CN117883057B - Blood pressure measuring method, system and storage medium combining ascending method and descending method - Google Patents

Abstract

The invention discloses a blood pressure measurement method, a blood pressure measurement system and a blood pressure measurement storage medium combining an ascending method and a descending method, and relates to the technical field of noninvasive blood pressure measurement. The invention comprises the following steps: acquiring a first pulse signal set in the pressure increasing process in the cuff pressurizing process; acquiring a second pulse signal set in the pressure reduction process in the cuff pressure release process; respectively carrying out denoising pretreatment on the first pulse signal set and the second pulse signal set; extracting digital signal feature vectors of the first pulse signal set and the second pulse signal set, and extracting pulse conduction time corresponding to each digital signal feature vector; inputting the mapping relation between the digital signal characteristic vector and the pulse conduction time into a long-short-period memory neural network model; and the long-term and short-term memory neural network model identifies whether the blood pressure is lower than normal blood pressure or higher than normal blood pressure according to the mapping relation. The invention can improve the accuracy of blood pressure measurement by respectively measuring the pulse signals under different states.

Description

Blood pressure measurement method, system and storage medium combining ascending method and descending method

Technical Field

The present invention relates to the technical field of non-invasive blood pressure measurement, and more specifically to a blood pressure measurement method, system and storage medium combining an ascending method and a descending method.

Background Art

The occurrence of high blood pressure may lead to cardiovascular or kidney diseases. High-salt and high-fat diets and irregular lifestyles have caused more and more people to suffer from high blood pressure, and the problem of high blood pressure has therefore attracted more and more attention.

As a chronic disease, hypertension itself does not have a significant impact on the body, so many patients find it difficult to detect whether their blood pressure is abnormal. However, once cardiovascular or kidney diseases are caused, it will cause more serious consequences. Therefore, blood pressure is often required to be measured or monitored in real time as an important indicator of physical health monitoring. Relevant studies have shown that daily monitoring and management of patients' blood pressure is effective in preventing hypertension and diseases caused by it. However, there is currently a lack of a simple and easy solution that can measure blood pressure in real time.

The current blood pressure detection method is easily affected by various noises. Therefore, how to provide a simple and effective blood pressure measurement method that avoids the influence of noise is urgently needed to be studied by those skilled in the art.

Summary of the invention

In view of this, the present invention provides a blood pressure measurement method, system and storage medium that combine the ascending method and the descending method, which solves the problems existing in the background technology by compensating each other by the ascending method and the descending method and combining digital signal processing technology.

In order to achieve the above object, the present invention adopts the following technical solution:

A blood pressure measurement method combining an ascending method and a descending method comprises the following steps:

During the cuff pressurization process, obtaining a first pulse signal set during the pressure increase process;

During the cuff pressure release process, obtaining a second pulse signal set during the pressure reduction process;

Performing denoising preprocessing on the first pulse signal set and the second pulse signal set respectively;

Extracting digital signal feature vectors of the first pulse signal set and the second pulse signal set, and extracting the pulse conduction time corresponding to each digital signal feature vector;

The mapping relationship between the digital signal feature vector and the pulse conduction time is input into the long short-term memory neural network model;

The long short-term memory neural network model identifies whether the blood pressure is lower than normal or higher than normal based on the mapping relationship.

Optionally, the method also includes drawing a blood pressure image during the blood pressure measurement process based on the output results of the long short-term memory neural network model.

Optionally, the acquisition process of the first pulse signal set and the second pulse signal set is as follows: according to a preset time interval, the pulse signal is periodically collected to obtain a plurality of periodic signals, and the plurality of periodic signals are arranged in chronological order to obtain a pulse signal set.

Optionally, the process of drawing the blood pressure image is: using an adaptive threshold method to screen the turning points of the data, and then obtaining the main wave trough and the main wave peak of each cycle, and intercepting each main wave trough to the main wave peak as a cycle image.

