[go: up one dir, main page]

WO2025218160A1 - 心音分割方法、装置、电子设备及可读存储介质 - Google Patents

心音分割方法、装置、电子设备及可读存储介质

Info

Publication number
WO2025218160A1
WO2025218160A1 PCT/CN2024/132614 CN2024132614W WO2025218160A1 WO 2025218160 A1 WO2025218160 A1 WO 2025218160A1 CN 2024132614 W CN2024132614 W CN 2024132614W WO 2025218160 A1 WO2025218160 A1 WO 2025218160A1
Authority
WO
WIPO (PCT)
Prior art keywords
heart sound
signal
time
duration
segmentation
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2024/132614
Other languages
English (en)
French (fr)
Inventor
刘澄玉
李昱旻
凌力
刘耀诚
潘俊杰
李欢
周亚楠
杨晨熙
李建清
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Goertek Inc
Southeast University
Original Assignee
Goertek Inc
Southeast University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Goertek Inc, Southeast University filed Critical Goertek Inc
Publication of WO2025218160A1 publication Critical patent/WO2025218160A1/zh
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B7/00—Instruments for auscultation
    • A61B7/02—Stethoscopes
    • A61B7/04—Electric stethoscopes
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods

Definitions

  • the present application relates to the technical field of medical signal processing, and in particular to a heart sound segmentation method, device, electronic device, and readable storage medium.
  • a key component of computer-assisted heart sound analysis is the segmentation of heart sound signals, specifically distinguishing the exact locations of the first heart sound (S1), systole, second heart sound (S2), and diastole of each cardiac cycle.
  • the first heart sound (S1) is caused by the closure of the mitral and tricuspid valves, the opening of the aortic and pulmonary valves, and the vibrations generated during ventricular contraction.
  • the second heart sound (S2) is primarily caused by the closure of the aortic and pulmonary valves, coupled with vibrations generated by the weakening of blood flow in the aorta and pulmonary artery.
  • Systole is the interval between S1 and S2
  • diastole is the period from S2 to the beginning of the next cardiac cycle, S1.
  • the accuracy of heart sound signal segmentation directly impacts the effectiveness of subsequent heart sound signal analysis.
  • LR-HSMM logistic regression-hidden semi-Markov model
  • the main purpose of this application is to provide a heart sound segmentation method, device, electronic device and readable storage medium, aiming to solve the technical problem of how to reduce the heart sound segmentation resource consumption of heart sound signals on the server.
  • a heart sound segmentation method which includes:
  • physiological signals include heart sound signals
  • the duration of the systolic period of the heart sound signal and the duration of the diastolic period of the heart sound signal are determined according to the first heart sound and the second heart sound.
  • the physiological signal further includes an electrocardiogram signal and a pulse signal.
  • the method further includes:
  • the first threshold and the second threshold are used as segmentation thresholds.
  • the step of determining a first threshold corresponding to the first time and the second time includes:
  • the first heart sound peak value is adjusted based on a preset adjustment coefficient to obtain a first threshold value, wherein the first threshold value is smaller than the first heart sound peak value.
  • the step of determining a second threshold corresponding to the third time and the fourth time includes:
  • the second heart sound peak value is adjusted based on a preset adjustment coefficient to obtain a second threshold value, wherein the second threshold value is smaller than the second heart sound peak value.
  • the segmentation threshold includes a first threshold and a second threshold
  • the step of segmenting the heart sound signal based on the segmentation threshold includes:
  • the heart sound signal within the first duration window is used as the first heart sound
  • the heart sound signal within the second duration window is used as the second heart sound
  • the step of determining a systolic duration of a heart sound signal and a diastolic duration of a heart sound signal based on the first heart sound and the second heart sound includes:
  • the time difference between the first start time and the second end time is used as the duration of the diastolic phase
  • the average systolic duration of all the systolic durations and the average diastolic duration of all the diastolic durations are determined;
  • the average systolic duration is used as the systolic duration of the heart sound signal, and the average diastolic duration is used as the diastolic duration of the heart sound signal.
  • a heart sound segmentation device which includes:
  • a signal acquisition module configured to synchronously acquire physiological signals, wherein the physiological signals include heart sound signals;
  • a segmentation module configured to obtain a segmentation threshold corresponding to the heart sound signal, and segment the heart sound signal based on the segmentation threshold to obtain a first heart sound and a second heart sound;
  • a determination module is used to determine the duration of the systole and the duration of the diastole according to the first heart sound and the second heart sound.
  • the present application also provides an electronic device, which is a physical device, and includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the heart sound segmentation method as described above.
  • the present application also provides a readable storage medium, which is a computer-readable storage medium.
  • the computer-readable storage medium stores a program for implementing the heart sound segmentation method.
  • the program for implementing the heart sound segmentation method is executed by a processor to implement the steps of the heart sound segmentation method as described above.
  • the present application also provides a computer program product, comprising a computer program, which implements the steps of the above-mentioned heart sound segmentation method when executed by a processor.
  • physiological signals are synchronously collected, wherein the physiological signals include heart sound signals; a segmentation threshold corresponding to the heart sound signal is obtained, and the heart sound signal is segmented based on the segmentation threshold to obtain a first heart sound and a second heart sound; and the duration of the systolic period and the duration of the diastolic period are determined based on the first heart sound and the second heart sound.
  • the embodiment of the present application performs heart sound segmentation on the heart sound signal based on the segmentation threshold to obtain the first heart sound and the second heart sound, and calculates the diastolic period and the systolic period based on the first heart sound and the second heart sound, completing the complete heart sound segmentation of the heart sound signal. Only a simple value comparison operation is required to complete the heart sound segmentation, without the need for complex model operations, reducing the computational complexity, and thus reducing the resource consumption of the heart sound segmentation of the heart sound signal.
  • FIG1 is a flow chart of a first embodiment of a heart sound segmentation method of the present application.
  • FIG2 is a schematic diagram of the overall architecture of the wearable device system of the present application.
  • FIG3 is a schematic diagram of the structure of the wearable device of the present application.
  • FIG4 is a schematic diagram of physiological signals of the heart sound segmentation method of the present application.
  • FIG5 is a schematic diagram of the prediction process of the heart sound segmentation method of the present application.
  • FIG6 is another schematic diagram of the prediction process of the heart sound segmentation method of the present application.
  • FIG7 is a schematic diagram of the device modules of the heart sound segmentation device of the present application.
  • FIG8 is a schematic diagram of the device structure of the hardware operating environment involved in the cardiac sound segmentation device in an embodiment of the present application.
  • the heart sound segmentation method includes:
  • Step S10 synchronously collecting physiological signals, wherein the physiological signals include heart sound signals;
  • the physiological signals include, but are not limited to, heart sound signals. For example, they may also include electrocardiogram (ECG) signals and pulse signals.
  • ECG and pulse signals are used to assist in the segmentation of heart sound signals, thereby improving segmentation accuracy.
  • the physiological signals may be collected by relevant devices. For example, if a user uses a wearable device, the user's physiological signals may be collected based on the wearable device.
  • the wearable device may be a smartwatch, smart bracelet, or the like.
  • the system simultaneously starts collecting physiological signals and determines the relationship between the ECG signal, pulse signal, and heart sound signal and time to ensure strict synchronization of the physiological signals. Furthermore, the system can also record the moment the data collection starts using the verified real-time time.
  • Step S20 obtaining a segmentation threshold corresponding to the heart sound signal, and segmenting the heart sound signal based on the segmentation threshold to obtain a first heart sound and a second heart sound;
  • Heart sound segmentation involves distinguishing the exact locations of the first heart sound (S1), systole, second heart sound (S2), and diastole of each cardiac cycle.
  • the first heart sound (S1) is caused by the closure of the mitral and tricuspid valves, the opening of the aortic and pulmonary valves, and the vibrations generated during ventricular contraction.
  • the second heart sound (S2) is primarily caused by the closure of the aortic and pulmonary valves, coupled with vibrations caused by the reduction of blood flow in the aorta and pulmonary arteries.
  • Systole is the interval between S1 and S2, while diastole is from S2 to the beginning of the next cardiac cycle, S1.
  • the accuracy of heart sound signal segmentation directly impacts the subsequent analysis of heart sound signals.
  • the duration of systole is the duration between S1 and S2, and the duration of diastole is the duration from S2 to the beginning of the next cardiac cycle, S1.
  • the segmentation threshold includes a first threshold and a second threshold
  • the step of segmenting the heart sound signal based on the segmentation threshold includes:
  • Step S201 obtaining or determining a heart sound envelope signal corresponding to the heart sound signal
  • the upper envelope of the heart sound signal may be determined, and the upper envelope may be filtered to obtain a heart sound envelope signal corresponding to the heart sound signal.
  • Step S202 taking the duration window in which the signal value of the heart sound envelope signal is greater than the first threshold as the first duration window
  • Step S203 taking the duration window in which the signal value of the heart sound envelope signal is greater than the second threshold as the second duration window;
  • Step S204 The heart sound signal within the first duration window is used as the first heart sound, and the heart sound signal within the second duration window is used as the second heart sound.
  • the filtering process for the heart sound signal may specifically be baseline removal and sliding average filtering process to reduce interference signals.
  • physiological signals include electrocardiogram (ECG) signals, phonocardiogram (PCG) signals, and pulse signals.
  • ECG electrocardiogram
  • PCG phonocardiogram
  • pulse signals pulse signals.
  • the heart sound signal is segmented, and in each cardiac cycle, the first heart sound (S1) and the second heart sound (S2) are obtained by segmentation.
  • Step S30 determining a systolic duration of the heart sound signal and a diastolic duration of the heart sound signal according to the first heart sound and the second heart sound.
  • the first heart sound is S1
  • the second is S2
  • systole is the interval between S1 and S2
  • diastole is the interval between S2 and the start of the next cardiac cycle, S1.
  • the duration of systole is the interval between S1 and S2
  • the duration of diastole is the interval between S2 and the start of the next cardiac cycle, S1.
  • the step of determining the systolic duration of the heart sound signal and the diastolic duration of the heart sound signal based on the first heart sound and the second heart sound includes:
  • Step S301 determining the cardiac cycles included in the heart sound signal, and traversing each of the cardiac cycles in sequence;
  • Step S302 taking the end time of the first heart sound in the traversed cardiac cycle as a first end time, determining a next cardiac cycle corresponding to the traversed cardiac cycle, and taking the start time of the first heart sound in the next cardiac cycle as a first start time;
  • Step S303 taking the start time of the second heart sound in the traversed cardiac cycle as a second start time, and taking the end time of the second heart sound in the traversed cardiac cycle as a second end time;
  • Step S304 taking the time difference between the first end time and the second start time as the contraction period duration
  • Step S305 taking the time difference between the first start time and the second end time as the duration of the diastolic period
  • Step S306 after each cardiac cycle is traversed, determining the average systolic duration of all the systolic durations, and determining the average diastolic duration of all the diastolic durations;
  • Step S307 Using the average systolic duration as the systolic duration of the heart sound signal, and using the average diastolic duration as the diastolic duration of the heart sound signal.
  • the first heart sound of the t-th cardiac cycle is recorded as S1(t)
  • the second heart sound of the t-th cardiac cycle is recorded as S2(t)
  • the starting time of S1(t) is recorded as S1 start (t)
  • the end time of S1(t) is recorded as S1 end (t)
  • the starting time of S2(t) is recorded as S2 start (t)
  • the end time of S2(t) is recorded as S2 end (t).
  • the duration of the systolic period corresponding to the t-th cardiac cycle is the time difference between S1 end (t) and S2 start (t)
  • the duration of the diastolic period is the time difference between S1 start (t+1) and S2 end (t).
  • the average duration of the systolic duration corresponding to all cardiac cycles can be used as the final systolic duration, and similarly, the average duration of the diastolic duration corresponding to all cardiac cycles can be used as the final diastolic duration.
  • the physiological signal also includes an electrocardiogram signal and a pulse signal
  • the method before the step of obtaining the segmentation threshold corresponding to the heart sound signal, the method further includes:
  • Step A10 determining the QRS wave peak point of the electrocardiogram signal, and taking the time corresponding to the QRS wave peak point as the first time;
  • Step A20 determining a trough point of the pulse signal, and using the time corresponding to the trough point as a second time;
  • Step A30 determining a first zero-crossing point and a second zero-crossing point of the pulse signal, taking the time corresponding to the first zero-crossing point as a third time, and taking the time corresponding to the second zero-crossing point as a fourth time;
  • Step A40 determining a first threshold corresponding to the first time and the second time, and determining a second threshold corresponding to the third time and the fourth time;
  • Step A50 Using the first threshold and the second threshold as segmentation thresholds.
  • the first time corresponding to the QRS wave peak point of the electrocardiogram signal in the cardiac cycle, the second time corresponding to the trough point of the pulse signal, and the third time of the first zero crossing point and the fourth time of the second zero crossing point of the pulse signal are determined, and then the first threshold value and the second threshold value of the cardiac cycle are determined, and the cardiac sound signal of the cardiac cycle is segmented using the first threshold value and the second threshold value of the cardiac cycle to obtain the second systolic duration and the second diastolic duration of the cardiac sound signal of the cardiac cycle, thereby performing cardiac sound segmentation on the cardiac sound signal based on each cardiac cycle, thereby improving the accuracy of cardiac sound segmentation of the cardiac sound signal.
  • the step of determining a first threshold corresponding to the first time and the second time includes:
  • Step B10 acquiring or determining a heart sound envelope signal corresponding to the heart sound signal
  • Step B20 taking the heart sound peak value of the heart sound envelope signal between the first time and the second time as the first heart sound peak value
  • Step B30 adjusting the first heart sound peak value based on a preset adjustment coefficient to obtain a first threshold value, wherein the first threshold value is smaller than the first heart sound peak value.
  • the preset adjustment coefficient can be any coefficient set in advance, such as 0.1, 0.15, 0.2, etc.
  • the first heart sound peak value is adjusted based on the preset adjustment coefficient.
  • the first threshold value can be obtained by multiplying the preset adjustment coefficient by the first heart sound peak value.
  • the first threshold is determined based on the first heart sound peak value between the first time and the second time.
  • the first threshold is related to the first heart sound peak value. Different peak values correspond to different threshold values, thereby realizing intelligent adjustment of the threshold value instead of using a fixed threshold value for heart sound segmentation, thereby improving the segmentation accuracy of heart sound segmentation.
  • the step of determining a second threshold corresponding to the third time and the fourth time includes:
  • Step C10 acquiring or determining a heart sound envelope signal corresponding to the heart sound signal
  • Step C20 taking the heart sound peak value of the heart sound envelope signal between the third time and the fourth time as the second heart sound peak value
  • Step C30 adjusting the second heart sound peak value based on a preset adjustment coefficient to obtain a second threshold value, wherein the second threshold value is smaller than the second heart sound peak value.
  • the preset adjustment coefficient can be the same as or different from the aforementioned adjustment coefficient, and the second heart sound peak value is adjusted based on the preset adjustment coefficient.
  • the second threshold value is obtained by multiplying the preset adjustment coefficient by the second heart sound peak value.
  • the second threshold value is correlated with the second peak value, with different peak values corresponding to different threshold values. This allows for intelligent adjustment of the threshold value, rather than using a fixed threshold for heart sound segmentation, thereby improving the accuracy of heart sound segmentation.
  • the heart sound segmentation process is as follows:
  • S3 calculate the upper envelope of the heart sound signal, perform baseline removal and sliding average filtering on the upper envelope to eliminate baseline drift and noise interference;
  • S4 calculate the peak value of the heart sound envelope signal between the R(t) and V(t) sequences, set the threshold to 10% of the peak value, and take the time difference between the envelope start point sequence S1 start (t) and the end point sequence S1 end (t) that is greater than the threshold as the S1 duration sequence S1(t);
  • S5 calculate the peak value of the heart sound envelope signal between the Cross_zero1(t) and Cross_zero2(t) sequences, with the threshold value also set at 10% of the peak value.
  • the time difference between the envelope start point sequence S2 start (t) and the end point sequence S2 end (t) that is greater than the threshold is used as the S2 duration sequence S2(t);
