WO2020155169A1 - 房颤筛查的方法和装置 - Google Patents

房颤筛查的方法和装置 Download PDF

Info

Publication number
WO2020155169A1
WO2020155169A1 PCT/CN2019/074670 CN2019074670W WO2020155169A1 WO 2020155169 A1 WO2020155169 A1 WO 2020155169A1 CN 2019074670 W CN2019074670 W CN 2019074670W WO 2020155169 A1 WO2020155169 A1 WO 2020155169A1
Authority
WO
WIPO (PCT)
Prior art keywords
signal
cardiac shock
acceleration
atrial fibrillation
pulse wave
Prior art date
Application number
PCT/CN2019/074670
Other languages
English (en)
French (fr)
Inventor
杨斌
李宏宝
张�杰
Original Assignee
华为技术有限公司
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 华为技术有限公司 filed Critical 华为技术有限公司
Priority to CN201980040319.8A priority Critical patent/CN112292069B/zh
Priority to EP19912359.7A priority patent/EP3900610A4/en
Priority to PCT/CN2019/074670 priority patent/WO2020155169A1/zh
Publication of WO2020155169A1 publication Critical patent/WO2020155169A1/zh

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/1102—Ballistocardiography
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/024—Detecting, measuring or recording pulse rate or heart rate
    • A61B5/02416—Detecting, measuring or recording pulse rate or heart rate using photoplethysmograph signals, e.g. generated by infrared radiation
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7221—Determining signal validity, reliability or quality
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7246—Details of waveform analysis using correlation, e.g. template matching or determination of similarity
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
    • A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
    • A61B5/6802—Sensor mounted on worn items
    • A61B5/681—Wristwatch-type devices
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
    • A61B5/7207—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal of noise induced by motion artifacts
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems

