CN109394188A - A kind of adnormal respiration detection method, device and equipment based on heart rate variability - Google Patents
A kind of adnormal respiration detection method, device and equipment based on heart rate variability Download PDFInfo
- Publication number
- CN109394188A CN109394188A CN201811429914.4A CN201811429914A CN109394188A CN 109394188 A CN109394188 A CN 109394188A CN 201811429914 A CN201811429914 A CN 201811429914A CN 109394188 A CN109394188 A CN 109394188A
- Authority
- CN
- China
- Prior art keywords
- sequence
- heart rate
- rate variability
- slope
- breathing
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 58
- 230000029058 respiratory gaseous exchange Effects 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 claims abstract description 26
- 238000012549 training Methods 0.000 claims abstract description 17
- 208000008784 apnea Diseases 0.000 claims abstract description 13
- 238000012360 testing method Methods 0.000 claims abstract description 13
- 238000013528 artificial neural network Methods 0.000 claims abstract description 10
- 238000011156 evaluation Methods 0.000 claims abstract description 10
- 238000000605 extraction Methods 0.000 claims abstract description 10
- 238000007619 statistical method Methods 0.000 claims abstract description 9
- 238000004590 computer program Methods 0.000 claims description 18
- 206010006334 Breathing abnormalities Diseases 0.000 claims description 15
- 230000000241 respiratory effect Effects 0.000 claims description 14
- 210000002569 neuron Anatomy 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 10
- 208000024584 respiratory abnormality Diseases 0.000 claims description 10
- 230000011218 segmentation Effects 0.000 claims description 6
- 201000010099 disease Diseases 0.000 claims description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 4
- 238000012300 Sequence Analysis Methods 0.000 abstract 1
- 239000012634 fragment Substances 0.000 abstract 1
- 108090000623 proteins and genes Proteins 0.000 abstract 1
- 230000006870 function Effects 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 206010021143 Hypoxia Diseases 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007954 hypoxia Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 201000002859 sleep apnea Diseases 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 208000007590 Disorders of Excessive Somnolence Diseases 0.000 description 1
- 206010020591 Hypercapnia Diseases 0.000 description 1
- 206010020772 Hypertension Diseases 0.000 description 1
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 206010041235 Snoring Diseases 0.000 description 1
- 206010041349 Somnolence Diseases 0.000 description 1
- 206010042434 Sudden death Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 210000003403 autonomic nervous system Anatomy 0.000 description 1
- 210000000467 autonomic pathway Anatomy 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 208000026106 cerebrovascular disease Diseases 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 208000029078 coronary artery disease Diseases 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 206010012601 diabetes mellitus Diseases 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 208000001797 obstructive sleep apnea Diseases 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 208000023504 respiratory system disease Diseases 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- 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
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
-
- 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
- A61B5/02405—Determining heart rate variability
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
- A61B5/0826—Detecting or evaluating apnoea events
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4818—Sleep apnoea
-
- 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
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Cardiology (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Physiology (AREA)
- Artificial Intelligence (AREA)
- Pulmonology (AREA)
- Evolutionary Computation (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Fuzzy Systems (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses adnormal respiration detection method, device and equipment based on heart rate variability, method includes: the electrocardiosignal for acquiring the first predetermined time that subject is in nighttime sleep state；Heartbeat interval is extracted to collected electrocardiosignal and constitutes heart rate variability sequence, and each grade of heart rate variability sequence is randomly divided into two groups of equivalent；Carry out to the continuous second predetermined time fragment sequence of the heart rate variability sequence truncation and to it extraction of two characteristic parameters；It is for statistical analysis to two characteristic parameters of training group, using two characteristic parameters of extraction as input, establish adnormal respiration detection model neural network based；Corresponding two characteristic parameters of test group are inputted into the adnormal respiration detection model model, to carry out adnormal respiration check and evaluation to the subject.The present invention is realized by the human ecg signal of noninvasive acquisition analyzes apnea using heart rate variability gene sequence analysis, and operation is simple, and applicability is good.
Description
Technical Field
The invention relates to the field of respiration detection, in particular to a method, a device and equipment for detecting abnormal respiration based on heart rate variability.
Background
Sleep apnea syndrome (sleep apnea syndrome) is a relatively common sleep respiratory disease, and is clinically characterized by night sleep snoring with apnea and daytime sleepiness. Repeated nighttime hypoxia and hypercapnia caused by apnea can cause hypertension, coronary heart disease, diabetes, cerebrovascular disease and other complications and traffic accidents, and even sudden death at night. In the current clinical diagnosis, a Polysomnography (PSG) is the most important method for diagnosing OSAHS, and not only can judge the severity of the disease, but also can comprehensively evaluate the sleep structure, the apnea during sleep, the hypoxia condition, the changes of electrocardio and blood pressure of a patient. But the monitoring is long in time, difficult to wear and high in price, so that the monitoring is inconvenient to popularize in the whole range.