  • the systolic duration sequence Sys(t) is calculated using the time difference between S1 end (t) and S2 start (t), and the diastolic duration sequence Dia(t) is calculated using S1 start t(t+1) and S2 end (t).
  • Blood pressure is a key physiological parameter reflecting human health. With the accelerated aging of the population and changes in modern lifestyles, the incidence of hypertension is also increasing. As of 2022, the number of people with hypertension in my country reached 245 million, while the control rate and awareness of hypertension are very low, at only 56.6% and 16.8% respectively. Hypertension is a major risk factor for cardiovascular disease, the leading cause of death in the human body. Therefore, accurate and convenient blood pressure monitoring can greatly assist in the prevention of hypertension.
  • Cuffless blood pressure measurement devices primarily estimate blood pressure based on pulse transit time (PWTT).
  • Pulse transit time (PWTT) is defined as the time required for blood to travel from the proximal endpoint to the distal endpoint at the same instant.
  • PWTT is typically determined by synchronously acquiring the ECG signal and the pulse wave signal. The time difference between the ECG R wave peak and the pulse wave signature is used as the starting point and the end point.
  • the peak of the R wave is not actually the onset of cardiac contraction.
  • the method further includes:
  • Step D10 extracting features from the physiological signal to obtain signal features, wherein the signal features include the duration of the pre-ejection phase and the pulse transit time;
  • the heart sound segmentation method is applied to a wearable device, which may specifically be a smart watch, a smart bracelet, and the like.
  • the wearable device includes a housing 1 and a sensor provided on the housing, wherein the sensor is used to synchronously collect physiological signals.
  • the sensor includes a first sensor for collecting heart sound signals, a second sensor for collecting pulse signals, and a third sensor for collecting electrocardiogram signals.
  • the first sensor may be a VPU (Voice Pick Up, bone conduction) sensor 250
  • the second sensor may be a photoelectric pulse sensor 240
  • the third sensor may be an electrode sensor.
  • the electrode sensor may include three electrodes.
  • the first electrode 210 and the third electrode 230 are used to form a circuit for collecting electrocardiogram signals.
  • the second electrode 220 provides a reference point to eliminate the potential difference between the body and the wearable device, thereby improving the signal-to-noise ratio of the electrocardiogram signal collection.
  • the wearable device may also include a device switch 110 for turning the wearable device on and off; a device processor 120 for executing program code in memory to perform various functions of the wearable device; a time calibration module 130 for displaying real-time time and calibrating data synchronization acquisition; an interaction module 140 for collecting personalized user information and responding to signals generated by the user performing blood pressure measurement operations, as well as simple blood pressure measurement usage instructions.
  • the blood pressure measurement operation signal includes a blood pressure measurement start signal, and the usage instructions include the blood pressure measurement signal collection location and the user's collection posture; a physiological signal acquisition module 150 for collecting the user's physiological signals related to blood pressure measurement and accelerometer and gyroscope signals.
  • Physiological signals related to blood pressure measurement include electrocardiogram signals, pulse signals, and heart sound signals.
  • a data processing module 160 is used to process the physiological signal segments collected by the physiological signal measurement module in real time. The data processing steps mainly include signal noise reduction, signal quality assessment, and feature extraction.
  • Wireless communication module 180 is used to wirelessly transmit collected physiological signal data, the user's actual blood pressure value, and personalized user information to a server or terminal for use in building a blood pressure measurement database.
  • Blood pressure measurement module 170 is used to analyze the user's physiological signal data and/or personalized information, ultimately predicting blood pressure, returning the predicted blood pressure result, and determining the current blood pressure level.
  • the physiological signal acquisition module also includes a 6-axis signal acquisition module. Acceleration and gyroscope signals are primarily acquired through the 6-axis signal acquisition module, which is primarily composed of a 6-axis sensor 260 integrated within the device.
  • the 6-axis signal acquisition module can calculate the current Euler angle to assist the user in locating the acquisition position and posture.
  • the 6-axis signal acquisition module can monitor the movement of the user's arm and combine it with the electrocardiogram (ECG) signal, heart sound signal, and pulse signal to perform physiological signal denoising, thereby improving the signal-to-noise ratio of these signals during the acquisition process.
  • ECG electrocardiogram
  • the structures illustrated in the embodiments of the present application do not constitute a specific limitation on the wearable device. It may have more or fewer of the above components, or combine or separate some components, or have different component arrangements.
  • the various components described above may be implemented in hardware, software, or a combination of hardware and software, including one or more signal processing or application-specific integrated circuits.
  • the detection subject can be a user using the wearable device. Furthermore, simultaneous physiological signal acquisition begins at the same instant, determining the relationship between the ECG signal, pulse signal, and heart sound signal and time to ensure strict synchronization of the physiological signals. Furthermore, the data can be recorded from the moment acquisition begins, using the calibrated real-time time.
  • the physiological signal may be processed, such as filtering, noise reduction, segmentation, etc.
  • Feature extraction is performed based on the processed physiological signal to obtain the signal features.
  • the step of extracting features from the physiological signal includes:
  • Step D101 performing signal preprocessing on the physiological signal to obtain a preprocessed physiological signal, wherein the signal preprocessing includes one or more of filtering, normalization, and noise reduction;
  • signal preprocessing preferably includes normalization, filtering, and noise reduction.
  • the collected physiological signals are normalized and then bandpass filtered using a pre-designed FIR bandpass filter on the ECG, pulse, and heart sound signals.
  • the filtered data and acceleration signals are then subjected to a secondary adaptive filter to remove noise caused by motion artifacts, resulting in clean, high-quality physiological signals.
  • Step D102 determining the signal duration of the preprocessed physiological signal
  • Step D103 if the duration of the signal is greater than a preset duration, segmenting the preprocessed physiological signal to obtain multiple sub-physiological signals;
  • the pre-processed physiological signal is segmented to obtain multiple sub-physiological signals.
  • the physiological signal can be segmented in a non-time-overlapping manner. For example, if the signal duration is 12 seconds and the signal is segmented with a duration of 3 seconds, it can be divided into four sub-physiological signals of 0 to 3 seconds, 3 to 6 seconds, 6 to 9 seconds, and 9 to 12 seconds.
  • the physiological signal can also be segmented in a time-overlapping manner, where each signal is divided into signal segments of a fixed duration (Sig_t), and the overlapping length is any value in the range (0 to Sig_t-1).
  • the signal duration is 9 seconds
  • the signal is segmented with a fixed duration of 3 seconds and an overlapping length of 1 second, it can be divided into four sub-physiological signals of 0 to 3 seconds, 2 to 5 seconds, 4 to 7 seconds, and 6 to 9 seconds.
  • the signal quality of each sub-physiological signal can be evaluated, the sub-physiological signals with poor signal quality can be deleted, and the signal features can be extracted based on the sub-physiological signals with good signal quality to ensure the validity of the extracted signal features.
  • the signal quality of each sub-physiological signal segment can be evaluated by calculating the RR interval and KSQI index of the ECG signal, the peak interval and number of zero crossings of the pulse signal, and the SSQI coefficient and signal mean of the heart sound signal, etc. in each sub-physiological signal segment. This is then combined with the time variation of the acceleration signal amplitude (e.g., excluding sub-physiological signals that overlap with the acceleration signal amplitude time), and signal segments that have been interfered with by noise.
  • the acceleration signal amplitude e.g., excluding sub-physiological signals that overlap with the acceleration signal amplitude time
  • a classification model such as an SVM (Support Vector Machine) model, to perform a rough classification of each signal segment, such as into usable and unusable sub-physiological signals, and extract signal features based on the usable sub-physiological signals.
  • SVM Small Vector Machine
  • Step D204 for each segment of the sub-physiological signal, extracting the sub-signal features of the sub-physiological signal;
  • Step D205 determining the mean signal feature of all the sub-signal features, and using the mean signal feature as the signal feature of the psychological signal.
  • the preprocessed physiological signal may be segmented to extract sub-signal features of each sub-physiological signal.
  • the preprocessed physiological signals are segmented, that is, the preprocessed ECG signal, the preprocessed pulse signal, and the preprocessed heart sound signal are segmented.
  • the sub-signal features of each sub-physiological signal are extracted, and each sub-signal feature constitutes an n-dimensional feature sequence X(t), where n is the number of features.
  • the mean of each dimensional feature of all X(t) is calculated to obtain the mean signal feature, which is the final signal feature.
  • the psychological signal physiological signal includes an ECG signal, a pulse signal, and a heart sound signal
  • three sub-physiological signals are obtained, namely sub-physiological signal 1, sub-physiological signal 2, and sub-physiological signal 3.
  • Sub-physiological signal 1 includes sub-ECG signal 1, sub-heart sound signal 1, and sub-pulse signal 1.
  • Sub-physiological signal 2 includes sub-ECG signal 2, sub-heart sound signal 2, and sub-pulse signal 2.
  • Sub-physiological signal 3 includes sub-ECG signal 3, sub-heart sound signal 3, and sub-pulse signal 3. Extract the signal features of sub-physiological signal 1 and record them as sub-signal feature 1 [1_1, 1_2, 1_3], extract the signal features of sub-physiological signal 1 and record them as sub-signal feature 2 [2_1, 2_2, 2_3], and extract the signal features of sub-physiological signal 3 and record them as sub-signal feature 3 [3_1, 3_2, 3_3].
  • the final signal features are [(1_1+2_1+3_1)/3, (1_2+2_2+3_2)/3, (1_3+2_3+3_3)/3].
  • outlier processing can be performed on all sub-signal features to remove abnormal features.
  • outlier feature sequence processing can be performed according to the boxplot principle.
  • the signal characteristics include but are not limited to the duration of the pre-ejection period and the pulse transmission time, such as the pulse arrival time (PAT), the ratio of the systolic duration of the pulse signal and the heart sound signal, the ratio of the diastolic duration of the pulse signal and the heart sound signal, time domain characteristics, frequency domain characteristics, time-frequency characteristics, statistical characteristics, etc.
  • PAT pulse arrival time
  • the ratio of the systolic duration of the pulse signal and the heart sound signal the ratio of the diastolic duration of the pulse signal and the heart sound signal
  • time domain characteristics frequency domain characteristics, time-frequency characteristics, statistical characteristics, etc.
  • the time domain features include but are not limited to the following features: R-R interval (RR), R-R standard deviation (SDNN), root mean square deviation (RMSSD) of the ECG signal; PP interval (PP), half pulse width (PW50), systolic time, diastolic time, rise time, fastest rise area, peak height, rise slope, etc. of the pulse signal; the first zero crossing time, the last inflection point time, the peak and the first zero crossing slope, the peak slope, the peak area, etc.
  • the signal is obtained by performing first-order difference processing on the pulse signal
  • the lowest point time, the peak and the lowest point slope, the first zero crossing and the lowest point slope of the APG signal (the signal is obtained by performing second-order difference processing on the pulse signal); the first heart sound duration, the second heart sound duration, the systolic duration, the diastolic duration, etc. in the heart sound signal.
  • Frequency domain features include but are not limited to the following features: power spectrum density of ECG signal; first component frequency and amplitude of pulse signal, second component frequency and amplitude, third component frequency and amplitude; main component frequency of heart sound signal S1, main component frequency of S2, etc.
  • Time-frequency features mainly include but are not limited to the following features: wavelet coefficients, Hilbert-Huang transform coefficients, Mel-frequency cepstral coefficients, linear prediction coefficient features, etc.
  • Statistical features mainly include but are not limited to the following features: kurtosis factor, skewness factor, standard deviation of characteristic sequence, etc.
  • Step D20 obtaining the duration of the systolic period of the pulse signal and the duration of the diastolic period of the pulse signal;
  • the signal characteristics of the pulse signal are different in the systolic period and the diastolic period. Based on this, the systolic period duration and the diastolic period duration are extracted from the pulse signal.
  • the specific extraction method can adopt existing technology and will not be repeated in this embodiment.
  • Step D30 taking the ratio of the systolic duration of the pulse signal to the systolic duration of the heart sound signal as the systolic duration ratio;
  • Step D40 taking the ratio of the diastolic duration of the pulse signal to the diastolic duration of the heart sound signal as the diastolic duration ratio
  • Step D50 taking the systolic duration ratio, the diastolic duration ratio and the signal feature as target signal features;
  • Step D60 inputting the signal features into a preset blood pressure prediction model for training, so that the blood pressure prediction model can output a blood pressure prediction result.
  • the trained blood pressure model may be a blood pressure prediction model trained based on a database, wherein the database includes at least real blood pressure data and signal feature data corresponding to each real blood pressure data.
  • the database may be obtained by pre-collecting the real blood pressure data and signal feature data.
  • the real blood pressure values and physiological signals of the test subjects can be collected multiple times in advance to establish an individual data set, and the individual data set can be used as the database for training the prediction model to complete the training of the blood pressure prediction model.
  • the pre-training process for a blood pressure prediction model can be as follows: S1: Select features from a multi-category feature library using an existing database; S2: Calculate the mutual information between each feature, where p(x) is the probability of x occurring, p(y) is the probability of y occurring, and p(x, y) is the probability of both x and y occurring simultaneously, i.e., the joint probability. Higher mutual information indicates a greater degree of dependency between the two features. Remove features below the mutual information threshold to obtain a new feature subset; S3, calculate the correlation coefficient between the new feature subset and blood pressure.
  • S4 sort the feature subset from high to low according to the correlation coefficient to obtain the sorted feature subset; S5, divide the sorted feature subset into training and test sets, with a training set and test set ratio of 8:2; S6, use ten-fold cross-validation and backward feature selection to select the number of features in the training set to obtain the feature subset S with the lowest RMSE (Root Mean Squared Error); S7, use the final feature subset to train a multivariate linear regression model: Where BP is the specific blood pressure value, S is the optimal feature subset, Ki is the fitting coefficient of the multiple linear regression model, and n is the dimension of the optimal feature subset.
  • BP is the specific blood pressure value
  • S is the optimal feature subset
  • Ki is the fitting coefficient of the multiple linear regression model
  • n is the dimension of the optimal feature subset.
  • personalized features such as the age, gender, height, weight, BMI (Body Mass Index) index of the tester can also be collected and used for model training with signal feature data to obtain a pre-trained personalized blood pressure prediction model.
  • personalized features such as the age, gender, height, weight, BMI (Body Mass Index) index of the tester are further tested.
  • the signal features and personalized features are input into the pre-trained personalized blood pressure prediction model, and the blood pressure prediction results are output. Considering the influence of factors such as age, gender, height, weight, BMI (Body Mass Index) index on blood pressure, the accuracy of blood pressure prediction can be further improved.
  • a blood pressure prediction result After obtaining a blood pressure prediction result, it can be output on the wearable device and uploaded to a terminal or server connected to the wearable device for the user to view.
  • the terminal and server can also view the user's historical blood pressure data, which helps doctors make diagnoses. Customizing a personalized blood pressure measurement plan based on historical data helps users more comprehensively understand their health status and provide more scientific medical advice.
  • physiological signals of the test subject are collected, wherein the physiological signals include electrocardiogram signals, pulse signals, and heart sound signals; feature extraction is performed on the physiological signals to obtain signal features, wherein the signal features include pre-ejection period duration and pulse transit time; and the signal features are input into a pre-trained blood pressure prediction model, so that the blood pressure prediction model outputs a blood pressure prediction result.
  • this embodiment predicts the test subject's blood pressure based on fused signal features such as pre-ejection period duration and pulse transit time, taking into account the impact of the pre-ejection period duration on blood pressure, thereby improving the accuracy of blood pressure prediction.
  • the second systolic period duration and the second diastolic period duration based on the heart sound signal are obtained, and the first systolic period duration and the first diastolic period duration of the pulse signal are obtained.
  • the ratio between the two is also used as a signal feature, thereby comprehensively measuring the diastolic period duration and systolic period duration of the heart sound signal and the pulse signal, which can further improve the accuracy of blood pressure prediction.
  • the step of extracting features from the physiological signal includes:
  • Step E10 determining the QRS peak value of the electrocardiogram signal, determining the heart sound peak value of the heart sound signal, determining the time difference between the two peak values, and using the time difference as the duration of the pre-ejection period;
  • feature extraction is performed on the physiological signal.
  • feature extraction can be performed on each sub-physiological signal.