Definitions

  • the present application relates to the field of electronic equipment, and more specifically, to a method and device for atrial fibrillation screening in the field of electronic equipment.
  • Atrial fibrillation also known as atrial fibrillation
  • AF atrial fibrillation
  • atrial fibrillation is a common arrhythmia. Long-lasting atrial fibrillation can cause serious complications, such as heart failure, high blood pressure, and the most harmful stroke. Therefore, the detection of atrial fibrillation is particularly important.
  • atrial fibrillation screening if the RR interval is completely irregular within a certain period of time, and the P wave in the electrocardiogram is deformed or disappears, it is judged as atrial fibrillation, otherwise it is not atrial fibrillation.
  • mobile terminals can be used to detect atrial fibrillation of users.
  • An existing method for screening atrial fibrillation uses a mobile terminal to detect the pulse of the user, and based on the change state of the pulse, it is determined whether the user is at risk of atrial fibrillation.
  • pulse can only reflect changes in heart rate, but not changes in atrial function. Therefore, the prediction accuracy of this program for atrial fibrillation is low.
  • the present application provides a method and device for detecting atrial fibrillation, which introduces a BCG signal during atrial fibrillation screening, which can help improve the accuracy of atrial fibrillation prediction.
  • a method for detecting atrial fibrillation including:
  • the pulse wave signal and the cardiac shock signal it is determined whether the user is atrial fibrillation.
  • the embodiment of the present application obtains the PPG signal and the ACC signal, and obtains the BCG signal and the ACC body motion signal according to the ACC signal, and then screens the user for atrial fibrillation according to the BCG signal and the PPG signal. Since the BCG signal can characterize the acceleration change of the body caused by atrial pumping, the embodiment of the present application introduces the BCG signal during atrial fibrillation screening, which can help improve the accuracy of atrial fibrillation prediction.
  • the determining whether the user is atrial fibrillation according to the pulse wave signal and the cardiac shock signal includes:
  • Extracting features of the pulse wave signal including at least one of Shannon entropy, average pulse peak interval, root mean square error, and maximum pulse peak interval;
  • the pulse wave signal and the cardiac shock signal it is determined whether the user is atrial fibrillation.
  • the embodiment of the present application extracts the characteristics of the pulse wave signal and the characteristics of the cardiac shock signal, and then can implement a two-class classification of the user's cardiac health status based on a machine learning algorithm.
  • the machine learning algorithm is, for example, support vector machine SVM, logistic regression LR or nearest neighbor algorithm KNN.
  • the extracting the characteristics of the cardiac shock signal includes:
  • At least one of the kurtosis coefficient, the skewness coefficient, the slope and the height of the H wave is obtained.
  • the method before the determining whether the user's heart rhythm is atrial fibrillation according to the pulse wave signal and the cardiac shock signal, the method further includes:
  • the signal quality of at least one of the acceleration body motion signal, the pulse wave signal, and the cardiac shock signal is greater than or equal to its corresponding threshold.
  • the extracted signal can be prevented from being interfered by certain factors (such as motion artifacts), so that the accuracy of the atrial fibrillation detection result can be improved.
  • the acquiring a cardiac shock signal and an acceleration body motion signal according to the acceleration signal includes:
  • the acceleration body motion signal is determined according to the acceleration signal and the cardiac shock signal.
  • the embodiment of the application selects singular spectrum analysis as the zero phase difference filter algorithm to extract the BCG signal from the ACC signal, and uses the signal remaining after the BCG signal is extracted from the ACC signal as the ACC body motion signal, thereby realizing the correction BCG signal and ACC body motion signal extraction.
  • a method for detecting atrial fibrillation is provided, and the device is used to execute the method in the first aspect or any possible implementation of the first aspect.
  • the apparatus may include a module for executing the method in the first aspect or any possible implementation of the first aspect.
  • a method for detecting atrial fibrillation includes a memory and a processor, the memory is used to store instructions, and the processor is used to execute instructions stored in the memory and store data in the memory. Execution of the instructions of causes the processor to execute the first aspect or the method in any possible implementation manner of the first aspect.
  • a computer-readable storage medium is provided, and instructions are stored in the computer-readable storage medium.
  • the instructions are run on a computer, the computer executes the first aspect or any possible aspect of the first aspect. The method in the implementation mode.
  • a computer program product containing instructions is provided.
  • the computer program product runs on a computer, the computer executes the method in the first aspect or any possible implementation of the first aspect.
  • Fig. 1 shows a schematic diagram of a device for detecting atrial fibrillation provided by an embodiment of the present application.
  • Fig. 2 shows a schematic flowchart of a method for detecting atrial fibrillation provided by an embodiment of the present application.
  • Fig. 3 shows an example of the original PPG signal and the original ACC signal.
  • Fig. 4 shows an example of a moving window length L shown in an embodiment of the present application.
  • Fig. 5 shows a specific example of the BCG signal.
  • Fig. 6 shows an example of the target BCG signal and the characteristic pivot.
  • FIG. 7 shows an example of the correspondence between the PPG signal and the BCG signal.
  • Fig. 8 shows a schematic block diagram of a device for detecting atrial fibrillation provided by an embodiment of the present application.
  • Fig. 9 shows a schematic block diagram of another device for detecting atrial fibrillation provided by an embodiment of the present application.
  • Fig. 1 shows a schematic diagram of a device 100 for detecting atrial fibrillation according to an embodiment of the present application.
  • the apparatus for detecting atrial fibrillation may be applied to terminal equipment.
  • the terminal device is, for example, a wearable device, such as a sports bracelet, which is not limited in the embodiment of the present application.
  • the device 100 for detecting atrial fibrillation includes a photoplethysmography (PPG) detection module 110, an accelerometer (ACC) detection module 120 and a processor 130.
  • PPG detection module can also be called a photoelectric module.
  • the atrial fibrillation detection device 100 may further include a communication interface for sending signals acquired by the PPG detection module 110 and the ACC detection module 120 to the processor 130.
  • the communication interface is, for example, a Bluetooth module
  • the processor is, for example, a mobile phone or a processor in the cloud, which is not limited in the embodiment of the present application.
  • the PPG detection module 110 is used to obtain the pulse wave signal of the user.
  • the ACC detection module 120 is used to obtain the acceleration signal of the user.
  • the pulse wave signal may also be referred to as a PPG signal, and the acceleration signal may also be referred to as an ACC signal.
  • the processor 130 is configured to obtain a cardiac shock signal and an acceleration body motion signal according to the ACC signal obtained by the ACC detection module 120.
  • the cardiac shock signal may also be referred to as a ballistic cardiograph (BCG) signal
  • the acceleration body motion signal may also be referred to as an ACC body motion signal.
  • BCG ballistic cardiograph
  • the BCG signal is used to characterize the body's acceleration changes caused by atrial pumping, and its waveform shape is related to atrial function, such as the P wave in the electrocardiogram.
  • the acceleration body motion signal is used to characterize the user's movement acceleration change, and is a signal with a larger amplitude in the ACC signal.
  • the processor 130 is further configured to determine whether the user is atrial fibrillation according to the pulse wave signal obtained by the PPG detection module 110 and the obtained cardiac shock signal.
  • the embodiment of the present application obtains the PPG signal and the ACC signal, and obtains the BCG signal and the ACC body motion signal according to the ACC signal, and then screens the user for atrial fibrillation according to the BCG signal and the PPG signal. Since the BCG signal can characterize the acceleration change of the body caused by atrial pumping, the embodiment of the present application introduces the BCG signal during atrial fibrillation screening, which can help improve the accuracy of atrial fibrillation prediction.
  • FIG. 2 shows a schematic flowchart of a method for detecting atrial fibrillation provided by an embodiment of the present application. It should be understood that FIG. 2 shows the steps or operations of the service processing method, but these steps or operations are only examples, and the embodiment of the present application may also perform other operations or variations of each operation in FIG. 2. In addition, the various steps in FIG. 2 may be performed in a different order from that presented in FIG. 2, and it is possible that not all operations in FIG. 2 are to be performed.
  • the original ACC signal (which can be expressed as ACC raw ).
  • the original ACC signal of the user can be detected by the ACC detection module 120.
  • the original ACC signal with a duration of 1 minute (min) can be obtained.
  • the PPG detection module 110 may be used to detect the user's original PGG signal.
  • the original ACC signal with a duration of 1 minute (min) can be obtained.
  • the left side (a) of FIG. 3 shows an example of the original PPG signal, and the right side (b) shows an example of the original ACC signal.
  • the BCG signal and the ACC body movement signal can be obtained based on the ACC signal.
  • 203 to 205 show an example of acquiring the BCG signal and the ACC body motion signal from the ACC signal.
  • SSA singular spectrum analysis
  • the moving window length L is selected.
  • Fig. 4 shows an example of a moving window length L shown in an embodiment of the present application.