Disclosure of Invention
The invention aims to provide a method, a device and equipment for detecting respiratory anomaly based on heart rate variability, which can collect electrocardiosignals of a patient in a sleep state at night, find the R peak position of each heartbeat, extract heartbeat intervals (RR intervals) to form an HRV sequence, extract characteristic parameters of the HRV sequence to form a characteristic vector, establish a respiratory anomaly detection model by a training set through a classifier, and realize respiratory anomaly detection by using the model.
The technical scheme of the invention is realized as follows:
a method for detecting respiratory anomaly based on heart rate variability comprises the following steps:
s1, collecting electrocardiosignals of a first preset time when the subject is in a sleep state at night;
s2, extracting heartbeat intervals of the collected electrocardiosignals to form a heart rate variability sequence { RRi, i is 1,2, … N }, and randomly dividing each grade of the heart rate variability sequence into two groups with the same quantity, wherein the two groups are respectively used as a training group and a testing group;
s3, intercepting a continuous second preset time segment sequence of the heart rate variability sequence and extracting two characteristic parameters of the continuous second preset time segment sequence;
s4, performing statistical analysis on the two characteristic parameters of the training set, taking the two extracted characteristic parameters as input, and establishing a breathing abnormity detection model based on a neural network;
and S5, inputting the two characteristic parameters corresponding to the test group into the breathing abnormality detection model so as to perform breathing abnormality detection evaluation on the subject.
Preferably, the characteristic parameters include a first characteristic parameter and a second characteristic parameter: wherein,
the first characteristic parameter extraction step is as follows:
calculating a trend forming sequence { trendi, i ═ 1,2, … M } after segmenting the heart rate variability sequence { RRi, i ═ 1,2, … N } by 5 minutes;
calculating the slope of the trend forming sequence { trandi, i ═ 1,2, … M } to form a slope sequence { slope, i ═ 1,2, … M };
calculating the mean value of the slope sequence to obtain a trend slope mean value slope, namely obtaining a first characteristic parameter;
the second characteristic parameter extraction step is as follows:
calculating a trend forming sequence { trendi, i ═ 1,2, … M } after segmenting the heart rate variability sequence { RRi, i ═ 1,2, … N } by 5 minutes;
calculating the slope of the trend forming sequence { trandi, i ═ 1,2, … M } to form a slope sequence { slope, i ═ 1,2, … M };
and calculating the fuzzy entropy of the slope sequence to obtain a second characteristic parameter fuzzy ysl.
Preferably, the extracting step of the second feature parameter specifically includes:
segmenting the heart rate variability sequence { RRi, i ═ 1,2, … N } according to the time length of 5 minutes to obtain a segmentation matrix sequence { RRi, j, i ═ 1,2, … M; j ═ 1,2, … N }, and each row of the segmentation matrix sequence is a 5-minute RR interval value;
calculating { RRi, j, i ═ 1,2, … M; j is 1,2, … N, forming a sequence { trendi, j, i is 1,2, … M; j is 1,2, … N, and calculating the slope of each line of the trend sequence to form a slope matrix { slope, j, i is 1,2, … M; j ═ 1,2, … N };
serializing the slope matrix, calculating the mean value of the slope to form a one-dimensional sequence, and calculating the fuzzy entropy of the one-dimensional sequence to obtain the fuzzy entropy of the one-dimensional sequence.
Preferably, step S4 is specifically:
constructing a 2-N-1 three-layer neural network according to two characteristic parameters of a training group sample, namely an input layer comprises 2 neurons, an output layer comprises 1 neuron and a middle layer comprises N neurons; the 2 neurons of the input layer are: and establishing a breathing anomaly detection model by using the trend slope mean slope and the trend slope fuzzy entropy fuzzysl.
Preferably, in step S5:
the breathing abnormity detection result obtained based on the breathing abnormity detection model is output by a classifier SVM, and the output label values '0, 1 and 2' of the classifier SVM respectively represent the breathing abnormity state of the subject and are used for corresponding to different breathing abnormity disease degrees and emergent event occurrence probabilities, wherein '0' represents that no apnea occurs and the emergent event occurrence probability is extremely low; "1" indicates mild or moderate apnea occurs and the probability of an emergency event is low; "2" represents the occurrence of severe apnea and high probability of occurrence of an emergency event.
Preferably, the first predetermined time is 6 hours and the second predetermined time is 5 minutes.