  • the electrocardiogram signal, heart sound signal and pulse signal are also the electrocardiogram signal, heart sound signal and pulse signal included in the sub-physiological signal.
  • the physiological signal includes an electrocardiogram (ECG) signal, a phonocardiogram (PCG) signal, and a pulse signal.
  • ECG electrocardiogram
  • PCG phonocardiogram
  • the signal peak of the ECG signal and the signal peak of the phonocardiogram signal are determined.
  • QRS peak of the ECG signal and the phonocardiogram peak of the phonocardiogram signal belonging to the same cardiac cycle are determined, and the time corresponding to these two signal peaks is obtained, and the time difference between the two is used as the pre-ejection duration.
  • the physiological signal includes multiple cardiac cycles, the pre-ejection duration corresponding to each cardiac cycle can be determined, and the average of all pre-ejection durations is used as the final pre-ejection duration.
  • Step E20 Acquire pulse transit time based on the pulse signal and the heart sound signal.
  • the time difference is the pulse transit time, so that one or more pulse wave characteristic points can be selected to obtain the corresponding one or more pulse transit times, that is, the pulse transit time includes one or more.
  • the user can set the selection rules of the pulse wave characteristic points according to actual conditions. This embodiment does not impose a specific limit on the number of characteristics of the pulse transit time.
  • one or more pulse arrival times are determined with the R wave peak of the ECG signal as the starting point, and these one or more pulse arrival times can also be used as extracted signal features.
  • fusion signal features such as the duration of the pre-ejection period and the pulse transit time are extracted to provide an effective data basis for predicting blood pressure values.
  • the blood pressure prediction process in this embodiment is as follows:
  • the wristwatch device is started by the device switch. At the same time, the wristwatch device can connect to the server and the mobile phone APP. After time calibration, the user can enter personalized information, such as height, weight, etc., and the user is prompted to configure the method. After the user wears the wristwatch device according to the prompt information, the wristwatch device starts blood pressure measurement and synchronously collects physiological signals.
  • the physiological signals include electrocardiogram signals, heart sound signals and pulse signals.
  • the user's acceleration, angular velocity and other information are collected to calculate the user's current Euler angle to assist the user in locating the collection position and posture; during the blood pressure measurement process, the user's acceleration and angular velocity information is collected to monitor the movement of the user's arm, and combined with the electrocardiogram signal, heart sound signal and pulse signal to denoise the physiological signal, and perform signal processing on the collected physiological signal, such as filtering (specifically, it may include bandpass filtering and adaptive filtering), signal quality evaluation, etc., and feature extraction is performed on the physiological signal whose signal quality evaluation result is high, and the extracted signal features are input into the blood pressure prediction model to perform blood pressure prediction, and the blood pressure prediction result is displayed and uploaded at the same time.
  • filtering specifically, it may include bandpass filtering and adaptive filtering
  • signal quality evaluation etc.
  • feature extraction is performed on the physiological signal whose signal quality evaluation result is high, and the extracted signal features are input into the blood pressure prediction model to perform blood pressure prediction, and the blood pressure prediction result is displayed and uploaded
  • An embodiment of the present invention further provides a heart sound segmentation device.
  • the heart sound segmentation device includes:
  • a signal acquisition module configured to synchronously acquire physiological signals, wherein the physiological signals include heart sound signals;
  • a segmentation module configured to obtain a segmentation threshold corresponding to the heart sound signal, and segment the heart sound signal based on the segmentation threshold to obtain a first heart sound and a second heart sound;
  • a determination module is used to determine the duration of the systole and the duration of the diastole according to the first heart sound and the second heart sound.
  • the physiological signal also includes an electrocardiogram signal and a pulse signal.
  • the segmentation module is further used to:
  • the first threshold and the second threshold are used as segmentation thresholds.
  • the segmentation module is further configured to:
  • the first heart sound peak value is adjusted based on a preset adjustment coefficient to obtain a first threshold value, wherein the first threshold value is smaller than the first heart sound peak value.
  • the segmentation module is further configured to:
  • the second heart sound peak value is adjusted based on a preset adjustment coefficient to obtain a second threshold value, wherein the second threshold value is smaller than the second heart sound peak value.
  • the segmentation threshold includes a first threshold and a second threshold, and the segmentation module is further configured to:
  • the heart sound signal within the first duration window is used as the first heart sound
  • the heart sound signal within the second duration window is used as the second heart sound
  • the determining module is further configured to:
  • the time difference between the first start time and the second end time is used as the duration of the diastolic phase
  • the average systolic duration of all the systolic durations and the average diastolic duration of all the diastolic durations are determined;
  • the average systolic duration is used as the systolic duration of the heart sound signal, and the average diastolic duration is used as the diastolic duration of the heart sound signal.
  • the heart sound segmentation device further includes a blood pressure prediction module, wherein the blood pressure prediction module is used to:
  • the ratio of the systolic duration of the pulse signal to the systolic duration of the heart sound signal is used as the systolic duration ratio
  • the ratio of the diastolic duration of the pulse signal to the diastolic duration of the heart sound signal is used as the diastolic duration ratio
  • the signal features are input into a preset blood pressure prediction model for training, so that the blood pressure prediction model outputs a blood pressure prediction result.
  • the blood pressure prediction model is also used for:
  • Determining a QRS peak value of the electrocardiogram signal determining a heart sound peak value of the heart sound signal, determining a time difference between two of the peak values, and using the time difference as a duration of the pre-ejection period;
  • a pulse transit time is acquired based on the pulse signal and the heart sound signal.
  • the signal acquisition module is also used to:
  • the user measures the acceleration and gyroscope signals during the measurement process.
  • the signal acquisition module includes: an electrocardiogram measurement module, a pulse measurement module, a heart sound signal measurement module and a 6-axis signal acquisition module.
  • ECG signals are primarily acquired through the ECG measurement module, which consists of a high-impedance chip and three highly conductive dry electrodes.
  • Pulse signals are also primarily acquired through the pulse measurement module, which primarily consists of a multi-wavelength LED (light-emitting diode), a photoelectric sensor, and a filter amplifier circuit.
  • the resulting pulse signal is a fusion of the multi-wavelength LEDs.
  • the high-impedance characteristics of the simulated ECG signal acquisition, the fusion of the pulse signal, the filter amplifier circuit, and the synchronization of the two physiological signals are all implemented using an integrated AFE chip.
  • the heart sound signal is mainly collected through the heart sound signal measurement module.
  • the heart sound signal measurement module is mainly composed of a digital VPU sensor.
  • the VPU sensor is attached to the inside of the watch case through a strict rigid connection method.
  • the amplification factor of the VPU sensor is adjusted to prevent signal overflow during the test to obtain a complete heart sound signal.
  • Acceleration and gyroscope signals are primarily collected by a 6-axis signal acquisition module, comprised primarily of a 6-axis sensor integrated within the watch.
  • the module calculates the current Euler angles to assist the user in determining the desired position and posture.
  • the module monitors the user's arm movement and combines it with the ECG, heart sound, and pulse signals to denoise these physiological signals, improving the signal-to-noise ratio during the acquisition process.
  • the heart sound segmentation device also includes:
  • the watch housing is used to house sensors for collecting physiological signals and the watch control system;
  • Time calibration module used to display real-time time and synchronize data acquisition and calibration
  • An interactive module configured to collect personalized user information, respond to signals generated by the user performing blood pressure measurement operations, and provide simple instructions for using the blood pressure watch.
  • the signals generated by the blood pressure operation include a blood pressure measurement start signal.
  • the instructions for using the watch include the blood pressure measurement watch signal collection location and the user's collection posture.
  • the data processing module is used to process the physiological signal segments collected by the physiological signal measurement module in real time.
  • the data processing steps mainly include signal noise reduction, signal quality assessment and feature extraction.
  • the wireless communication module is used to transmit the collected physiological signal data, the real user blood pressure value and the user's personalized information to the server or mobile terminal through the wireless module for the construction of the blood pressure measurement watch database.
  • the exterior of the watch housing includes the watch's switch and three dry electrodes for ECG monitoring.
  • the watch's switch primarily controls the watch's on/off function and accesses the watch's internal menu.
  • the first and third electrodes form a circuit for ECG signal acquisition, while the second electrode provides a reference point to eliminate the potential difference between the body and the watch, improving the signal-to-noise ratio of ECG signal acquisition.
  • the interior of the watch housing includes a rigidly connected VPU sensor and a photoelectric pulse sensor for measuring heart sound signals and photoplethysmography signals.
  • the time calibration module generates a real-time clock, controls the sensors to simultaneously start collecting physiological signals, and determines the relationship between the ECG signal, pulse signal, and heart sound signal and time to ensure strict synchronization of physiological signals.
  • the calibrated real-time time is then used to record the moment data collection begins.
  • the interactive module includes an input module, a display module, and a prompt module, all of which are implemented by the watch's internal MCU (Microcontroller Unit) and the watch screen.
  • Input module 141 within the interactive module is used to input personalized information into the watch through the watch screen before taking a blood pressure measurement. This information includes not only personal information such as gender, height, age, and weight, but also information such as whether or not the user is taking antihypertensive medication and the name of the medication.
  • the display module in the interactive module is used to display how to use the watch and the measurement steps. After completing the personalized information input step, the user can click on the blood pressure measurement function on the screen to see how to wear the watch and the posture the user should maintain during the measurement. After completing the usage tutorial, the user will enter the testing phase.
  • the watch can prompt the user to adjust the arm position through the prompt module to ensure the quality of physiological signal acquisition.
  • the prompt module in the interactive module includes a voice chip and a linear vibration motor, which is used to prompt the user's operation process, arm placement and measurement posture to ensure the accuracy of blood pressure measurement.
  • the data processing module includes: a signal noise reduction module and a signal quality evaluation module.
  • the signal noise reduction module normalizes the collected physiological signals and then applies bandpass filtering to the ECG, pulse, and heart sound signals using a pre-designed FIR (Finite Impulse Response) bandpass filter.
  • FIR Finite Impulse Response
  • the signal quality assessment module divides each signal into segments of a fixed duration (Sig_t), typically >5 seconds, with an overlap length of any value between 0 and Sig_t-1. For each segment, it calculates features such as the RR interval and KSQI index for the ECG signal; the peak interval, peak interval standard deviation, and number of zero crossings for the pulse signal; and the SSQI coefficient and signal mean for the heart sound signal. Combined with the time-varying amplitude of the acceleration signal, the SVM model is used to perform a coarse classification of each segment, eliminating segments affected by noise.
  • the wireless communication module is used to send the collected physiological signals, input personalized information and the actual measured blood pressure value to the terminal and upload them to the cloud server for data collection.
  • the heart sound segmentation device provided by the present invention employing the heart sound segmentation method described in the first, second, or third embodiments, can address the technical problem of reducing resource consumption in heart sound segmentation.
  • the heart sound segmentation device provided by the present invention achieves the same beneficial effects as the heart sound segmentation method described in the aforementioned embodiments.
  • Other technical features of the heart sound segmentation device are the same as those disclosed in the aforementioned embodiments and are not further elaborated here.
  • An embodiment of the present invention provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the heart sound segmentation method in the above-mentioned embodiment 1.
  • FIG8 illustrates a schematic diagram of an electronic device suitable for implementing embodiments of the present disclosure.
  • the electronic device in the embodiments of the present disclosure may be a wearable device, etc.
  • the electronic device illustrated in FIG8 is merely an example and should not limit the functionality or scope of use of the embodiments of the present disclosure.
  • the electronic device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM 1002) or a program loaded from a storage device into a random access memory (RAM 1004).
  • ROM 1002 read-only memory
  • RAM 1004 random access memory
  • various programs and data required for the operation of the electronic device are also stored.
  • the processing device 1001, ROM 1002, and RAM 1004 are connected to each other via a bus 1005.
  • An input/output (I/O) interface is also connected to the bus 1005.
  • the following systems may be connected to the I/O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009.
  • the communication device 1009 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data.
  • the figure shows an electronic device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented or have instead.
  • an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart.
  • the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002.
  • the processing device 1001 the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.
  • the electronic device provided by the present invention employing the heart sound segmentation method described in the above-mentioned embodiment, can solve the technical problem of reducing resource consumption in heart sound segmentation.
  • the electronic device provided by the present invention achieves the same beneficial effects as the heart sound segmentation method described in the above-mentioned embodiment.
  • Other technical features of the electronic device are the same as those disclosed in the above-mentioned embodiment and are not further elaborated here.
  • An embodiment of the present invention provides a computer-readable storage medium having computer-readable program instructions stored thereon, and the computer-readable program instructions are used to execute the heart sound segmentation method in the above-mentioned embodiment 1.
  • the computer-readable storage medium provided in the embodiment of the present invention can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.
  • the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in combination with an instruction execution system, system or device.
  • the program code contained on the computer-readable storage medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.
  • the computer-readable storage medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.
  • the above-mentioned computer-readable storage medium carries one or more programs.
  • the electronic device When the above-mentioned one or more programs are executed by an electronic device, the electronic device: synchronously collects physiological signals, wherein the physiological signals include heart sound signals; obtains a segmentation threshold corresponding to the heart sound signal, segments the heart sound signal based on the segmentation threshold to obtain a first heart sound and a second heart sound; and determines the duration of the systole and the duration of the diastole based on the first heart sound and the second heart sound.
  • Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages.
  • the program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server.
  • the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).
  • LAN local area network
  • WAN wide area network
  • Internet service provider e.g., AT&T, MCI, Sprint, EarthLink, MSN, GTE, etc.
  • each box in the flow chart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function.
  • the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved.
  • each box in the block diagram and/or flow chart, and the combination of the boxes in the block diagram and/or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
  • modules involved in the embodiments described in this disclosure may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.
  • the computer-readable storage medium provided herein stores computer-readable program instructions for executing the aforementioned heart sound segmentation method, thereby solving the technical problem of reducing resource consumption during heart sound segmentation.
  • the computer-readable storage medium provided in this embodiment of the present invention achieves the same beneficial effects as the heart sound segmentation methods provided in the first, second, or third embodiments above, and will not be further elaborated here.
  • An embodiment of the present invention further provides a computer program product, comprising a computer program, which implements the steps of the above-mentioned heart sound segmentation method when executed by a processor.
  • the computer program product provided in this application can solve the technical problem of reducing resource consumption in heart sound segmentation.
  • the computer program product provided in this embodiment of the present invention offers the same beneficial effects as the heart sound segmentation methods provided in Examples 1, 2, or 3 above, and will not be further elaborated here.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • Acoustics & Sound (AREA)
  • Theoretical Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Medical Informatics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)