  • the target BCG signal is the template used in SSA filtering, and can be any sample of the BCG signal obtained in advance.
  • Fig. 5 shows a specific example of the BCG signal.
  • the BCG signal includes J wave, H wave, I wave, K wave, L wave, M wave and N wave, where J wave is the largest peak point in the BCG signal, and H wave is before the J wave.
  • a peak point, the H wave is related to the P wave in the ECG.
  • the cardiac shock signal may be extracted from the acceleration signal according to the moving window length L and the target BCG signal.
  • the ACC signal can be divided into several signals according to the moving window length L, that is, several characteristic principal elements. Since the moving window length L is related to the frequency and sampling rate of the target BCG signal, the spectral density between the data of the several characteristic pivots has correlation. As an example, the several characteristic pivots may belong to different frequency bands.
  • the signal can be obtained : X+x 0 (i).
  • the function G can be designed, and the characteristic principal component PC can be selected according to the following formula:
  • the PC feature principal element selected according to the target BCG signal in 205 is the BCG signal extracted according to the ACC signal.
  • the ACC bm signal is obtained according to the extracted BCG signal and ACC signal.
  • the signal remaining after the BCG signal is extracted from the ACC signal may be an ACC body motion signal.
  • acquiring the PPG signal according to the PPG raw signal may specifically be noise reduction processing of the PPG raw signal through a filter, and the processed signal is the PPG signal.
  • noise reduction processing may be performed on the ACC raw signal.
  • ACC RAW the signal noise reduction or noise reduction processing may be performed after the extraction of the ACC signal BCG signals, the present application is not limited to this embodiment.
  • the peak point of the PPG signal corresponds to the position of the J wave in the BCG signal.
  • the first peak on the left side of the J wave in the BCG signal can be determined as the H wave.
  • At least one of the kurtosis, standard deviation, and Shannon entropy of the ACC bm signal may be extracted as a feature of the ACC bm signal.
  • the feature of the ACC bm signal can be denoted as feature 1 (feat 1).
  • At least one of the kurtosis coefficient, the skewness coefficient, the slope, and the height of the H wave of the BCG signal may be extracted as a feature of the BCG signal.
  • the feature of the BCG signal can be denoted as feature 2 (feat 2).
  • At least one of Shannon entropy, mean pulse peak interval (mean_RR), root mean square error (RMSSD), and maximum pulse peak interval of the PPG signal can be extracted as the feature of the PPG signal.
  • the feature of the PPG signal can be denoted as feature 3 (feat 3).
  • the detection of PPG signals and BCG signals may be interfered by motion artifacts.
  • the detection of PPG signals and BCG signals may be interfered by motion artifacts.
  • the BCG signal and PPG signal can be used to determine whether the atrial fibrillation is.
  • feature x may be feature 1, that is, the feature of ACC bm . That is, when the signal is greater than the ACC bm threshold value corresponding to a signal quality characteristic ACC bm ACC bm determined, is performed 212, otherwise the stop detection.
  • the feature x may be feature 1 and feature 2, that is, the feature of ACC bm and the feature of BCG signal. That is, when more than ACC bm signal corresponding to the threshold value according to the quality ACC bm signal characteristic ACC bm determined, and greater than BCG signal corresponding to the threshold value the quality of BCG signal characteristic BCG signals determined, is performed 212, otherwise stop testing.
  • the feature x may be feature 1, feature 2, and feature 3, that is, the feature of ACC bm , the feature of BCG signal, and the feature of PPG signal. That is, when a larger than, the mass ACC bm signal characteristic ACC bm determined ACC bm signal corresponding to the threshold value and greater than BCG signal corresponding to the threshold value the quality of BCG signal characteristic BCG signal is determined, and, according to When the quality of the PPG signal determined by the characteristics of the PPG signal is greater than the threshold corresponding to the PPG signal, execute 212, otherwise stop the detection.
  • the user's heart health state can be classified into two categories, that is, it is determined that the user's heart rhythm is normal or atrial fibrillation.
  • the machine learning algorithm is, for example, a support vector machine (SVM), a logistic regression (LR), or a nearest neighbor algorithm (k-nearest neighbor, KNN), which is not limited in the embodiment of the application.
  • the embodiment of the present application obtains the PPG signal and the ACC signal, and obtains the BCG signal and the ACC body motion signal according to the ACC signal, and then screens the user for atrial fibrillation according to the BCG signal and the PPG signal. Since the BCG signal can characterize the acceleration change of the body caused by atrial pumping, the embodiment of the present application introduces the BCG signal during atrial fibrillation screening, which can help improve the accuracy of atrial fibrillation prediction.
  • FIG. 8 shows a schematic block diagram of a device 1000 for detecting atrial fibrillation according to an embodiment of the present application.
  • the device for screening atrial fibrillation includes an acquiring unit 1010 and a determining unit 1020.
  • the acquiring unit 1010 is used to acquire the pulse wave signal and acceleration signal of the user.
  • the determining unit 1020 is configured to determine the cardiac shock signal and the acceleration body motion signal according to the acceleration signal, wherein the cardiac shock signal is used to characterize the body acceleration change caused by atrial pumping, and the acceleration body motion signal is used to characterize the user The movement acceleration changes.
  • the determining unit 1020 is further configured to determine whether the user is atrial fibrillation according to the pulse wave signal and the cardiac shock signal.
  • the embodiment of the present application obtains the PPG signal and the ACC signal, and obtains the BCG signal and the ACC body motion signal according to the ACC signal, and then screens the user for atrial fibrillation according to the BCG signal and the PPG signal. Since the BCG signal can characterize the acceleration change of the body caused by atrial pumping, the embodiment of the present application introduces the BCG signal during atrial fibrillation screening, which can help improve the accuracy of atrial fibrillation prediction.
  • the determining unit 1020 is specifically configured to:
  • Extracting features of the pulse wave signal including at least one of Shannon entropy, average pulse peak interval, root mean square error, and maximum pulse peak interval;
  • the pulse wave signal and the cardiac shock signal it is determined whether the user is atrial fibrillation.
  • the determining unit 1020 is specifically configured to:
  • At least one of the kurtosis coefficient, the skewness coefficient, the slope and the height of the H wave is obtained.
  • the determining unit 1020 is further configured to:
  • the signal quality of at least one of the acceleration body motion signal, the pulse wave signal, and the cardiac shock signal is greater than or equal to its corresponding threshold.
  • the determining unit 1020 is specifically configured to:
  • the acceleration body motion signal is determined according to the acceleration signal and the cardiac shock signal.
  • the acquiring unit 1010 may be implemented by a communication interface
  • the determining unit 1020 may be implemented by a processor.
  • the apparatus 1100 for detecting atrial fibrillation may include a processor 1110, a memory 1120 and a communication interface 1130.
  • the memory 1120 may be used to store codes and the like executed by the processor 1110
  • the processor 1110 may be used to process data or programs.
  • the steps of the foregoing method can be completed by hardware integrated logic circuits in the processor 1110 or instructions in the form of software.
  • the steps of the method disclosed in the embodiments of the present invention may be directly embodied as being executed and completed by a hardware processor, or executed and completed by a combination of hardware and software modules in the processor.
  • the software module can be located in a mature storage medium in the field such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, registers.
  • the storage medium is located in the memory 1120, and the processor 1110 reads the information in the memory 1120, and completes the steps of the foregoing method in combination with its hardware. In order to avoid repetition, it will not be described in detail here.
  • the device 1000 shown in FIG. 8 or the device 1100 shown in FIG. 9 can implement each process of the atrial fibrillation detection method corresponding to the foregoing method embodiment. Specifically, the device 1000 or the device 1100 can refer to the above description, in order to avoid repetition , I won’t repeat it here.
  • the embodiment of the present application also provides a computer-readable medium for storing a computer program, and the computer program includes instructions for executing the corresponding method in the foregoing method embodiment.
  • An embodiment of the present application also provides a computer program product, the computer program product comprising: computer program code, when the computer program runs on behalf of the processor of the Bluetooth test device, the device for avoiding message fragmentation is executed.
  • the size of the sequence number of the foregoing processes does not mean the order of execution.
  • the execution order of each process should be determined by its function and internal logic, and should not be implemented in this application.
  • the implementation process of the example constitutes any limitation.
  • the disclosed system, device, and method may be implemented in other ways.
  • the device embodiments described above are merely illustrative.
  • the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined or It can be integrated into another system, or some features can be ignored or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium.
  • the technical solution of this application essentially or the part that contributes to the existing technology or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (read-only memory, ROM), random access memory (random access memory, RAM), magnetic disk or optical disk and other media that can store program code .