The embodiment of the invention also provides a respiratory anomaly detection device based on heart rate variability, which comprises:
the electrocardiosignal acquisition unit is used for acquiring electrocardiosignals of a subject in a first preset time of a night sleep state;
the grouping unit is used for extracting heartbeat intervals of the acquired electrocardiosignals to form a heart rate variability sequence { RRi, i is 1,2, … N }, and randomly dividing each grade of the heart rate variability sequence into two groups with the same quantity to be used as a training group and a testing group respectively;
the characteristic parameter extraction unit is used for intercepting a continuous second preset time segment sequence of the heart rate variability sequence and extracting two characteristic parameters of the continuous second preset time segment sequence;
the model establishing unit is used for carrying out statistical analysis on the two characteristic parameters of the training set, taking the two extracted characteristic parameters as input, and establishing a breathing abnormity detection model based on a neural network;
and the evaluation unit is used for inputting the two characteristic parameters corresponding to the test group into the breathing abnormity detection model so as to carry out breathing abnormity detection evaluation on the subject.
Embodiments of the present invention further provide a respiratory anomaly detection device based on heart rate variability, including a processor, a memory, and a computer program stored in the memory, the computer program being executable by the processor to implement the respiratory anomaly detection method based on heart rate variability as described above.
The embodiment of the invention adopts a method for carrying out mathematical statistical analysis on the characteristic parameters to construct a respiratory anomaly detection model based on heart rate variability. Because the detection model is obtained according to the statistical analysis of the characteristic parameters, a model with significant differences can be constructed to realize the detection of the breathing abnormality, and the output label values of 0, 1 and 2 respectively represent that the detected patient has no breathing abnormality, mild or moderate breathing abnormality, severe breathing abnormality and other three breathing abnormality states. Meanwhile, the two characteristic parameters do not make stationarity assumption on the HRV sequence, so that the method only needs to collect electrocardiosignals of the patient sleeping for 6 hours at night. Meanwhile, the operation of the design of the invention is simpler, so the invention is feasible in the aspect of realization.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a respiratory anomaly detection method based on heart rate variability according to an embodiment of the present invention.
Fig. 2 is a block diagram of an experimental process provided in an embodiment of the present invention.
Fig. 3(a) -3 (c) are HRV waveform signals for three different breathing states provided by an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1-2, a method for detecting respiratory anomaly based on heart rate variability provided by an embodiment of the present invention includes the following steps:
and S1, acquiring the Electrocardiosignals (ECG) of the first preset time when the subject is in the sleep state at night.
Wherein the first predetermined time is preferably 6 hours, but is not limited thereto.
And S2, extracting heartbeat intervals of the acquired electrocardiosignals to form a heart rate variability sequence { RRi, i ═ 1,2, … N }, and randomly dividing each grade of the heart rate variability sequence into two groups with equal quantity, wherein the two groups are respectively used as a training group and a testing group.
Wherein, the R peak value is extracted from the collected Electrocardiosignal (ECG) beat by beat, and the R-R interval is calculated to obtain the Heart Rate Variability (HRV) sequence { RRi, i ═ 1,2, … N }.
And S3, intercepting a continuous second preset time segment sequence of the heart rate variability sequence and extracting characteristic parameters of the continuous second preset time segment sequence.
Wherein, the extracted first characteristic parameter is: the trend slope mean slope and the extracted second characteristic parameter are as follows: the trend slope blurs the entropy fuzzysl.
Specifically, the calculation process of the trend slope is as follows:
a1, segmenting the heart rate variability sequence { RRi, i ═ 1,2, … N } according to the time length of 5 minutes to obtain a segmentation matrix sequence { RRi, j, i ═ 1,2, … M; j ═ 1,2, … N }, and each row of the segmentation matrix sequence is an inter-RR period value in a 5-minute period;
a2, pair sequence { RRi, j, i ═ 1,2, … M; j is 1,2, … N, and is reconstructed into a series of non-overlapped subsequences Y (Y) with the duration of T/21,y2,…,yj),j＝1,2,…M；yjIs a subsequence, and M is the number of subsequences.
a3, subtracting the mean m1 of the upper and lower envelope lines of Y from Y to obtain h1 (h) for the reconstructed subsequence Y1＝Y-m1) Repeat n times as a new input to yield h1n (h)1n＝h1(n-1)-m1n) As the first IMF value, and n satisfies the condition:
for input Y, the calculation formula is:
the trend series can be obtained.
a4, calculating the slope of the trend sequence by using a linear regression model method to obtain a slope sequence { slope, j, i ═ 1,2, … M; j ═ 1,2, … N };
a5, serializing the slope into slope { k11, k21, k22, … kij, i ═ 1: M, j ═ 1: min (i, M-i) }, and averaging it:
thereby obtaining a first characteristic trend slope mean slope.
Wherein, the calculation process of the fuzzy entropy fuzzy zysl of the trend slope of the second characteristic parameter is as follows:
b1, obtaining a slope sequence slope { K11, K21, K22, … Kij, i ═ 1: M, j ═ 1: min (i, M-i) } according to the method above for the heart rate variability sequence { RRi, i ═ 1,2, … N };
b2, calculating fuzzy entropy of the slope sequence:
reconstructing slope sequence slope (k 11, k21, k22, … kij, i 1: M, j 1: min (i, M-i)) by using phase spaceWhere m is the embedding dimension.