Abstract

本申请公开了一种心音分割方法、装置、电子设备及可读存储介质，本申请涉及医学信号处理技术领域，所述心音分割方法包括：同步采集生理信号，其中，所述生理信号包括心音信号；获取所述心音信号对应的分割阈值，基于所述分割阈值分割所述心音信号，得到第一心音与第二心音；根据所述第一心音、第二心音确定心音信号的收缩期持续时长与心音信号的舒张期持续时长。本申请降低了心音信号的心音分割资源耗费。

Description

心音分割方法、装置、电子设备及可读存储介质 技术领域
本申请涉及医学信号处理技术领域，尤其涉及一种心音分割方法、装置、电子设备及可读存储介质。
背景技术
计算机辅助心音分析的一个关键部分是心音信号的分割，具体为区分出每个心动周期的第一心音(S1)、收缩期、第二心音(S2)和舒张期的确切位置。在每个心动周期中，第一心音(S1)是由于二尖瓣和三尖瓣关闭，主动脉瓣和肺动脉瓣开启以及心室收缩过程中产生的振动引起的；第二心音(S2)第二心音形成的主要原因是主动脉瓣和肺动脉瓣的关闭，同时由于主动脉和肺动脉的血流减弱而产生的振动。收缩期是S1和S2之间的区间，舒张期是从S2到下一个心动周期S1开始。心音信号分割的正确性直接影响后续心音信号的分析效果。
相关技术中，通常使用网络模型进行心音分割，图基于逻辑回归-隐半马尔科夫模型(LR-HSMM,Logistic Regression hidden semi-Markov model)的分割算法是常用的心音分割方法之一，然而基于模型的心音分割方式需要进行复杂的模型计算，计算复杂度高，也就导致硬件等资源耗费高，因此，目前亟需一种资源耗费低的针对心音信号的心音分割方式。
以上背景技术内容的公开仅用于辅助理解本申请的发明构思及技术方案，其并不必然属于本专利申请的现有技术，也不必然会给出技术教导，在于提供一般的背景信息，并不一定构成现有技术。
发明内容
本申请的主要目的在于提供一种心音分割方法、装置、电子设备及可读存储介质，旨在解决服务器上如何降低心音信号的心音分割资源耗费的技术问题。
为实现上述目的，本申请提供一种心音分割方法，所述心音分割方法包括：
同步采集生理信号，其中，所述生理信号包括心音信号；
获取所述心音信号对应的分割阈值，基于所述分割阈值分割所述心音信号，得到第一心音与第二心音；
根据所述第一心音、第二心音确定心音信号的收缩期持续时长与心音信号的舒张期持续时长。
可选地，所述生理信号还包括心电信号与脉搏信号，所述获取所述心音信号对应的分割阈值的步骤之前，所述方法还包括：
确定所述心电信号的QRS波峰值点，将所述QRS波峰值点对应的时间作为第一时间；
确定所述脉搏信号的波谷点，将所述波谷点对应的时间作为第二时间；
确定所述脉搏信号的第一个过零点与第二个过零点，将所述第一个过零点对应的时间作为第三时间，将所述第二个过零点对应的时间作为第四时间；
确定所述第一时间与所述第二时间对应心音信号的第一阈值，确定所述第三时间与所述第四时间对应心音信号的第二阈值；
将所述第一阈值与所述第二阈值作为分割阈值。
可选地，所述确定所述第一时间与所述第二时间对应的第一阈值的步骤，包括：
获取或确定所述心音信号对应的心音包络信号；
将所述心音包络信号在所述第一时间与所述第二时间之间的心音峰值，作为第一心音峰值；
基于预设调整系数调整所述第一心音峰值，得到第一阈值，其中，所述第一阈值小于所述第一心音峰值。
可选地，所述确定所述第三时间与所述第四时间对应的第二阈值的步骤，包括：
获取或确定所述心音信号对应的心音包络信号；
将所述心音包络信号在所述第三时间与所述第四时间之间的心音峰值，作为第二心音峰值；
基于预设调整系数调整所述第二心音峰值，得到第二阈值，其中，所述第二阈值小于所述第二心音峰值。
可选地，所述分割阈值包括第一阈值与第二阈值，所述基于所述分割阈值分割所述心音信号的步骤，包括：
获取或确定所述心音信号对应的心音包络信号；
将所述心音包络信号的信号值大于所述第一阈值的持续时长窗口，作为第一持续时长窗口；
将所述心音包络信号的信号值大于所述第二阈值的持续时长窗口，作为第二持续时长窗口；
将在所述第一持续时长窗口内的心音信号作为第一心音，将在所述第二持续时长窗口内的心音信号作为第二心音。
可选地，所述根据所述第一心音、第二心音确定心音信号的收缩期持续时长与心音信号的舒张期持续时长的步骤，包括：
确定所述心音信号包括的心动周期，依次遍历每一所述心动周期；
将遍历的所述心动周期内所述第一心音的结束时间作为第一结束时间，确定遍历的所述心动周期对应的下一心动周期，将所述下一心动周期内所述第一心音的起始时间作为第一起始时间；
将遍历的所述心动周期内所述第二心音的起始时间作为第二起始时间，将遍历的所述心动周期内所述第二心音的结束时间作为第二结束时间；
将所述第一结束时间与所述第二起始时间的时间差，作为收缩期时长；
将所述第一起始时间与所述第二结束时间之间的时间差，作为舒张期持续时长；
直至每一所述心动周期遍历结束后，确定所有所述收缩期时长的平均收缩期时长，确定所有所述舒张期持续时长的平均舒张期持续时长；
将所述平均收缩期时长作为心音信号的收缩期持续时长，将所述平均舒张期持续时长作为心音信号的舒张期持续时长。
此外，为实现上述目的，本申请还提供一种心音分割装置，所述心音分割装置包括：
信号采集模块，用于同步采集生理信号，其中，所述生理信号包括心音信号；
分割模块，用于获取所述心音信号对应的分割阈值，基于所述分割阈值分割所述心音信号，得到第一心音与第二心音；
确定模块，用于根据所述第一心音、第二心音确定收缩期持续时长与舒张期持续时长。
本申请还提供一种电子设备，所述电子设备为实体设备，所述电子设备包括：至少一个处理器；以及，与所述至少一个处理器通信连接的存储器；其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行如上所述心音分割方法的步骤。
本申请还提供一种可读存储介质，所述可读存储介质为计算机可读存储介质，所述计算机可读存储介质上存储有实现心音分割方法的程序，所述实现心音分割方法的程序被处理器执行以实现如上所述心音分割方法的步骤。
本申请还提供一种计算机程序产品，包括计算机程序，所述计算机程序被处理器执行时实现如上述的心音分割方法的步骤。
本申请中同步采集生理信号，其中，所述生理信号包括心音信号；获取所述心音信号对应的分割阈值，基于所述分割阈值分割所述心音信号，得到第一心音与第二心音；根据所述第一心音、第二心音确定收缩期持续时长与舒张期持续时长。如此，与现有技术在基于模型的心音分割方式相比，本申请实施例，基于分割阈值对心音信号进行心音分割，得到第一心音与第二心音，基于第一心音与第二心音从而计算舒张期与收缩期，完成心音信号的完整心音分割，只需简单的值比较运算即可完成心音分割，不需要复杂的模型运算，降低了计算复杂度，从而降低了心音信号的心音分割资源耗费。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本申请的实施例，并与说明书一起用于解释本申请的原理。
为了更清楚地说明本申请实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，对于本领域普通技术人员而言，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1为本申请心音分割方法第一实施例的流程示意图；
图2为本申请可穿戴式设备系统总架构示意图；
图3为本申请可穿戴式设备结构示意图；
图4为本申请心音分割方法生理信号示意图；
图5为本申请心音分割方法的预测流程示意图；
图6为本申请心音分割方法的另一预测流程示意图；
图7为本申请心音分割装置的装置模块示意图；
图8为本申请实施例中心音分割装置涉及的硬件运行环境的设备结构示意图。
本申请目的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
具体实施方式
为使本发明的上述目的、特征和优点能够更加明显易懂，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述。显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动的前提下所获得的所有其它实施例，均属于本发明保护的范围。
实施例一
本申请提出第一实施例的心音分割方法，请参照图1，所述心音分割方法包括：
步骤S10，同步采集生理信号，其中，所述生理信号包括心音信号；
该生理信号包括但不限于心音信号，如还可以包括心电信号与脉搏信号，以心电信号与脉搏信号辅助心音信号的心音分割，提高分割精度。该生理信号可通过相关设备采集得到，如用户使用可穿戴式设备，则可基于可穿戴式设备采集用户的生理信号。可该可穿戴式设备具体可为智能手表、智能手环等等。
进一步地，在同一时刻内同时开始同步采集生理信号，确定心电信号、脉搏信号与心音信号与时间的关系，以确保生理信号的严格同步性。并且还可以通过校对后的实时时间，记录数据从开启采集的时刻。
步骤S20，获取所述心音信号对应的分割阈值，基于所述分割阈值分割所述心音信号，得到第一心音与第二心音；
心音信号的心音分割，具体为区分出每个心动周期的第一心音(S1)、收缩期、第二心音(S2)和舒张期的确切位置。第一心音(S1)是由于二尖瓣和三尖瓣关闭，主动脉瓣和肺动脉瓣开启以及心室收缩过程中产生的振动引起的；第二心音(S2)第二心音形成的主要原因是主动脉瓣和肺动脉瓣的关闭，同时由于主动脉和肺动脉的血流减弱而产生的振动。收缩期是S1和S2之间的区间，舒张期是从S2到下一个心动周期S1开始。心音信号分割的正确性直接影响后续心音信号的分析效果。则收缩期持续时长也即为S1和S2之间的时长，舒张期持续时长为从S2到下一个心动周期S1之间的时长。
在一种可行的实施方式中，所述分割阈值包括第一阈值与第二阈值，所述基于所述分割阈值分割所述心音信号的步骤，包括：
步骤S201，获取或确定所述心音信号对应的心音包络信号；
具体地，可确定所述心音信号的上包络线，对所述上包络线进行滤波处理，得到该心音信号对应的心音包络信号。
步骤S202，将所述心音包络信号的信号值大于所述第一阈值的持续时长窗口，作为第一持续时长窗口；
步骤S203，将所述心音包络信号的信号值大于所述第二阈值的持续时长窗口，作为第二持续时长窗口；
步骤S204，将在所述第一持续时长窗口内的心音信号作为第一心音，将在所述第二持续时长窗口内的心音信号作为第二心音。
需要说明地是，对心音信号的滤波处理具体可为去基线和滑动平均滤波处理，以减少干扰信号。
可以理解地是，对于每一心动周期，均有其对应的第一持续时长窗口与第二持续时长窗口，将第一持续时长窗口内的第一心音记为S1(t)，其中，t为第t个心动周期，记第二持续时长窗口内的第二心音为S2(t)。参照图4所示，生理信号包括心电(electrocardiogram，ECG)信号、心音(phonocardiogram，PCG)信号与脉搏信号。示例性地，对心音信号进行心音分割，在每一心动周期内，分割得到第一心音(S1)与第二心音(S2)。
步骤S30，根据所述第一心音、第二心音确定心音信号的收缩期持续时长与心音信号的舒张期持续时长。
记第一心音为S1，第二心音为S2，收缩期是S1和S2之间的区间，舒张期是从S2到下一个心动周期S1开始。也即收缩期持续时长为S1和S2之间的区间，舒张期持续时长为从S2到下一个心动周期S1开始之间的时长。
在一种可行的实施方式中，所述根据所述第一心音、第二心音确定心音信号的收缩期持续时长与心音信号的舒张期持续时长的步骤，包括：
步骤S301，确定所述心音信号包括的心动周期，依次遍历每一所述心动周期；
步骤S302，将遍历的所述心动周期内所述第一心音的结束时间作为第一结束时间，确定遍历的所述心动周期对应的下一心动周期，将所述下一心动周期内所述第一心音的起始时间作为第一起始时间；
步骤S303，将遍历的所述心动周期内所述第二心音的起始时间作为第二起始时间，将遍历的所述心动周期内所述第二心音的结束时间作为第二结束时间；
步骤S304，将所述第一结束时间与所述第二起始时间的时间差，作为收缩期时长；
步骤S305，将所述第一起始时间与所述第二结束时间之间的时间差，作为舒张期持续时长；
步骤S306，直至每一所述心动周期遍历结束后，确定所有所述收缩期时长的平均收缩期时长，确定所有所述舒张期持续时长的平均舒张期持续时长；
步骤S307，将所述平均收缩期时长作为心音信号的收缩期持续时长，将所述平均舒张期持续时长作为心音信号的舒张期持续时长。