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Public Health (AREA)
  • Molecular Biology (AREA)
  • Veterinary Medicine (AREA)
  • General Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Animal Behavior & Ethology (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Physiology (AREA)
  • Surgery (AREA)
  • Cardiology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Signal Processing (AREA)
  • Artificial Intelligence (AREA)
  • Psychiatry (AREA)
  • Dentistry (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)

Abstract

一种房颤检测的方法和装置（100），在房颤筛查时引入了BCG信号，能够有利于提高房颤预测的准确性。房颤检测的方法包括：获取用户的脉搏波信号和加速度信号；根据加速度信号，确定心冲击信号和加速度体动信号，其中，心冲击信号用于表征心房泵血引起的躯体的加速度变化，加速度体动信号用于表征用户的运动加速度变化；根据脉搏波信号和心冲击信号，确定用户是否房颤。

Description

房颤筛查的方法和装置 技术领域
本申请涉及电子设备领域，并且更具体的，涉及电子设备领域中的房颤筛查的方法和装置。
背景技术
房颤(atrail fibrillation,AF)，又称心房颤动，是常见的一种心律失常。长期持续的房颤会引起严重的并发症，比如心力衰竭、高血压，以及危害最为严重的脑卒中等。因此，房颤的检测显得尤为重要。在进行房颤筛查时，如果在一定时间段内RR间隔完全无规律，且心电图中的P波变形或消失，则判定为房颤，否则为非房颤。
目前使用移动终端能够实现对用户的房颤的检测。现有的一种房颤筛查的方法，使用移动终端实现对用户脉搏的检测，基于脉搏的变化状态，判断用户是否存在房颤的风险。但是，脉搏只能反映心率的变化，并不能反映心房功能变化，因此该方案对于房颤的预测准确率较低。
发明内容
本申请提供一种房颤检测的方法和装置，在房颤筛查时引入了BCG信号，能够有利于提高房颤预测的准确性。
第一方面，提供了一种房颤检测的方法，包括：
获取用户的脉搏波信号和加速度信号；
根据所述加速度信号，确定心冲击信号和加速度体动信号，其中，所述心冲击信号用于表征心房泵血引起的躯体的加速度变化，加速度体动信号用于表征用户的运动加速度变化；
根据所述脉搏波信号和所述心冲击信号，确定所述用户是否房颤。
因此，本申请实施例通过获取PPG信号和ACC信号，并根据ACC信号获取BCG信号和ACC体动信号，然后再根据BCG信号和PPG信号筛查用户是否房颤。由于BCG信号能够表征心房泵血引起的躯体的加速度变化，因此本申请实施例在房颤筛查时引入BCG信号，能够有利于提高房颤预测的准确性。
结合第一方面，在第一方面的某些实现方式中，所述根据所述脉搏波信号和所述心冲击信号，确定所述用户是否房颤，包括：
提取所述脉搏波信号的特征，所述脉搏波信号的特征包括香农熵、脉搏峰值间隔均值、均方根误差、脉搏峰值间隔最大值中的至少一种；
提取所述心冲击信号的特征，所述心冲击信号的特征包括所述心冲击信号的H波的峰度系数、偏度系数、斜率和高度中的至少一种；
根据所述脉搏波信号的特征和所述心冲击信号的特征，确定所述用户是否房颤。
本申请实施例通过提取脉搏波信号的特征和心冲击信号的特征，然后可以基于机器学习算法，对用户的心脏金康状态实现二分类。机器学习算法例如为支持向量机SVM、逻辑回归LR或最近邻算法KNN等。
结合第一方面，在第一方面的某些实现方式中，所述提取所述心冲击信号的特征，包括：
根据所述脉搏波信号的峰值点，确定所述心冲击信号的J波的位置；
根据所述心冲击信号的J波的位置，确定所述心冲击信号的H波的位置；
获取所述H波的峰度系数、偏度系数、斜率和高度中的至少一种。
结合第一方面，在第一方面的某些实现方式中，所述根据所述脉搏波信号和所述心冲击信号，确定用户心律是否房颤之前，还包括：
确定所述加速度体动信号、所述脉搏波信号和所述心冲击信号中的至少一种的信号质量大于或等于其对应的阈值。
这样，在对用户进行房颤筛查时，能够避免所提取的信号受到某些因素(比如运动伪迹)的干扰，从而能够提高房颤检测结果的准确性。
结合第一方面，在第一方面的某些实现方式中，所述根据所述加速度信号，获取心冲击信号和加速度体动信号，包括：
根据目标心冲击信号的频率和所述目标心冲击信号的采样率，确定移动窗长大小；
根据所述移动窗长和所述目标心冲击信号，在所述加速度信号中确定所述心冲击信号；
根据所述加速度信号和所述心冲击信号，确定所述加速度体动信号。
这样，本申请实施例通过选择奇异谱分析作为零相位差滤波算法，从ACC信号中提取出BCG信号，并将ACC信号中提取BCG信号之后剩余的信号，作为ACC体动信号，从而实现了对BCG信号和ACC体动信号的提取。
第二方面，提供一种房颤检测的方法，所述装置用于执行上述第一方面或第一方面的任一可能的实现方式中的方法。具体地，所述装置可以包括用于执行第一方面或第一方面的任一可能的实现方式中的方法的模块。
第三方面，提供一种房颤检测的方法，所述装置包括存储器和处理器，所述存储器用于存储指令，所述处理器用于执行所述存储器存储的指令，并且对所述存储器中存储的指令的执行使得所述处理器执行第一方面或第一方面的任一可能的实现方式中的方法。
第四方面，提供一种计算机可读存储介质，所述计算机可读存储介质中存储有指令，当所述指令在计算机上运行时，使得计算机执行第一方面或第一方面的任一可能的实现方式中的方法。
第五方面，提供一种包含指令的计算机程序产品，当该计算机程序产品在计算机上运行时，使得计算机执行第一方面或第一方面的任一可能的实现方式中的方法。
附图说明
图1示出了本申请实施例提供的一种房颤检测的装置的示意图。
图2示出了本申请实施例提供的一种房颤检测的方法的示意性流程图。
图3示出了原始PPG信号和原始ACC信号的一个例子。
图4示出了本申请实施例示出的一个移动窗长L的示例。
图5示出了BCG信号的一个具体例子。
图6示出了目标BCG信号和特征主元的一个示例。
图7示出了PPG信号与BCG信号对应的一个示例。
图8示出了本申请实施例提供的一种房颤检测的装置的示意性框图。
图9示出了本申请实施例提供的另一种房颤检测的装置的示意性框图。
具体实施方式
下面将结合附图，对本申请中的技术方案进行描述。
图1示出了本申请实施例提供的一种房颤检测的装置100的示意图。本申请实施例中，房颤检测的装置可以应用于终端设备。终端设备例如为可穿戴设备，比如运动手环等，本申请实施例对此不作限定。如图1所示，该房颤检测的装置100包括光电容积脉搏波(Photoplethysmography，PPG)检测模块110，加速度计(Accelerometer，ACC)检测模块120和处理器130。其中，PPG检测模块还可以称为光电模块。
可选的，房颤检测装置100还可以包括通信接口，用于将PPG检测模块110和ACC检测模块120获取的信号发送至处理器130。作为示例，通信接口例如为蓝牙模块，处理器例如为手机、或者云端的处理器等，本申请实施例对此不作限定。
具体而言，PPG检测模块110，用于获取用户的脉搏波信号。ACC检测模块120，用于获取用户的加速度信号。本申请实施例中，脉搏波信号也可以称为PPG信号，加速度信号也可以称为ACC信号。
处理器130，用于根据ACC检测模块120获取的ACC信号，获取心冲击信号和加速度体动信号。本申请实施例中，心冲击信号也可以称为心冲击图(Ballistocardiograph，BCG)信号，加速度体动信号也可以称为ACC体动信号。其中，BCG信号用于表征心房泵血引起的躯体的加速度变化，其波形形态与心房功能相关，比如与心电图中的P波相关。加速度体动信号用于表征用户的运动加速度变化，为ACC信号中幅值较大的信号。
处理器130，还用于根据所述PPG检测模块110获取脉搏波信号和获取的所述心冲击信号，确定所述用户是否房颤。
因此，本申请实施例通过获取PPG信号和ACC信号，并根据ACC信号获取BCG信号和ACC体动信号，然后再根据BCG信号和PPG信号筛查用户是否房颤。由于BCG信号能够表征心房泵血引起的躯体的加速度变化，因此本申请实施例在房颤筛查时引入BCG信号，能够有利于提高房颤预测的准确性。
图2示出了本申请实施例提供的一种房颤检测的方法的示意性流程图。应理解，图2示出了业务处理的方法的步骤或操作，但这些步骤或操作仅是示例，本申请实施例还可以执行其他操作或者图2中的各个操作的变形。此外，图2中的各个步骤可以按照与图2呈现的不同的顺序来执行，并且有可能并非要执行图2中的全部操作。
201，获取原始ACC信号(可表示为ACC raw)。具体的，可以通过ACC检测模块120检测用户的原始ACC信号。一个示例，可以获取时长为1分钟(min)的原始ACC信号。
202，获取原始PPG信号(可表示为PPG raw)。具体的，可以通过PPG检测模块110检测用户的原始PGG信号。一个示例，可以获取时长为1分钟(min)的原始ACC信号。
图3中左侧(a)图示出了原始PPG信号的一个例子，右侧(b)图示出了原始ACC信号的一个例子。
本申请一个实施例中，可以根据ACC信号，获取BCG信号和ACC体动信号。作为示例，203至205示出了根据ACC信号获取BCG信号和ACC体动信号的一个例子。
203，对202中获取的ACC信号选择奇异谱分析(singular spectrum analysis,SSA)作为零相位差滤波算法，即SSA滤波。
204，移动窗长L选取。
具体的，可以根据目标BCG信号的频率(比如(f 1，f 2，f 3))和所述目标BCG信号的采样率(f s)，确定移动窗长L大小，即L＝F(f s，f 1，f 2，f 3)。图4示出了本申请实施例示出的一个移动窗长L的示例。这里，目标BCG信号即为SSA滤波时采用的模板，可以为任意一个预先获取的BCG信号的样例。图5示出了BCG信号的一个具体例子。如图5所示，BCG信号包括J波、H波、I波、K波、L波、M波和N波，其中J波为BCG信号中的最大的峰值点，H波为J波之前的一个波峰点，H波与心电图中的P波相关。
