlation threshold.

[0150] In an optional embodiment, the parameter group obtaining module 1202 is specifically configured to determine a current signal channel, counterpulsation information, and inflation / deflation information; and select an adaptive window parameter corresponding to the current signal channel, the counterpulsation information, and the inflation / deflation information.

[0151] In an optional embodiment, the target parameter group includes an adaptive window parameter; and the parameter group obtaining module 1302 is specifically configured to extract a feature point of the current blood pressure signal to obtain an initial feature point for signal segmentation; screen the initial feature point to obtain a target feature point, and perform signal segmentation based on the target feature point; obtain each adaptive window module; adjust each adaptive window module based on the current blood pressure signal after signal segmentation to obtain each initial adaptive window parameter; and optimize each initial adaptive window parameter to obtain each adaptive window parameter.

[0152] The modules in the blood pressure feature position extraction device can be implemented by software, hardware, or a combination thereof. The modules can be embedded in or independent of a processor in a computer device in hardware form, or stored in a memory in a computer device in software form, so that the processor can call and execute the operations of the modules.

[0153] In an example embodiment, a computer device, which can be a terminal, is provided. An internal structure diagram of the computer device can be as shown in FIG. 14. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected through a system bus. The communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to perform wired or wireless communication with external terminals. The wireless communication can be achieved by WIFI, mobile cellular network, NFC (Near Field Communication), or other technologies. The computer program is executed by the processor to implement a blood pressure feature position extraction method. The display unit of the computer device is configured to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, a trackball, or a touchpad arranged on the shell of the computer device. The input device can also be an external keyboard, a touchpad, or a mouse, etc.

[0154] Those skilled in the art can understand that the structure shown in FIG. 14 is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. Specifically, the computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0155] In an example embodiment, a computer device is also provided, which includes a memory and a processor. The memory stores a computer program. The processor executes the computer program to implement the steps in the above method embodiments.

[0156] In an example embodiment, a computer readable storage medium is provided, which stores a computer program. The computer program is executed by a processor to implement the steps in the above method embodiments.

[0157] In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of any of the above method embodiments.

[0158] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0159] It can be understood by those skilled in the art that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. Any reference to memory, database or other medium used in the embodiments provided by the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided by the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided by the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0160] Any combination of the technical features in the above embodiments can be made, and for the sake of brevity, not all possible combinations are described, however, any combination of the technical features is deemed to be within the scope of the present disclosure as long as there is no inconsistency.

[0161] The above embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but it should not be understood as a limitation on the patent scope of the present application. It should be pointed out that for ordinary skilled persons in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for extracting blood pressure feature position, comprising: obtaining a current electrocardiogram signal and a current blood pressure signal; performing parameter analysis on the current electrocardiogram signal and the current blood pressure signal to obtain a target parameter group; extracting a blood pressure feature position from the current blood pressure signal to obtain an initial blood pressure feature position; screening the initial blood pressure feature position according to the target parameter group to obtain a target blood pressure feature position. 2.The method of claim 1, wherein the obtaining a current electrocardiogram signal and a current blood pressure signal comprises: obtaining an electrocardiogram signal collected by an electrocardiogram device as a current electrocardiogram signal; obtaining a first measured blood pressure signal collected by a sensor, converting the first measured blood pressure signal based on local atmospheric pressure to obtain a first blood pressure signal; converting a second measured blood pressure signal collected by the sensor based on the obtained second measured blood pressure signal to obtain a second blood pressure signal; taking the first blood pressure signal as a first current blood pressure signal and taking the second blood pressure signal as a second current blood pressure signal, wherein the current blood pressure signal comprises the first current blood pressure signal and the second current blood pressure signal. 3.The method of claim 1, wherein the extracting a blood pressure feature position from the current blood pressure signal to obtain an initial blood pressure feature position comprises: performing period extraction based on the current electrocardiogram signal to obtain a first period segmentation result and performing period extraction based on the current blood pressure signal to obtain a second period segmentation result; obtaining a target period segmentation result according to the first period segmentation result and the second period segmentation result; performing feature position extraction on the current blood pressure signal based on the target period segmentation result to obtain an initial blood pressure feature position. 4.The method of claim 1, wherein the extracting a blood pressure feature position from the current blood pressure signal to obtain an initial blood pressure feature position comprises: performing feature position extraction on the current blood pressure signal to obtain a first phase position and a second phase position; obtaining a predetermined time difference value; obtaining a third phase position based on the first phase position and the time difference value; taking the second phase position and the third phase position as an initial blood pressure feature position. 5.The method of claim 1, wherein the screening the initial blood pressure feature position according to the target parameter group to obtain a target blood pressure feature position comprises: obtaining a position screening condition set, wherein the position screening condition set comprises at least one position screening condition; when at least one position screening condition in the position screening condition set corresponding to each target parameter in the target parameter group is determined to be satisfied, taking the initial blood pressure feature position as a target blood pressure feature position. 6.The method of claim 5, wherein after the obtaining a corresponding position screening condition set, the method further comprises: obtaining a local condition set, wherein the local condition set is a subset of the position screening condition set; obtaining a score corresponding to each position screening condition in the local condition set based on each target parameter in the target parameter group. obtaining a weight of each position screening condition in the local condition set, and obtaining a weighted value of each position screening condition in the local condition set based on the score and the weight; when the weighted value is greater than a condition threshold, determining that a target parameter corresponding to the local condition set satisfies each position screening condition in the local condition set.