Optionally, the first pulse signal set and the second pulse signal set are pre-processed for denoising respectively, specifically: the pulse signals are processed in sequence using a second-order bandpass filter and a signal smoothing algorithm based on wavelet filtering, the second-order bandpass filter is used to truncate and denoise the characteristics of the noise, and the signal smoothing algorithm based on wavelet filtering is used to separate and denoise the noise.

Optionally, the pulse conduction time is the time required for blood to flow from the heart to the measurement point, and the conduction time is calculated using characteristics between multiple different signals.

A blood pressure measurement system combining an ascending method and a descending method comprises the following steps:

A first signal acquisition module: used for acquiring a first pulse signal set in a process of increasing pressure during the cuff pressurization process;

A second signal acquisition module: used for acquiring a second pulse signal set in a pressure reduction process during the cuff pressure release process;

De-noising processing module: used for performing de-noising pre-processing on the first pulse signal set and the second pulse signal set respectively;

A characteristic signal extraction module: used to extract digital signal characteristic vectors of the first pulse signal set and the second pulse signal set, and to extract the pulse conduction time corresponding to each digital signal characteristic vector;

Long short-term memory neural network model input module: used to input the mapping relationship between the digital signal feature vector and the pulse conduction time into the long short-term memory neural network model;

Long short-term memory neural network model processing module: used to identify whether the blood pressure is lower than normal or higher than normal based on the mapping relationship.

Optionally, it also includes an image drawing module: used to draw a blood pressure image during the blood pressure measurement process according to the output results of the long short-term memory neural network model.

A computer storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any one of the blood pressure measurement methods combining an ascending method with a descending method are implemented.

It can be known from the above technical solutions that, compared with the prior art, the present invention provides a blood pressure measurement method, system and storage medium combining the ascending method and the descending method, wherein the ascending method blood pressure measurement has the advantages of being fast and comfortable, but has poor anti-interference ability. When there is interference during the measurement process or the measured object has arrhythmia, the result error is relatively large. The descending method uses platform pressure reduction and has the advantage of strong anti-interference ability, but the measurement time is long and the comfort is poor. Compared with the existing measurement method that only has one of them, after the two methods are combined, only the ascending method measurement is required for normal measurement, which retains the advantages of being fast, comfortable and accurate. When the ascending method is interfered or the measured object has arrhythmia, the descending method measurement will continue to be used to improve the accuracy of the measurement.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

Fig. 1 is a schematic diagram of the process of the present invention;

FIG2 is a schematic diagram of a normal blood pressure image of the present invention;

FIG. 3 is a schematic diagram of an abnormal blood pressure image according to the present invention.

DETAILED DESCRIPTION

The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

The embodiment of the present invention discloses a blood pressure measurement method combining an ascending method and a descending method, as shown in FIG1 , comprising the following steps:

S1: during the cuff pressurization process, obtaining a first pulse signal set during the pressure increase process;

S2: during the cuff pressure release process, obtaining a second pulse signal set during the pressure reduction process;

S3: performing denoising preprocessing on the first pulse signal set and the second pulse signal set respectively;

S4: extracting digital signal feature vectors of the first pulse signal set and the second pulse signal set, and extracting the pulse transmission time corresponding to each digital signal feature vector;

S5: inputting the mapping relationship between the digital signal feature vector and the pulse conduction time into the long short-term memory neural network model;

S6: The long short-term memory neural network model identifies whether the blood pressure is lower than normal or higher than normal based on the mapping relationship.

Furthermore, this embodiment also includes drawing a blood pressure image during the blood pressure measurement process according to the output results of the long short-term memory neural network model.

Furthermore, the blood pressure image drawing process is: using the adaptive threshold method to screen the turning points of the data, and then obtaining the main wave trough and the main wave peak of each cycle, and intercepting each main wave trough to the main wave peak as a cycle image.

Furthermore, in S1 and S2, the acquisition process of the first pulse signal set and the second pulse signal set is as follows: according to a preset time interval, the pulse signal is periodically collected to obtain multiple periodic signals, and the multiple periodic signals are arranged in chronological order to obtain a pulse signal set.