205，特征主元选取。
一个可选的实施例，可以根据所述移动窗长L和所述目标BCG信号，在所述加速度信号中提取所述心冲击信号。
具体的，可以根据移动窗长L的将ACC信号分成若干个信号，即若干个特征主元。由于移动窗长L与目标BCG信号的频率以及采样率有关，因此该若干个特征主元的数据之间的频谱密度具有相关性。作为一个示例，该若干个特征主元可以属于不同的频段。
然后，如图6所示，通过在特征主元(即图6中x段的信号)之前增加目标BCG信号的样例成分(即图6中x 0(i)段的信号)，可得到信号：x+x 0(i)。这样，目标BCG信号在原始ACC信号中的比重增大，对应的与目标BCG信号相关性高的特征主元将靠前。因此，基于上述原理，可以设计函数G，可以根据以下公式选取特征主元PC：
PC＝G(x+x 0(i))
206，获取BCG信号，ACC体动信号(可表示为ACC bm)，以及PPG信号。
具体的，205中根据目标BCG信号选取的PC特征主元即为根据ACC信号提取的BCG信号。
然后，根据所述提取的BCG信号和ACC信号，获取所述ACC bm信号。作为一个示例，在ACC信号中提取BCG信号之后所剩余的信号，可以为ACC体动信号。
一个示例，本申请实施例中，根据PPG raw信号获取PPG信号，具体可以为对PPG raw信号在经过过滤器的降噪处理，处理之后的信号即为PPG信号。
可选的，本申请实施例中可以对ACC raw信号进行降噪处理。具体的，可以在获得ACC raw信号之后，对该ACC raw信号进行降噪处理，或者可以对提取BCG信号之后的ACC信号进行降噪处理，本申请实施例对此不作限定。
207，对PPG信号进行峰值提取。
208，根据PPG信号峰值点确定BCG信号中J波位置。
如图7所示，PPG信号的峰值点与BCG信号中的J波的位置相对应。
209，根据BCG信号中J波位置，确定BCG信号的H波的位置。
具体的，可以将BCG信号中J波左侧的第一个波峰确定为H波。
210，分别提取ACC bm信号、BCG信号和PPG信号的特征。
作为一个示例，可以提取ACC bm信号的峰度、标准差、香农熵中的至少一种，作为ACC bm信号的特征。ACC bm信号的特征可以记为特征1(feat 1)。
作为一个示例，可以提取BCG信号的H波的峰度系数、偏度系数、斜率和高度中的至少一种，作为BCG信号的特征。BCG信号的特征可以记为特征2(feat 2)。
作为一个示例，可以提取PPG信号的香农熵、脉搏峰值间隔均值(mean_RR)、均方根误差(RMSSD)、脉搏峰值间隔最大值中的至少一种，作为PPG信号的特征。PPG信号的特征可以记为特征3(feat 3)。
本申请实施例中，可以根据所述BCG信号的特征和所述PPG信号的特征，确定所述用户是否房颤。
可选的，根据所述BCG信号的特征和所述PPG信号的特征，确定所述用户是否房颤之前，在还可以根据ACC bm信号、BCG信号和PPG信号中的至少一种信号的信号质量大于或等于一定阈值，即图2中的211，判断特征x是否大于或等于阈值，其中x＝1,2,3。
也就是说，根据本次测试所获取的信号的信号质量是否满足计算要求。具体而言，本申请实施例中，PPG信号和BCG信号的检测可能会受到运动伪迹的干扰。通过比较ACC bm信号、BCG信号和PPG信号中的至少一种信号与其对应的阈值的大小，可以判断在某一次的测试中所提取的信号的受运动伪迹的干扰是否影响了检测结果的准确性。也就是说，当运动伪迹对检测结果的影响不明显时，可以根据BCG信号和PPG信号，判断是否房颤。当运动伪迹对检测结果的干扰比较大时，房颤筛查的的准确性会降低。
当特征x满足大于或等于对应的阈值时，则执行212。当特征x小于等于其对应的阈值时，则停止检测。
作为一个示例，特征x可以为特征1，即ACC bm的特征。也就是说，当根据ACC bm的特征确定的ACC bm信号的质量大于ACC bm信号对应的阈值时，则执行212，否则停止检测。
作为另一个示例，特征x可以为特征1和特征2，即ACC bm的特征和BCG信号的特征。也就是说，当根据ACC bm的特征确定的ACC bm信号的质量大于ACC bm信号对应的阈值，且，根据BCG信号的特征确定的BCG信号信号的质量大于BCG信号信号对应的阈值时，则执行212，否则停止检测。
作为另一个示例，特征x可以为特征1、特征2和特征3，即ACC bm的特征、BCG信号的特征和PPG信号的特征。也就是说，当根据ACC bm的特征确定的ACC bm信号的质量大于ACC bm信号对应的阈值，且，根据BCG信号的特征确定的BCG信号信号的质量大于BCG信号信号对应的阈值，且，根据PPG信号的特征确定的PPG信号信号的质量大于PPG信号信号对应的阈值时，则执行212，否则停止检测。
212，根据PPG信号和BCG信号，判定是否房颤。
作为示例，可以根据PPG信号的特征和BCG信号的特征，基于机器学习算法，对用户的心脏健康状态实现二分类，即判断用户心律为正常，或房颤。这里，机器学习算法例如为支持向量机(support vector machine,SVM)、逻辑回归(logistic regression，LR)或最近邻算法(k-nearest neighbor,KNN)等，本申请实施例对此不作限定。
因此，本申请实施例通过获取PPG信号和ACC信号，并根据ACC信号获取BCG信 号和ACC体动信号，然后再根据BCG信号和PPG信号筛查用户是否房颤。由于BCG信号能够表征心房泵血引起的躯体的加速度变化，因此本申请实施例在房颤筛查时引入BCG信号，能够有利于提高房颤预测的准确性。
图8示出了本申请实施例提供的一种房颤检测的装置1000的示意性框图。该房颤筛查的装置包括获取单元1010和确定单元1020。
获取单元1010，用于获取用户的脉搏波信号和加速度信号。
确定单元1020，用于根据所述加速度信号，确定心冲击信号和加速度体动信号，其中，所述心冲击信号用于表征心房泵血引起的躯体的加速度变化，加速度体动信号用于表征用户的运动加速度变化。
所述确定单元1020，还用于根据所述脉搏波信号和所述心冲击信号，确定所述用户是否房颤。
因此，本申请实施例通过获取PPG信号和ACC信号，并根据ACC信号获取BCG信号和ACC体动信号，然后再根据BCG信号和PPG信号筛查用户是否房颤。由于BCG信号能够表征心房泵血引起的躯体的加速度变化，因此本申请实施例在房颤筛查时引入BCG信号，能够有利于提高房颤预测的准确性。
可选的，所述确定单元1020具体用于：
提取所述脉搏波信号的特征，所述脉搏波信号的特征包括香农熵、脉搏峰值间隔均值、均方根误差、脉搏峰值间隔最大值中的至少一种；
提取所述心冲击信号的特征，所述心冲击信号的特征包括所述心冲击信号的H波的峰度系数、偏度系数、斜率和高度中的至少一种；
根据所述脉搏波信号的特征和所述心冲击信号的特征，确定所述用户是否房颤。
可选的，所述确定单元1020具体用于：
根据所述脉搏波信号的峰值点，确定所述心冲击信号的J波的位置；
根据所述心冲击信号的J波的位置，确定所述心冲击信号的H波的位置；
获取所述H波的峰度系数、偏度系数、斜率和高度中的至少一种。
可选的，所述确定单元1020还用于：
确定所述加速度体动信号、所述脉搏波信号和所述心冲击信号中的至少一种的信号质量大于或等于其对应的阈值。
可选的，所述确定单元1020具体用于：
根据目标心冲击信号的频率和所述目标心冲击信号的采样率，确定移动窗长大小；
根据所述移动窗长和所述目标心冲击信号，在所述加速度信号中确定所述心冲击信号；
根据所述加速度信号和所述心冲击信号，确定所述加速度体动信号。
应注意，本申请实施例中，获取单元1010可以由通信接口实现，确定单元1020可以由处理器实现。如图9所示，房颤检测的装置1100可以包括处理器1110、存储器1120和通信接口1130。其中，存储器1120可以用于存储处理器1110执行的代码等，处理器1110可以用于对数据或程序进行处理。
在实现过程中，上述方法的各步骤可以通过处理器1110中的硬件的集成逻辑电路或者软件形式的指令完成。结合本发明实施例所公开的方法的步骤可以直接体现为硬件处理 器执行完成，或者用处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器1120，处理器1110读取存储器1120中的信息，结合其硬件完成上述方法的步骤。为避免重复，这里不再详细描述。
图8所示的装置1000或图9所示的装置1100能够实现前述方法实施例对应的房颤检测方法的各个过程，具体的，该装置1000或装置1100可以参见上文中的描述，为避免重复，这里不再赘述。
本申请实施例还提供了一种计算机可读介质，用于存储计算机程序，该计算机程序包括用于执行上述方法实施例中对应的方法的指令。
本申请实施例还提供了一种计算机程序产品，所述计算机程序产品包括：计算机程序代码，当所述计算机程序代蓝牙测试的装置的处理器运行时，使得该避免报文分片的装置执行上述任方法实施例中对应的方法。
本申请中的各个实施例可以独立的使用，也可以进行联合的使用，这里不做限定。
应理解，本申请实施例中出现的第一、第二等描述，仅作示意与区分描述对象之用，没有次序之分，也不表示本申请实施例中对设备个数的特别限定，不能构成对本申请实施例的任何限制。
还应理解，在本申请的各种实施例中，上述各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现 有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(read-only memory，ROM)、随机存取存储器(random access memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本申请的具体实施方式，但本申请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申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (10)