记第t个心动周期的第一心音为S1(t)，第t个心动周期的第二心音为S2(t)，S1(t)的起始时间记为S1start(t)，S1(t)的结束时间记为S1end(t)，S2(t)的起始时间记为S2start(t)，S2(t)的结束时间记为S2end(t)，则第t个心动周期对应的收缩期持续时长为S1end(t)与S2start(t)之间的时间差，舒张期持续时长为S1start(t+1)与S2end(t)之间的时间差，基于此，若心音信号包括多个心动周期的心音信号，则对于每一心动周期对应一个收缩期持续时长与舒张期持续时长，可将所有心动周期对应的收缩期持续时长的持续时长均值作为最终的收缩期持续时长，类似地，将所有心动周期对应的舒张期持续时长的持续时长均值作为最终的舒张期持续时长。
实施例二
基于本申请第一实施例，在本申请另一实施例中，与上述实施例一相同或相似的内容，可以参考上文介绍，后续不再赘述。在此基础上，在一种可行的实施方式中，所述生理信号还包括心电信号与脉搏信号，所述获取所述心音信号对应的分割阈值的步骤之前，所述方法还包括：
步骤A10，确定所述心电信号的QRS波峰值点，将所述QRS波峰值点对应的时间作为第一时间；
步骤A20，确定所述脉搏信号的波谷点，将所述波谷点对应的时间作为第二时间；
步骤A30，确定所述脉搏信号的第一个过零点与第二个过零点，将所述第一个过零点对应的时间作为第三时间，将所述第二个过零点对应的时间作为第四时间；
步骤A40，确定所述第一时间与所述第二时间对应的第一阈值，确定所述第三时间与所述第四时间对应的第二阈值；
步骤A50，将所述第一阈值与所述第二阈值作为分割阈值。
可以理解地是，对于每一心动周期的心电信号与脉搏信号，确定该心动周期内心电信号QRS波峰值点对应的第一时间，脉搏信号的波谷点对应的第二时间，以及脉搏信号的第一个过零点第三时间与第二个过零点第四时间，进而确定该心动周期的第一阈值与第二阈值，以该心动周期的第一阈值与第二阈值对该心动周期的心音信号进行心音分割，得到该心动周期的心音信号的第二收缩期持续时长与第二舒张期持续时长，从而基于每一心动周期对心音信号进行心音分割，提高了心音信号的心音分割的精度。
在一种可行的实施方式中，所述确定所述第一时间与所述第二时间对应的第一阈值的步骤，包括：
步骤B10，获取或确定所述心音信号对应的心音包络信号；
步骤B20，将所述心音包络信号在所述第一时间与所述第二时间之间的心音峰值，作为第一心音峰值；
步骤B30，基于预设调整系数调整所述第一心音峰值，得到第一阈值，其中，所述第一阈值小于所述第一心音峰值。
该预设调整系数可为提前设置的任意系数，如0.1、0.15、0.2等等，基于预设调整系数调整所述第一心音峰值，具体可为以预设调整系数乘以第一心音峰值，得到第一阈值。
本实施例中，以第一时间与所述第二时间之间的第一心音峰值，确定第一阈值，该第一阈值与第一心音峰值相关，不同的峰值对应不同阈值，从而可以实现阈值的智能化调整，而不是以固定的阈值进行心音分割，提高了心音分割的分割精度。
在一种可能的实施方式中，所述确定所述第三时间与所述第四时间对应的第二阈值的步骤，包括：
步骤C10，获取或确定所述心音信号对应的心音包络信号；
步骤C20，将所述心音包络信号在所述第三时间与所述第四时间之间的心音峰值，作为第二心音峰值；
步骤C30，基于预设调整系数调整所述第二心音峰值，得到第二阈值，其中，所述第二阈值小于所述第二心音峰值。
该预设调整系数可为与上述调整系数相同或不同的调整系数，基于预设调整系数调整所述第二心音峰值，也可为以预设调整系数乘以第二心音峰值，得到第二阈值。该第二阈值与第二峰值相关，不同的峰值对应不同阈值，从而可以实现阈值的智能化调整，而不是以固定的阈值进行心音分割，提高了心音分割的分割精度。
为了助于理解本申请的技术构思或技术原理，列举一具体实施例：
在本具体实施例中，心音分割流程为：
S1，识别心电信号QRS波峰值点，获得峰值点位置序列R(t)；
S2，识别脉搏信号波谷点和两个过零点，获得波谷点位置序列V(t)，第一个过零点位置序列Cross_zero1(t)，第二个过零点位置序列Cross_zero2(t)；
S3，计算心音信号的上包络线，对上包络线进行去基线和滑动平均滤波，消除基线漂移和噪声干扰；
S4，计算心音包络信号在R(t)和V(t)序列之间的峰值，阈值大小设为峰值的10％，将大于阈值的包络起始点序列S1start(t)和结束点序列S1end(t)时间差作为S1持续时长序列S1(t)；
S5，计算心音包络信号在Cross_zero1(t)和Cross_zero2(t)序列之间的峰值，阈值大小同样为峰值的10％，将大于阈值的包络起始点序列S2start(t)和结束点序列S2end(t)时间差作为S2持续时长序列S2(t)；
S6，利用S1end(t)与S2start(t)时间差计算得到收缩期持续时长序列Sys(t)，利用S1start(t+1)与S2end(t)舒张期持续时长序列Dia(t)。
需要说明的是，上述具体实施例仅用于理解本申请，并不构成对本申请心音分割流程的限定，基于此技术构思进行更多形式的简单变换，均在本申请的保护范围内。
实施例三
血压是反应人体健康的一项重要生理参数，随着人口老龄化的加快以及现代人们生活方式的改变，高血压的发病率也在不断上升。截至2022年，我国高血压患病人数高达2.45亿人，而高血压的控制率和知晓率很低，只有56.6％和16.8％。高血压是心血管疾病的重要危险因素之一，而心血管疾病则是人类健康的“第一杀手”。因此，通过一种精准方便的设备对血压进行监测，对高血压的预防有着极大的帮助。
传统的血压测量方法大都是基于示波法的袖带式电子血压计，然而这种方法在测量过程中袖带的充放气会对用户造成极大的不适感，而且测量设备体积大，不够便携。近些年来无袖带血压测量设备的出现，解决了袖带的不适感，极大的减小了体积。随着近些年可穿戴式设备的用户逐渐增多，人们对应可穿戴式设备测量血压的需求也日渐增加，尤其是有些无袖带测量设备被集成到智能手表中，提高了用户的欢迎度和测量的实时性，但目前无袖带血压测量设备的精度有待提高。
无袖带血压测量设备主要它通过脉搏传递时间来估测血压。脉搏传递时间(PWTT)被定义为同一时刻心脏射血从近端点到达远端点所需要的时间，通常获得脉搏传递时间的方法是同步采集心电信号和脉搏波信号，以心电信号的R波波峰为起点，以脉搏波特征点为终点，该段时间差为脉搏传递时间。
然而实际上R波峰处并不是心脏开始收缩的时间，心脏开始收缩之前有一段准备的时间称为射血前期(PEP，preejection period)。由于射血前期的存在，使得基于脉搏传递时间估测的血压结果是不可靠的。
基于上述问题，以及本申请第一实施例与第二实施例，在本申请另一实施例中，与上述实施例一或实施例二或实施例三相同或相似的内容，可以参考上文介绍，后续不再赘述。在此基础上，在一种可行的实施方式中，所述根据所述第一心音、第二心音确定心音信号的收缩期持续时长与心音信号的舒张期持续时长的步骤之后，所述方法还包括：
步骤D10，对所述生理信号进行特征提取，得到信号特征，其中，所述信号特征包括射血前期持续时长与脉搏传递时间；
本实施例中该心音分割方法应用与可穿戴式设备，该可穿戴式设备具体可为智能手表、智能手环等等。
示例性，参照图2-3所示，该可穿戴式设备包括外壳1，与设于外壳的传感器，所述传感器用于同步采集生理信号。该传感器包括用于采集心音信号的第一传感器、用于采集脉搏信号的第二传感器、用于采集心电信号的第三传感器，该第一传感可为VPU(Voice Pick Up，骨传导)传感器250，该第二传感器可为光电脉搏传感器240，该第三传感器可为电极传感器，具体该电极传感器可包括三个电极，第一电极210和第三电极230用于构成回路，用于心电信号采集，第二电极220提供一个参考点位来消除身体和可穿戴式设备之间的电势差，提高心电信号采集的信噪比。
进一步地，参照图2-3所示，该可穿戴式设备还可以包括装置开关110，用于开关可穿戴式设备；装置处理器120，用于执行存储器中的程序代码，以执行可穿戴式设备的各种功能；时间校准模块130，用于显示实时时间以及数据同步采集校准；交互模块140，用于收集用户的个性化信息，响应用户进行血压测量操作产生的信号以及简单的血压测量使用指示，所述进行血压操作产生的信号包括开启血压测量信号，所述使用提示包括血压测量信号采集位置和用户采集姿势；生理信号采集模块150，用于收集用户与血压测量有关的生理信号以及加速度陀螺仪信号。所述与血压测量有关的生理信号包括心电信号，脉搏信号和心音信号。数据处理模块160，用于实时处理生理信号测量模块所收集到的生理信号片段，所述数据处理步骤主要包括信号降噪，信号质量评估以及特征提取。无线通信模块180，用于将采集到的生理信号数据，真实的用户血压值以及用户个性化信息，通过无线模块传输到服务器或者终端，用于血压测量数据库的构建。血压测量模块170，用于分析用户的生理信号数据和/或个性化信息，最终进行血压预测，返回血压预测结果，并判断当前血压水平。
此外，参照图3所示，所述生理信号采集模块还包括6轴信号采集模块，加速度和陀螺仪信号主要通过6轴信号采集模块采集得到，所述6轴信号采集模块主要由设备内部集成的6轴传感器260构成。在血压测量进行之前，6轴信号采集模块能够计算当前的欧拉角，辅助用户定位采集位置以及姿势；在进行血压测量过程中，6轴信号采集模块能够监测用户手臂的移动情况，与心电信号，心音信号和脉搏信号结合，进行生理信号的去噪，能够在采集过程中提高上述信号的信噪比。
可以理解的是，本申请实施例示意的结构并不构成对可穿戴式设备的具体限定。其可以具有上述更多的或者更少的部件，或者组合某些部件，或者拆分某些部件，或者不同的部件布置。上述的各种部件可以在包括一个或多个信号处理或专用集成电路在内的硬件、软件、或硬件和软件的组合中实现。
该检测对象可为使用该可穿戴式设备的用户。进一步地，在同一时刻内同时开始同步采集生理信号，确定心电信号、脉搏信号与心音信号与时间的关系，以确保生理信号的严格同步性。并且还可以通过校对后的实时时间，记录数据从开启采集的时刻。
进一步地，在提取生理信号的信号特征之前，为提高提取到的信号特征的准确度，可对生理信号进行信号处理，如对生理信号进行滤波、降噪、分段等处理。基于处理后的生理信号进行特征提取，得到信号特征。
在一种可行的实施方式中，所述对所述生理信号进行特征提取的步骤，包括：
步骤D101，对所述生理信号进行信号预处理，得到预处理后的生理信号，其中，所述信号预处理包括滤波、归一化、降噪中的一种或多种；
本实施例中，优选地，信号预处理包括归一化、滤波与降噪。可选地，将采集到的生理信号进行归一化操作，进一步的经预先设计好的FIR带通滤波器，对心电信号、脉搏信号和心音信号进行带通滤波。将滤波后的数据与加速度信号再经自适应滤波进行二次处理，滤除由于运动伪迹产生的噪声，得到干净的高质量生理信号。
步骤D102，确定所述预处理后的生理信号的信号持续时长；
步骤D103，若所述信号持续时长大于预设时长，则对所述预处理后的生理信号进行信号分段处理，得到多段子生理信号；
需要说明地是，对所述预处理后的生理信号进行信号分段处理，得到多段子生理信号，可为以无时间重叠的方式对生理信号进行分段处理，如信号持续时长为12秒，以时长3秒进行信号分段，则可以分为0～3秒、3～6秒、6～9秒、9～12秒四个子生理信号。也可以以有时间重叠的方式对生理信号进行分段处理，将每种信号分为固定时长(Sig_t)的信号片段，重叠长度为范围(0～Sig_t-1)的任意值。如信号持续时长为9秒，以固定时长3秒，重叠长度1秒进行信号分段，则可以分为0～3秒、2～5秒、4～7秒、6～9秒四个子生理信号。
进一步地，对预处理后的生理信号进行信号分段处理，得到多段子生理信号后，还可以对评估每一段子生理信号的信号质量，删除信号质量差的子生理信号，基于信号质量较好的子生理信号提取信号特征，保证提取的信号特征的有效性。
作为其中一种实施方式，评估每一段子生理信号的信号质量，可为在每一个子生理信号信号片段中，计算心电信号的RR间期，KSQI指数等，脉搏信号信号的峰值间期、过零点个数等，心音信号的SSQI系数、信号均值等特征，再结合加速度信号幅值的变化时间(如排除与加速度信号幅值时间重叠的子生理信号)，排除噪声干扰过的信号片段。利用将这些特征输入至分类模型，如SVM(Support Vector Machine，支持向量机)模型，对每段信号进行粗分类，如分为可用子生理信号与不可用子生理信号，基于用子生理信号提取信号特征。