Adjacent vectorAnddegree of similarity ofDetermined by the fuzzy element function:
whereinAs neighboring vectorsAndthe maximum absolute difference of;
the fuzzy entropy of the slope trend can be defined as:
wherein:then obtaining the fuzzy entropy fuzzy zysl of the slope of the second characteristic trend.
And S4, performing statistical analysis on the two characteristic parameters of the training set, taking the two extracted characteristic parameters as input, and establishing a breathing abnormity detection model based on a neural network.
Specifically, a 2-N-1 three-layer neural network is constructed according to two characteristic parameters of a training set, namely an input layer is 2 neurons, an output layer is 1 neuron, and a middle layer is N neurons; the 2 neurons of the input layer are: and establishing a breathing anomaly detection model by using the trend slope mean slope and the trend slope fuzzy entropy fuzzysl.
And S5, inputting the two characteristic parameters corresponding to the test group into the breathing abnormality detection model so as to perform breathing abnormality detection evaluation on the subject.
The breathing abnormity detection result obtained based on the breathing abnormity detection model is output by the classifier SVM, and the output label values '0, 1 and 2' of the classifier SVM respectively represent the breathing abnormity state of the subject and are used for corresponding to different breathing abnormity disease degrees and emergent event occurrence probabilities, wherein '0' represents that no apnea occurs and the emergent event occurrence probability is extremely low (such as the HRV waveform shown in figure 3 (a)); "1" indicates mild or moderate apnea, low probability of the occurrence of an emergency event (HRV waveform as shown in FIG. 3 (b)); "2" represents the occurrence of severe apnea and high probability of the occurrence of an emergency event (HRV waveform as shown in fig. 3 (c)).
In the embodiment of the invention, the characteristic parameter extraction comprises a trend slope and fuzzy entropy fuzzysl of the trend slope. Respiratory abnormalities are assessed based on heart rate variability, which is actually a concern for autonomic nerves, a typical multi-input nonlinear system. Therefore, attention is paid not only to the slight fluctuation condition of the optical fiber with time, but also to the nonlinear complexity characteristic of the optical fiber. In the previous research, the entropy indexes are obviously different among the respiratory abnormality patients with different degrees, and in the invention, the data are subjected to time-interval average processing, so that the difference is enhanced. The detection result of the breathing abnormality can be used as an auxiliary index of the occurrence probability of the sudden event of the patient, and the method is also greatly helpful for analyzing the functions of the autonomic nervous system, detecting the sleep breathing event and the like.
The two characteristic parameters do not make stationarity assumption on the HRV sequence, so that the method can be applied only by collecting electrocardiosignals for sleeping for 6 hours at night without detection of a whole-night polysomnography detector. Meanwhile, the operation designed by the invention is simpler, and the classifiers are common, so the method is feasible in the aspect of implementation.
A second embodiment of the present invention provides a respiratory anomaly detection device based on heart rate variability, including:
the electrocardiosignal acquisition unit is used for acquiring electrocardiosignals of a subject in a first preset time of a night sleep state;
the grouping unit is used for extracting heartbeat intervals of the acquired electrocardiosignals to form a heart rate variability sequence { RRi, i is 1,2, … N }, and randomly dividing each grade of the heart rate variability sequence into two groups with the same quantity to be used as a training group and a testing group respectively;
the characteristic parameter extraction unit is used for intercepting a continuous second preset time segment sequence of the heart rate variability sequence and extracting two characteristic parameters of the continuous second preset time segment sequence;
the model establishing unit is used for carrying out statistical analysis on the two characteristic parameters of the training set, taking the two extracted characteristic parameters as input, and establishing a breathing abnormity detection model based on a neural network;
and the evaluation unit is used for inputting the two characteristic parameters corresponding to the test group into the breathing abnormity detection model so as to carry out breathing abnormity detection evaluation on the subject.
A third embodiment of the invention provides a breathing anomaly detection device based on heart rate variability, comprising a processor, a memory and a computer program stored in the memory, the computer program being executable by the processor to implement a breathing anomaly detection method based on heart rate variability as described above.
A fourth embodiment of the present invention provides a computer-readable storage medium comprising a stored computer program, wherein the computer program, when executed, controls a device on which the computer-readable storage medium is located to perform the method for detecting respiratory abnormalities based on heart rate variability as described above.
Illustratively, the computer program may be divided into one or more units, which are stored in the memory and executed by the processor to accomplish the present invention. The one or more units may be a series of computer program instruction segments capable of performing specific functions for describing the execution of the computer program in a respiratory abnormality detection device based on heart rate variability.