  1. 一种房颤检测的方法，其特征在于，包括：
    获取用户的脉搏波信号和加速度信号；
    根据所述加速度信号，确定心冲击信号和加速度体动信号，其中，所述心冲击信号用于表征心房泵血引起的躯体的加速度变化，加速度体动信号用于表征用户的运动加速度变化；
    根据所述脉搏波信号和所述心冲击信号，确定所述用户是否房颤。
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述脉搏波信号和所述心冲击信号，确定所述用户是否房颤，包括：
    提取所述脉搏波信号的特征，所述脉搏波信号的特征包括香农熵、脉搏峰值间隔均值、均方根误差、脉搏峰值间隔最大值中的至少一种；
    提取所述心冲击信号的特征，所述心冲击信号的特征包括所述心冲击信号的H波的峰度系数、偏度系数、斜率和高度中的至少一种；
    根据所述脉搏波信号的特征和所述心冲击信号的特征，确定所述用户是否房颤。
  3. 根据权利要求2所述的方法，其特征在于，所述提取所述心冲击信号的特征，包括：
    根据所述脉搏波信号的峰值点，确定所述心冲击信号的J波的位置；
    根据所述心冲击信号的J波的位置，确定所述心冲击信号的H波的位置；
    获取所述H波的峰度系数、偏度系数、斜率和高度中的至少一种。
  4. 根据权利要求1-3任一项所述的方法，其特征在于，所述根据所述脉搏波信号和所述心冲击信号，确定用户心律是否房颤之前，还包括：
    确定所述加速度体动信号、所述脉搏波信号和所述心冲击信号中的至少一种的信号质量大于或等于其对应的阈值。
  5. 根据权利要求1-4中任一项所述的方法，其特征在于，所述根据所述加速度信号，获取心冲击信号和加速度体动信号，包括：
    根据目标心冲击信号的频率和所述目标心冲击信号的采样率，确定移动窗长大小；
    根据所述移动窗长和所述目标心冲击信号，在所述加速度信号中确定所述心冲击信号；
    根据所述加速度信号和所述心冲击信号，确定所述加速度体动信号。
  6. 一种房颤检测的装置，其特征在于，包括：
    获取单元，用于获取用户的脉搏波信号和加速度信号；
    确定单元，用于根据所述加速度信号，确定心冲击信号和加速度体动信号，其中，所述心冲击信号用于表征心房泵血引起的躯体的加速度变化，加速度体动信号用于表征用户的运动加速度变化；
    所述确定单元，还用于根据所述脉搏波信号和所述心冲击信号，确定所述用户是否房颤。
  7. 根据权利要求6所述的装置，其特征在于，所述确定单元具体用于：
    提取所述脉搏波信号的特征，所述脉搏波信号的特征包括香农熵、脉搏峰值间隔均值、均方根误差、脉搏峰值间隔最大值中的至少一种；
    提取所述心冲击信号的特征，所述心冲击信号的特征包括所述心冲击信号的H波的峰度系数、偏度系数、斜率和高度中的至少一种；
    根据所述脉搏波信号的特征和所述心冲击信号的特征，确定所述用户是否房颤。
  8. 根据权利要求7所述的装置，其特征在于，所述确定单元具体用于：
    根据所述脉搏波信号的峰值点，确定所述心冲击信号的J波的位置；
    根据所述心冲击信号的J波的位置，确定所述心冲击信号的H波的位置；
    获取所述H波的峰度系数、偏度系数、斜率和高度中的至少一种。
  9. 根据权利要求6-8任一项所述的装置，其特征在于，所述确定单元还用于：
    确定所述加速度体动信号、所述脉搏波信号和所述心冲击信号中的至少一种的信号质量大于或等于其对应的阈值。
  10. 根据权利要求6-9中任一项所述的装置，其特征在于，所述确定单元具体用于：
    根据目标心冲击信号的频率和所述目标心冲击信号的采样率，确定移动窗长大小；
    根据所述移动窗长和所述目标心冲击信号，在所述加速度信号中确定所述心冲击信号；
    根据所述加速度信号和所述心冲击信号，确定所述加速度体动信号。
PCT/CN2019/074670 2019-02-03 2019-02-03 房颤筛查的方法和装置 WO2020155169A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
CN201980040319.8A CN112292069B (zh) 2019-02-03 2019-02-03 房颤筛查的方法和装置
EP19912359.7A EP3900610A4 (en) 2019-02-03 2019-02-03 ATRIAL FIBRILLATION SCREENING METHOD AND DEVICE
PCT/CN2019/074670 WO2020155169A1 (zh) 2019-02-03 2019-02-03 房颤筛查的方法和装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/074670 WO2020155169A1 (zh) 2019-02-03 2019-02-03 房颤筛查的方法和装置