步骤D204，对于每一段所述子生理信号，提取所述子生理信号的子信号特征；
步骤D205，确定所有所述子信号特征的均值信号特征，将所述均值信号特征作为所述心理信号的信号特征。
如果所述预处理后的生理信号的信号持续时长大于预设时长，如5秒、6秒、7秒等，可对预处理后的生理信号进行信号分段处理，提取每一段子生理信号的子信号特征。
可以理解地是，对预处理后的生理信号进行信号分段处理，也即对预处理后的心电信号、预处理后的脉搏信号与预处理的心音信号进行分段处理。提取每一子生理信号的子信号特征，每一子信号特征构成n维特征序列X(t)，n为特征个数，计算所有X(t)的每一维特征的均值，得到均值信号特征，也即最终的信号特征。举例来说，假设包括心电信号、脉搏信号与心音信号的心理信号生理信号，分段处理后得到三段子生理信号，分别为子生理信号1、子生理信号2、子生理信号3，子生理信号1包括子心电信号1、子心音信号1与子脉搏信号1，子生理信号2包括子心电信号2、子心音信号2与子脉搏信号2，子生理信号3包括子心电信号3、子心音信号3与子脉搏信号3。提取子生理信号1的信号特征，记为子信号特征1【1_1、1_2、1_3】，提取子生理信号1的信号特征，记为子信号特征2【2_1、2_2、2_3】，提取子生理信号3的信号特征，记为子信号特征3【3_1、3_2、3_3】，则最终得到的信号特征为【(1_1+2_1+3_1)/3、(1_2+2_2+3_2)/3、(1_3+2_3+3_3)/3】。
此外，进一步地，在提取到每一子生理信号的子信号特征后，可对所有子信号特征进行异常值处理，删除异常的特征。可选地，对于每一段子生理信号的信号特征，遵循箱线图原则进行异常值特征序列处理，示例性的处理流程可如下：S1，每段子生理信号特征的特征值，构成n维特征序列X(t)，n为特征个数；S2，设置每一维特征的上边缘与下边缘，如计算每一维特征的上四分位数Q1i，下四分位数Q3i，四分位距IQRi，取上边缘Q1i-1.5IQRi，下边缘Q3i+1.5IQRi，i＝1：n；S3，过滤掉每一维特征在上下边缘之外的异常数据；S4，得到去除异常值后的特征序列S(t)。S5，对筛选后的特征序列计算其均值，以获得均值信号特征S-。
该信号特征包括但不限于射血前期持续时间与脉搏传递时间，如还可以包括脉冲到达时间(pulse arrival time，PAT)、脉搏信号和心音信号收缩期持续时间比、脉搏信号和心音信号舒张期持续时间比、时域特征，频域特征，时频特征，统计学特征等等。
其中，时域特征包括但不限于以下特征：心电信号的R-R间期(RR)，R-R标准差(SDNN)，均方根差(RMSSD)等；脉搏信号的PP间期(PP)，半幅脉宽(PW50)，收缩期时间，舒张期时间，上升时间，最快上升面积，峰值高度，上升斜率等；VPG信号(对脉搏信号进行一阶差分处理得到信号)的第一过零点时间，最后一个拐点时间，峰值与第一过零点斜率，峰值斜率，峰值面积等；APG信号(对脉搏信号进行二阶差分处理得到信号)最低点时间，峰值点与最低点斜率，第一过零点与最低点斜率；心音信号中第一心音持续时间，第二心音持续时间，收缩期持续时间，舒张期持续时间等。
频域特征包括但不限于以下特征：心电信号功率谱密度；脉搏信号第一组成频率及其幅值大小，第二组成频率及其幅值大小，第三组成频率及其幅值大小；心音信号S1主要组成频率，S2主要组成频率等。
时频特征主要包括但不限于以下特征：小波系数，希尔伯特黄变换系数，梅尔倒频谱系数，线性预测系数特征等；
统计学特征主要包括但不限于以下特征：峰度因子，偏度因子，特征序列的标准差等。
步骤D20，获取所述脉搏信号的收缩期持续时长与所述脉搏信号的舒张期持续时长；
脉搏信号在收缩期与舒张期的信号特征不同，基于此从脉搏信号中提取到收缩期持续时间与舒张期持续时间，具体提取方式可采用现有技术，本实施例中不再赘述。
步骤D30，将所述脉搏信号的收缩期持续时长与所述心音信号的收缩期持续时长的比值，作为收缩期持续时长比；
步骤D40，将所述脉搏信号的舒张期持续时长与所述心音信号的舒张期持续时长的比值，作为舒张期持续时长比；
步骤D50，将所述收缩期持续时长比、所述舒张期持续时长比与所述信号特征作为目标信号特征；
步骤D60，将所述信号特征输入预设的血压预测模型中进行训练，以供所述血压预测模型输出得到血压预测结果。
该训练的血压模型，可为基于数据库训练的血压预测模型，数据库至少包括真实血压数据，以及每一真实血压数据对应的信号特征数据。该数据库可为通过预先收集真实血压数据与信号特征数据得到。
进一步地，为了提高血压预测模型的预测准确度，实现血压的个性化预测，可以预先多次收集检测对象的真实血压值和生理信号，建立个体数据集，以该个体数据集作为训练预测模型的数据库，完成血压预测模型的训练。
作为其中一种实施方式，血压预测模型的预训练过程可为：S1，通过已有数据库，在多类别特征库当中进行特征选择；S2，两两计算特征之间的互信息，其中p(x)为x出现的概率，p(y)为y出现的概率，p(x，y)为x，y同时出现的概率，即联合概率。互信息越高，代表两个特征之间依赖程度更高。将低于互信息阈值的特征去掉，得到新的特征子集；S3，计算新的特征子集与血压之间的相关系数，相关系数越高，代表特征和血压的线性相关性更高；S4，按照相关系数对特征子集进行从高到低特征排序，得到排序后的特征子集；S5，对排序后的特征子集进行训练集和测试集划分，训练集和测试集比例为8：2；S6，针对训练集，采用十折交叉验证和后向特征选择进行特征个数选择，得到RMSE(Root Mean Squared Error，均方根误差)最低的特征子集S；S7，使用最终特征子集训练多元线性回归模型：其中BP为具体血压值，S为最优特征子集，Ki为多元线性回归模型拟合系数，n为最优特征子集的维数。
此外，还可以收集检测者的年龄，性别，身高，体重，BMI(BodyMassIndex，身体质量指数)指数等个性化特征，与信号特征数据进行模型训练，得到预训练完成的个性化血压预测模型，基于生理信号提取信号特征后，进一步检测者的年龄，性别，身高，体重，BMI(BodyMassIndex，身体质量指数)指数等个性化特征，将信号特征与个性化特征输入至预训练完成的个性化血压预测模型中，输出得到血压预测结果，考虑年龄，性别，身高，体重，BMI(BodyMassIndex，身体质量指数)指数等因素对血压的影响，可进一步提高血压预测的准确度。
进一步地，在得到血压预测结果之后，可在可穿戴式设备上输出该血压预测结果，同时还可将该血压预测结果上传至与可穿戴式设备通信连接的终端或服务器上，以供用户查看，终端和服务器能够实现用户的历史血压数据查看，有助于医生诊断。根据历史数据定制个性化血压测量方案，更全面的帮助用户了解自身健康状况，进而更科学的给出用户就诊意见。
本实施例中采集检测对象的生理信号，其中，所述生理信号包括心电信号、脉搏信号与心音信号；对所述生理信号进行特征提取，得到信号特征，其中，所述信号特征包括射血前期持续时间与脉搏传递时间；将所述信号特征输入至预训练的血压预测模型中，以供所述血压预测模型输出得到血压预测结果。如此，与现有技术在基于脉搏传递时间估测血压的方式相比，本实施例，基于射血前期持续时间与脉搏传递时间等融合信号特征，预测检测者的血压，考量了射血前期持续时间这一因素对血压的影响，从而提高了血压的预测准确度。
本实施例中，对心音信号进行心音分割后，得到基于心音信号的第二收缩期持续时间与第二舒张期持续时间，并获取脉搏信号的第一收缩期持续时间与第以舒张期持续时间，将两者之间的比值也作为信号特征，从而综合衡量了心音信号与脉搏信号的舒张期持续时间与收缩期持续时间，可以进一步地提高了血压的预测准确度。
在一种可能的实施方式中，所述对所述生理信号进行特征提取的步骤，包括：
步骤E10，确定所述心电信号的QRS峰值，确定所述心音信号的心音峰值，确定两个所述峰值之间的时间差，将所述时间差作为射血前期持续时长；
需要说明地是，若对生理信号进行了分段处理，则本实施例中的对生理信号就进行特征提取，实际上可为对每一子生理信号进行特征提取，心电信号、心音信号与脉搏信号也为子生理信号中包括的心电信号、心音信号与脉搏信号。
可以理解地是，参照图4所示，生理信号包括心电(electrocardiogram，ECG)信号、心音(phonocardiogram，PCG)信号与脉搏信号。确定心电信号的信号峰值，确定心音信号的信号峰值，具体可为确定属于同一个心跳周期的心电信号的QRS峰值，心音信号的心音峰值，获取这两个信号峰值对应的时间，将两者之间的时间差作为射血前期持续时间。如生理信号包括多个心跳周期，则可以确定每一心跳周期对应的射血前期持续时间，将所有射血前期持续时间的均值作为最终的射血前期持续时间。
步骤E20，基于所述脉搏信号与所述心音信号获取脉搏传递时间。
以心音信号的S1峰值点为起点，以脉搏波特征点为终点，该段时间差为脉搏传递时间，从而可以选择一个或多个脉搏波特征点得到对应的一个或多个脉搏传递时间，也即脉搏传递时间包括一个或多个，用户可根据实际情况设置脉搏波特征点的选择规则，本实施例对脉搏传递时间的特征数量并不做具体限制。
类似地，基于同步采集心电信号和脉搏信号，以心电信号的R波波峰为起点，确定一个或多个脉冲到达时间(pulse arrival time，PAT)，将这一个或多个脉冲到达时间也可作为提取得到的信号特征。
本实施例中，提取射血前期持续时间、脉搏传递时间等融合信号特征，为预测血压值提供了有效地数据基础。
为了助于理解本申请的技术构思或技术原理，列举一具体实施例：
参见图5-6所示，在本具体实施例中的血压预测流程为：
通过装置开关启动腕表式设备，同时腕表式设备可连接服务器与手机APP，时间校准后用户可输入个性化信息，如身高、体重等等，提示用户配置方式，用户按提示信息佩戴该腕表式设备后，腕表式设备开启血压测量，同步采集生理信号，该生理信号包括心电信号、心音信号与脉搏信号，同时还以采集用户的加速度、角速度等信息，计算用户当前的欧拉角，辅助用户定位采集位置以及姿势；在进行血压测量过程中，采集用户的加速度、角速度信息能够监测用户手臂的移动情况，与心电信号，心音信号和脉搏信号结合，进行生理信号的去噪，对采集到的生理信号进行信号处理，如滤波(具体可包括带通滤波与自适应滤波)、信号质量评估等，对信号质量评估的评估结果为信号质量高的生理信号进行特征提取，将提取到的信号特征输入至血压预测模型中，进行血压预测，并显示血压预测结果同时上传血压预测结果。
需要说明的是，上述具体实施例仅用于理解本申请，并不构成对本申请血压预测流程的限定以及对应用设备的限定，基于此技术构思进行更多形式的简单变换，均在本申请的保护范围内。
实施例四
本发明实施例还提供一种心音分割装置，请参照图7，所述心音分割装置包括：
信号采集模块，用于同步采集生理信号，其中，所述生理信号包括心音信号；
分割模块，用于获取所述心音信号对应的分割阈值，基于所述分割阈值分割所述心音信号，得到第一心音与第二心音；
确定模块，用于根据所述第一心音、第二心音确定收缩期持续时长与舒张期持续时长。
所述生理信号还包括心电信号与脉搏信号，所述分割模块，还用于：
确定所述心电信号的QRS波峰值点，将所述QRS波峰值点对应的时间作为第一时间；
确定所述脉搏信号的波谷点，将所述波谷点对应的时间作为第二时间；
确定所述脉搏信号的第一个过零点与第二个过零点，将所述第一个过零点对应的时间作为第三时间，将所述第二个过零点对应的时间作为第四时间；
确定所述第一时间与所述第二时间对应心音信号的第一阈值，确定所述第三时间与所述第四时间对应心音信号的第二阈值；
将所述第一阈值与所述第二阈值作为分割阈值。
所述分割模块，还用于：
获取或确定所述心音信号对应的心音包络信号；
将所述心音包络信号在所述第一时间与所述第二时间之间的心音峰值，作为第一心音峰值；
基于预设调整系数调整所述第一心音峰值，得到第一阈值，其中，所述第一阈值小于所述第一心音峰值。
所述分割模块，还用于：
获取或确定所述心音信号对应的心音包络信号；
将所述心音包络信号在所述第三时间与所述第四时间之间的心音峰值，作为第二心音峰值；
基于预设调整系数调整所述第二心音峰值，得到第二阈值，其中，所述第二阈值小于所述第二心音峰值。
所述分割阈值包括第一阈值与第二阈值，所述分割模块，还用于：
获取或确定所述心音信号对应的心音包络信号；
将所述心音包络信号的信号值大于所述第一阈值的持续时长窗口，作为第一持续时长窗口；
将所述心音包络信号的信号值大于所述第二阈值的持续时长窗口，作为第二持续时长窗口；