The breathing abnormity detection equipment based on heart rate variability can be computing equipment such as a desktop computer, a notebook computer, a palm computer and a cloud server cluster. The respiratory abnormality detection device based on heart rate variability may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that the schematic diagram is merely an example of a breathing anomaly detection device based on heart rate variability, does not constitute a limitation of a breathing anomaly detection device based on heart rate variability, may include more or fewer components than shown, or combine certain components, or different components, for example, the breathing anomaly detection device based on heart rate variability may also include an input-output device, a network access device, a bus, etc.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, the control center of the heart rate variability based breathing abnormality detection device connects the various parts of the entire heart rate variability based breathing abnormality detection device with various interfaces and lines.
The memory may be used to store the computer programs and/or modules, and the processor may implement the various functions of the heart rate variability based breathing abnormality detection apparatus by running or executing the computer programs and/or modules stored in the memory, and invoking the data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
Wherein the unit integrated with the breathing anomaly detection device based on heart rate variability can be stored in a computer readable storage medium if it is implemented in the form of a software functional unit and sold or used as a stand-alone product. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
It should be noted that the above-described device embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the apparatus provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (8)
1. A method for detecting respiratory anomaly based on heart rate variability, comprising the steps of:
s1, collecting electrocardiosignals of a first preset time when the subject is in a sleep state at night;
s2, extracting heartbeat intervals of the collected electrocardiosignals to form a heart rate variability sequence { RRi, i is 1,2, … N }, and randomly dividing each grade of the heart rate variability sequence into two groups with the same quantity, wherein the two groups are respectively used as a training group and a testing group;
s3, intercepting a continuous second preset time segment sequence of the heart rate variability sequence and extracting two characteristic parameters of the continuous second preset time segment sequence;
s4, performing statistical analysis on the two characteristic parameters of the training set, taking the two extracted characteristic parameters as input, and establishing a breathing abnormity detection model based on a neural network;
and S5, inputting the two characteristic parameters corresponding to the test group into the breathing abnormality detection model so as to perform breathing abnormality detection evaluation on the subject.
2. The method of detecting respiratory abnormalities based on heart rate variability of claim 1, wherein said characteristic parameters include a first characteristic parameter and a second characteristic parameter: wherein,
the first characteristic parameter extraction step is as follows:
calculating a trend sequence { trendi, i ═ 1,2, … M } after segmenting the heart rate variability sequence { RRi, i ═ 1,2, … N } by 5 minutes;
calculating the slope of the trend sequence { trendi, i ═ 1,2, … M } to form a slope sequence { slope, i ═ 1,2, … M };
calculating the mean value of the slope sequence to obtain a trend slope mean value slope, namely obtaining a first characteristic parameter;
the second characteristic parameter extraction step is as follows:
calculating a trend forming sequence { trendi, i ═ 1,2, … M } after segmenting the heart rate variability sequence { RRi, i ═ 1,2, … N } by 5 minutes;
calculating the slope of the trend forming sequence { trandi, i ═ 1,2, … M } to form a slope sequence { slope, i ═ 1,2, … M };
and calculating the fuzzy entropy of the slope sequence to obtain a second characteristic parameter fuzzy ysl.
3. The method for detecting respiratory abnormalities based on heart rate variability according to claim 2, wherein said second characteristic parameter is extracted by:
segmenting the heart rate variability sequence { RRi, i ═ 1,2, … N } according to the time length of 5 minutes to obtain a segmentation matrix sequence { RRi, j, i ═ 1,2, … M; j ═ 1,2, … N }, and each row of the segmentation matrix sequence is a 5-minute RR interval value;
calculating { RRi, j, i ═ 1,2, … M; j is 1,2, … N, forming a sequence { trendi, j, i is 1,2, … M; j is 1,2, … N, and calculating the slope of each line of the trend sequence to form a slope matrix { slope, j, i is 1,2, … M; j ═ 1,2, … N };
serializing the slope matrix, calculating the mean value of the slope to form a one-dimensional sequence, and calculating the fuzzy entropy of the one-dimensional sequence to obtain the fuzzy entropy of the one-dimensional sequence.
4. The method for detecting respiratory abnormality based on heart rate variability according to claim 3, wherein the step S4 is specifically as follows:
constructing a neural network with three layers of 2-N-1 according to two characteristic parameters of a training set, namely an input layer is 2 neurons, an output layer is 1 neuron, and a middle layer is N neurons; the 2 neurons of the input layer are: and establishing a breathing anomaly detection model by using the trend slope mean slope and the trend slope fuzzy entropy fuzzysl.