Publications (1)

Publication Number Publication Date
WO2020155169A1 true WO2020155169A1 (zh) 2020-08-06

Family

ID=71839903

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/074670 WO2020155169A1 (zh) 2019-02-03 2019-02-03 房颤筛查的方法和装置

Country Status (3)

Country Link
EP (1) EP3900610A4 (zh)
CN (1) CN112292069B (zh)
WO (1) WO2020155169A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114041786A (zh) * 2022-01-11 2022-02-15 华南师范大学 心冲击图信号的检测方法、装置以及设备

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115137369B (zh) * 2021-03-30 2023-10-20 华为技术有限公司 基于不同房颤阶段进行房颤预警的电子设备以及系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104352229A (zh) * 2014-10-21 2015-02-18 成都艾克尔特医疗科技有限公司 一种基于健康监测手环的自助房颤检测方法
CN104837401A (zh) * 2012-12-14 2015-08-12 皇家飞利浦有限公司 通过光电血管容积图(ppg)和加速度计检测显著心率失常事件的系统和方法
CN105902265A (zh) * 2016-04-18 2016-08-31 广东乐心医疗电子股份有限公司 一种房颤检测装置以及包括该装置的智能可穿戴设备
CN108606798A (zh) * 2018-05-10 2018-10-02 东北大学 基于深度卷积残差网络的非接触式房颤智能检测系统
US10105547B2 (en) * 2015-11-02 2018-10-23 West Affum Holdings Corp. Wearable cardioverter defibrillator (WCD) causing patient's QRS width to be plotted against the heart rate
CN109199327A (zh) * 2017-06-30 2019-01-15 三星电子株式会社 用于连续生物特征监控的自供电可穿戴设备