将在所述第一持续时长窗口内的心音信号作为第一心音，将在所述第二持续时长窗口内的心音信号作为第二心音。
所述确定模块，还用于：
确定所述心音信号包括的心动周期，依次遍历每一所述心动周期；
将遍历的所述心动周期内所述第一心音的结束时间作为第一结束时间，确定遍历的所述心动周期对应的下一心动周期，将所述下一心动周期内所述第一心音的起始时间作为第一起始时间；
将遍历的所述心动周期内所述第二心音的起始时间作为第二起始时间，将遍历的所述心动周期内所述第二心音的结束时间作为第二结束时间；
将所述第一结束时间与所述第二起始时间的时间差，作为收缩期时长；
将所述第一起始时间与所述第二结束时间之间的时间差，作为舒张期持续时长；
直至每一所述心动周期遍历结束后，确定所有所述收缩期时长的平均收缩期时长，确定所有所述舒张期持续时长的平均舒张期持续时长；
将所述平均收缩期时长作为心音信号的收缩期持续时长，将所述平均舒张期持续时长作为心音信号的舒张期持续时长。
所述心音分割装置还包括血压预测模块，所述血压预测模式，用于：
对所述生理信号进行特征提取，得到信号特征，其中，所述信号特征包括射血前期持续时长与脉搏传递时间；
获取所述脉搏信号的收缩期持续时长与所述脉搏信号的舒张期持续时长；
将所述脉搏信号的收缩期持续时长与所述心音信号的收缩期持续时长的比值，作为收缩期持续时长比；
将所述脉搏信号的舒张期持续时长与所述心音信号的舒张期持续时长的比值，作为舒张期持续时长比；
将所述收缩期持续时长比、所述舒张期持续时长比与所述信号特征作为目标信号特征；
将所述信号特征输入预设的血压预测模型中进行训练，以供所述血压预测模型输出得到血压预测结果。
所述血压预测模式，还用于：
确定所述心电信号的QRS峰值，确定所述心音信号的心音峰值，确定两个所述峰值之间的时间差，将所述时间差作为射血前期持续时长；
基于所述脉搏信号与所述心音信号获取脉搏传递时间。
此外，所述信号采集模块，还用于：
用户测量过程中的加速度和陀螺仪信号。
所述信号采集模块包括：心电测量模块、脉搏测量模块、心音信号测量模块与6轴信号采集模块。
心电信号主要通过心电测量模块采集得到，所述心电测量模块主要由高阻抗芯片以及导电性良好的三个干电极构成。所述脉搏信号主要通过脉搏测量模块采集得到，所述脉搏测量模块主要由多波长LED(light-emitting diode，发光二级管)，光电传感器以及滤波放大电路构成，最终得到的脉搏信号是由多波长LED融合而成的。为保证无袖带血压测量手表的体积，模拟的心电信号采集的高阻抗特性，脉搏信号的融合，滤波放大电路及两种生理信号的同步性均由集成的AFE芯片实现。
心音信号主要通过心音信号测量模块采集得到，所述心音信号测量模块主要由数字VPU传感器构成，将VPU传感器通过严格的刚性连接方式贴合在手表外壳内部，调节VPU传感器的放大倍数，防止测试过程中信号的溢出，以得到完整的心音信号。
加速度和陀螺仪信号主要通过6轴信号采集模块采集得到，所述6轴信号采集模块主要由手表内部集成的6轴传感器构成。在血压测量进行之前，6轴信号采集模块能够计算当前的欧拉角，辅助用户定位采集位置以及姿势；在进行血压测量过程中，6轴信号采集模块能够监测用户手臂的移动情况，与心电信号，心音信号和脉搏信号结合，进行生理信号的去噪，能够在采集过程中提高上述信号的信噪比。
此外，该心音分割装置还包括：
手表外壳，用于放置生理信号采集所用传感器以及手表控制系统；
时间校准模块，用于显示实时时间以及数据同步采集校准；
交互模块，用于收集用户的个性化信息，响应用户进行血压测量操作产生的信号以及简单的血压测量手表使用指示。所述进行血压操作产生的信号包括开启血压测量信号。所述手表使用提示包括血压测量手表信号采集位置和用户采集姿势；
数据处理模块，用于实时处理生理信号测量模块所收集到的生理信号片段，所述数据处理步骤主要包括信号降噪，信号质量评估以及特征提取。
无线通信模块，用于将采集到的生理信号数据，真实的用户血压值以及用户个性化信息，通过无线模块传输到服务器或者手机终端，用于血压测量手表数据库的构建。
所述手表外壳外部包括手表的开关和心电监测的三个干电极。手表开关主要控制手表的开关机以及手表内部菜单的调取。第一电极和第三电极用于构成回路，用于心电信号采集，第二电极提供一个参考点位来消除身体和手表之间的电势差，提高心电信号采集的信噪比。腕表外壳内部包括刚性连接的VPU传感器以及光电脉搏传感器，用于心音信号和光电容积脉搏信号的测量。
所述时间校准模块用于产生实时时钟，在同一时刻内控制传感器同时开始同步采集生理信号，确定心电信号、脉搏信号与心音信号与时间的关系，以确保生理信号的严格同步性。并通过校对后的实时时间，记录数据从开启采集的时刻。
所述交互模块包括输入模块，显示模块以及提示模块，其功能都由手表内部MCU(Microcontroller Unit，微控制单元)和手表屏幕实现。所述交互模块中的输入模块141，用于过手表的屏幕，在进行血压测量之前，将个性化信息输入到手表内部，不仅包括性别，身高，年龄以及体重等个人信息，还包括是否服用降压药物以及降压药物名称等信息。
所述交互模块中的显示模块，用于显示手表使用方法，以及测量步骤。用户通过完成个性化信息输入步骤之后，通过屏幕点击血压测量功能，就能看到手表佩戴的方式和测量时用户应保持的姿势。在完成使用教程之后，将进入测试阶段，手表可以通过提示模块提示手臂位置的调整，以确保生理信号采集质量。
所述交互模块中的提示模块，包括语音芯片和线性振动马达，用于提示用户操作流程，手臂放置位置和测量姿势，确保血压测量准确性。
所述数据处理模块包括：信号降噪模块与信号质量评估模块。
信号降噪模块，用于采集到的生理信号进行归一化操作，进一步的经预先设计好的FIR(Finite Impulse Response，有限脉冲响应)带通滤波器，对心电信号、脉搏信号和心音信号进行带通滤波。将滤波后的数据与加速度信号再经自适应滤波进行二次处理，滤除由于运动伪迹产生的噪声，得到干净的高质量生理信号。
信号质量评估模块，用于将每种信号分为固定时长(Sig_t)的信号片段，时长一般>5s，重叠长度为范围(0～Sig_t-1)的任意值。在每一个信号片段中，计算心电信号的RR间期，KSQI指数等，脉搏信号的峰值间期、峰值间期标准差、过零点个数等，心音信号的SSQI系数，信号均值等特征，再结合加速度信号幅值的变化时间，利用SVM模型对每段信号进行粗分类，排除噪声干扰过的信号片段。
所述无线通信模块用于将采集得到的生理信号，输入的个性化信息以及真实测量得到的血压值发送到终端，并上传至云端服务器用于数据收集。
本发明提供的心音分割装置，采用上述实施例一或实施例二或实施例三中的心音分割方法，能够解决如何降低心音信号的心音分割资源耗费的技术问题。与现有技术相比，本发明实施例提供的心音分割装置的有益效果与上述实施例提供的心音分割方法的有益效果相同，且所述心音分割装置中的其他技术特征与上一实施例方法公开的特征相同，在此不做赘述。
实施例五
本发明实施例提供一种电子设备，电子设备包括：至少一个处理器；以及，与至少一个处理器通信连接的存储器；其中，存储器存储有可被至少一个处理器执行的指令，指令被至少一个处理器执行，以使至少一个处理器能够执行上述实施例一中的心音分割方法。
下面参考图8，其示出了适于用来实现本公开实施例的电子设备的结构示意图。本公开实施例中的该电子设备可为可穿戴式设备等。图8示出的电子设备仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
如图8所示，电子设备可以包括处理装置1001(例如中央处理器、图形处理器等)，其可以根据存储在只读存储器(ROM1002)中的程序或者从存储装置加载到随机访问存储器(RAM1004)中的程序而执行各种适当的动作和处理。在RAM1004中，还存储有电子设备操作所需的各种程序和数据。处理装置1001、ROM1002以及RAM1004通过总线1005彼此相连。输入/输出(I/O)接口也连接至总线1005。
通常，以下系统可以连接至I/O接口1006：包括例如触摸屏、触摸板、键盘、鼠标、图像传感器、麦克风、加速度计、陀螺仪等的输入装置1007；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置1008；包括例如磁带、硬盘等的存储装置1003；以及通信装置1009。通信装置1009可以允许电子设备与其他设备进行无线或有线通信以交换数据。虽然图中示出了具有各种系统的电子设备，但是应理解的是，并不要求实施或具备所有示出的系统。可以替代地实施或具备更多或更少的系统。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信装置从网络上被下载和安装，或者从存储装置1003被安装，或者从ROM1002被安装。在该计算机程序被处理装置1001执行时，执行本公开实施例的方法中限定的上述功能。
本发明提供的电子设备，采用上述实施例中的心音分割方法，能解决如何降低心音信号的心音分割资源耗费的技术问题。与现有技术相比，本发明实施例提供的电子设备的有益效果与上述实施例提供的心音分割方法的有益效果相同，且该电子设备中的其他技术特征与上一实施例方法公开的特征相同，在此不做赘述。
应当理解，本公开的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式的描述中，具体特征、结构、材料或者特点可以在任何的一个或多个实施例或示例中以合适的方式结合。
以上所述，仅为本发明的具体实施方式，但本发明的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应以所述权利要求的保护范围为准。
实施例六
本发明实施例提供一种计算机可读存储介质，具有存储在其上的计算机可读程序指令，计算机可读程序指令用于执行上述实施例一中的心音分割方法。
本发明实施例提供的计算机可读存储介质例如可以是U盘，但不限于电、磁、光、电磁、红外线、或半导体的系统、系统或器件，或者任意以上的组合。计算机可读存储介质的更具体地例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本实施例中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、系统或者器件使用或者与其结合使用。计算机可读存储介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
上述计算机可读存储介质可以是电子设备中所包含的；也可以是单独存在，而未装配入电子设备中。
上述计算机可读存储介质承载有一个或者多个程序，当上述一个或者多个程序被电子设备执行时，使得电子设备：同步采集生理信号，其中，所述生理信号包括心音信号；获取所述心音信号对应的分割阈值，基于所述分割阈值分割所述心音信号，得到第一心音与第二心音；根据所述第一心音、第二心音确定收缩期持续时长与舒张期持续时长。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码，上述程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本发明各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施例中所涉及到的模块可以通过软件的方式实现，也可以通过硬件的方式来实现。其中，模块的名称在某种情况下并不构成对该单元本身的限定。
本发明提供的可读存储介质为计算机可读存储介质，所述计算机可读存储介质存储有用于执行上述心音分割方法的计算机可读程序指令，能够解决如何降低心音信号的心音分割资源耗费的技术问题。与现有技术相比，本发明实施例提供的计算机可读存储介质的有益效果与上述实施例一或实施例二或实施例三提供的心音分割方法的有益效果相同，在此不做赘述。
实施例七
本发明实施例还提供一种计算机程序产品，包括计算机程序，所述计算机程序被处理器执行时实现如上述的心音分割方法的步骤。
本申请提供的计算机程序产品能够解决如何降低心音信号的心音分割资源耗费的技术问题。与现有技术相比，本发明实施例提供的计算机程序产品的有益效果与上述实施例一或实施例二或实施例三提供的心音分割方法的有益效果相同，在此不做赘述。
以上仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利处理范围内。