Furthermore, in S3, the first pulse signal set and the second pulse signal set are subjected to denoising preprocessing respectively, specifically: the pulse signals are processed in sequence using a second-order bandpass filter and a signal smoothing algorithm based on wavelet filtering, the second-order bandpass filter is used to truncate and denoise the characteristics of the noise, and the signal smoothing algorithm based on wavelet filtering is used to separate and denoise the noise.

Further, in S5, the pulse transmission time is the time required for blood to flow from the heart to the measurement point, and the transmission time is calculated using the characteristics between multiple different signals. This embodiment selects to extract two types of pulse transmission time, PATro and PATrb, from two signals, ECG at the heart position and pulse at the fingertip position.

Furthermore, the formation of blood pressure is mainly determined by three factors: blood volume, peripheral resistance, and vascular wall elasticity. For the same individual, there will be no obvious changes in peripheral resistance and vascular wall elasticity in the short term, which can be considered as a constant value. In this case, the size of blood pressure is mainly determined by blood volume. The PPG signal reflects the periodic changes in blood volume in the blood vessels. For multiple PPG signals, or multiple signals of PPG signals and ECG signals, the pulse propagation velocity can be calculated to construct a relationship model between the PPG signal and blood pressure. In this embodiment, a long short-term memory neural network model is used to complete the construction of the relationship between the pulse signal and blood pressure.

Specifically, in this embodiment, first, the arm is fitted with a cuff, and the device starts to inflate, so that the cuff pressure rises at a constant speed of about 10 mmHg/s. The gas pressure change in the blood pressure cuff is detected and the pressure pulse wave is extracted. When the detected pulse wave amplitude can form a typical envelope and the amplitude interval is uniform, the coefficient method is used to obtain the blood pressure value, and the measurement is ended. As shown in Figure 2.

If the detected pulse wave amplitude forms an atypical envelope or the amplitude interval is uneven (as shown in Figure 3), it means that the blood pressure measurement process is disturbed or the measured object has arrhythmia. When it is detected that the arterial blood flow is blocked, the plateau method is used to reduce the blood pressure and continue the measurement.

This embodiment also discloses a blood pressure measurement system combining the ascending method and the descending method, comprising the following steps:

A first signal acquisition module: used for acquiring a first pulse signal set in a process of increasing pressure during the cuff pressurization process;

A second signal acquisition module: used for acquiring a second pulse signal set in a pressure reduction process during the cuff pressure release process;

De-noising processing module: used for performing de-noising pre-processing on the first pulse signal set and the second pulse signal set respectively;

A characteristic signal extraction module: used to extract digital signal characteristic vectors of the first pulse signal set and the second pulse signal set, and to extract the pulse conduction time corresponding to each digital signal characteristic vector;

Long short-term memory neural network model input module: used to input the mapping relationship between the digital signal feature vector and the pulse conduction time into the long short-term memory neural network model;

Long short-term memory neural network model processing module: used to identify whether the blood pressure is lower than normal or higher than normal based on the mapping relationship.

Furthermore, it also includes an image drawing module: used to draw a blood pressure image during the blood pressure measurement process according to the output results of the long short-term memory neural network model.

This embodiment further discloses a computer storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of any one of the blood pressure measurement methods combining the ascending method with the descending method are implemented.

In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims (9)

1. A blood pressure measurement method combining an ascending method and a descending method, comprising the steps of:

Detecting the pressure pulse wave which is extracted by the gas pressure change in the blood pressure cuff, obtaining a blood pressure value by adopting a coefficient method when the detected pulse wave amplitude can form a typical envelope curve and the amplitude intervals are uniform, ending the measurement, and obtaining a first pulse signal set;

If the detected pulse wave amplitude forms atypical envelope lines or the amplitude intervals are uneven, the phenomenon that the blood pressure measurement process is disturbed or the measured object has arrhythmia is indicated, and when the arterial blood flow is detected to be blocked, the platform method is adopted for reducing the pressure to continue measurement, so as to obtain a second pulse signal set;