5. The method for detecting respiratory abnormalities based on heart rate variability of claim 4, wherein in step S5:
the breathing abnormity detection result obtained based on the breathing abnormity detection model is output by a classifier SVM, and the output label values '0, 1 and 2' of the classifier SVM respectively represent the breathing abnormity state of the subject and are used for corresponding to different breathing abnormity disease degrees and emergent event occurrence probabilities, wherein '0' represents that no apnea occurs and the emergent event occurrence probability is extremely low; "1" indicates mild or moderate apnea occurs and the probability of an emergency event is low; "2" represents the occurrence of severe apnea and high probability of occurrence of an emergency event.
6. The method of detecting respiratory abnormalities based on heart rate variability of claim 1 wherein said first predetermined time is 6 hours and said second predetermined time is 5 minutes.
7. A device for detecting respiratory anomalies based on heart rate variability, comprising:
the electrocardiosignal acquisition unit is used for acquiring electrocardiosignals of a subject in a first preset time of a night sleep state;
the grouping unit is used for extracting heartbeat intervals of the acquired electrocardiosignals to form a heart rate variability sequence { RRi, i is 1,2, … N }, and randomly dividing each grade of the heart rate variability sequence into two groups with the same quantity to be used as a training group and a testing group respectively;
the characteristic parameter extraction unit is used for intercepting a continuous second preset time segment sequence of the heart rate variability sequence and extracting two characteristic parameters of the continuous second preset time segment sequence;
the model establishing unit is used for carrying out statistical analysis on the two characteristic parameters of the training set, taking the two extracted characteristic parameters as input, and establishing a breathing abnormity detection model based on a neural network;
and the evaluation unit is used for inputting the two characteristic parameters corresponding to the test group into the breathing abnormity detection model so as to carry out breathing abnormity detection evaluation on the subject.
8. A heart rate variability based breathing anomaly detection device, comprising a processor, a memory and a computer program stored in the memory, the computer program being executable by the processor to implement a heart rate variability based breathing anomaly detection method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811429914.4A CN109394188B (en) | 2018-11-27 | 2018-11-27 | Method, device and equipment for detecting respiratory anomaly based on heart rate variability |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811429914.4A CN109394188B (en) | 2018-11-27 | 2018-11-27 | Method, device and equipment for detecting respiratory anomaly based on heart rate variability |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109394188A true CN109394188A (en) | 2019-03-01 |
| CN109394188B CN109394188B (en) | 2022-03-08 |
Family
ID=65455930
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811429914.4A Active CN109394188B (en) | 2018-11-27 | 2018-11-27 | Method, device and equipment for detecting respiratory anomaly based on heart rate variability |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109394188B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110490257A (en) * | 2019-08-21 | 2019-11-22 | 四川长虹电器股份有限公司 | It is a kind of based on the electro-physiological signals entropy analysis method for removing trend term |
| CN111166294A (en) * | 2020-01-29 | 2020-05-19 | 北京交通大学 | Automatic sleep apnea detection method and device based on inter-heartbeat period |
| WO2021135672A1 (en) * | 2019-12-31 | 2021-07-08 | 华南师范大学 | Signal detection method and system for assessing sleep apnea |
| CN113627549A (en) * | 2021-08-17 | 2021-11-09 | 硕橙（厦门）科技有限公司 | Method, device and equipment for detecting abnormal time sequence hopping |
| CN113679369A (en) * | 2021-08-23 | 2021-11-23 | 广东高驰运动科技有限公司 | Heart rate variability evaluation method, intelligent wearable device and storage medium |
| CN113892939A (en) * | 2021-09-26 | 2022-01-07 | 燕山大学 | Method for monitoring respiratory frequency of human body in resting state based on multi-feature fusion |
| CN114271804A (en) * | 2021-12-16 | 2022-04-05 | 宁波诺丁汉大学 | Heart rate state auxiliary detection system based on consumption-level equipment, heart rate state monitoring system, heart rate state monitoring method, storage medium and terminal |
| CN114403892A (en) * | 2022-01-24 | 2022-04-29 | 中山大学 | Method, device and equipment for interactively adjusting respiratory feedback based on heart rate variability |