7. The method of claim 5, wherein the target parameter group comprises an adaptive window parameter; the method further comprises: performing correlation calculation on the adaptive window parameter and the current blood pressure signal to obtain a correlation calculation result; when the correlation calculation result is greater than or equal to a self-correlation threshold, determining that the position screening condition corresponding to the self-correlation is satisfied.

8. The method of claim 7, wherein before the correlation calculation on the adaptive window parameter and the current blood pressure signal to obtain the correlation calculation result, the method further comprises: determining a current signal channel, counterpulsation information, and inflation / deflation information; selecting an adaptive window parameter corresponding to the current signal channel, counterpulsation information, and inflation / deflation information.

9. The method of claim 1, wherein the target parameter group comprises an adaptive window parameter; and the extraction method of the adaptive window parameter comprises: performing feature point extraction on the current blood pressure signal to obtain initial feature points for signal segmentation; performing screening on the initial feature points according to a preset condition to obtain target feature points, and performing signal segmentation based on the target feature points; obtaining each adaptive window module; adjusting each adaptive window module based on the current blood pressure signal after signal segmentation to obtain each initial adaptive window parameter; optimizing each initial adaptive window parameter to obtain each adaptive window parameter.

10. The method of claim 3, wherein the initial blood pressure feature position comprises an aortic blood pressure feature point; and the aortic blood pressure feature point comprises at least one of a systolic peak, a dicrotic notch, a diastolic peak, and a diastolic end.

11. The method of claim 4, wherein the first phase position is a systolic peak position, the second phase position is a diastolic end phase position, and the third phase position is a dicrotic notch phase position.

12. The method of claim 9, wherein the optimization of each initial adaptive window parameter comprises normalization and frequency domain adjustment.

13. A blood pressure feature position extraction device, comprising: a signal acquisition module configured to acquire a current electrocardiogram signal and a current blood pressure signal; a parameter group acquisition module configured to perform parameter analysis on the current electrocardiogram signal and the current blood pressure signal to obtain a target parameter group; a feature extraction module configured to perform blood pressure feature position extraction on the current blood pressure signal to obtain an initial blood pressure feature position; a screening module configured to perform screening on the initial blood pressure feature position according to the target parameter group to obtain a target blood pressure feature position.

14. A counterpulsation device control system, comprising: an electrocardiogram device configured to acquire a current electrocardiogram signal; a sensor configured to acquire a measured blood pressure signal; A control device configured to obtain a target blood pressure feature position based on the blood pressure feature position extraction method of any one of claims 1 to 12, and output an instruction for the counterpulsation device to inflate or deflate at the target blood pressure feature position. A counterpulsation device configured to inflate or deflate based on the instruction.

15. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program, which is executed by a processor, implements the steps of the method of any one of claims 1 to 12.

Images