Respectively carrying out denoising pretreatment on the first pulse signal set and the second pulse signal set;

extracting digital signal feature vectors of the first pulse signal set and the second pulse signal set, and extracting pulse conduction time corresponding to each digital signal feature vector;

Inputting the mapping relation between the digital signal characteristic vector and the pulse conduction time into a long-short-period memory neural network model;

the long-term and short-term memory neural network model identifies whether the blood pressure is lower than a normal blood pressure threshold value or not according to the mapping relation whether above the normotensive threshold.

2. The method for measuring blood pressure by combining an ascending method and a descending method according to claim 1, further comprising drawing a blood pressure image during blood pressure measurement according to an output result of the long-short-term memory neural network model.

3. The method for measuring blood pressure by combining an ascending method and a descending method according to claim 1, wherein the first pulse signal set and the second pulse signal set are obtained as follows: according to the preset time interval, periodically acquiring pulse signals to obtain a plurality of periodic signals, and arranging the plurality of periodic signals in time sequence to obtain a pulse signal set.

4. The method for measuring blood pressure by combining an ascending method and a descending method according to claim 2, wherein the drawing process of the blood pressure image is as follows: and screening turning points of the data by adopting a self-adaptive threshold method, further obtaining a main wave trough and a main wave crest of each period, and intercepting each main wave trough to the main wave crest as a period image.

5. The method for measuring blood pressure by combining an ascending method and a descending method according to claim 1, wherein denoising pretreatment is performed on the first pulse signal set and the second pulse signal set respectively, specifically: pulse signals are sequentially processed by a second-order band-pass filter and a signal smoothing algorithm based on wavelet filtering, the second-order band-pass filter is used for cutting off and denoising the characteristics of noise, and the signal smoothing algorithm based on wavelet filtering is used for separating noise from noise.

6. A combined ascending and descending blood pressure measurement according to claim 1 wherein pulse transit time is the time required for blood to flow from the heart to the measurement point, the transit time being calculated using features between multiple different signals.

7. A blood pressure measurement system combining an ascent method and a descent method, comprising the steps of:

A first signal acquisition module: detecting the pressure pulse wave which is extracted by the gas pressure change in the blood pressure cuff, obtaining a blood pressure value by adopting a coefficient method when the detected pulse wave amplitude can form a typical envelope curve and the amplitude intervals are uniform, ending the measurement, and obtaining a first pulse signal set;

A second signal acquisition module: if the detected pulse wave amplitude forms atypical envelope lines or the amplitude intervals are uneven, the phenomenon that the blood pressure measurement process is disturbed or the measured object has arrhythmia is indicated, and when the arterial blood flow is detected to be blocked, the platform method is adopted for reducing the pressure to continue measurement, so as to obtain a second pulse signal set;

And the denoising processing module: the denoising preprocessing is used for respectively denoising the first pulse signal set and the second pulse signal set;

the characteristic signal extraction module: the pulse signal processing device is used for extracting digital signal feature vectors of the first pulse signal set and the second pulse signal set and extracting pulse conduction time corresponding to each digital signal feature vector;

the long-term memory neural network model input module: the method comprises the steps of inputting a mapping relation between a digital signal characteristic vector and pulse conduction time into a long-term and short-term memory neural network model;

The long-term memory neural network model processing module is as follows: is used for identifying whether the blood pressure is lower than normal blood pressure or higher than normal blood pressure according to the mapping relation.

8. The system for measuring blood pressure by combining an ascending method and a descending method according to claim 7, further comprising an image drawing module: and the method is used for drawing a blood pressure image in the blood pressure measuring process according to the output result of the long-short-term memory neural network model.

9. A computer storage medium, wherein a computer program is stored on the computer storage medium, and when executed by a processor, the computer program implements the steps of a blood pressure measurement method according to any one of claims 1-6, in combination with a rising method and a falling method.