| CN116978561A (en) * | 2023-07-17 | 2023-10-31 | 北京师范大学-香港浸会大学联合国际学院 | Motion risk assessment method, system, equipment and medium based on fuzzy entropy |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120179061A1 (en) * | 2009-07-16 | 2012-07-12 | Resmed Limited | Detection of sleep condition |
| CN104840186A (en) * | 2015-05-07 | 2015-08-19 | 中山大学 | Evaluation method of autonomic nervous function of patient suffering from CHF (Congestive Heart-Failure) |
| US20150282723A1 (en) * | 2012-10-16 | 2015-10-08 | Xotox Tools Ag | Device and Method for Detecting and Signalling a Stress State of a Person |
| EP2976993A2 (en) * | 2014-07-21 | 2016-01-27 | Withings | System to monitor and assist individual's sleep |
| CN105411565A (en) * | 2015-11-20 | 2016-03-23 | 北京理工大学 | Heart rate variability feature classification method based on generalized scale wavelet entropy |
| WO2017011431A2 (en) * | 2015-07-15 | 2017-01-19 | Valencell, Inc. | Methods of controlling biometric parameters via musical audio |
| CN106361277A (en) * | 2016-08-26 | 2017-02-01 | 中山大学 | Sleep apnea syndrome assessment method based on electrocardiogram signals |
| US20170055899A1 (en) * | 2015-08-28 | 2017-03-02 | Awarables, Inc. | Visualizing, Scoring, Recording, and Analyzing Sleep Data and Hypnograms |
| US20170055898A1 (en) * | 2015-08-28 | 2017-03-02 | Awarables, Inc. | Determining Sleep Stages and Sleep Events Using Sensor Data |
| CN107736894A (en) * | 2017-09-24 | 2018-02-27 | 天津大学 | A kind of electrocardiosignal Emotion identification method based on deep learning |
| CN107874750A (en) * | 2017-11-28 | 2018-04-06 | 华南理工大学 | Pulse frequency variability and the psychological pressure monitoring method and device of sleep quality fusion |
| CN107998500A (en) * | 2017-11-28 | 2018-05-08 | 广州视源电子科技股份有限公司 | Method and system for playing sleep aid content and sleep aid device |
| CN108392211A (en) * | 2018-01-11 | 2018-08-14 | 浙江大学 | A kind of fatigue detection method based on Multi-information acquisition |
| US20180303357A1 (en) * | 2017-04-19 | 2018-10-25 | Physical Enterprises, Inc. | Systems and methods for providing user insights based on heart rate variability |
-
2018
- 2018-11-27 CN CN201811429914.4A patent/CN109394188B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120179061A1 (en) * | 2009-07-16 | 2012-07-12 | Resmed Limited | Detection of sleep condition |
| US20150282723A1 (en) * | 2012-10-16 | 2015-10-08 | Xotox Tools Ag | Device and Method for Detecting and Signalling a Stress State of a Person |
| EP2976993A2 (en) * | 2014-07-21 | 2016-01-27 | Withings | System to monitor and assist individual's sleep |
| CN104840186A (en) * | 2015-05-07 | 2015-08-19 | 中山大学 | Evaluation method of autonomic nervous function of patient suffering from CHF (Congestive Heart-Failure) |
| WO2017011431A2 (en) * | 2015-07-15 | 2017-01-19 | Valencell, Inc. | Methods of controlling biometric parameters via musical audio |
| US20170055898A1 (en) * | 2015-08-28 | 2017-03-02 | Awarables, Inc. | Determining Sleep Stages and Sleep Events Using Sensor Data |
| US20170055899A1 (en) * | 2015-08-28 | 2017-03-02 | Awarables, Inc. | Visualizing, Scoring, Recording, and Analyzing Sleep Data and Hypnograms |
| CN105411565A (en) * | 2015-11-20 | 2016-03-23 | 北京理工大学 | Heart rate variability feature classification method based on generalized scale wavelet entropy |
| CN106361277A (en) * | 2016-08-26 | 2017-02-01 | 中山大学 | Sleep apnea syndrome assessment method based on electrocardiogram signals |
| US20180303357A1 (en) * | 2017-04-19 | 2018-10-25 | Physical Enterprises, Inc. | Systems and methods for providing user insights based on heart rate variability |
| CN107736894A (en) * | 2017-09-24 | 2018-02-27 | 天津大学 | A kind of electrocardiosignal Emotion identification method based on deep learning |
| CN107874750A (en) * | 2017-11-28 | 2018-04-06 | 华南理工大学 | Pulse frequency variability and the psychological pressure monitoring method and device of sleep quality fusion |
| CN107998500A (en) * | 2017-11-28 | 2018-05-08 | 广州视源电子科技股份有限公司 | Method and system for playing sleep aid content and sleep aid device |
| CN108392211A (en) * | 2018-01-11 | 2018-08-14 | 浙江大学 | A kind of fatigue detection method based on Multi-information acquisition |
Non-Patent Citations (2)
| Title |
|---|
| BO SHI,ET AL: "Entropy Analysis of Short-Term Heartbeat Interval Time Series during Regular Walking", 《ENTROPY》 * |
| VINZENZ VON TSCHARNER，ET AL: "Multi-scale transitions of fuzzy sample entropy of RR-intervals and their phase-randomized surrogates: A possibility to diagnose congestive heart failure", 《BIOMEDICAL SIGNAL PROCESSING AND CONTROL》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110490257A (en) * | 2019-08-21 | 2019-11-22 | 四川长虹电器股份有限公司 | It is a kind of based on the electro-physiological signals entropy analysis method for removing trend term |