Claims (9)

  1. 一种心音分割方法，其特征在于，所述心音分割方法包括：
    同步采集生理信号，其中，所述生理信号包括心音信号；
    获取所述心音信号对应的分割阈值，基于所述分割阈值分割所述心音信号，得到第一心音与第二心音；
    根据所述第一心音、第二心音确定心音信号的收缩期持续时长与心音信号的舒张期持续时长。
  2. 如权利要求1所述的心音分割方法，其特征在于，所述生理信号还包括心电信号与脉搏信号，所述获取所述心音信号对应的分割阈值的步骤之前，所述方法还包括：
    确定所述心电信号的QRS波峰值点，将所述QRS波峰值点对应的时间作为第一时间；
    确定所述脉搏信号的波谷点，将所述波谷点对应的时间作为第二时间；
    确定所述脉搏信号的第一个过零点与第二个过零点，将所述第一个过零点对应的时间作为第三时间，将所述第二个过零点对应的时间作为第四时间；
    确定所述第一时间与所述第二时间对应的第一阈值，确定所述第三时间与所述第四时间对应的第二阈值；
    将所述第一阈值与所述第二阈值作为分割阈值。
  3. 如权利要求2所述的心音分割方法，其特征在于，所述确定所述第一时间与所述第二时间对应的第一阈值的步骤，包括：
    获取或确定所述心音信号对应的心音包络信号；
    将所述心音包络信号在所述第一时间与所述第二时间之间的心音峰值，作为第一心音峰值；
    基于预设调整系数调整所述第一心音峰值，得到第一阈值，其中，所述第一阈值小于所述第一心音峰值。
  4. 如权利要求2所述的心音分割方法，其特征在于，所述确定所述第三时间与所述第四时间对应的第二阈值的步骤，包括：
    获取或确定所述心音信号对应的心音包络信号；
    将所述心音包络信号在所述第三时间与所述第四时间之间的心音峰值，作为第二心音峰值；
    基于预设调整系数调整所述第二心音峰值，得到第二阈值，其中，所述第二阈值小于所述第二心音峰值。
  5. 如权利要求1所述的心音分割方法，其特征在于，所述分割阈值包括第一阈值与第二阈值，所述基于所述分割阈值分割所述心音信号的步骤，包括：
    获取或确定所述心音信号对应的心音包络信号；
    将所述心音包络信号的信号值大于所述第一阈值的持续时长窗口，作为第一持续时长窗口；
    将所述心音包络信号的信号值大于所述第二阈值的持续时长窗口，作为第二持续时长窗口；
    将在所述第一持续时长窗口内的心音信号作为第一心音，将在所述第二持续时长窗口内的心音信号作为第二心音。
  6. 如权利要求1所述的心音分割方法，其特征在于，所述根据所述第一心音、第二心音确定心音信号的收缩期持续时长与心音信号的舒张期持续时长的步骤，包括：
    确定所述心音信号包括的心动周期，依次遍历每一所述心动周期；
    将遍历的所述心动周期内所述第一心音的结束时间作为第一结束时间，确定遍历的所述心动周期对应的下一心动周期，将所述下一心动周期内所述第一心音的起始时间作为第一起始时间；
    将遍历的所述心动周期内所述第二心音的起始时间作为第二起始时间，将遍历的所述心动周期内所述第二心音的结束时间作为第二结束时间；
    将所述第一结束时间与所述第二起始时间的时间差，作为收缩期时长；
    将所述第一起始时间与所述第二结束时间之间的时间差，作为舒张期持续时长；
    直至每一所述心动周期遍历结束后，确定所有所述收缩期时长的平均收缩期时长，确定所有所述舒张期持续时长的平均舒张期持续时长；
    将所述平均收缩期时长作为心音信号的收缩期持续时长，将所述平均舒张期持续时长作为心音信号的舒张期持续时长。
  7. 一种心音分割装置，其特征在于，所述心音分割装置包括：
    信号采集模块，用于采集生理信号，其中，所述生理信号包括心音信号；
    分割模块，用于获取所述心音信号对应的分割阈值，基于所述分割阈值分割所述心音信号，得到第一心音与第二心音；
    确定模块，用于根据所述第一心音、第二心音确定心音信号的收缩期持续时长与心音信号的舒张期持续时长。
  8. 一种电子设备，其特征在于，所述电子设备包括：
    至少一个处理器；以及，
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行如权利要求1至6中任一项所述心音分割方法的步骤。
  9. 一种可读存储介质，其特征在于，所述可读存储介质为计算机可读存储介质，所述计算机可读存储介质上存储有实现心音分割方法的程序，所述实现心音分割方法的程序被处理器执行以实现如权利要求1至6中任一项所述心音分割方法的步骤。
PCT/CN2024/132614 2024-04-15 2024-11-18 心音分割方法、装置、电子设备及可读存储介质 Pending WO2025218160A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202410454429.1 2024-04-15
CN202410454429.1A CN118427589A (zh) 2024-04-15 2024-04-15 心音分割方法、装置、电子设备及可读存储介质

Publications (1)

Publication Number Publication Date
WO2025218160A1 true WO2025218160A1 (zh) 2025-10-23

Family

ID=92331100

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2024/132614 Pending WO2025218160A1 (zh) 2024-04-15 2024-11-18 心音分割方法、装置、电子设备及可读存储介质

Country Status (2)

Country Link
CN (1) CN118427589A (zh)
WO (1) WO2025218160A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118766498B (zh) * 2024-09-11 2025-04-01 潍坊歌尔电子有限公司 腕戴设备

Also Published As

Publication number Publication date
CN118427589A (zh) 2024-08-02

Similar Documents

Publication Publication Date Title
CN102245102B (zh) 用于心冲击图信号的分析的方法和设备
Kovács et al. A rule-based phonocardiographic method for long-term fetal heart rate monitoring
EP3453321B1 (en) Non-invasive method and system for estimating blood pressure from photoplethysmogram using statistical post-processing
WO2025218511A1 (zh) 血压预测方法、装置、电子设备及可读存储介质
TW201806370A (zh) 提供即時訊號分段和基準點對準架構的系統與方法
JP6310401B2 (ja) 生理的リズムを表す信号を処理する方法、システム及びコンピュータプログラム
TW201642803A (zh) 可穿戴式脈搏感應裝置訊號品質估算
CN114159038B (zh) 血压测量方法、装置、电子设备和可读存储介质
JP2019097757A (ja) 生体情報計測装置、生体情報計測プログラム、及び生体情報計測方法
CN106073784A (zh) 一种呼吸率提取方法及装置
CN114652288A (zh) 一种非袖带式动态血压测量系统
WO2025236869A1 (zh) 健康监测设备、方法及存储介质
WO2019079829A9 (en) Method of preprocessing and screening auscultatory sound signals
WO2025218160A1 (zh) 心音分割方法、装置、电子设备及可读存储介质
Oliveira et al. Coupled hidden Markov model for automatic ECG and PCG segmentation
CN104739384A (zh) 动脉波分析方法及其系统
CN118430774A (zh) 心脏衰老程度预测方法、电子设备及可读存储介质
WO2025218159A1 (zh) 心音信号质量评估方法、电子设备及可读存储介质
CN117045217B (zh) 一种无袖带血压测量方法及其相关设备
TW202344221A (zh) 一種血壓測量方法及血壓測量系統
CN115517632B (zh) 共振呼吸频率测定方法、交互提示生成方法、装置及设备
FR3036026A1 (fr) Procede et dispositif de determination de parametres representatifs d'une activite cardiovasculaire
CN120694624B (zh) 具有房颤检测功能的电子血压计、房颤检测方法及装置
US20250120610A1 (en) System and method for respiratory rate monitoring
RU2756157C1 (ru) Способ анализа баллистокардиографического сигнала для детектирования единичных сердечных ударов в реальном времени

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 24935688

Country of ref document: EP

Kind code of ref document: A1