Family Cites Families (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7846104B2 (en) * 2007-02-08 2010-12-07 Heart Force Medical Inc. Monitoring physiological condition and detecting abnormalities
JP2008206704A (ja) * 2007-02-26 2008-09-11 Matsushita Electric Works Ltd 心拍検出装置
US20110251502A1 (en) * 2008-12-12 2011-10-13 Koninklijke Philips Electronics N.V. Method and apparatus for the analysis of ballistocardiogram signals
KR101417226B1 (ko) * 2011-12-15 2014-07-09 현대자동차주식회사 심탄도 분석 장치와 방법 및 이를 이용한 차량의 심탄도 활용 시스템
SG11201404113TA (en) * 2012-01-16 2014-10-30 Agency Science Tech & Res Method and system for optical blood pressure monitoring
WO2014011599A1 (en) * 2012-07-09 2014-01-16 Crone William E Perfusion detection system
US20150025334A1 (en) * 2014-09-09 2015-01-22 Lakshya JAIN Method and system for monitoring pain of patients
CN107072550A (zh) * 2014-11-07 2017-08-18 皇家飞利浦有限公司 体动记录方法和装置
US20160302677A1 (en) * 2015-04-14 2016-10-20 Quanttus, Inc. Calibrating for Blood Pressure Using Height Difference
US10722182B2 (en) * 2016-03-28 2020-07-28 Samsung Electronics Co., Ltd. Method and apparatus for heart rate and respiration rate estimation using low power sensor
EP3305180A1 (en) * 2016-10-05 2018-04-11 Murata Manufacturing Co., Ltd. Method and apparatus for monitoring heartbeats
US11337638B2 (en) * 2016-11-03 2022-05-24 Huawei Technologies Co., Ltd. ECG signal processing method and apparatus
US11076767B2 (en) * 2016-11-29 2021-08-03 Koninklijke Philips N.V. Method and system of monitoring cardiac activity of a user
KR101971208B1 (ko) * 2017-01-31 2019-04-22 (주)감성과학연구센터 가속도와 자이로 센서를 이용한 심탄도 모니터링 장치 및 그 방법
CN108701219B (zh) * 2017-03-14 2021-05-04 华为技术有限公司 波形信号处理的方法及装置
CN107647860B (zh) * 2017-08-31 2021-01-15 深圳和而泰智能控制股份有限公司 一种心率检测方法、装置、电子设备及存储介质
CN108992053B (zh) * 2018-06-21 2020-10-23 河北工业大学 一种实时的无束缚检测心率和心跳间隔的方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104837401A (zh) * 2012-12-14 2015-08-12 皇家飞利浦有限公司 通过光电血管容积图(ppg)和加速度计检测显著心率失常事件的系统和方法
CN104352229A (zh) * 2014-10-21 2015-02-18 成都艾克尔特医疗科技有限公司 一种基于健康监测手环的自助房颤检测方法
US10105547B2 (en) * 2015-11-02 2018-10-23 West Affum Holdings Corp. Wearable cardioverter defibrillator (WCD) causing patient's QRS width to be plotted against the heart rate
CN105902265A (zh) * 2016-04-18 2016-08-31 广东乐心医疗电子股份有限公司 一种房颤检测装置以及包括该装置的智能可穿戴设备
CN109199327A (zh) * 2017-06-30 2019-01-15 三星电子株式会社 用于连续生物特征监控的自供电可穿戴设备
CN108606798A (zh) * 2018-05-10 2018-10-02 东北大学 基于深度卷积残差网络的非接触式房颤智能检测系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3900610A4 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114041786A (zh) * 2022-01-11 2022-02-15 华南师范大学 心冲击图信号的检测方法、装置以及设备

Also Published As

Publication number Publication date
EP3900610A1 (en) 2021-10-27
EP3900610A4 (en) 2022-01-12
CN112292069B (zh) 2022-03-29
CN112292069A (zh) 2021-01-29

Similar Documents

Publication Publication Date Title
US11723576B2 (en) Detecting atrial fibrillation using short single-lead ECG recordings
CN109171712B (zh) 心房颤动识别方法、装置、设备及计算机可读存储介质
KR102451795B1 (ko) 심전도 신호의 검출 방법
US20200312459A1 (en) Atrial fibrillation signal recognition method, apparatus and device
CN109522916B (zh) 识别单导心电图（ecg）信号中的节律的级联二元分类器
EP3558101B1 (en) Methods and systems for determining abnormal cardiac activity
EP2829223B1 (en) Monitoring physiological parameters
CN109700450B (zh) 一种心率检测方法及电子设备
US20120071730A1 (en) Adaptive Processing of Ambulatory Electrocardiogram Signals
US8780786B2 (en) Method and apparatus for denoising of physiological signals
EP2777485B1 (en) Signal processor, signal processing method, and signal processing program
US20180011532A1 (en) Methods and apparatuses for determining head movement
WO2021017313A1 (zh) 房颤的检测方法、装置、计算机设备及存储介质
EP2430975A1 (en) Principal component analysis or independent component analysis applied to ambulatory electrocardiogram signals
US20160081566A1 (en) Identifying a type of cardiac event from a cardiac signal segment
US10271741B2 (en) Biometric scale
WO2020155169A1 (zh) 房颤筛查的方法和装置
CN105574348B (zh) 一种基于bcg信号的心跳周期获取方法和装置
JP4945309B2 (ja) 脳波測定方法及び脳波測定装置並びに記録媒体
WO2022202942A1 (ja) 心電図解析支援装置、プログラム、心電図解析支援方法、心電図解析支援システム、ピーク推定モデル生成方法、及び区間推定モデル生成方法
US9962103B2 (en) Systems and methods for assessing electrocardiogram reliability
JP6458387B2 (ja) 生体電気ノイズ同定システム及び生体電気ノイズ除去システム
CN111528833B (zh) 一种心电信号的快速识别与处理方法及系统
WO2019100564A1 (zh) 检测报告数据生成方法
US20150182140A1 (en) Arterial pulse analysis method and system thereof

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: 19912359

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2019912359

Country of ref document: EP

Effective date: 20210719