| WO2021135672A1 (en) * | 2019-12-31 | 2021-07-08 | 华南师范大学 | Signal detection method and system for assessing sleep apnea |
| CN111166294A (en) * | 2020-01-29 | 2020-05-19 | 北京交通大学 | Automatic sleep apnea detection method and device based on inter-heartbeat period |
| CN113627549A (en) * | 2021-08-17 | 2021-11-09 | 硕橙（厦门）科技有限公司 | Method, device and equipment for detecting abnormal time sequence hopping |
| CN113679369A (en) * | 2021-08-23 | 2021-11-23 | 广东高驰运动科技有限公司 | Heart rate variability evaluation method, intelligent wearable device and storage medium |
| CN113679369B (en) * | 2021-08-23 | 2023-12-19 | 广东高驰运动科技有限公司 | Evaluation method of heart rate variability, intelligent wearable device and storage medium |
| CN113892939A (en) * | 2021-09-26 | 2022-01-07 | 燕山大学 | Method for monitoring respiratory frequency of human body in resting state based on multi-feature fusion |
| CN114271804A (en) * | 2021-12-16 | 2022-04-05 | 宁波诺丁汉大学 | Heart rate state auxiliary detection system based on consumption-level equipment, heart rate state monitoring system, heart rate state monitoring method, storage medium and terminal |
| CN114403892A (en) * | 2022-01-24 | 2022-04-29 | 中山大学 | Method, device and equipment for interactively adjusting respiratory feedback based on heart rate variability |
| CN114403892B (en) * | 2022-01-24 | 2024-04-02 | 中山大学 | Method, device and equipment for interactively adjusting respiratory feedback based on heart rate variability |
| CN116978561A (en) * | 2023-07-17 | 2023-10-31 | 北京师范大学-香港浸会大学联合国际学院 | Motion risk assessment method, system, equipment and medium based on fuzzy entropy |
| CN116978561B (en) * | 2023-07-17 | 2024-03-22 | 北京师范大学-香港浸会大学联合国际学院 | Motion risk assessment method, system, equipment and medium based on fuzzy entropy |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109394188B (en) | 2022-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109394188B (en) | Method, device and equipment for detecting respiratory anomaly based on heart rate variability | |
| Eltrass et al. | A new automated CNN deep learning approach for identification of ECG congestive heart failure and arrhythmia using constant-Q non-stationary Gabor transform | |
| Valenza et al. | Mood recognition in bipolar patients through the PSYCHE platform: preliminary evaluations and perspectives | |
| Büyükçakır et al. | Hilbert vibration decomposition-based epileptic seizure prediction with neural network | |
| Fatimah et al. | Efficient detection of myocardial infarction from single lead ECG signal | |
| Eltrass et al. | Automated ECG multi-class classification system based on combining deep learning features with HRV and ECG measures | |
| Yan et al. | Multi-modality of polysomnography signals’ fusion for automatic sleep scoring | |
| Yu et al. | Epileptic seizure prediction based on local mean decomposition and deep convolutional neural network | |
| CN110801221A (en) | Sleep apnea fragment detection method and device based on unsupervised feature learning | |
| Ge et al. | Multi-label correlation guided feature fusion network for abnormal ECG diagnosis | |
| Udawat et al. | An automated detection of atrial fibrillation from single‑lead ECG using HRV features and machine learning | |
| Patro et al. | A hybrid approach of a deep learning technique for real-time ECG beat detection | |
| Nezamabadi et al. | Unsupervised ECG analysis: A review | |
| Dos Santos et al. | Application of an automatic adaptive filter for heart rate variability analysis | |
| Jeong et al. | Convolutional neural network for classification of eight types of arrhythmia using 2D time–frequency feature map from standard 12-lead electrocardiogram | |
| Dhyani et al. | Arrhythmia disease classification utilizing ResRNN | |
| CN109674474B (en) | Sleep apnea recognition method, device and computer readable medium | |
| Kumar et al. | Automated Schizophrenia detection using local descriptors with EEG signals | |
| Mazidi et al. | Premature ventricular contraction (PVC) detection system based on tunable Q-factor wavelet transform | |
| Bahador et al. | Multimodal spatio-temporal-spectral fusion for deep learning applications in physiological time series processing: A case study in monitoring the depth of anesthesia | |
| Prakash et al. | A system for automatic cardiac arrhythmia recognition using electrocardiogram signal | |
| Molina–Picó et al. | Influence of QRS complex detection errors on entropy algorithms. Application to heart rate variability discrimination | |
| Huang et al. | Joint ensemble empirical mode decomposition and tunable Q factor wavelet transform based sleep stage classifications | |
| Chen et al. | RAFNet: Restricted attention fusion network for sleep apnea detection | |
| Wang et al. | Multiscale residual network based on channel spatial attention mechanism for multilabel ECG classification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |